Archive for the ‘Personalized and Precision Medicine & Genomic Research’ Category
Protected: Analysis of Cardio-Electrical Synchronization of In vitro Cultured Stem Cells
Posted in Electrophysiology, Frontiers in Cardiology and Cardiovascular Disorders, Genome Biology, Personalized and Precision Medicine & Genomic Research, Resident-cell-based, Stem Cells for Regenerative Medicine, tagged Cardio-Electrical Synchronization of In vitro Cultured Stem Cells on September 23, 2014|
NIH Considers Guidelines for CAR-T therapy: Report from Recombinant DNA Advisory Committee
Posted in Autologous Cell Therapy, Bioengineering & reverse engineering design, Cancer and Current Therapeutics, CANCER BIOLOGY & Innovations in Cancer Therapy, CE Mark & Global Regulatory Affairs: process management and strategic planning - GCP, Computational Biology/Systems and Bioinformatics, Disease Biology, Drug Toxicity, FDA, FDA Regulatory Affairs, Genetics & Pharmaceutical, GLP, Human Immune System in Health and in Disease, Immunodiagnostics, Innovation in Immunology Diagnostics, Innovations, ISO 14155, Personalized and Precision Medicine & Genomic Research, Quality Assurance, Translational Research, tagged Adult ALL, Adverse event, Alliance for Clinical Trials in Oncology, Apoptosis, autologous transplant, B and T cell gene rearrangements, Cancer - General, CD8+ T cells, Clinical trial, clinical trial guidelines, Food and Drug Administration, gene expression, gene therapy, health, insertional mutagenesis, interleukins, medicine, National Institutes of Health, Personalized medicine, Pharmacovigilance, research, safety guidelines on September 23, 2014| Leave a Comment »
NIH Considers Guidelines for CAR-T therapy: Report from Recombinant DNA Advisory Committee
Reporter: Stephen J. Williams, Ph.D.
UPDATED 5/27/2024
The practice of pharmacovigilence, both premarketing and postmarketing, has very well defined best practices concerning most small molecule drugs and even medical devices. However, for many cell based therapies and many gene based therapies, often still administered within the university, academic setting, pharmacovigilence reporting and adherence may be a not as efficient and thorough as conducted by large big pharmaceutical firms. Big pharma will devote massive resources for the conduct of pharmacovigilence data collecting and analysis. For many cell based therapies, like CAR-T therapies and some gene therapies are almost conducted as clinical trials within university medical centers, which may not have the resources for a large pharmacovigilence program.
In a report by IQVIA, oncologists were asked about their concerns with cell based therapies. A recurring concern involved the lack of information on the adverse events related to these therapies, especially after an oncologist’s patient would return from administration of their CAR-T therapy and then both patient and oncologist felt ‘on their own’.
Most recently the FDA has issued black box warning on many CAR-T therapies for their risk in inducing secondary malignancies (see What does this mean for Immunotherapy? FDA put a temporary hold on Juno’s JCAR015, Three Death of Cerebral Edema in CAR-T Clinical Trial and Kite Pharma announced Phase II portion of its CAR-T ZUMA-1 trial).
Note: the IQVIA will be submitted as an abstract at the current ASCO meeting
UPDATED 5/10/2022
In the mid to late 1970’s a public debate (and related hysteria) had emerged surrounding two emerging advances in recombinant DNA technology;
- the development of vectors useful for cloning pieces of DNA (the first vector named pBR322) and
- the discovery of bacterial strains useful in propagating such vectors
As discussed by D. S, Fredrickson of NIH’s Dept. of Education and Welfare in his historical review” A HISTORY OF THE RECOMBINANT DNA GUIDELINES IN THE UNITED STATES” this international concern of the biological safety issues of this new molecular biology tool led the National Institute of Health to coordinate a committee (the NIH Recombinant DNA Advisory Committee) to develop guidelines for the ethical use, safe development, and safe handling of such vectors and host bacterium. The first conversations started in 1974 and, by 1978, initial guidelines had been developed. In fact, as Dr. Fredrickson notes, public relief was voiced even by religious organizations (who had the greatest ethical concerns)
On December 16, 1978, a telegram purporting to be from the Vatican was hand delivered to the office of Joseph A. Califano, Jr., Secretary of Health, Education,
and Welfare. “Habemus regimen recombinatum,” it proclaimed, in celebration of the
end of a long struggle to revise the NIH Guidelines for Research Involving
The overall Committee resulted in guidelines (2013 version) which assured the worldwide community that
- organisms used in such procedures would have limited pathogenicity in humans
- vectors would be developed in a manner which would eliminate their ability to replicate in humans and have defined antibiotic sensitivity
So great was the success and acceptance of this committee and guidelines, the NIH felt the Recombinant DNA Advisory Committee should meet regularly to discuss and develop ethical guidelines and clinical regulations concerning DNA-based therapeutics and technologies.
A PowerPoint Slideshow: Introduction to NIH OBA and the History of Recombinant DNA Oversight can be viewed at the following link:
Please see the following link for a video discussion between Dr. Paul Berg, who pioneered DNA recombinant technology, and Dr. James Watson (Commemorating 50 Years of DNA Science):
http://media.hhmi.org/interviews/berg_watson.html
The Recombinant DNA Advisory Committee has met numerous times to discuss new DNA-based technologies and their biosafety and clinical implication including:
- January 24, 2013 Biosafety Considerations for Research with Highly Pathogenic Avian Influenza Virus H5N1 that is Transmissible between Mammals by Respiratory Droplets
- 2008 Guidelines for HIV Vaccination Protocols Appendix M-VI-A of the NIH Guidelines (the “Vaccine Exemption”)
A recent Symposium was held in the summer of 2010 to discuss ethical and safety concerns and discuss potential clinical guidelines for use of an emerging immunotherapy technology, the Chimeric Antigen Receptor T-Cells (CART), which at that time had just been started to be used in clinical trials.
Considerations for the Clinical Application of Chimeric Antigen Receptor T Cells: Observations from a Recombinant DNA Advisory Committee Symposium Held June 15, 2010[1]
Contributors to the Symposium discussing opinions regarding CAR-T protocol design included some of the prominent members in the field including:
Drs. Hildegund C.J. Ertl, John Zaia, Steven A. Rosenberg, Carl H. June, Gianpietro Dotti, Jeffrey Kahn, Laurence J. N. Cooper, Jacqueline Corrigan-Curay, And Scott E. Strome.
The discussions from the Symposium, reported in Cancer Research[1]. were presented in three parts:
- Summary of the Evolution of the CAR therapy
- Points for Future Consideration including adverse event reporting
- Considerations for Design and Implementation of Trials including mitigating toxicities and risks
1. Evolution of Chimeric Antigen Receptors
Early evidence had suggested that adoptive transfer of tumor-infiltrating lymphocytes, after depletion of circulating lymphocytes, could result in a clinical response in some tumor patients however developments showed autologous T-cells (obtained from same patient) could be engineered to express tumor-associated antigens (TAA) and replace the TILS in the clinical setting.
However there were some problems noticed.
- Problem: HLA restriction of T-cells. Solution: genetically engineer T-cells to redirect T-cell specificity to surface TAAs
- Problem: 1st generation vectors designed to engineer T-cells to recognize surface epitopes but engineered cells had limited survival in patients. Solution: development of 2nd generation vectors with co-stimulatory molecules such as CD28, CD19 to improve survival and proliferation in patients
A summary table of limitations of the two types of genetically-modified T-cell therapies were given and given (in modified form) below
Type of Gene-modified T-Cell
| Limitations | aβ TCR | CAR | |
| Affected by loss or decrease of HLA on tumor cells | yes | no | |
| Affected by altered tumor cell antigen processing? | yes | no | |
| Need to have defined tumor target antigen? | no | yes | |
| Vector recombination with endogenous TCR | yes | no |
A brief history of construction of 2nd and 3rd generation CAR-T cells given by cancer.gov:
http://www.cancer.gov/cancertopics/research-updates/2013/CAR-T-Cells
Differences between second- and third-generation chimeric antigen receptor T cells. (Adapted by permission from the American Association for Cancer Research: Lee, DW et al. The Future Is Now: Chimeric Antigen Receptors as New Targeted Therapies for Childhood Cancer. Clin Cancer Res; 2012;18(10); 2780–90. doi:10.1158/1078-0432.CCR-11-1920)
Constructing a CAR T Cell (from cancer.gov)
The first efforts to engineer T cells to be used as a cancer treatment began in the early 1990s. Since then, researchers have learned how to produce T cells that express chimeric antigen receptors (CARs) that recognize specific targets on cancer cells.
The T cells are genetically modified to produce these receptors. To do this, researchers use viral vectors that are stripped of their ability to cause illness but that retain the capacity to integrate into cells’ DNA to deliver the genetic material needed to produce the T-cell receptors.
The second- and third-generation CARs typically consist of a piece of monoclonal antibody, called a single-chain variable fragment (scFv), that resides on the outside of the T-cell membrane and is linked to stimulatory molecules (Co-stim 1 and Co-stim 2) inside the T cell. The scFv portion guides the cell to its target antigen. Once the T cell binds to its target antigen, the stimulatory molecules provide the necessary signals for the T cell to become fully active. In this fully active state, the T cells can more effectively proliferate and attack cancer cells.
2. Adverse Event Reporting and Protocol Considerations
The symposium had been organized mainly in response to two reported deaths of patients enrolled in a CART trial, so that clinical investigators could discuss and formulate best practices for the proper conduct and analysis of such trials. One issue raised was lack of pharmacovigilence procedures (adverse event reporting). Although no pharmacovigilence procedures (either intra or inter-institutional) were devised from meeting proceedings, it was stressed that each institution should address this issue as well as better clinical outcome reporting.
Case Report of a Serious Adverse Event Following the Administration of T Cells Transduced With a Chimeric Antigen Receptor Recognizing ERBB2[2] had reported the death of a patient on trial.
In A phase I clinical trial of adoptive transfer of folate receptor-alpha redirected autologous T cells for recurrent ovarian cancer[3] authors: Lana E Kandalaft*, Daniel J Powell and George Coukos from University of Pennsylvania recorded adverse events in pilot studies using a CART modified to recognize the folate receptor, so it appears any adverse event reporting system is at the discretion of the primary investigator.
Other protocol considerations suggested by the symposium attendants included:
- Plan for translational clinical lab for routine blood analysis
- Subject screening for pulmonary and cardiac events
- Determine possibility of insertional mutagenesis
- Informed consent
- Analysis of non T and T-cell subsets, e.g. natural killer cells and CD*8 cells
3. Consideration for Design of Trials and Mitigating Toxicities
- Early Toxic effects– Cytokine Release Syndrome– The effectiveness of CART therapy has been manifested by release of high levels of cytokines resulting in fever and inflammatory sequelae. One such cytokine, interleukin 6, has been attributed to this side effect and investigators have successfully used an IL6 receptor antagonist, tocilizumab (Acterma™), to alleviate symptoms of cytokine release syndrome (see review Adoptive T-cell therapy: adverse events and safety switches by Siok-Keen Tey).
Below is a video form Dr. Renier Brentjens, M.D., Ph.D. for Memorial Sloan Kettering concerning the finding he made that the adverse event from cytokine release syndrome may be a function of the tumor cell load, and if they treat the patient with CAR-T right after salvage chemotherapy the adverse events are alleviated..
Please see video below:
http link: https://www.youtube.com/watch?v=4Gg6elUMIVE
- Early Toxic effects – Over-activation of CAR T-cells; mitigation by dose escalation strategy (as authors in reference [3] proposed). Most trials give billions of genetically modified cells to a patient.
- Late Toxic Effects – long-term depletion of B-cells . For example CART directing against CD19 or CD20 on B cells may deplete the normal population of CD19 or CD20 B-cells over time; possibly managed by IgG supplementation
Below is a curation of various examples of the need for developing a Pharmacovigilence Framework for Engineered T-Cell Therapies
As shown above the first reported side effects from engineered T-cell or CAR-T therapies stemmed from the first human trial occuring at University of Pennsylvania, the developers of the first CAR-T therapy. The clinical investigators however anticipated the issue of a potential cytokine storm and had developed ideas in the pre-trial phase of how to ameliorate such toxicity using anti-cytokine antibodies. However, until the trial was underway they were unsure of which cytokines would be prominent in causing a cytokine storm effect from the CAR-T therapy. Fortunately, the investigators were able to save patient 1 (described here in other posts) using anti-IL1 and 10 antibodies.
Over the years, however, multiple trials had to be discontinued as shown below in the following posts:
What does this mean for Immunotherapy? FDA put a temporary hold on Juno’s JCAR015, Three Death of Celebral Edema in CAR-T Clinical Trial and Kite Pharma announced Phase II portion of its CAR-T ZUMA-1 trial
The NIH has put a crimp in the clinical trial work of Steven Rosenberg, Kite Pharma’s star collaborator at the National Cancer Institute. The feds slammed the brakes on the production of experimental drugs at two of its facilities–including cell therapies that Rosenberg works with–after an internal inspection found they weren’t in compliance with safety and quality regulations.
In this instance Kite was being cited for manufacturing issues, apparantly fungal contamination in their cell therapy manufacturing facility. However shortly after other CAR-T developers were having tragic deaths in their initial phase 1 safety studies.
Juno Halts Cancer Trial Using Gene-Altered Cells After 3 Deaths
Juno halts its immunotherapy trial for cancer after three patient deaths
JULY 7, 2016
In Juno patient deaths, echoes seen of earlier failed company
JULY 8, 2016
https://www.statnews.com/2016/07/08/juno-echoes-of-dendreon/
After a deadly clinical trial, will immune therapies for cancer be a bust?
JULY 8, 2016
This led to warnings by FDA and alteration of their trials as well as the use of their CART as a monotherapy
Hours after Juno CAR-T study deaths announced, Kite enrolls CAR-T PhII
Well That Was Quick! FDA Lets Juno Restart Trial With a New Combination Chemotherapuetic
Rachel Lerman at Seattle Times
FDA lets Juno restart cancer-treatment trial
Originally published July 12, 2016 at 4:07 pm Updated July 13, 2016 at 11:21 am
SOURCE: http://www.seattletimes.com/business/technology/fda-lets-juno-restart-cancer-treatment-trial/
Juno Therapeutics said Tuesday it will restart one of its most prominent clinical trials after the Food and Drug Administration lifted a hold that had been placed last week on the trial.
The FDA halted Juno’s “Rocket” clinical trial after the company reported thattwo patients undergoing treatment had died. Juno determined the deaths resulted from swelling in the brain caused by a new drug that had been added to the treatment.
he trial seeks to treat patients with relapsed acute lymphoblastic leukemia by using engineered T-cells to attack cancer cells.
Juno added the chemotherapy drug fludarabine to the treatment plan as part of an early step that gets the patient’s body ready for the T-cell injection. Previously, Juno was using only cyclophosphamide in that part of the treatment.
Under an agreement with the FDA, Juno will continue the trial without fludarabine, using only cyclophosphamide instead.
So What Did this all mean for the CAR-T world? Is it end for CAR-T Therapies?
NO!
This, as I have posted before is a matter of pharmacovigilence, the part of drug development and premarketing trials and postmarketing analysis that deals with adverse events and safety
see post of FDA guidelines for CAR-T therapy here
The JUNO trial called for co-treatment with the drug fludarabine, and antimetabolite known, in some cases to promote a cytotoxic lysis syndrome and central nervous system complications. GRANTED these two side effects were deemed RARE however it appears that the addition of fludarabine pre CART therapy aggravated either the side effect of fludarabine pretreatment or a cytoxic lysis syndrome from CAR-T (an adverse event from CAR-T therapy as I had posted here INCLUDING REPORTS OF TWO DEATHS DURING THE MSK CAR-t TRIAL
https://pharmaceuticalintelligence.com/2015/09/14/steroids-inflammation-and-car-t-therapy/
Certainly with so many issues there would seem to be more rigorous work to either establish a pharmacovigilence framework or to develop alternative engineered T cells with a safer profile
However here we went again
New paper sheds fresh light on Tmunity’s high-profile CAR-T deaths
Jason Mast
Editor
The industry-wide effort to push CAR-T therapies — wildly effective in several blood cancers — into solid tumors took a hit last year when Tmunity, a biotech founded by CAR-T pioneer Carl June and backed by several blue-chip VCs, announced it shut down its lead program for prostate cancer after two patients died.
On a personal note this trial was announced in a Bio International meeting here in Philadelphia a few years ago in 2019
see Live Conference Coverage on this site
eProceedings for BIO 2019 International Convention, June 3-6, 2019 Philadelphia Convention Center; Philadelphia PA, Real Time Coverage by Stephen J. Williams, PhD @StephenJWillia2
and the indication was for prostate cancer, in particular hormone resistant castration resistant. Another one was planned for pancreatic cancer from the same group and the early indications were favorable.
From Onclive
Tmunity Therapeutics, a clinical-stage biotherapeutics company, has halted the development of its lead CAR T-cell product following the deaths of 2 patients who were enrolled to a trial investigating its use in solid tumors.1
The patients reportedly died from immune effector cell-associated neurotoxicity syndrome (ICANS), which is a known adverse effect associated with CAR T-cell therapies.
“What we are discovering is that the cytokine profiles we see in solid tumors are completely different from hematologic cancers,” Oz Azam, co-founder of Tmunity said in an interview with Endpoints News. “We observed ICANS. And we had 2 patient deaths as a result of that. We navigated the first event and obviously saw the second event, and as a result of that we have shut down the version one of that program and pivoted quickly to our second generation.”
Previously, with first-generation CAR T-cell therapies in patients with blood cancers, investigators were presented with the challenge of overcoming cytokine release syndrome. Now ICANS, or macrophage activation, is proving to have deadly effects in the realm of solid tumors. Carl June, the other co-founder of Tmunity, noted that investigators will now need to dedicate their efforts to engineering around this, as had been done with tocilizumab (Actemra) in 2012.
The company is dedicated to the development of novel approaches that produce best-in-class control over T-cell activation and direction in the body.2 The product examined in the trial was developed to utilize engineered patient cells to target prostate-specific membrane antigen; it was also designed to use a dominant TGFβ receptor to block an important checkpoint involved in cancer.
Twenty-four patients were recruited for the dose-escalating study and the company plans to release data from high-dose cohorts later in 2021.
“We are going to present all of this in a peer-reviewed publication because we want to share this with the field,” Azam said. “Because everything we’ve encountered, no matter what…people are going to encounter this when they get into the clinic, and I don’t think they’ve really understood yet because so many are preclinical companies that are not in the clinic with solid tumors. And the rubber meets the road when you get in the clinic, because the ultimate in vivo model is the human model.”
Azam added that the company plans to develop a new investigational new drug for version 2, which they hope will result in a safer product.
References
- Carroll J. Exclusive: Carl June’s Tmunity encounters a lethal roadblock as 2 patient deaths derail lead trial, raise red flag forcing rethink of CAR-T for solid tumors. Endpoints News. June 2, 2021. Accessed June 3, 2021. https://bit.ly/3wPYWm0
- Research and Development. Tmunity Therapeutics website. Accessed June 3, 2021. https://bit.ly/3fOH3OR
Forward to 2022
Reprogramming a new type of T cell to go after cancers with less side effects, longer impact
Immunotherapy is one of the more appealing and effective kinds of cancer treatment when it works, but the relatively new approach is still fairly limited in the kinds of cancer it can be used for. Researchers at the Sloan Kettering Institute have discovered a new kind of immune cell and how it could be used to expand the reach of immunotherapy treatments to a much wider pool of patients.
The cells in question are called killer innate-like T cells, a threatening name for a potentially lifesaving innovation. Unlike normal killer T cells, killer innate-like T cells stay active much longer and can burrow further into potentially cancerous tissue to attack tumors. The research team first reported these cells in 2016, but it’s only recently that they were able to properly understand and identify them.
“We think these killer innate-like T cells could be targeted or genetically engineered for cancer therapy,” said the study’s lead author, Ming Li, Ph.D., in a press release. “They may be better at reaching and killing solid tumors than conventional T cells.”
Below is the referenced paper from Pubmed:
Evaluation of the safety and efficacy of humanized anti-CD19 chimeric antigen receptor T-cell therapy in older patients with relapsed/refractory diffuse large B-cell lymphoma based on the comprehensive geriatric assessment system
Affiliations
- PMID: 34587859
- DOI: 10.1080/10428194.2021.1986216
Abstract
Anti-CD19 chimeric antigen receptor (CAR) T-cell therapy has led to unprecedented results to date in relapsed/refractory (R/R) diffuse large B-cell lymphoma (DLBCL), yet its clinical application in elderly patients with R/R DLBCL remains somewhat limited. In this study, a total of 31 R/R DLBCL patients older than 65 years of age were enrolled and received humanized anti-CD19 CAR T-cell therapy. Patients were stratified into a fit, unfit, or frail group according to the comprehensive geriatric assessment (CGA). The fit group had a higher objective response (OR) rate (ORR) and complete response (CR) rate than that of the unfit/frail group, but there was no difference in the part response (PR) rate between the groups. The unfit/frail group was more likely to experience AEs than the fit group. The peak proportion of anti-CD19 CAR T-cells in the fit group was significantly higher than that of the unfit/frail group. The CGA can be used to effectively predict the treatment response, adverse events, and long-term survival.
Introduction
Diffuse large B-cell lymphoma (DLBCL) is the most common subtype of non-Hodgkin lymphoma (NHL), accounting for 30–40% of cases, with the median age of onset being older than 65 years [1]. Although the five-year survival rate for patients with DLBCL has risen to more than 60% with the application of standardized treatments and hematopoietic stem cell transplantation, nearly half of patients progress to relapsed/refractory (R/R) DLBCL. Patients with R/R DLBCL, especially elderly individuals, have a poor prognosis [2,3], so new treatments are needed to prolong survival and improve the prognosis of this population.
As a revolutionary immunotherapy therapy, anti-CD19 chimeric antigen receptor (CAR) T-cell therapy has achieved unprecedented results in hematological tumors [4]. As CD19 is expressed on the surface of most B-cell malignant tumors but not on pluripotent bone marrow stem cells, CD19 has been used as a target for B-cell malignancies, including B-cell acute lymphoblastic leukemia, NHL, multiple myeloma, and chronic lymphocytic leukemia [5]. Despite the wide application and high efficacy of anti-CD19 CAR T-cell therapy, reports of adverse events (AEs) such as cytokine release syndrome (CRS) and immune effector cell-associated neurotoxic syndrome (ICANS) have influenced its use [6]. Especially in elderly patients, AEs associated with anti-CD19 CAR T-cell therapy might be more obvious.
Although anti-CD19 CAR T-cell therapy has been reported in the treatment of NHL, including R/R DLBCL, few studies to date have assessed the safety of anti-CD19 CAR T-cell therapy in elderly R/R DLBCL patients, and its clinical application in the elderly R/R DLBCL population is limited. In ZUMA-1 [7] to R/R DLBCL patients who received CAR T-cell therapy, the CR rate in patients ≥65 years was higher than that of in patients <65 years (75% vs. 53%). Lin et al. [8] reported 49 R/R DLBCL patients (24 patients >65 years, 25 patients <65 years) who received CAR T-cell therapy with a median follow-up of 179 days. The CR rate at 100 days was 51%, while the 6-month progression-free survival (PFS) and overall survival (OS) were 48% and 71%, respectively. Neither of the two studies carried out a comprehensive geriatric assessment (CGA) of fit, unfit, and frail groups of R/R DLBCL patients over 65 years of age and further analyzed the differences in efficacy and side effects in the three groups. The CGA is an effective system designed to evaluate the prognosis and improve the survival of elderly patients with cancer. The CGA system includes age, activities of daily living (ADL), instrumental ADL (IADL), and the Cumulative Illness Rating Score for Geriatrics (CIRS-G) [9].
In this study, elderly R/R DLBCL patients were grouped according to their CGA results (fit vs. unfit/frail) before receiving humanized anti-CD19 CAR T-cell therapy. We then analyzed the efficacy and AEs of anti-CD19 CAR T-cell therapy and compared findings between these groups.
Well it appears that the discriminator was only fitness going into the trial a bit odd that the whole field appears to be lacking in development of Safety Biomarkers.
However Genentech (subsidiary of Roche) may now be using some data to develop therapies which may combat resistance to CART therapies which may provide at least, for now, a toxicokinetic approach to reducing AEs by lowering the amount of CARTs needed to be administered.
Cancer cells deploy various tactics to avoid being targeted and killed by the immune system. A research team led by Roche’s Genentech has now identified one such method that cancer cells use to resist T-cell assault by repairing damage.
To destroy their targets, cancer-killing T cells known as cytotoxic T lymphocytes (CTLs) secrete the toxin perforin to form little pores in the target cells’ surface. Another type of toxin called granzymes are delivered directly into the cells through those portals to induce cell death.
By using high-res imaging in live cells, the Genentech-led team found that the membrane damage caused by perforin could trigger a repair response. The tumor cells could recruit endosomal sorting complexes required for transport (ESCRT) proteins to remove the lesions, thereby preventing granzymes from entering, the team showed in a new study published in Science.
The following is the Science paper
Membrane repair in target cell defenses
Killer T cells destroy virus-infected and cancer cells by secreting two protein toxins that act as a powerful one-two punch. Pore-forming toxins, perforins, form holes in the plasma membrane of the target cell. Cytotoxic proteins released by T cells then pass through these portals, inducing target cell death. Ritter et al. combined high-resolution imaging data with functional analysis to demonstrate that tumor-derived cells fight back (see the Perspective by Andrews). Protein complexes of the ESCRT family were able to repair perforin holes in target cells, thereby delaying or preventing T cell–induced killing. ESCRT-mediated membrane repair may thus provide a mechanism of resistance to immune attack. —SMH
Abstract
Cytotoxic T lymphocytes (CTLs) and natural killer cells kill virus-infected and tumor cells through the polarized release of perforin and granzymes. Perforin is a pore-forming toxin that creates a lesion in the plasma membrane of the target cell through which granzymes enter the cytosol and initiate apoptosis. Endosomal sorting complexes required for transport (ESCRT) proteins are involved in the repair of small membrane wounds. We found that ESCRT proteins were precisely recruited in target cells to sites of CTL engagement immediately after perforin release. Inhibition of ESCRT machinery in cancer-derived cells enhanced their susceptibility to CTL-mediated killing. Thus, repair of perforin pores by ESCRT machinery limits granzyme entry into the cytosol, potentially enabling target cells to resist cytolytic attack.
Cytotoxic lymphocytes, including cytotoxic T lymphocytes (CTLs) and natural killer (NK) cells, are responsible for identifying and destroying virus-infected or tumorigenic cells. To kill their targets, CTLs and NK cells secrete a pore-forming toxin called perforin through which apoptosis-inducing serine proteases (granzymes) are delivered directly into the cytosol. Successful killing of target cells often requires multiple hits from single or multiple T cells (1). This has led to the idea that cytotoxicity is additive, often requiring multiple rounds of sublethal lytic granule secretion events before a sufficient threshold of cytosolic granzyme activity is reached to initiate apoptosis in the target (2).
Loss of plasma membrane integrity induced by cytolytic proteins or mechanical damage leads to a membrane repair response. Damage results in an influx of extracellular Ca2+, which has been proposed to lead to the removal of the membrane lesion by endocytosis, resealing of the lesions by lysosomal secretion, or budding into extracellular vesicles (3). Perforin pore formation was initially reported to enhance endocytosis of perforin (4), but subsequent work has challenged this claim (5). Endosomal sorting complexes required for transport (ESCRT) proteins can repair small wounds and pores in the plasma membrane caused by bacterial pore-forming toxins, mechanical wounding, and laser ablation (6, 7). ESCRT proteins are transiently recruited to sites of membrane damage in a Ca2+-dependent fashion, where they assemble budding structures that shed to eliminate the wound and restore plasma membrane integrity. ESCRT-dependent membrane repair has been implicated in the resealing of endogenous pore-mediated plasma membrane damage during necroptosis (8) and pyroptosis (9).
Localization of target-derived ESCRT proteins to the cytolytic synapse
To investigate whether ESCRT-mediated membrane repair might be involved in the removal of perforin pores during T cell killing, we first determined whether ESCRT proteins in cancer-derived cells were recruited to sites of CTL engagement after perforin secretion. We used CTLs from OT-I mice that express a high-affinity T cell receptor (TCR) that recognizes the ovalbumin peptide SIINFEKL (OVA257-264) bound to the major histocompatibility complex (MHC) allele H-2Kb (10). We performed live-cell microscopy of OT-I CTLs engaging SIINFEKL-pulsed target cells that express enhanced green fluorescent protein (EGFP)–tagged versions of Tsg101 or Chmp4b, two ESCRT proteins implicated in membrane repair (6). To correlate recruitment of ESCRT proteins with perforin exposure in time, we monitored CTL-target interaction in media with a high concentration of propidium iodide (PI), a cell-impermeable fluorogenic dye that can rapidly diffuse through perforin pores to bind and illuminate nucleic acids in the cytosol and nucleus of the target (5). EGFP-tagged ESCRT proteins were consistently recruited to the site of CTL engagement within 30 to 60 s after PI influx (Fig. 1, A and B). EGFP-Tsg101 and EGFP-Chmp4b in target cells accumulated at the cytolytic synapse after PI influx in 25 of 27 (92.6%) and 31 of 33 (93.9%) of conjugates monitored, respectively, compared with a cytosolic EGFP control, which was not recruited (Fig. 1C and movies S1 to S3). Notably, ESCRT-laden material, presumably membrane fragments, frequently detached from the target cell and adhered to the surface of the CTL (Fig. 1, D and E, and movie S2). We observed this phenomenon in ~60% of conjugates imaged in which targets expressed EGFP-Tsg101 or EGFP-Chmp4b (17 of 27 and 20 of 33 conjugates, respectively; Fig. 1D). Shedding of ESCRT-positive membrane from the cell after repair occurs after laser-induced plasma membrane wounding (6, 7). Plasma membrane fragments shed from the target cell into the synaptic cleft likely contain ligands for CTL-resident receptors. Target cell death would separate the CTL and target, revealing target-derived material on the CTL surface.
FIG. 1. Fluorescently tagged ESCRT proteins in targets localize to site of CTL killing after perforin secretion.
(A) Live-cell spinning disk confocal imaging of a fluorescently labeled OT-I CTL (magenta) engaging an MC38 cancer cell expressing EGFP-Tsg101 (green) in media containing 100 μM PI (red). Yellow arrowheads highlight ESCRT recruitment. T-0:00 is the first frame of PI influx into the target cell (time in minutes:seconds). Scale bar, 10 μm. (B) Graph of EGFP-Tsg101 and PI fluorescence intensity at the IS within the target over time, from example in (A). AU, arbitrary units. (C and D) Quantification of CTL-target conjugates exhibiting accumulation of EGFP at the synapse after PI influx (C) or detectable EGFP-labeled material associated with CTL after target interaction (D) (EGFP condition: N = 22 conjugates in seven independent experiments; EGFP-Tsg101 condition: N = 27 conjugates in nine independent experiments; EGFP-Chmp4b condition: N = 33 conjugates in 24 independent experiments). (E) Live-cell spinning disk confocal imaging of OT-I CTL (magenta) killing MC38 expressing EGFP-Chmp4b (green), demonstrating the presence of target-derived EGFP-Chmp4b material (yellow arrowheads) associated with CTL membrane after a productive target encounter. T-0:00 is the first frame of PI influx into the target cell. Scale bar, 10 μm.
3D cryo-SIM and FIB-SEM imaging of CTLs caught in the act of killing target cells
Although live-cell imaging indicated that ESCRT complexes were rapidly recruited at sites of T cell–target cell contact, light microscopy alone is of insufficient resolution to establish that this event occurred at the immunological synapse (IS). We thus sought to capture a comprehensive view of the IS in the moments immediately after secretion of lytic granules. We used cryo–fluorescence imaging followed by correlative focused ion beam–scanning electron microscopy (FIB-SEM), which can achieve isotropic three-dimensional (3D) imaging of whole cells at 8-nm resolution or better (11–13). To capture the immediate response of target cells after perforin exposure, we developed a strategy whereby cryo-fixed CTL-target conjugates were selected shortly after perforation, indicated by the presence of a PI gradient in the target (fig. S1A). In live-cell imaging experiments, PI fluorescence across the nucleus of SIINFEKL-pulsed ID8 target cells began as a gradient and became homogeneous 158 ± 64 s, on average, after initial PI influx (N = 31 conjugates; fig. S1, B and C, and movie S4). Thus, fixed CTL-target conjugates that exhibited a gradient of PI across the nucleus would have been captured within ~3 min of perforin exposure.
Coverslips of CTL-target conjugates underwent high-pressure freezing and were subsequently imaged with wide-field cryogenic fluorescence microscopy followed by 3D cryo–structured illumination microscopy (3D cryo-SIM) performed in a customized optical cryostat (14). We selected candidate conjugates for FIB-SEM imaging on the basis of whether a gradient of PI fluorescence was observed across the nucleus of the target emanating from an attached CTL (movie S5). FIB-SEM imaging of the CTL-target conjugate at 8-nm isotropic voxels resulted in a stack of >10,000 individual electron microscopy (EM) images. The image stack was then annotated using a human-assisted machine learning–computer vision platform to segment the plasma membranes of each cell along with cell nuclei and various organelles (https://ariadne.ai/).
We captured four isotropic 3D 8-nm-resolution EM datasets of CTLs killing cancer cells moments after the secretion of lytic granule contents (Fig. 2A and movie S6). Semiautomated segmentation of the cell membranes, nuclei, lytic granules, Golgi apparatus, mitochondria, and centrosomes of the T cells allow for easier visualization and analysis of the 3D EM data. All FIB-SEM datasets and segmentations can be explored online at https://openorganelle.janelia.org (see links in the supplementary materials). Reconstructed views of the segmented data clearly demonstrate the polarization of the centrosome, Golgi apparatus, and lytic granules to the IS—all of which are hallmarks of CTL killing [Fig. 2A, i to iii, and movie S6, time stamp (TS) 1:33] (15, 16). On the target cell side, we noted cytoplasmic alterations consistent with cell damage including enhanced electron density of mitochondria adjacent to the IS (fig. S2A). Close visual scanning of the postsynaptic target cell membrane in the raw EM data failed to reveal obvious perforin pores, which have diameters (16 to 22 nm) close to the limit of resolution for this technique (17).
FIG. 2. Eight-nm-resolution 3D FIB-SEM imaging of whole CTL-target conjugate.
(A) 3D rendering of segmented plasma membrane predictions derived from isotropic 8-nm-resolution FIB-SEM imaging of a high-pressure frozen OT-I CTL (red) captured moments after secretion of lytic granules toward a peptide-pulsed ID8 ovarian cancer cell (blue). (i) Side-on sliced view corresponding to the gray horizontal line within the inset box in (A). Seen here are 3D renderings of the segmented plasma membrane of the cancer cell (blue) as well as the CTL plasma membrane (red), centrosome (gold), Golgi apparatus (cyan), lytic granules (purple), mitochondria (green), and nucleus (gray). (ii and iii) A zoomed-in view from the dashed white box in (i) shows the details of the IS (ii) and a single corresponding FIB-SEM slice docked onto the segmented data (iii). (B) Single top-down FIB-SEM slice showing overlaid target cell (blue) and CTL (red) segmentation. (i) Zoomed-in view from dashed white box in (B) details the intercellular material (IM) (gray) between the CTL and target at the IS. (C) Zoomed-in image of a 3D rendering of the surface of the target cell plasma membrane (white) opposite the intercellular material (IM) at the IS. Yellow arrowheads mark plasma membrane buds protruding into the synaptic cleft. (i and ii) Accompanying images demonstrate the orientation of the view in (C) with the rendering of the CTL (red) present (i) and removed (ii), and the dashed yellow box in (ii) indicates the area of detail shown in (C).
The segmentation of the two cells illustrates the detailed topography of the plasma membrane of the CTL and target at the IS (fig. S2B). The raw EM and segmentation data reveal a dense accumulation of particles, vesicles, and multilamellar membranous materials, which crowd the synaptic cleft between the CTL and the target (Fig. 2B and movie S6, TS 0:40 to 0:50). The source of this intercellular material (IM) was likely in part the lytic granules because close inspection revealed similar particles and dense vesicles located within as-yet-unreleased granules (fig. S2C). To determine whether some of the membranous material within the intercellular space might also have been derived from the target cell, we examined the surface topology of the postsynaptic target cell. We noted multiple tubular and bud-like protrusions of the target cell membrane that extended into the synaptic space; thus, at least some of the membrane structures observed were still in continuity with the target cell (Fig. 2C and movie S6, TS 0:58 to 1:11). ESCRT proteins have been shown to generate budding structures in the context of plasma membrane repair (6), which led us to next assess where target-derived ESCRT proteins are distributed in the context of the postsecretion IS.
To map the localization of target-derived ESCRT proteins onto a high-resolution landscape of the IS, we captured three FIB-SEM datasets that have associated 3D cryo-SIM fluorescence data for mEmerald-Chmp4b localization (Fig. 3A, fig. S3, and movie S7). This correlative light and electron microscopy (CLEM) revealed that mEmerald-Chmp4b expressed in the target cell was specifically recruited to the target plasma membrane opposite the secreted IM (Fig. 3, B and C). The topography of the plasma membrane at the site of ESCRT recruitment was markedly convoluted, exhibiting many bud-like projections (movie S7, TS 0:37 to 0:40). mEmerald-Chmp4b fluorescence also overlapped with some vesicular structures in the intercellular synaptic space (Fig. 3C). Together, the live-cell imaging and the 3D cryo-SIM and FIB-SEM CLEM demonstrate the localization of ESCRT proteins at the synapse that was the definitive site of CTL killing and was thus spatially and temporally correlated to perforin secretion. These data implicate the ESCRT complex in the repair of perforin pores.
FIG. 3. Correlative 3D cryo-SIM and FIB-SEM reveal localization of target-derived ESCRT within the cytolytic IS.
(A) Three example datasets showing correlative 3D cryo-SIM and FIB-SEM imaging of OT-I CTLs (red) captured moments after secretion of lytic granules toward peptide-pulsed ID8 cancer cells (blue) expressing mEmerald-Chmp4b (green fluorescence). (B and C) Single FIB-SEM slices corresponding to the orange boxes in (A), overlaid with CTL and cancer cell segmentation (B) or correlative cryo-SIM fluorescence of mEmerald-Chmp4b derived from the target cell (C).
Function of ESCRT proteins in repair of perforin pores
We next investigated whether ESCRT inhibition could enhance the susceptibility of target cells to CTL-mediated killing. Prolonged inactivation of the ESCRT pathway is itself cytotoxic (9). We thus developed strategies to ablate ESCRT function that would allow us a window of time to assess CTL killing (fig. S4). We used two approaches to block ESCRT function: CRISPR knockout of the Chmp4b gene or overexpression of VPS4aE228Q (E228Q, Glu228 → Gln), a dominant-negative kinase allele that impairs ESCRT function (fig. S4, A to C) (10). We took care to complete our assessment of target killing well in advance of spontaneous target cell death (fig. S4D).
We tested the capacity of OT-I CTLs to kill targets presenting one of four previously characterized peptides that demonstrate a range of potencies at stimulating the OT-I TCR: SIINFEKL (N4), the cognate peptide, and three separate variants (in order of highest to lowest affinity), SIITFEKL (T4), SIIQFEHL (Q4H7), and SIIGFEKL (G4) (18, 19). Target cells were pulsed with peptide, washed, transferred to 96-well plates, and allowed to adhere before the addition of OT-I CTLs. Killing was assessed by monitoring the uptake of a fluorogenic caspase 3/7 indicator (Fig. 4, A to D, and fig. S5A). Killing was significantly more efficient in ESCRT-inhibited target cells for both CRISPR depletion of Chmp4b (Fig. 4, A to C) and expression of the dominant-negative VPS4aE228Q (Fig. 4D). The difference in killing between the ESCRT-inhibited and control cells was greater when the lower-potency T4, Q4H7, and G4 peptides were used. Nevertheless, ESCRT inhibition moderately improved killing efficiency even in the case of the high-potency SIINFEKL peptide. ESCRT inhibition had no effect on MHC class I expression on the surface of target cells (fig. S5B). Thus, ESCRT inhibition could sensitize target cells to perforin- and granzyme-mediated killing, especially at physiologically relevant TCR-peptide MHC affinities.
FIG. 4. ESCRT inhibition enhances susceptibility of cancer cells to CTL killing and recombinant lytic proteins.
(A) Representative time-lapse data of killing of peptide-pulsed Chmp4b knockout (KO) or control B16-F10 cells by OT-I CTLs. Affinity of the pulsed peptide to OT-I TCR decreases from left to right. Error bars indicate SDs. (B) Images extracted from T4 medium-affinity peptide condition show software-detected caspase 3/7+ events in control and Chmp4b KO conditions. (C and D) Data representing the 4-hour time point of assays measuring OT-I T cells killing either Chmp4b KO (C) or VPS4 dominant-negative (D) target cells with matched controls. Error bars indicate SDs of data. Data are representative of at least three independent experimental replicates. pMHC, peptide-MHC; HA, hemagglutinin. (E and F) Determination of sublytic dose of Prf. B16-F10 cells expressing VPS4a (WT or E228Q) were exposed to increasing concentrations of Prf. Cell viability was determined by morphological gating (E). FSC, forward scatter; SSC, side scatter. (G and H) B16-F10 cells expressing VPS4a (WT or E228Q) were exposed to a sublytic dose of Prf in combination with increasing concentrations of recombinant GZMB (rGZMB). Cell death was determined by Annexin V–allophycocyanin (APC) staining (G). Controls include a condition with no perforin and 5000 ng/ml rGZMB and sublytic perforin with no rGZMB. Graphs in (F) and (H) represent the means of three experiments, and error bars indicate SDs. Statistical significance was determined by multiple unpaired t tests with alpha = 0.05. ns, not significant; *P < 0.05; **P < 0.01; ***P < 0.001.
We next directly tested the effects of ESCRT inhibition when target cells were exposed to both recombinant perforin (Prf) and granzyme B (GZMB), the most potently proapoptotic granzyme in humans and mice (20). Prf alone at high concentrations can lyse cells (4), so we first determined a sublytic Prf concentration that would temporarily permeabilize the plasma membrane but permit the cells to recover. B16-F10 cells expressing either VPS4aWT (WT, wild-type) or VPS4aE228Q were exposed to a range of Prf concentrations in the presence of PI, and cell viability and PI uptake were assessed using flow cytometry. Cells that expressed dominant-negative VPS4aE228Q were more sensitive to Prf alone than ESCRT-competent cells (Fig. 4, E and F). At 160 ng/ml Prf, there was no significant difference in cell viability for either condition. Cells in the live gate that were PI+ had been permeabilized by Prf but recovered. Although the percentage of PI+ live cells was similar under both sets of conditions, the mean fluorescence intensity of PI was higher in live ESCRT-inhibited cells (fig. S6). A delay in plasma membrane resealing could account for this difference.
We reasoned that delaying perforin pore repair might also enhance GZMB uptake into the target. ESCRT-inhibited cells were more sensitive to combined perforin-GZMB when cell death was measured by Annexin V staining (Fig. 4, G and H). Similar results were observed when these experiments were repeated with a murine lymphoma cancer cell line (fig. S7). The observation that ESCRT-inhibited target cells are more sensitive to both CTL-secreted and Prf-GZMB supports the hypothesis that the ESCRT pathway contributes to membrane repair after Prf exposure.
Escaping cell death is one of the hallmarks of cancer. Our findings suggest that ESCRT-mediated membrane repair of perforin pores may restrict accessibility of the target cytosol to CTL-secreted granzyme, thus promoting survival of cancer-derived cells under cytolytic attack. Although other factors may contribute to setting the threshold for target susceptibility to killing, the role of active repair of perforin pores must now be considered as a clear contributing factor.
Acknowledgments
We thank members of the Mellman laboratory for advice, discussion, and reagents; B. Haley for assistance with plasmid construct design; the Genentech FACS Core Facility for technical assistance; S. Van Engelenburg of Denver University for invaluable discussions and guidance; A. Wanner, S. Spaar, and the Ariande AI AG (https://ariadne.ai/) for assistance with FIB-SEM segmentation, CLEM coregistration, data presentation, and rendering; D. Bennett of the Janelia Research Campus for assisting with data upload to https://openorganelle.janelia.org; and the Genentech Postdoctoral Program for support.
Funding: A.T.R. and I.M. are funded by Genentech/Roche. C.S.X., G.S., A.W., D.A., N.I., and H.F.H. are funded by the Howard Hughes Medical Institute (HHMI).
Please look for a Followup Post concerning “Developing a Pharmacovigilence Framework for Engineered T-Cell Therapies”
References
- Ertl HC, Zaia J, Rosenberg SA, June CH, Dotti G, Kahn J, Cooper LJ, Corrigan-Curay J, Strome SE: Considerations for the clinical application of chimeric antigen receptor T cells: observations from a recombinant DNA Advisory Committee Symposium held June 15, 2010. Cancer research 2011, 71(9):3175-3181.
- Morgan RA, Yang JC, Kitano M, Dudley ME, Laurencot CM, Rosenberg SA: Case report of a serious adverse event following the administration of T cells transduced with a chimeric antigen receptor recognizing ERBB2. Molecular therapy : the journal of the American Society of Gene Therapy 2010, 18(4):843-851.
- Kandalaft LE, Powell DJ, Jr., Coukos G: A phase I clinical trial of adoptive transfer of folate receptor-alpha redirected autologous T cells for recurrent ovarian cancer. Journal of translational medicine 2012, 10:157.
Other posts on this site on Immunotherapy and Cancer include
Report on Cancer Immunotherapy Market & Clinical Pipeline Insight
New Immunotherapy Could Fight a Range of Cancers
Combined anti-CTLA4 and anti-PD1 immunotherapy shows promising results against advanced melanoma
Molecular Profiling in Cancer Immunotherapy: Debraj GuhaThakurta, PhD
Pancreatic Cancer: Genetics, Genomics and Immunotherapy
$20 million Novartis deal with ‘University of Pennsylvania’ to develop Ultra-Personalized Cancer Immunotherapy
Upcoming Meetings on Cancer Immunogenetics
Tang Prize for 2014: Immunity and Cancer
ipilimumab, a Drug that blocks CTLA-4 Freeing T cells to Attack Tumors @DM Anderson Cancer Center
Juno’s approach eradicated cancer cells in 10 of 12 leukemia patients, indicating potential to transform the standard of care in oncology
Personalized Medicine Coalition Recognizes Mark Levin with Award for Leadership
Posted in Personalized and Precision Medicine & Genomic Research on September 15, 2014| Leave a Comment »
Personalized Medicine Coalition Recognizes Mark Levin with Award for Leadership
Reporter: Aviva Lev-Ari, PhD, RN
Tiffany Harrington
Personalized Medicine Coalition
tharrington@personalizedmedicinecoalition.org
202-589-1755
FOR IMMEDIATE RELEASE
Personalized Medicine Coalition Recognizes Mark Levin with Award for Leadership
Award to be presented November 12, 2014 highlights lifelong personalized medicine vision
WASHINGTON (Sept. 15, 2014) — The Personalized Medicine Coalition (PMC) today announced that Mr. Mark Levin, co-founder of and partner at Third Rock Ventures, will receive the 2014 Leadership in Personalized Medicine Award for his long commitment to personalized medicine.
“I have always felt that the successful implementation of the principles of personalized medicine into medical practice will depend on the embrace of these principles in the business community,” stated Raju Kucherlapati, Ph.D., Paul C. Cabot professor in the Harvard Medical School Department of Genetics and member of the Presidential Commission for the Study of Bioethical Issues, who nominated Levin for this year’s recognition. His letter stated that no one better exemplifies that commitment than Levin. “Mark relentlessly pursues perfection, and is daring to bring forth novel ideas that can change the world… This is what leadership is all about.”
Mark Levin is a co-founder of Third Rock Ventures and an industry leader with 40 years of experience, most of which were spent launching and building biotechnology companies, including many focused on personalized medicine. At Third Rock Ventures, Levin runs the discovery process to conceive and launch companies around disruptive technologies and innovative science that promise to dramatically improve patients’ lives.
Brian Munroe, PMC board member and senior vice president of government affairs at Endo Health Solutions, seconded the nomination, noting that Levin founded PMC “in the belief that personalized medicine has the potential to revolutionize pharma and biotech,” but that personalized medicine “faces challenges in funding, regulation and implementation, and that the only way the field can reach its potential is if all the stakeholders band together.”
Prior to Third Rock, Mark was co-founder of Mayfield Fund’s life sciences effort, where he was also the founding CEO of Tularik, Cell Genesys/Abgenix, Focal, Stem Cells and Millennium Pharmaceuticals. He served as CEO of Millennium Pharmaceuticals for 12 years. Earlier in his career, he was an engineer and project leader at Lilly and Genentech. He holds an M.S. in chemical and biochemical engineering from Washington University.
“Thank you for this wonderful honor,” stated Mr. Levin. “The best part of the last 40 years has been working with incredible people… to make a difference for patients. It cannot get any better than that!”
Previous recipients of the award include Dr. Janet Woodcock, director of the Food and Drug Administration’s Center for Drug Evaluation and Research, Dr. Elizabeth G. Nabel, director of the National Heart, Lung and Blood Institute at the National Institutes of Health, Dr. Ralph Snyderman, chancellor emeritus of Duke University, Health and Human Services Secretary Michael Levitt, Brook Byers of Kleiner Perkins Caufield & Byers, Dr. William Dalton, president and CEO of the Moffitt Cancer Center, Dr. Leroy Hood, president and co-founder of the Institute for Systems Biology, Randal W. Scott, Ph.D., founder, Genomic Health Inc. and current chairman and CEO, InVitae Corporation, and Kathy Giusti, founder and CEO of the Multiple Myeloma Research Foundation.
Mr. Levin will be honored at the PMC Boston Cocktail Reception the evening of November 11 at the Hotel Commonwealth in Boston, Mass., and the award will be presented at the Personalized Medicine Conference, which will be held at Harvard Medical School on November 12, 2014, and at which Mr. Levin will deliver an address on his vision of personalized medicine. The Personalized Medicine Conference is co-hosted and presented by Partners HealthCare Center for Personalized Genetic Medicine (PCPGM), Harvard Business School and Harvard Medical School. The Conference is organized by PCPGM in association with the American Association for Cancer Research and PMC. The distinctive collaboration of this group of organizations reflects the diversity, depth and breadth of the Conference’s program.
SOURCE
From: <tharrington@personalizedmedicinecoalition.org>
Date: 15 Sep 2014 12:09:21 -0400
To: <avivalev-ari@alum.berkeley.edu>
Subject: Mark Levin to Receive PMC Leadership Award
Somatic, germ-cell, and whole sequence DNA in cell lineage and disease profiling
Posted in Amino acids, Best evidence, CANCER BIOLOGY & Innovations in Cancer Therapy, Computational Biology/Systems and Bioinformatics, Curation, Developmental biology, Disease Biology, Evolutionary cognition, Experimental validation, Explanatory, Gene Regulation, Gene Regulation and Evolution, Genetics & Pharmaceutical, Genomic Expression, Historical relevance, Innovations, Metabolism, Molecular Genetics & Pharmaceutical, mtDNA, Nitric Oxide in Health and Disease, Personalized and Precision Medicine & Genomic Research, Pharmaceutical Drug Discovery, Pharmacologic toxicities, Phosphorylation, Proteins, Proteomics, Signaling, Signaling & Cell Circuits, Small Molecules in Development of Therapeutic Drugs, Transcriptomics, Translational Science, Ubiquitinylation, tagged ablation of toxicity, breast cancer, breast cancer genes, Cancer - General, gene maps, Mitochondrial DNA, mtDNA mutations, novel therapeutic targets, phylogeography, population migration, somatic DNA, transcription, transfer RNA on September 14, 2014| Leave a Comment »
Somatic, germ-cell, and whole sequence DNA in cell lineage and disease profiling
Curator: Larry H Bernstein, MD, FCAP
In humans, mitochondrial DNA spans about 16,500 DNA building blocks (base pairs), representing a small fraction of the total DNA in cells. Mitochondrial DNA contains 37 genes, essential for normal mitochondrial function and thirteen of them provide instructions for making enzymes involved in inner membrane function. The remaining 24 genes are transcribed into transfer RNA (tRNA) and ribosomal RNA (rRNA), which are needed to transfer amino acids into proteins.
Somatic mutations occur in the DNA of certain cells during a person’s lifetime and typically are not passed to future generations. They differ from germ-line mutations that have a lineal descent from the maternal parent, and they occur later in life. Mutations in the sperm DNA are not carried on to future generations, as the sperm mitochondria are destroyed after the egg is fertilized.
There is limited evidence linking somatic mutations in mitochondrial DNA with certain cancers, including breast, colon, stomach, liver, and kidney tumors. These mutations might also be associated with cancer of blood-forming tissue (leukemia) and cancer of immune system cells (lymphoma). There are many heritable diseases that are related to germ-line mutations, and germ-line mutations have a role in many common diseases. Mitochondrial DNA is particularly vulnerable to the effects of reactive oxygen species (ROS), and with a limited ability of the mitochondrion to repair itself, ROS easily damage mitochondrial DNA. The repair mechanism is tied to ubiquitinylation system. A list of disorders associated with mitochondrial genes is provided from Wikipedia.
Inherited changes in mitochondrial DNA may be associated with pathologies in growth and development, and multiorgan system disorders, as mutations disrupt the mitochondria’s ability to generate the cell’s energy. The effects of these conditions are most pronounced in organs and tissues with high energy requirements (such as the heart, brain, and muscles). Although the health consequences of inherited mitochondrial DNA mutations vary widely, some frequently observed features include muscle weakness and wasting, problems with movement, diabetes, kidney failure, heart disease, loss of intellectual functions (dementia), hearing loss, and abnormalities involving the eyes and vision.
A buildup of somatic mutations in mitochondrial DNA has been considered to have a role in or associated with increased risk of certain age-related disorders such as heart disease, Alzheimer disease, and Parkinson disease, and the severity of many mitochondrial disorders is thought to be associated with the percentage of mitochondria affected by a particular genetic change. Consequently, the progressive accumulation of these mutations over a person’s lifetime may play a role in aging.
Mitochondrial DNA is typically diagrammed as a circular structure with genes and regulatory regions labeled.
Mitochondrial DNA
http://ghr.nlm.nih.gov/html/images/chromosomeIdeograms/mitochondria/wholeMitochondria.jpg
Additional Resources:
- Additional NIH Resources – National Institutes of Health
NHGRI Talking Glossary: Mitochondrial DNA
- Gene Reviews – Clinical summary (6 links)
- Research Resources – Tools for researchers (5 links)
- OMIM – Genetic disorder catalog (2 links)
- Genetics Education
- Human Genome Project
- Resources for Genetics Researchers
mtDNA : The Eve Gene – by Stephen Oppenheimer
Mutations are a cumulative dossier of our own maternal prehistory. The main task of DNA is to copy itself to each new generation. We can use these mutations to reconstruct a genetic tree of mtDNA, because each new mtDNA mutation in a prospective mother’s ovum will be transferred in perpetuity to all her descendants down the female line. Each new female line is thus defined by the old mutations as well as the new ones.
By looking at the DNA code in a sample of people alive today, and piecing together the changes in the code that have arisen down the generations, biologists can trace the line of descent back in time to a distant shared ancestor. Because we inherit mtDNA only from our mother, this line of descent is a picture of the female genealogy of the human species.
formation of gene trees
The diagram above shows the drawing of gene trees using single mutations
http://www.bradshawfoundation.com/journey/images/gene-diagram3.gif
Not only can we retrace the tree, but by taking into account here the sampled people came from, we can see where certain mutations occurred – for example, whether in Europe, or Asia, or Africa. What’s more, because the changes happen at a statistically consistent (though random) rate, we can approximate the time when they happened. This has made it possible, during the late 1990s and in the new century, for us to do something that anthropologists of the past could only have dreamt of: we can now trace the migrations of modern humans around our planet.
It turns out that the oldest changes in our mtDNA took place in Africa 150,000 – 190,000 years ago. Then new mutations start to appear in Asia, about 60,000 – 80,000 years ago. This tells us that modern humans evolved in Africa, and that some of us migrated out of Africa into Asia after 80,000 years ago. A method established in 1996, which dates each branch of the gene tree by averaging the number of new mutations in daughter types of that branch, has stood the test of time.
A final point on the methods of genetic tracking of migrations: it is important to distinguish this new approach to tracing the history of molecules on a DNA tree, known as phylogeography (literally ‘tree-geography’), from the mathematical study of the history of whole human populations, which has been used for decades and is known as classical population genetics.
The two disciplines are based on the same Mendelian biological principles, but have quite different aims and assumptions, and the difference is the source of much misunderstanding and controversy. The simplest way of explaining it is that phylogeography studies the prehistory of individual DNA molecules, while population genetics studies the prehistory of populations. Put another way, each human population contains multiple versions of any particular DNA molecule, each with its own history and different origin.
gene-diagram
The diagram above shows the tracing of gene spread geographically.
Green disks represent migrant new growth on the tree
http://www.bradshawfoundation.com/journey/images/gene-diagram4.gif
http://www.bradshawfoundation.com/journey/eve.html
David Moskowitz, MD, PhD
Founder and President, GenoMed
Germline genes make the best drug targets
- They operate earliest in the disease pathway
- Unlike tissue-expressed genes, which operate years after the disease began
- But which everybody else is using as drug targets
Variation in germline DNA is where all disease starts
- Cancer patients overexpress oncogenes and underexpress tumor suppressors
beginning in their germline DNA
- Mutations in tumor DNA are “private”
- Each tumor is a “snowflake”
Tumor-expressed genes can be compensatory, not causative
- “Passengers, not drivers”
- We have the drivers
Tumorigenesis SNPs
Using a SNPnet™ covering only 1/3 of the genome, we found about
2,500 genes associated with each of 6 different cancers in whites
- Nobody else has found any yet
- This will change in 2-3 years
We estimate 10,000 genes per cancer
What cellular program takes up 1/3-1/2 of the genome?
What program takes up >1/3 of the genome?
- Differentiation…
Does sporadic cancer arise when a tissue stem cell fails to differentiate?
- In the embryo, the surrounding tissue expresses “fields”
Lent C. Johnson published a “field” based hypothesis of bone tumors that coincides with differentiation at the
- METAPHYSIS
- HYPOPHYSIS
and the type CELL – chondroblast, osteoblast, giant cell (osteoclast), fibroblast
Orthopedic surgeons use magnetic fields for healing
- of powerful transcription factors.
- Not so in adult life: a proliferating tissue stem cell is literally on its own.
Germlines hold the key to effective “differentiation therapy”
- Ideal for patients with stage 3-4 cancer
- Examples of differentiation therapy:
- 1,25-vitamin D and
- retinoic acid
Non-toxic but more effective treatment for late stage disease,
GenoMed’s 2,500 cancer-causing genes:
- ½ are oncogenes,
- ½ are tumor suppressors
Design inhibitors to oncogenes
- Screen 1st for toxicity;
- genomic epidemiology guarantees clinical efficacy
Jewish Heritage Written in DNA
By Kate Yandell | Sept 9, 2014
Fully sequenced genomes of more than 100 Ashkenazi people clarify the group’s history and provide a reference for researchers and physicians trying to pinpoint disease-associated genes.
A whole-genome sequence study from 128 healthy Jewish people is aimed at identifying disease-associated variants in the jewish population of Ashkenazi ancestry, according to a study published Sept 9 in Nature Communications. The library of sequences confirms earlier conclusions about Ashkenazi history hinted at by more limited DNA sequencing studies. The sequences point to an approximate 350-person bottleneck in the Ashkenazi population as recently as 700 years ago (1400 A.D.), and suggest that the population has a mixture of European and Middle Eastern ancestry.
The study “provides a very nice reference panel for the very unique population of Ashkenazi Jews,” said Alon Keinan, who studies human population genomics at Cornell University in New York. Keinan
is acknowledged in the study but was not involved in the research.
“One might have thought that, after many years of genetic studies relating to Ashkenazi Jews . . . there would be little room for additional insights,” Karl Skorecki of the Rambam Healthcare Campus
in Israel who also was not involved in the study wrote in an e-mail to The Scientist. The study, he added, provides “a powerful further validation and further resolution of the demographic history of
the Ashkenazi Jews in relation to non-Jewish Europeans that is reassuringly consistent with inferences drawn from two decades of studies using uniparental regions . . . and from array-based data.”
Itsik Pe’er, coauthor of the new study and an associate professor of computer science at Columbia University in New York City, recalled that several years ago, he and his colleagues kept running into the same problem as they tried to understand the genetics of disease in Ashkenazi populations. They were comparing their Ashkenazi samples to the only control genomes that were available, which were of largely non-Jewish European origin. The Ashkenazi genomes had variation that was absent in these general European genomes, making it hard to distinguish rare variants in Ashkenazi people.
“Technology is there to tell us everything in that [Ashkenazi] patient’s genome, but the genome was not there to distinguish the variants that are there and to tell us whether they are normal or whether we should get worried,” said Pe’er. Pe’er’s group teamed up with researchers from additional universities and hospitals in the U.S., Belgium, and Israel to sequence a collection of healthy Ashkenazi people’s genomes. The panel of reference sequences performs better than a group of European genomes at filtering out harmless variants from Ashkenazi Jewish genomes, thereby making it easier to identify potentially harmful ones. According to Pe’er, researchers will also be able to use the panel to infer
more complete sequences from partially sequenced genomes by looking for familiar sequences from the reference genomes.
The team also used its data to better understand the history of the Ashkenazi Jewish people through analyzing both level of similarity within Ashkenazi genomes and between Ashkenazi and non-Jewish
European genomes. By analyzing the length of identical DNA sequences that Ashkenazi individuals share, the researchers were able to estimate that 25 to 32 generations ago, the Ashkenazi Jewish population shrunk to just several hundred people, before expanding rapidly to eventually include the millions of Ashkenazi Jews alive today. Further, the researchers concluded that modern Ashkenazi Jews likely have an approximately even mixture of European and Middle Eastern ancestry. This suggests that after the Jewish people migrated from the Middle East to Europe, they recruited people from local European populations.
These results are compatible with those of prior work on mitochondrial DNA (mtDNA), which is passed on maternally. This prior work suggested that Ashkenazi men from the Middle East intermarried with local European women. The Ashkenazi population “hasn’t been likely as isolated as at least some researchers considered,” said Keinan.
Finally, the newly sequenced genomes shed light on the deeper history of Europe, showing that the European and Middle Eastern portions of Ashkenazi ancestry diverged just around 20,000 years ago.
“This is, I think, the first evidence from whole human genomes that the most important wave of settlement from the Near East was most likely shortly after the Last Glacial Maximum . . . and, notably, before the Neolithic transition—which is what researchers working on mitochondrial DNA have been arguing for some years,” Martin Richards, an archeogeneticist at the University of Huddersfield in the U.K., told The Scientist in an e-mail.
Skorecki noted that the new study “demonstrates the utility of sequencing whole genomes in a diverse population… with sufficient numbers of samples, parent population information, and
computational analytic power, we can expect important and surprising utilities for personal genomic and insights in terms of human demographic history from whole genomes.”
- Carmi et al., “Sequencing an Ashkenazi reference panel supports population-targeted personal genomics and illuminates Jewish and European origins,” Nature
Communications,
http://dx.doi.org:/10.1038/ncomms5835, 2014.
Added Layers of Proteome Complexity
By Anna Azvolinsky | July 17, 2014
Scientists discover a broad spectrum of alternatively spliced human protein variants within a well-studied family of genes.
There may be more to the human proteome than previously thought. Some genes are known to have several different alternatively spliced protein variants, but the Scripps Research Institute’s Paul Schimmel and his colleagues have now uncovered almost 250 protein splice variants of an essential, evolutionarily conserved family of human genes. The results were published today (July 17) in Science.
Focusing on the 20-gene family of aminoacyl tRNA synthetases (AARSs), the team captured AARS transcripts from human tissues—some fetal, some adult—and showed that many of these messenger RNAs (mRNAs) were translated into proteins. Previous studies have identified
several splice variants of these enzymes that have novel functions, but uncovering so many more variants was unexpected, Schimmel said. Most of these new protein products lack the catalytic domain but retain other AARS non-catalytic functional domains. “The main point is that a vast new area of biology, previously missed, has been uncovered,”
said Schimmel.
“This is an incredible study that fundamentally changes how we look at the protein-synthesis machinery,” Michael Ibba, a protein translation researcher at Ohio State University who was not involved in the work, told The Scientist in an e-mail. “The unexpected and potentially vast
expanded functional networks that emerge from this study have the potential to influence virtually any aspect of cell growth.”
The team—including researchers at the Hong Kong University of Science and Technology, Stanford University, and aTyr Pharma, a San Diego-based biotech company that Schimmel co-founded—comprehensively captured and sequenced the AARS mRNAs from six human tissue types using high-throughput deep sequencing. While many of the transcripts were expressed in each of the tissues, there was also some tissue specificity.
Next, the team showed that a proportion of these transcripts, including those missing the catalytic domain, indeed resulted in stable protein products: 48 of these splice variants associated with polysomes. In vitro translation assays and the expression of more than 100 of these variants in cells confirmed that many of these variants could be made into
stable protein products.
The AARS enzymes—of which there’s one for each of the 20 amino acids—bring together an amino acid with its appropriate transfer RNA (tRNA) molecule. This reaction allows a ribosome to add the amino acid to a growing peptide chain during protein translation. AARS
enzymes can be found in all living organisms and are thought to be among the first proteins to have originated on Earth.
To understand whether these non-catalytic proteins had unique biological activities, the researchers expressed and purified recombinant AARS fragments, testing them in cell-based assays for proliferation, cell differentiation, and transcriptional regulation, among other
phenotypes. “We screened through dozens of biological assays and found that these variants operate in many signaling pathways,” said Schimmel.
“This is an interesting finding and fits into the existing paradigm that, in many cases, a single gene is processed in various ways [in the cell] to have alternative functions,” said Steven Brenner, a computational genomics researcher at the University of California, Berkeley.
The team is now investigating the potentially unique roles of these protein splice variants in greater detail—in both human tissue as well as in model organisms. For example, it is not yet clear whether any of these variants directly bind tRNAs.
“I do think [these proteins] will play some biological roles,” said Tao Pan, who studies the functional roles of tRNAs at the University of Chicago. “I am very optimistic that interesting biological functions will come out of future studies on these variants.”
Brenner agreed. “There could be very different biological roles [for some of these proteins]. Biology is very creative that way, [it’s] able to generate highly diverse new functions using combinations of existing protein domains.” However, the low abundance of these variants
is likely to constrain their potential cellular functions, he noted.
Because AARSs are among the oldest proteins, these ancient enzymes were likely subject to plenty of change over time, said Karin Musier-Forsyth, who studies protein translational
at the Ohio State University. According to Musier-Forsyth, synthetases are already known to have non-translational functions and differential localizations. “Like the addition of post-translational modifications, splicing variation has evolved as another way to repurpose protein function,” she said.
One of the protein variants was able to stimulate skeletal muscle fiber formation ex vivo and upregulate genes involved in muscle cell differentiation and metabolism in primary human skeletal myoblasts. “This was really striking,” said Musier-Forsyth. “This suggests
that, perhaps, peptides derived from these splice variants could be used as protein-based therapeutics for a variety of diseases.”
W.S. Lo et al., “Human tRNA synthetase catalytic nulls with diverse functions,” Science, http://dx.doi.org:/10.1126/science.1252943, 2014.
It’s Not Only in DNA’s Hands
By Ilene Schneider LabRoots Aug 22, 2014
Blood stem cells have the potential to turn into any type of blood cell, whether it is the oxygen-carrying red blood cells or the immune system’s many types of white blood cells that help fight infection. How exactly is the fate of these stem cells regulated? Preliminary findings from research conducted by scientists from the Weizmann Institute of Science and the Hebrew University are starting to reshape the conventional understanding of the way blood stem cell fate decisions are controlled, thanks to a new technique for epigenetic analysis developed at these institutions. Understanding epigenetic mechanisms (environmental influences other than genetics) of cell fate could lead to the deciphering of the molecular mechanisms of many diseases,
including immunological disorders, anemia, leukemia, and many more. The study of epigenetics also lends strong support to findings that environmental factors and lifestyle play a more prominent
role in shaping our destiny than previously realized.
The process of differentiation – in which a stem cell becomes a specialized mature cell – is controlled by a cascade of events in which specific genes are turned “on” and “off” in a highly regulated and accurate order. The instructions for this process are contained within the DNA itself in short regulatory sequences.
- These regulatory regions are normally in a “closed” state, masked by special proteins called histones to ensure against unwarranted activation. Therefore, to access and “activate”
the instructions, - this DNA mask needs to be “opened” by epigenetic modifications of the histones so it can be read by the necessary machinery.
In a paper published in Science, Dr. Ido Amit and David Lara-Astiaso of the Weizmann Institute’s Department of Immunology, along with Prof. Nir Friedman and Assaf Weiner of the Hebrew University of Jerusalem, charted – for the first time – histone dynamics during blood development. Thanks to the new technique for epigenetic profiling they developed, in which just a handful of cells – as few as 500 – can be sampled and analyzed accurately, they have identified the exact
DNA sequences, as well as the various regulatory proteins, that are involved in regulating the process of blood stem cell fate.
This research has also yielded unexpected results: As many as
- 50% of these regulatory sequences are established and opened during intermediate stages of cell development.
The meaning of the research is that epigenetics can be active at stages in which it had been thought that cell destiny was already set. “This changes our whole understanding of the process of blood stem cell fate decisions,” says Lara-Astiaso, “suggesting that the process is more
dynamic and flexible than previously thought.”
Although this research was conducted on mouse blood stem cells, the scientists believe that the mechanism may hold true for other types of cells. “This research creates a lot of excitement in the field, as it sets the groundwork to study these regulatory elements in humans,” says Weiner.
Largest Cancer Genetic Analysis Reveals New Way of Classifying Cancer
Thu, 08/07/2014 – 2:24pm
Researchers with The Cancer Genome Atlas (TCGA) Research Network have completed the largest, most diverse tumor genetic analysis ever conducted, revealing a new approach to classifying cancers. The work, led by researchers at the UNC Lineberger Comprehensive
Cancer Center at the University of North Carolina at Chapel Hill and other TCGA sites, not only
- revamps traditional ideas of how cancers are diagnosed and treated, but could also have
- a profound impact on the future landscape of drug development.
“We found that one in 10 cancers analyzed in this study would be classified differently using this new approach,” said Chuck Perou, PhD, professor of genetics and pathology, UNC Lineberger member and senior author of the paper, which appears online Aug. 7 in Cell.
“That means that
- 10 percent of the patients might be better off getting a different therapy—that’s huge.”
Since 2006, much of the research has identified cancer as not a single disease, but many types and subtypes and has defined these disease types based on the tissue—breast, lung, colon, etc.—in which it originated. In this scenario, treatments were tailored to which
tissue was affected, but questions have always existed because some treatments work, and fail for others, even when a single tissue type is tested.
In their work, TCGA researchers analyzed more than 3,500 tumors across 12 different tissue types to see how they compared to one another — the largest data set of tumor genomics ever assembled, explained Katherine Hoadley, PhD, research assistant professor
in genetics and lead author. They found that
- cancers are more likely to be genetically similar based on the type of cell in which the cancer originated, compared to the type of tissue in which it originated.
This is fundamental premise of pathology! (Larry Bernstein) It goes back to Rudolph Virchow.
“In some cases, the cells in the tissue from which the tumor originates are the same,” said Hoadley. “But in other cases, the tissue in which the cancer originates is made up of multiple types of cells that can each give rise to tumors. Understanding the cell in which the cancer originates appears to be very important in determining the subtype of a tumor
and, in turn, how that tumor behaves and how it should be treated.”
Perou and Hoadley explain that the new approach may also shift how cancer drugs are developed, focusing more on the development of drugs targeting larger groups of cancers with genomic similarities, as opposed to a single tumor type as they are currently developed.
One striking example of the genetic differences within a single tissue type is breast cancer.
The breast, a highly complex organ with multiple types of cells, gives rise to multiple types of breast cancer; luminal A, luminal B, HER2-enriched and basal-like, which was previously known. In this analysis, the basal-like breast cancers looked more like ovarian cancer
and cancers of a squamous-cell type origin, a type of cell that composes the lower-layer of a tissue, rather than other cancers that arise in the breast.
“This latest research further solidifies that basal-like breast cancer is an entirely unique disease and is completely distinct from other types of breast cancer,” said Perou. In addition, bladder cancers were also quite diverse and might represent at least three different disease types that also showed differences in patient survival.
As part of the Alliance for Clinical Trials in Oncology, a national network of researchers conducting clinical trials, UNC researchers are already testing the effectiveness of carboplatin—a common treatment for ovarian cancer—on top of standard of care chemotherapy for triple-negative breast cancer (TNBC) patients, of which 80 percent are the basal-like subtype. The results of this study (called CALGB40603)
were just published on Aug. 6 in the Journal of Clinical Oncology and showed a benefit of carboplatin in TNBC patients. This new clinical trial result suggests that there may be great value in comparing clinical results across tumor types for which this study highlights as having common genomic similarities.
As participants in TCGA, UNC Lineberger scientists have been involved in multiple individual tissue type studies including most recently an analysis of a comprehensive genomic profile of lung adenocarcinoma. Perou’s seminal work in 2000 led to the first discovery of breast
cancer as not one, but in fact, four distinct subtypes of disease. These most recent findings should continue to lay the groundwork for what could be the next generation of cancer diagnostics.
Source: University of North Carolina at Chapel Hill School of Medicine
New Gene Tied to Breast Cancer Risk
Wed, 08/06/2014
Marilynn Marchione – AP Chief Medical Writer – Associated Press
It’s long been known that faulty BRCA genes greatly raise the risk for breast cancer. Now, scientists say a more recently identified, less common gene can do the same.
Mutations in the gene can make breast cancer up to nine times more likely to develop, an international team of researchers reports in this week’s New England Journal of Medicine.
About 5 to 10 percent of breast cancers are thought to be due to bad BRCA1 or BRCA2 genes. Beyond those, many other genes are thought to play a role but how much each one raises risk has not been known, said Dr. Jeffrey Weitzel, a genetics expert at City of Hope Cancer Center
in Duarte, Calif.
The new study on the gene- called PALB2 – shows “this one is serious,” and probably is the most dangerous in terms of breast cancer after the BRCA genes, said Weitzel, one of leaders of the study.
It involved 362 members of 154 families with PALB2 mutations – the largest study of its kind. The faulty gene seems to give a woman a 14 percent chance of breast cancer by age 50 and 35 percent by age 70 and an even greater risk if she has two or more close relatives with the disease.
That’s nearly as high as the risk from a faulty BRCA2 gene, Dr. Michele Evans of the National Institute on Aging and Dr. Dan Longo of the medical journal staff write in a commentary in the journal.
The PALB2 gene works with BRCA2 as a tumor suppressor, so when it is mutated, cancer can flourish.
How common the mutations are isn’t well known, but it’s “probably more than we thought because people just weren’t testing for it,” Weitzel said. He found three cases among his own breast cancer
patients in the last month alone.
Among breast cancer patients, BRCA mutations are carried by 5 percent of whites and 12 percent of Eastern European (Ashkenazi) Jews. PALB2 mutations have been seen in up to 4 percent of families with a history of breast cancer.
Men with a faulty PALB2 gene also have a risk for breast cancer that is eight times greater than men in the general population.
Testing for PALB2 often is included in more comprehensive genetic testing, and the new study should give people with the mutation better information on their risk, Weitzel said. Doctors say that people with faulty cancer genes should be offered genetic counseling and may want to consider more frequent screening and prevention options, which can range from hormone-blocking pills to breast removal.
The actress Angelina Jolie had her healthy breasts removed last year after learning she had a defective BRCA1 gene.
The study was funded by many government and cancer groups around the world and was led by Dr. Marc Tischkowitz of the University of Cambridge in England. The authors include Mary-Clare King, the University of Washington scientist who discovered the first breast
cancer predisposition gene, BRCA1.
Study: http://www.nejm.org/doi/full/10.1056/NEJMoa1400382
Gene info: http://ghr.nlm.nih.gov/gene/PALB2
Structure of the DDB1–CRBN E3 ubiquitin ligase in complex with thalidomide
Eric S. Fischer, Kerstin Böhm, John R. Lydeard, Haidi Yang, …, J. Wade Harper, Jeremy L. Jenkins & Nicolas H. Thomä
Nature (07 Aug 2014); 512, 49–53 http://dx.doi.org:/10.1038/nature13527
Published online 16 July 2014
In the 1950s, the drug thalidomide, administered as a sedative to pregnant women, led to the birth of thousands of children with multiple defects. Despite the teratogenicity of thalidomide and its derivatives lenalidomide and pomalidomide,
- these immunomodulatory drugs (IMiDs) recently emerged as effective treatments for
multiple myeloma and 5q-deletion-associated dysplasia.
- IMiDs target the E3 ubiquitin ligase CUL4–RBX1–DDB1–CRBN (known as CRL4CRBN) and
- promote the ubiquitination of the IKAROS family transcription factors IKZF1 and IKZF3 by CRL4CRBN.
Here we present crystal structures of the DDB1–CRBN complex bound to thalidomide,
lenalidomide and pomalidomide. The structure establishes that
- CRBN is a substrate receptor within CRL4CRBN and enantioselectively binds IMiDs.
Using an unbiased screen, we identified the
- homeobox transcription factor MEIS2 as an endogenous substrate of CRL4CRBN.
Our studies suggest that IMiDs block endogenous substrates (MEIS2) from binding to CRL4CRBN while the ligase complex is recruiting IKZF1 or IKZF3 for degradation.
This dual activity implies that
- small molecules can modulate an E3 ubiquitin ligase and thereby upregulate or downregulate the ubiquitination of proteins.
Curator’s Viewpoint:
The short pieces may not appear to be so closely connected, except for the last subject on the pharmaceutical targeting of an E3 ubiquitin ligase ubiquitination of proteins, but even in that case, we have to keep in mind that protein formation by amino acid transcription, remodeling, and recapture of amino acids are in equilibrium through ubiquitylation. So I put it there. The DNA in populations ties some mutations to disease that is tied specifically to populations, not only the sephardic population, but in Asia as well.
The next article for consideration is methodological considerations. The BRCA2 in the sephardic population is one of a number of mutations we can identify, extending to Tay Sachs disease, for instance. How this might have occurred in the history of the jewish people is not so obvious, except perhaps in the segregation of the jewish population for centuries. The mutation would be confined within the population with limited marriage outside of the jewish community. It has been known for some time that there is a Cohen gene that traces back to the priests (Kohanim) of the Holy Temple, the descendents of Aaron (Aharon), the brother of Moses. The priests would stand at the Ark and bless the congregation in the most holy convocation of Yom Kippur, according to tradition. Marriages were arranged between the bride and the groom. Of course, arranged marriages were also the case in other ethnic communities, and between the privileged.
That was dramatically the case during the reign of Queen Victoria of England, with Royal arrangements across Europe.
That would be a factor in the transmission of hemophilia, and in mental disorders in the Royal families. Haemophilia figured prominently in the history of European royalty in the 19th and 20th centuries. Britain’s Queen Victoria, through two of her five daughters (Princess Alice and Princess Beatrice), passed the mutation to various royal houses across the continent, including the royal families of Spain, Germany and Russia. Victoria’s son Prince Leopold, Duke of Albany suffered from the disease. The Prince Leopold, Duke of Albany KG KT GCSI GCMG GCStJ (Leopold George Duncan Albert; 7 April 1853 – 28 March 1884) was the eighth child and fourth son of Queen Victoria and Prince Albert of Saxe-Coburg and Gotha. Leopold was later created Duke of Albany, Earl of Clarence, and Baron Arklow. He had haemophilia, which led to his death at the age of 30. The sex-linked X chromosome disorder manifests almost entirely in males, although the gene for the disorder is located on the X chromosome and may be inherited from either mother or father. Expression of the disorder is much more common in males than in females. This is because, although the trait is recessive, males only inherit one X chromosome, from their mothers. Of course, this is classical Mendelian genetics. Victoria appears to have been a spontaneous or de novo mutation and is usually considered the source of the disease in modern cases of haemophilia among royalty. The mutation would probably be assumed today to have occurred at the conception of Princess Alice, as she was the only known carrier among Victoria and Albert’s first seven children. Leopold was a sufferer of haemophilia and her daughters Alice and Beatrice were confirmed carriers of the gene.
Cousin marriage is marriage between people with a common grandparent or other more distant ancestor. In various cultures and legal jurisdictions, Marriages between first and second cousins account for over 10% of marriages worldwide, and they are common in the Middle East, where in some nations they account for over half of all marriages. Proportions of first-cousin marriage in the United States, Europe and other Western countries like Brazil have declined since the 19th century, though even during that period they were not more than 3.63 percent of all unions in Europe. Cousin marriage is allowed throughout the Middle East for all recorded history, and is used mostly in Syria. It has often been chosen to keep cultural values intact through many generations and preserve familial wealth. In Iraq the right of the cousin has also traditionally been followed and a girl breaking the rule without the consent of the ibn ‘amm could have ended up murdered by him. The Syrian city of Aleppo during the 19th century featured a rate of cousin marriage among the elite of 24% according to one estimate, a figure that masked widespread variation: some leading families had none or only one cousin marriage, while others had rates approaching 70%. Cousin marriage rates were highest among women, merchant families, and older well-established families. The percentage of Iranian cousin marriages increased from 34 to 44% between the 1940s and 1970s. Cousin marriage among native Middle Eastern Jews is generally far higher than among the European Ashkenazim, who assimilated European marital practices after the diaspora.
The essential elements of the marriage contract were now an offer by the man, an acceptance by the woman, and the performance of such conditions as the payment of dowry. According to anthropologist Ladislav Holý, cousin marriage is not an independent phenomenon but rather one expression of a wider Middle Eastern preference for agnatic solidarity, or solidarity with one’s father’s lineage.
A 2009 study found that many Arab countries display some of the highest rates of consanguineous marriages in the world, and that first cousin marriages which may reach 25-30% of all marriages. Research among Arabs and worldwide has indicated that consanguinity could have an effect on some reproductive health parameters such as postnatal mortality and rates of congenital malformations.
In the terraced streets of Bradford, Yorkshire, a child’s death is anything but rare. At the boy’s inquest, coroner Mark Hinchliffe said Hamza Rehman had died because his Pakistan-born parents (shopkeeper Abdul and housewife Rozina) are first cousins. Muslims have practiced marriages between first cousins in non-prohibited countries since the time of the Quran.
Four years before, Hamza’s older sister, three-month-old Khadeja, had died of the same brain disorder which causes fits, sickness and chest infections. The couple had another baby born with equally devastating neurological problems.
A heartbroken Mr Rehman told the inquest that he and his wife were unsure whether to have any more children. The coroner expressed deep sympathy before saying that Hamza’s death should serve as a warning to others.
I have diverged somewhat onto the genetic risks of consanguinous marriages, which George Darwin, son of Charles Darwin, argues were had a small effect in then English society. But most importantly, we see the larger factor here of social and familial inheritance, and also the concept of cultural identity.
Insofar as the somatic and mitochondrial mutations are concerned, I call attention to the finding in the GWAS study above discussed that the results were supportive of the conclusions from mtDNA. This gives some reason to consider whether sufficient information is obtained from the mtDNA, without the more robust GWAS. One cannot fully consider this without some knowledge of the methodology of specimen preparation.
It is not difficult to prepare mitochondria from cells and obtain a very good preparation before further analysis, whether of the membrane structures, the enzymatic activity, or of the DNA and RNA polynucleotides. The separation is easily achieved with differential centrifugation. On the other hand, the finding of the basal layer of epithelium having a different signature than the superficial layer, established by the genomic studies, but known histologically for non-neoplastic tissue, is a matter for cell separation methods that are not easy. It is from the lower layer of cells that we derive carcinoma in-situ. These cells were identified in breast, are expected to be found in uterus, and were like the cells in ovarian-cancer, which suggested the use of a common treatment regimen as adjunct in triple negative breast cancer and ovarian cancer. The importance of a suuficiently prepared cellular specimen as opposed to tissue specimen can’t be taken for granted.
Germline Genes and Drug Targets: Medicine more Proactive and Disease Prevention more Effective.
Posted in Computational Biology/Systems and Bioinformatics, Personalized and Precision Medicine & Genomic Research on September 10, 2014| Leave a Comment »
Germline Genes and Drug Targets: Medicine more Proactive and Disease Prevention more Effective
Curators for a forthcoming article on Predictive Therapeutics:
- Aviva Lev-Ari, PhD, RN and Larry H Bernstein, MD, FCAP –
Reporter for the content, below:
- Aviva Lev-Ari, PhD, RN
A Perspective on Predictive Therapeutics by Larry H Bernstein, MD, FCAP
The approach is novel. I am quite versed in vit D metabolism and in retinol and retinoids.
The articles should not be ads, but should lay out a hypothesis, proof of concept, and extension to therapeutics.
The germ-line concept as an alternative approach to somatic cell genomics is powerful. Somatic mutations I have thought for some time come late, and are part of a cascade of changes that lead to adaptive mutational expression.
What he is proposing with respect to the identification of SNPs associated with key germ-line targets is unexpected, and I can’t comment on it, but it would tie in somewhat with the surprising and rapid progress being made with stem cells. But the success with stem cells still does not have to deal with an organ system in a living animal or person. It’s a long way to Tipperari!
His attack to the problem is by identifying key differentiation related SNPs, and to address the targets with known INDISPENSIBLE metabolic and nontoxic agents for pharmacotherapy.
I would not go so far as the statement that all disease is related to germline genomic expression, if that is an extension of the hypothesis. But it does bring together the functional concept of disordered metabolism related to germline SNP expression in a broader sense than just cancer, and perhaps related to immune tolerance, TLR receptors, and a number of chronic diseases. It is an interesting divergence.
There is sufficient complexity in life processes that I can’t really conceptualize how he puts this all together.
About the Pioneer @ GenoMed, Inc.
Physician-scientist who identified angiotensin I-converting enzyme (ACE) as a “master” disease gene; President and CEO of GenoMed; St. Louis, MO
David W. Moskowitz, MD- Chairman, Chief Executive Officer, and Chief Medical Officer
Dr. Moskowitz majored in Chemistry (summa cum laude) at Harvard College, Biochemistry (first class honours) at Merton College, Oxford, and received an MD (cum laude) from the Harvard-MIT Division in Health Sciences and Technology (Harvard Medical School). He trained for 7 years in Internal Medicine, Biochemistry, and Nephrology at Washington University School of Medicine in St. Louis before spending 11 years on the faculty of St. Louis University School of Medicine. Since 1994, Dr. Moskowitz has experienced first hand the clinical effectiveness of knowing a disease-associated gene (the angiotensin converting enzyme, or ACE, gene). Dr. Moskowitz is a pioneer in the field of medical genomics, and has been recognized for his groundbreaking treatment of diseases associated with the angiotensin I-converting enzyme, such as chronic renal failure due to hypertension or type II diabetes.
VIEW VIDEO
http://www.genomed.com/about-us.html
GenoMed is a Next Generation DMtm company that uses medical genomics to improve patient outcomes. GenoMed is working to translate knowledge of medical genomics–the study of which genes cause disease–into clinical practice. We combine biotechnology with Disease Management (DM). We develop new and better drugs, we use existing drugs for new disease indications, and we uncover disease before symptoms arise. By studying disease genes, we hope to make medicine more proactive and disease prevention more effective.
Drug discovery: Once GenoMed identifies a disease gene without any existing therapy, the company pursues strategic alliances with large, research-oriented pharmaceutical companies to develop new drugs against the target.
Using existing drugs for new clinical indications: Occasionally, knowing a disease gene can make an existing drug more effective. For example, GenoMed has demonstrated that a proprietary regimen of an existing ACE inhibitor can dramatically delay the progression of end-stage kidney disease due to Type 2 diabetes or hypertension in both African American and Caucasian men, as well as the progression of peripheral vascular disease, and even emphysema. This is the first time an ACE inhibitor has been found to be useful for emphysema.
Gene-based diagnostic tests: Knowing the genes which cause a disease allows a physician to diagnose that disease before symptoms ever become visible. In clinical medicine, the earlier the diagnosis, the better the clinical outcome.
GenoMed was inspired by Dr. David Moskowitz’s research on the angiotensin I-converting enzyme (ACE) gene during the mid 1990s. His lab discovered that ACE was a “master” disease gene. ACE was found to be associated with about 160 common, serious diseases such as type 2 diabetes, common cancers (except for prostate and breast), and psychiatric diseases. Moskowitz, a nephrologist, treated 1,000 of his own patients based on his knowledge of diseases caused in part by ACE. His early efforts produced dramatic results — the rate of progression of kidney disease due to high blood pressure was reduced by an average of 300% in both African American and Caucasian male patients. Through this new treatment, patients who normally reached dialysis in 4 years were not predicted to reach end-stage kidney disease for 16 years. Patient outcomes for kidney failure due to type 2 diabetes, atherosclerotic peripheral vascular disease, and emphysema (COPD) were equally exciting. In February 2001 Moskowitz founded GenoMed with the help of industry veterans Jerry White, Richard Kranitz and Peter Brooks.
Competitive Position
Like the science of genomic medicine, GenoMed takes a targeted and efficient approach to finding and commercializing disease genes. Our past experience in medical genomics has helped us to identify a class of single nucleotide polymorphisms (SNPs) that we believe has strong associations with all common diseases. We use the least expensive, fastest throughput genotyping currently available in the world. Our ability to move much more quickly than larger, more bureaucratic corporations maximizes our intellectual property produced per dollar spent.
The medical industry is on an unsustainable course. Costs, already high, are still rising while outcomes mostly haven’t changed. The aging of the Baby Boomers threatens to bankrupt Medicare in the next few years. China and India can’t afford kidney dialysis for the hundreds of millions of people who need it. Only prevention can improve outcomes while simultaneously lowering costs. Fortunately, genomics lets us find the root causes of disease. GenoMed is inventing the field of preventive molecular medicine. We are also inventing a new business model for medicine.
GenoMed guarantees the best outcomes in the medical literature for diabetes, high blood pressure (also called “hypertension”), COPD (also called “emphysema”), sickle cell disease, or your money back! (more info…)
The best outcomes in the medical literature, or it’s free™.
SOURCE
Help us make the world dialysis-free by 2020.
Technology and Approach
GenoMed’s primary scientific initiative consists of its SNPnet©. The SNPnet©™ is the set of single nucleotide polymorphisms (SNPs) GenoMed uses to locate disease genes. We use a fishing metaphor since finding disease genes is like fishing for a handful of letters in an ocean of three billion letters. Our SNPnet© is currently made up of over 80,000 SNPs and covers the entire human genome. Once the disease genes are identified, disease-associated SNPs will be placed onto a single DNA chip, the HealthChip®, for clinical diagnostic testing.
Targeted Diseases
Diseases with Published Superior Clinical Outcomes*:
- Sickle Cell Disease
- Kidney failure due to type 2 (“adult onset”) diabetes
- Kidney failure due to high blood pressure
- Emphysema (“COPD”)
- Poor circulation due to high blood pressure
* see Moskowitz, “ACE Example”
If you would like information about subscribing to our Clinical Outcomes Improvement Program (COIP®) for one of the above diseases, then Contact GenoMed.
Diseases in Clinical Trials:
- Cancer (of any organ, any stage, including leukemias and lymphomas)
- HIV
- SARS
- Influenza
- Hepatitis (A, B, and C)
- Multiple sclerosis
- Alopecia
- Psoriasis (see Moskowitz, “Role of ACE”)
- Chronic fatigue syndrome/fibromyalgia
- Lupus
- Rheumatoid Arthritis
- Alzheimer’s Disease
- Parkinson’s Disease
- ALS (“Lou Gehrig’s Disease”)
- Age-related macular degeneration
- Glaucoma
- West Nile virus (see Moskowitz, “Role of ACE”)
Pre-Clinical Research (looking for disease-predisposition genes):
Currently collections are underway or scheduled for the following diseases:
All Cancers
GenoMed would be delighted to discuss collaborations with qualified groups that are dedicated to solving specific diseases
Clinical Outcomes Improvement Program (COIP®)
PATIENTS
| GenoMed invites patients to join its Clinical Outcomes Improvement Program (COIP®). GenoMed has so far published superior clinical outcomes for the following diseases: hypertension, type 2 diabetes, and emphysema. If you have one of these diseases, please contact us. An annual subscription to GenoMed’s COIP® costs $200. We would like to work with your current physician. |
GenoMed is currently recruiting individuals for 2 clinical trials: |
Awards
|
SOURCE
http://www.genomed.com/companynews/publications.html
Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer
Posted in Artificial Intelligence in CANCER, Biological Networks, Biomarkers & Medical Diagnostics, CANCER BIOLOGY & Innovations in Cancer Therapy, Cancer Prevention: Research & Programs, ChatGPT, GPT-4, Computational Biology/Systems and Bioinformatics, Gene Regulation and Evolution, Genome Biology, Health Economics and Outcomes Research, Machine Learning, Personalized and Precision Medicine & Genomic Research, tagged antitumor therapy, Artificial intelligence, Bioinformatics, Cancer - General, Cell Biology, Computational Biology/Systems and Bioinformatics, DNA, DNA Sequencing, driver mutations, gene expression, genetics, genome, genomics, GPT, informatics, InfraNodus, knowledge graph, Lung cancer, mutation, mutational analysis, National Institutes of Health, Non-small cell lung cancer, Personalized medicine, Proceedings of the National Academy of Sciences of the United States of America, Prostate cancer, research, smoking, The Cancer Genome Atlas (TCGA), The Clinical Lung Cancer Genome Project (CLCGP), whole exome sequencing on September 5, 2014| Leave a Comment »
Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer
Curator, Writer: Stephen J. Williams, Ph.D.
UPDATED 08/11/2025
Human Curation vs. AI tools: ChatGPT & Knowledge Graphs [KG] Output: A case study for the following original curation:
- Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer
This update was performed by the following methods:
A. GPT 5 Text analysis and Reasoning
B. Insertion of Knowledge Graph on topic Curation of Genomic Analysis from Non Small Cell Lung Cancer Studies from Nodus Labs using InfraNodus software
C. Domain Knowledge Expert evaluation of the Update outcomes
This article has the following Structure:
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
Part B: InfraNodus Analysis of manual curation and Knowledge Graph Creation
Part C: Chat GPT 5 Analysis of Manually Curated Material
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
Results of Article Update with GPT 5
1. GPT5 alone was not able to understand the goal of the article, namely to determine knowledge gaps in a particular research area involving 5 genomic studies on lung cancer patients
2. GPT5 alone was not able to group concepts or comonalities between biological pathways unless supplied with a manually curated list of KEGG pathways from a list of mutated genes. However this precluded any effect that fusion proteins had on the analysis and so GPT5 would only concentrate on mutated genes commonly found in literature
3. GPT was not able to access some of the open Access databases like NCBI Gene Ontology database
Results of Article Update with KnowledgeGraph presentation to GPT 5
4. As the Knowledge Graph understood the importance of fusion proteins and transversions, the knowledgegraph augmented the GPT analysis and so enriched the known pathways as well as could correctly identify the less represented pathways in the knowledge graph
5. This led to the identification of many novel signaling pathways not identified in the original analysis, and was able to perform this task with ease and speed
6. GPT with InfraNodus Analysis was able to propose pertinent questions for future research (the goal of the original curation) such as:
- How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
- How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Novelty in comparison to Original article published on 09/05/2014
7. it appears that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis
8. by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs
9. The combination of ChatGPT5 and Knowledge graphs of this manually curated biomedical text added a further layer of complexity of gaps of knowledge not seen in the original curations including the need to study noncanonical signaling pathways like WNT and Hedgehog in smoker versus nonsmoker cohorts of lung cancer patients
A Comparison of Manual Expert-Curative and an LLM-based analysis of Knowledge Gaps in Non Small Lung Cancer Whole Exome Sequencing Studies and a Use Case Example of Chat GPT 5
Part A: Introduction to LLM, Knowledge Graph software InfraNodus, ChatGPT5 and Background Information on curated material for Test Case
The development of Large Language Models (LLMs), together with development of knowledge graphs, have facilitated the ability to analyze text and determine the relationships among the various concepts contained within series of texts. These concepts and relationships can be visualized, and new insights inferred from these visualizations. As a result, this type of analysis suggests new directions and lines of research.
Alternatively, these types of visualizations can also reveal gaps in knowledge which should be addressed. A new type of LLM and visualization tools have been developed to understand the gaps in knowledge in biomedical text.
Nodus Labs InfrNodus AI Knowledge Graph Software Tools Allow Text Relationship Visualization and Integrated AI Functionality
Infranodus makes knowlegde graphs from text and then is able to visualize the relationships between concepts (or nodes). In doing so, the tool also highlights the various knowledge gaps (or large differences between nodes) which can be used to investigate new hypotheses and research directions of previously univestigated relationships between concepts. This generates new research questions, in which these gaps can be used as prompts in the software’s integrated AI tool. The AI tool, much like a GPT, returns recommendations for research to be conducted in the area.
In addition, the InfraNodus software can detect if text is too biased on a particular concept or conclusion, and using a GPT3 or GPT4, can determine if the nodes are too dispersed and will recommend which gaps should be focused on.
The software can upload any biomedical text in various formats
A full demonstration is on their website but a good summary is found on their Youtube site at
https://www.youtube.com/watch?v=wCEhiIJsmrg
A couple of use cases include
- AI-Assisted Thinking & Insight Generation:
- AI Writing & Creative Thinking
- Mind Mapping
- Brainstorming
- Knowledge Graphs & Personal Notes
- Introspection & Self-Reflection
- Marketing & Consulting:
- Market Research
- Customer Reviews, Voice of Customer
- Search Engine Optimization
- Qualitative Research & Thematic Analysis
- Innovation & Trend Research
- Research, Text Visualization & Analysis:
- Text Network Analysis
- Text Mining & Topic Modeling
- Overview and Summarization
Previously we had manually curated and analyzed the knowledge gaps from a series of publications on whole exome sequencing of biopsied tumors from cohorts of non small lung cancer patients. This curation (from 2016) is seen in the lower half of this updated link below and I separated with a bar and highlighted in Yellow as Text for AI Analysis.
A literature analysis of the driver mutations found in five NSLC exome sequencing projects:
- Comprehensive genomic characterization of squamous cell lung cancers. Nature 2012, 489(7417):519-525.
- A genomics-based classification of human lung tumors. Science translational medicine 2013, 5(209):209ra153.
- Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et al: Genomic landscape of non-small cell lung cancer in smokers and never-smokers. Cell 2012, 150(6):1121-1134.
- Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et al: Mapping the hallmarks of lung adenocarcinoma with massively parallel sequencing. Cell 2012, 150(6):1107-1120.
- Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et al: Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer. Nature genetics 2012, 44(10):1104-1110.
were performed.
The purpose of this analysis was to uncover biological functions related to the sets of mutated genes with limited research publications in the area of non small cell lung cancer. The identification of such biological functions would represent a gap in knowledge in this disease. In addition, this analysis attempted to find new lines of research or potential new biotargets to investigate for lung cancer therapy.
However this manual method is time consuming and may miss relationships not defined in a GO ontology or gene knowledgebases.
Therefore we turned to an AI-driven approach:
- Using InfraNodus ability to develop a knowledge graph based on our curation and determine if the AI platform could infer knowledge gaps
- Utilize Chat GPT5 to analyze the same curated set to determine if OpenAI analysis would lead to the similar analysis from curated material
- Determine if combining a knowledge graph within GPT would lead to a higher level of analysis
See below (Part D) of this update for the curated studies which were included in this analysis and the text which was entered into both InfraNodus and Chat GPT5.
As a summary, it seems that manual curation is necessary to assist in the building of relevant knowledge graphs in the biomedical fields to augment generative AI analysis. In addition, it appears that , by itself, generative AI is not optimized for inference of higher concepts from biomedical text, and therefore, at this point, requires the input from human curators developing domain-specific knowledge graphs.
Part B. InfraNodus Analysis of manual curation and Knowledge Graph Creation
Methods:
Text of the curation was copied and directly pasted into the text analysis module of InfraNodus. There was no editing of words however genes in the curation were linked to their GeneCard entry. GeneCards is a database run by the Weizmann Institute. InfraNodus utilizes a combination of LLMs and its own GraphRAG system to provide insights from text analysis. While it leverages various models, including those from OpenAI and Anthropic, it’s not limited to a single LLM. Instead, InfraNodus integrates these models within its GraphRAG framework, which enhances their capabilities by adding a relational understanding of the context through a knowledge graph.
InfraNodus then autogenerates a knowledge graph and returns entities and relationships between entities. InfraNodus offers the opportunity to modify the knowledge graph however for this analysis we used the first graph InfraNodus generated. Inspection of this graph (as shown below) was deemed reasonable.
Results
The knowledge graph of the input text is shown below:
InfraNodus generated Knowledge Graph of 5 WES Non Smal Cell Lung Cancer studies involving smokers and non smokers
Four main concepts were returned: tumors, genes, literature, and mutations.
A snapshot of the Analysis window is given below. It should be noted that InfraNodus felt there needed to be more connections between Pathway and Mutational Patterns.
An InfraNodus reposrt with Knowlege Graph on Whole Exome Sequencing studies in NSCLC to determine mutational spectrum in smokers versus non smokers
Auto generated summary report
Context name: text_250808T0144
Created on: aug 7, 2025 9:47 pm
Last updated on: aug 7, 2025 10:10 pm
Main concepts:
[[tumors]], analysis, [[mutations]], identify, [[lung]], [[genes]]
Main topics:
- Tumor Genomics: [[tumors]] [[lung]] reveal
- Genetic Alterations: identify [[genes]] study
- Pathway Analysis: analysis pathway literature
- Mutation Patterns: [[mutations]] [[egfr]] [[rbm10]]
Structural gap (topics to connect):
- Pathway Analysis: analysis pathway
- Smoking Influence: mutational [[smoking]]
Topical connectors:
alk clinical [[egfr]] mutational pathway [[paper]] found key literature study [[genomic]] reveal [[transversion]]
Top relations / ngrams:
1) [[lung]] [[tumors]]
2) alk fusion
3) link function
4) eml alk
5) function [[gene_ontology]]
Modulary: 0.47
Relations:
InfraNodus identified 744 relations between entities (nodes)
A list of some of the more frequent are given here:
| source | target | occurrences | weight | betweenness | |
| [[lung]] | [[tumors]] | 8 | 24 | 0.4676 | |
| analysis | pathway | 5 | 12 | 0.2291 | |
| significantly | [[genes]] | 5 | 9 | 0.1074 | |
| significantly | [[mutated]] | 4 | 12 | 0.0281 | |
| [[mutated]] | [[genes]] | 4 | 12 | 0.0847 | |
| [[transversion]] | high | 3 | 12 | 0.0329 | |
| [[smoking]] | history | 3 | 10 | 0.0352 | |
| study | identify | 3 | 9 | 0.2051 | |
| mutational | pattern | 3 | 9 | 0.0921 | |
| [[rbm10]] | [[mutations]] | 3 | 8 | 0.1776 | |
| literature | analysis | 3 | 7 | 0.2218 | |
| [[egfr]] | [[mutations]] | 3 | 7 | 0.2139 | |
| [[transversion]] | group | 3 | 7 | 0.0259 | |
| enriched | cohort | 3 | 6 | 0.0219 | |
| [[whole_exome_sequencing]] | [[tumors]] | 3 | 6 | 0.3485 | |
| identify | [[genes]] | 3 | 6 | 0.2268 | |
| including | analysis | 3 | 5 | 0.1985 | |
| alteration | [[genes]] | 3 | 4 | 0.1298 | |
| [[tumors]] | analysis | 3 | 4 | 0.5192 | |
| alk | fusion | 2 | 15 | 0.0671 | |
| link | function | 2 | 14 | 0.0269 | |
| function | [[gene_ontology]] | 2 | 13 | 0.0054 | |
Notice how the betweenness or importance of connection of disparate concepts vary but are high between concepts like tumors and analysis, or lung and tumor, however many important linked concepts like alk and fusion may have low betweenness but are mentioned frequently and have a much higher weight or closeness to each other. Gene-mutations-transversions-smoking seem to have a high correspondence to each other
For a full list please see the file
InfraNodus relations five WES studies on NSCLC and smoking
sjwilliams_text_250808T0144_nodedataon NSCLCWESstudies
Generated the following responses using AI to bridge the gap between
- Mutation Patterns: [[mutations]], [[egfr]], [[rbm10]]and
- Genetic Alterations: identify, [[genes]], study:The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.elaborate
<MainTopics>
- Tumor Genomics: [[tumors]], [[lung]], reveal, base, [[genomic]], [[data]], classification, subtype,
- Genetic Alterations: identify, [[genes]], study, alteration, reported, significantly, [[lung_adenocarcinoma]], key,
- Pathway Analysis: analysis, pathway, literature, including, activation, target, [[nsclc]], [[patients]],
- Mutation Patterns: [[mutations]], [[egfr]], [[rbm10]], male, enriched, cohort, [[erbb2]], noted,
- Smoking Influence: mutational, [[smoking]], [[transversion]], pattern, high, notably, [[smokers]], show,
- Research Strategies: found, [[paper]], [[omics]], unique, profile, result, multus, characterization,
- Targeted Therapy: alk, [[lung_cancer]], fusion, [[therapy]], ro, eml, include, targeted,
- Mutation Signatures: clinical, [[tumor]], approach, mutation, sample, signature, gender, specific,
- Gene Function: link, [[gene]], note, function, author, [[gene_ontology]],
</MainTopics>
<TopicalGap>:
- Genetic Alterations: identify [[genes]]
- Mutation Patterns: [[mutations]] [[egfr]]
</TopicalGap>
questions generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?elaborate
ideas generated using AI to help you explore “alk, clinical, [[egfr]], mutational, pathway, [[paper]], found, key, literature, study, [[genomic]], reveal, [[transversion]]…”:Develop a predictive model that utilizes genomic data and smoking history to forecast patient response to targeted therapies. This model would identify key mutational signatures linked to EGFR and other genes, highlighting the impact of smoking-induced transversions on drug efficacy.elaborate
Project Notes
”
The recent comprehensive studies on lung adenocarcinoma have significantly advanced our understanding of the genetic landscape by identifying key mutations and their intricate interactions. Notably, EGFR and RBM10 exhibit distinct mutational patterns, with RBM10 inactivations being notably enriched in male cohorts. This gender-linked enrichment underscores a potential differential oncogenic pathway involving ERBB2 and RB1 alterations.
Moreover, these projects emphasize the quest to map significant gene alterations within lung adenocarcinoma. The identification of such genes not only corroborates prior reports but also expands upon them by highlighting new connections between mutation signatures and clinical factors like smoking history. These findings are crucial as they can inform future therapeutic targeting strategies, ensuring that personalized treatment approaches consider both gender-specific genomic enrichments and mutation-driven tumorigenesis pathways elucidated through rigorous analyses.”
<ConceptualGateways>
alk
clinical
[[egfr]]
mutational
pathway
[[paper]]
found
key
literature
study
[[genomic]]
reveal
[[transversion]]
</ConceptualGateways>
How do mutational patterns, specifically EGFR mutations and transversions related to smoking history, influence the effectiveness of targeted therapies in NSCLC patients?
The report from the NCI Bulletin outlines significant advancements in understanding lung cancer through genome sequencing projects. These studies have revealed a plethora of genetic and epigenetic alterations across various forms of lung tumors, including adenocarcinomas, squamous cell carcinomas, and small cell lung cancers. Notably, some identified alterations could be targeted by existing therapies, providing potential new avenues for treatment.Dr. Meyerson emphasizes the complexity of these genetic changes, highlighting that distinct mechanisms inactivating genes can vary between tumors. The report also notes gaps in knowledge regarding non-coding DNA alterations, which comprise a major part of the human genome.Key findings include:1. Comprehensive genomic analyses revealing unique driver mutations in lung adenocarcinoma, such as those affecting MET and ERBB2, alongside significant mutations in known cancer drivers like TP53 and KRAS.2. A classification system based on genomic data enabling more accurate patient stratification—achieving a 75% classification rate of lung cancer subtypes.3. Smoking history is shown to influence mutational patterns significantly, with smokers exhibiting a higher incidence of point mutations compared to never-smokers.Moreover, the integration of genomic data and pathway analysis highlighted recurrent mutations across various pathways related to tumorigenesis, suggesting new therapeutic targets and underscoring the importance of personalized medicine approaches that factor in gender-specific mutation distributions.This synthesis of findings not only corroborates earlier studies but also extends our understanding of the interplay between genomic alterations, smoking habits, and clinical outcomes in lung cancer. Future research is needed to explore the implications of these findings further and to develop targeted therapies that leverage the identified genetic alterations.
- Tumor Genomics
- Genetic Alterations
- Pathway Analysis
- Mutation Patterns
Main Ideas Summary from Infranodus:
The report from the NCI Bulletin highlights significant developments in lung cancer genomics through five genome sequencing projects. These studies have uncovered various genetic and epigenetic alterations across multiple forms of lung cancer, including adenocarcinomas, squamous cell cancers, and small cell lung cancers. Notably, these alterations may correspond to existing drugs, offering new avenues for targeted therapy.
Key findings include the identification of unique mutations in genes like NF1, MET, and ERBB2, with particular attention to smoking’s role in mutational patterns. The analysis shows that smokers exhibit a higher incidence of specific point mutations, marking a distinct divergence in mutation profiles compared to never-smokers.
The research also emphasizes the need for continued exploration of the data to link mutation signatures with clinical outcomes, particularly regarding gender-specific differences in mutation prevalence. Emerging insights suggest that pathways involving MYC and alterations in splicing factors could be vital targets for future therapeutic strategies.
Overall, the studies collectively underscore an urgent need for integrating genomic data into clinical practice, which can lead to more personalized treatment approaches for lung cancer patients by considering both the genetic landscape of tumors and their histories, such as smoking exposure. The ongoing efforts to map gene alterations within lung adenocarcinoma not only reinforce existing knowledge but also reveal new potential therapeutic targets that can significantly impact patient outcomes.
Questions to Explore from InfraNodus:
How does the interaction between [[EGFR]] mutations and sex-specific gene alterations, including [[RBM10]], influence treatment outcomes in lung adenocarcinoma?
How does the intersection of mutational patterns from smoking influence pathway activation in NSCLC, and can identifying these interactions improve targeted therapy development?
Part C: Chat GPT 5 Analysis of Manually Curated Material
Now let us see how Chat GPT5 analyzed the same material.
Methods
Nice — I’ll work from the KEGG-pathway list shown in your text (the table of pathways with PubMed counts) and call out major KEGG pathways that are not represented there.
Important caveat: “Not represented in the table” below means not listed in the KEGG-pathway hits shown in your pasted literature analysis, not that these pathways never play a role in lung cancer. Absence from that table can reflect lack of reporting in the specific WES/WGS studies or the PubMed keyword search used — it’s not proof the pathway is uninvolved biologically.
The above Important caveat was very important because it showed that ChatGPT5 could understand what my experimental goals were, or at least understood the problem I was presenting to ChatGPT5!
Major KEGG pathways missing from the provided KEGG list
(However Note that GPT did NOT take into account the mutational spectrum of the studies or the gene lists supplied in the curation)
These are commonly cited cancer-related KEGG pathways that do not appear in the table you gave:
- Wnt signaling pathway
- Notch signaling pathway
- Hedgehog signaling pathway
- TGF-beta signaling pathway
- Hippo signaling pathway
- p53 signaling pathway — (note: TP53 is mutated in many tumors, so p53 biology is implicated in the text, but “p53 signaling” does not appear in that KEGG hits table)
- Apoptosis (intrinsic/extrinsic apoptotic pathways)
- Autophagy
- NF-kappa B signaling pathway
- Ubiquitin-mediated proteolysis / proteasome
- DNA repair pathways (several separate KEGG entries):
- Homologous recombination
- Mismatch repair
- Nucleotide excision repair
- Base excision repair
- Fanconi anemia pathway
- Cellular metabolism pathways commonly in cancer:
- Glycolysis / Gluconeogenesis
- Citrate cycle (TCA cycle) / Oxidative phosphorylation
- Fatty acid metabolism / beta-oxidation
- Pentose phosphate pathway
- Immune-signaling / antigen processing:
- T cell receptor signaling pathway
- B cell receptor signaling pathway
- Antigen processing and presentation
- Autocrine/paracrine inflammation/chemokine signaling beyond the one low-count entry (general cytokine networks other than the single “cytokine–cytokine receptor interaction” hit)
- Signal transduction modules sometimes separate in KEGG:g. Calcium signaling was listed in your table, but other modules like cGMP–PKG signaling or PKA/PKC broader signaling networks are not.
Quick summary
The KEGG table in your text highlights many cancer and receptor-tyrosine/MAPK/PI3K related pathways (cell cycle, MAPK, ErbB, JAK-STAT, focal adhesion, etc.). What’s not listed are numerous developmental morphogen pathways (Wnt/Notch/Hedgehog/TGF-β/Hippo), many DNA-repair and core metabolic pathways, canonical apoptosis/autophagy/ubiquitin pathways, and broad adaptive-immune signaling pathways.
If you want, I can:
- (A) cross-check this against the full KEGG pathway list and produce a definitive “KEGG universe → present vs absent in your table” spreadsheet, or
- (B) prioritize which of the missing pathways you’d most want investigated in lung tumor sequencing data and suggest genes to look for.
Which follow-up would you prefer?
Now taking out the KEGG list I gave GPT in order to force GPT to do a similar but unbiased analysis
From the studies you’ve shared, we can identify which KEGG pathways are under-represented (i.e., appear less frequently altered than expected) in the altered genes in lung cancer.
To do this, we note that the researchers used KEGG and other pathway analysis tools (PathScan, literature curation, proteomics) to see which biological pathways the mutated genes mapped to.
While many well-known cancer pathways were found to be activated (MAPK, PI3K-AKT, mTOR, cell cycle, oxidative stress, etc.), a few key pathways were reported as unexpectedly low in mutation frequency despite their known role in cancer biology.
KEGG Pathways Under-Represented in Altered Genes in Lung Cancer
From the descriptions in Papers 1–5, these are the main pathways that appear under-represented:
- MAPK signaling pathway
- Normally, MAPK is a major cancer driver pathway. In this dataset, MAPK activity was high in proteomics, but many tumors lacked mutations in MAPK pathway genes.
- This means MAPK activation is often non-mutational (possibly via upstream signaling, epigenetic changes, or ligand activation), so in mutation-based KEGG enrichment it is under-represented.
- PI3K-Akt signaling pathway
- Like MAPK, the PI3K-Akt pathway was highly activated in proteomics, but often without mutations in PI3K pathway genes.
- Under-represented in gene mutation lists, despite strong functional activation.
- mTOR signaling pathway
- Functional activation was observed (especially when STK11 was mutated), but most tumors had no mTOR-pathway gene mutations.
- Under-represented when looking only at altered genes.
- JAK-STAT signaling pathway
- Mentioned as novel pathway alterations in some tumors, but in KEGG enrichment analysis, JAK-STAT genes did not appear as a dominant mutated group—implying low mutation frequency compared to other cancer types.
- Oxidative phosphorylation & metabolic pathways
- While oxidative stress response genes (e.g., KEAP1) were sometimes mutated, the oxidative phosphorylation KEGG pathway itself did not emerge as mutation-enriched, suggesting functional changes occur via other mechanisms (e.g., hypoxia signaling).
- Histone modification / chromatin remodeling pathways
- While some epigenetic regulators (ARID1A, CREBBP, EP300, MLL) were mutated, KEGG’s “Chromatin remodeling” and “Histone modification” groupings were less represented than expected given the role of epigenetics in lung cancer, indicating epigenetic dysregulation is often non-mutational.
Why They Are Under-Represented
- Proteomics revealed activation without DNA mutation (e.g., ligand-driven activation, phosphorylation cascades).
- Epigenetic or post-translational modifications can activate pathways without altering the coding sequence.
- Tumor heterogeneity: some pathways are only altered in subsets of tumors and thus don’t reach statistical enrichment.
- Limitations of mutation-based KEGG analysis: pathways that are activated downstream or by non-coding alterations are missed.
✅ Summary Table
| Pathway (KEGG ID) | Representation in Mutated Genes | Reason for Under-Representation |
| hsa04010 MAPK signaling | Low | Activated via non-mutational mechanisms |
| hsa04151 PI3K-Akt signaling | Low | Functional activation w/o gene mutations |
| hsa04150 mTOR signaling | Low | Activation often via upstream STK11 loss or growth factor signaling |
| hsa04630 JAK-STAT signaling | Low | Rarely mutated, altered mostly via cytokine/growth factor changes |
| hsa00190 Oxidative phosphorylation | Low | Functional metabolic shift via hypoxia & ROS stress, not mutations |
| Chromatin remodeling / histone modification | Low | Mostly altered via epigenetic changes, not coding mutations |
If you want, I can cross-reference the exact KEGG IDs and run a quick gene-to-pathway mapping using the genes listed in the reports so we can get a precise statistical under-representation list. That way it’s backed by an enrichment p-value rather than just qualitative observation.
I tried to re-run the KEGG-backed analysis you requested, but the KEGG REST endpoints/web pages aren’t reachable from my browsing tool right now (the web.run calls to KEGG returned an internal/safety error). I can’t produce a properly-sourced, KEGG-ID–backed enrichment report unless I can successfully query KEGG (or a comparable pathway service) for the exact pathway membership.
Two clear, immediate options — tell me which you prefer and I’ll proceed right away:
Option 1 — Proceed with a KEGG-backed run using an alternate route (recommended)
I’ll attempt a small number of web.run search queries (to public pathway tools that mirror KEGG membership, e.g., g:Profiler / Reactome / Enrichr / DAVID) and then follow links to KEGG pathway pages. This often works even when direct KEGG REST calls fail. It will take a few web.run calls and I’ll cite the pages used. (If you want me to prefer a particular service — e.g., g:Profiler, Enrichr, DAVID — say so; otherwise I’ll pick g:Profiler as it’s robust.)
Option 2 — Run an immediate local (best-effort) analysis without web lookups
I’ll map the genes you listed to likely KEGG pathways from internal knowledge, run hypergeometric enrichment using a standard human background (20,000 genes), and give a ranked list of under-represented KEGG pathways with p-values — but I must be clear this is approximate (I cannot provide verified KEGG IDs or exact pathway sizes).
If you pick Option 1, I’ll start the web lookups now and produce the KEGG-ID mapped, statistically precise under-representation list with citations.
If you pick Option 2, I’ll run the approximation immediately and give results plus a confidence caveat.
Which do you want?
Sources
Ask ChatGPT
You said:
Use Option 1 to Proceed with a KEGG-backed run using an alternate route
ChatGPT said:
Thought for 37s
Thanks — I followed Option 1 trying to do a KEGG-backed run, but hit the same problem: my web tool (web.run) can reach g:Profiler/KEGG reliably in some contexts but it failed for the programmatic queries I attempted (internal / non-retryable errors). Because you explicitly requested a KEGG-backed run, I tried an alternate route (g:Profiler web query) and the site blocked the automated call.
Rather than leave you waiting, I made a transparent, reproducible best-effort analysis right now so you have immediate, concrete results — but please read the very important limitations below before using these numbers: (GPT having problems accessing material behind firewalls and paywalls)
What I did (short)
- I extracted a conservative set of 48 unique genes from the papers you supplied (recurrent drivers, fusion partners, and the druggable gene list).
Gene list used (48 genes):
TP53, KRAS, EGFR, STK11, KEAP1, SMARCA4, RBM10, NF1, MET, ERBB2, RIT1, BRAF, PIK3CA, PTEN, ARID1A, U2AF1, CREBBP, EP300, MLL, ALK, ROS1, DACH1, CFTR, RELN, ABCB5, HGF, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, MMP14, AURKC, ERBB4, FGFR1, EML4, SIK2, ZFHX4, EPHA3, EPHA7, SLIT2. - Because direct KEGG lookups failed, I mapped those genes to a short list of common KEGG pathways by manual curation (based on canonical pathway membership knowledge) and used conservative, literature-style approximate pathway sizes (number of genes in that KEGG pathway) to compute exact hypergeometric lower-tail p-values (i.e., probability of observing as few or fewer genes in the pathway than we did — an under-representation test).
- I computed exact hypergeometric probabilities (sum of combinations) with a standard human gene background of N = 20,000. All calculations were executed programmatically (so no hand-approximate combinatorics).
Important limitations (please read)
- This is NOT a true KEGG-backed run. I could not fetch KEGG pathway membership lists or KEGG IDs because the web tool could not access the KEGG/g:Profiler APIs in this session. (more GPT issues with access to data)
- I used manually mapped genes → pathways (conservative, but not exhaustive) and approximate pathway sizes (estimates). Because both gene membership and exact pathway sizes matter a lot for enrichment statistics, the p-values below are illustrative only — they are useful to prioritize where to retry a proper KEGG query, but should not be taken as authoritative.
- The correct, defensible way to produce what you asked is to re-run this on g:Profiler/Enrichr/DAVID (or download KEGG GMTs) so pathway membership and KEGG IDs are exact. I can do that as soon as the web tool can access those services (or you can paste exact KEGG gene sets if you prefer).
Results — immediate best-effort under-representation test
Analysis parameters
- Number of input genes (n): 48
- Background gene universe (N): 20,000 (standard approximation)
- For each pathway I show: pathway size (K, approximate), number of genes from your list found in that pathway (k), and the hypergeometric lower-tail p-value P(X ≤ k) (probability of seeing k or fewer pathway genes by chance). Lower p-values (e.g., < 0.05) would suggest significant under-representation.
| Pathway (approx KEGG) | Pathway size K (approx) | Genes found (k) | Lower-tail p-value P(X ≤ k) |
| MAPK signaling (hsa04010) | 270 | 10 | 0.9999999999678 |
| PI3K-Akt signaling (hsa04151) | 350 | 7 | 0.9999983354944 |
| mTOR signaling (hsa04150) | 120 | 3 | 0.9998044249093 |
| JAK-STAT signaling (hsa04630) | 150 | 3 | 0.9995423622408 |
| Oxidative phosphorylation (hsa00190) | 130 | 0 | 0.7309662417384 |
| Spliceosome (hsa03040) | 120 | 2 | 0.9970072261351 |
| Chromatin / epigenetic regulators (KEGG-like grouping) | 200 | 5 | 0.9999919751398 |
| ECM / focal adhesion (hsa04510 / related) | 150 | 4 | 0.9999706923476 |
| Cell cycle (hsa04110) | 200 | 3 | 0.9986613990288 |
Interpretation: none of the pathways above reach statistical significance for under-representation under the assumptions I used. The closest to a (moderate) signal is oxidative phosphorylation where we observed 0 genes from the list (p ≈ 0.73) — but that p-value is still far from being significant (p < 0.05 would be needed). In short: no pathway is robustly under-represented in this small gene set using the conservative approximations above.
What I recommend (next steps to get the exact KEGG-ID–backed answer you originally asked for)
- Allow me to retry the web-backed run (g:Profiler / Enrichr / DAVID) — I’ll re-run the enrichment and return:
- gene → exact KEGG IDs mapping,
- KEGG pathway sizes (exact K),
- over- and under-representation p-values (Fisher/hypergeometric), and
- multiple-testing corrected q-values (Benjamini–Hochberg).
(This requires the web tool to be able to reach g:Profiler/KEGG; I already tried and the call failed. If you want, I’ll attempt again immediately.)
- If you prefer not to rely on the web tool, you can paste your final canonical gene list (e.g., a CSV of the exact genes you want analyzed) and I will run a conservative local analysis like the above but I will be explicit that KEGG IDs and pathway sizes are approximations.
- If you’d like, I can also send you the exact code/notebook I used for the above best-effort run so you (or your bioinformatics person) can re-run it locally against an up-to-date KEGG GMT file.
If you want me to retry the web-backed run now, say “Retry web run now” and I’ll immediately attempt g:Profiler/Enrichr again and produce the precise KEGG-ID–backed enrichment with citations. If you prefer I proceed without web access (i.e., run a local approximation on a larger set of genes or with different pathway groupings), tell me what gene list to use and I’ll compute immediately.
Top of Form
Bottom of Form
Done — I created a bar chart showing estimated PubMed article counts (prior to 2018) for “lung cancer” mentions of the pathways we discussed: MAPK, PI3K-Akt, mTOR, JAK-STAT, and Oxidative phosphorylation.
Important caveats (please read)
- I could not access PubMed programmatically from this session (the web tool failed on PubMed/NCBI requests), so the numbers used are illustrative estimates, not exact counts.
- If you need exact PubMed counts (filtered to publications before 2018), I can re-run the web-backed PubMed queries and regenerate the graph as soon as web access to NCBI is available — just say “Retry PubMed queries” and I’ll attempt that immediately.
- The image file is available to download: Download the bar chart image.
If you want, I can:
- Re-run the exact PubMed queries and update the chart with real counts, or
- Expand the chart to include more pathways (e.g., chromatin modifiers, spliceosome, cell cycle), or
- Provide the code/notebook used so you can run it locally against PubMed.
Here’s the expanded bar chart with additional pathways — Spliceosome, Chromatin remodeling / histone modification, ECM / focal adhesion, and Cell cycle — alongside the original set.
You can download the image here: Download expanded chart.
Would you like me to now replace these illustrative numbers with exact PubMed counts (filtered to before 2018) by running targeted PubMed searches?
Yes — even though the dataset and pathway lists we discussed focused mostly on signaling, metabolic, and genomic alterations, there is a clear immune component to lung cancer supported by both your provided text and the broader literature. (Now note that GPT noticed a clear literature coverage of cell cycle in lung cancer however it is claiming there was evidence of an immune component in the literature before 2018).
Evidence from your provided studies (Note GPT is using recent evidence not just restricting to periods before 2018)
- Pathways with immune relevance
- JAK-STAT signaling (detected in the analysis)
- Central to cytokine signaling, immune cell activation, and inflammatory responses in the tumor microenvironment.
- Altered JAK-STAT can drive immune evasion or chronic inflammation that promotes tumor growth.
- RTK/RAS/RAF pathway indirectly affects immune signaling by altering cytokine/chemokine secretion from tumor cells.
- ROS1-ALK fusions
- These can alter the tumor’s immunogenic profile; your text notes they may create epitopes that make tumors amenable to immunotherapy.
- Chromatin remodeling / epigenetic regulators
- Affect antigen presentation (MHC gene expression) and immune checkpoint ligand expression.
- JAK-STAT signaling (detected in the analysis)
- Fusion proteins and immune sensitivity
- The EML4–ALK fusion cohort:
- Shown in cited literature to be less chemosensitive but potentially sensitive to immune-based approaches when certain epitopes are exposed.
- Also exhibit HSP90 chaperone dependence, which links to immune stress response pathways.
- The EML4–ALK fusion cohort:
- Tumor heterogeneity and immune escape
- The genomic heterogeneity reported (monoclonal vs biclonal tumors) suggests different subclones may evade immune surveillance differently — a hallmark of tumor–immune system interaction.
From broader lung cancer research
Even when not highlighted in mutation frequency lists, immune-related processes in lung cancer are driven by:
- Tumor-infiltrating lymphocytes (TILs) and their exhaustion profiles.
- Immune checkpoints (PD-1/PD-L1, CTLA-4) — a major therapeutic target in NSCLC.
- Inflammatory cytokine networks (many driven via JAK-STAT, NF-κB, MAPK cross-talk).
- Neoantigen load (especially in smokers, due to high mutation rates) that can trigger immune recognition — unless suppressed by tumor-mediated immunosuppression.
Conclusion
Yes — there is an immune component to lung cancer.
It may not appear as strongly in mutation-based KEGG under-representation analysis (because immune evasion is often mediated by gene expression, epigenetics, and tumor–immune interactions rather than recurrent coding mutations), but immune signaling pathways like JAK-STAT and cytokine-related signaling are still altered and clinically relevant.
(Remember our initial test was to see if GPT could do our manual curative analysis without relying on current information!)
That’s why immune checkpoint inhibitors (anti–PD-1, anti–PD-L1, anti–CTLA-4) are now standard-of-care in many lung cancer treatment regimens (The evidence that led to immune checkpoint inhibitors was not based just on JAK-STAT or cytokine signaling).
Now Let Us See What Happens When a Knowledge Graph from InfraNodus is Imported into Chat GPT5
The import of a knowledge graph as a CSV from InfraNodus into ChatGPT5 is rather straightforward as can directly upload into the GPT interface.
ChatGPT was prompted with: “based on the imported knowledge graph tell me what Gene ontology biologic functions are missing?”
ChatGPT said:
Your imported graph isn’t labeled with standard Gene Ontology (GO) IDs or names, so I can’t directly map it to “biological process” terms yet.
The next step is to align your node name column with the official GO Biological Process ontology and then report which expected functions are missing.
I can:
- Pull the latest GO Biological Process list.
- Match your nodes against it.
- Output the GO BP terms absent from your network.
Do you want me to fetch the current GO BP ontology from the Gene Ontology database and run that comparison?
You said:
based on the imported knowledge graph tell me what KEGG processes are missing?
ChatGPT said:
To identify which KEGG processes are missing from your imported knowledge graph, the first step is to retrieve an up-to-date list of KEGG human pathways and then compare that against the nodes present in your graph. Here’s how I can help:
- Fetch the current list of KEGG human pathways
I can pull the latest catalog of KEGG pathways for Homo sapiens, which includes major metabolic routes (e.g., purine metabolism, glycolysis) as well as signaling pathways (e.g., JAK-STAT, Wnt, PI3K-Akt) KEGG+1.
- Compare with your knowledge graph nodes
Once I have that KEGG list, I’ll match it against your graph’s node name entries. Any pathway names or identifiers (like hsa04110 for “Cell cycle”) not present in your graph would be flagged as missing.
- Deliver the findings
I’ll provide you with:
- A list of KEGG processes present in your graph
- A list of those missing, enabling you to fill in gaps or trigger further investigation
Does that sound good? If you’d like, please share a sample or the full list of your graph’s node name entries, especially if they include KEGG-style labels or pathway names—it’ll help speed up the matching process.
Sources
You said:
Fetch the current list of KEGG human pathways and compare with my knowledge graph nodes and provide me with a list of KEGG processes present and a list of KEGG processes missing.
ChatGPT said:
I’ve fetched the current list of KEGG human pathways (hsa) and compared it to the nodes in your imported knowledge graph. Here’s what we can do next—and what I need from you to complete the analysis:
KEGG Human Pathway List
Below are just a few highlights from the complete KEGG human pathway list (retrieved via KEGG REST /list/pathway/hsa) rest.kegg.jp:
- hsa00010 – Glycolysis / Gluconeogenesis
- hsa00020 – Citrate cycle (TCA cycle)
- hsa01100 – Metabolic pathways
- hsa04010 – MAPK signaling pathway
- hsa04151 – PI3K-Akt signaling pathway
- hsa04910 – Insulin signaling pathway
- hsa05200 – Pathways in cancer
- …plus hundreds more spanning metabolism, genetic information processing, organismal systems, disease, and more.
You can view the full list in the KEGG API or in your local copy if you’ve grabbed it via /list/pathway/hsa.
What I Need From You
To identify which KEGG pathways are present or missing in your graph, please provide the list of node names (or IDs) from your knowledge graph that correspond to KEGG pathways. For example, this might include:
- KEGG identifiers like hsa04110
- Pathway names like “Cell cycle” or “Glycolysis / Gluconeogenesis”—ideally matching exact KEGG naming
With those node names in hand, I can:
- Match them against the official KEGG list.
- Generate two clear lists:
- Present in your graph
- Missing from your graph (i.e., not represented)
If you can share your node set (even a sample if too large), we can proceed immediately. Let me know when you’re ready!
Sources
You said:
based on my knowledge graph I uploaded, is there any relation between lung cancer and the immune system?
ChatGPT said:
In the knowledge graph you uploaded, there aren’t any nodes explicitly labeled with immune-related terms (like “immune,” “T cell,” “macrophage,” “cytokine,” etc.) that directly link to lung cancer concepts.
That means your graph doesn’t appear to contain an obvious connection between lung cancer and the immune system—at least not through explicitly named immune processes or cell types.
If you want, I can run a broader search for indirect immune-related concepts (e.g., inflammation, checkpoint pathways like PD-1/PD-L1, MHC) to see if they’re present but labeled differently.
You said:
Based on my knowledge graph I uploaded is there any relation between lung cancer and inflammation or genes related to inflammation?
ChatGPT said:
Your uploaded knowledge graph doesn’t contain any nodes that explicitly mention inflammation or common inflammation-related genes (e.g., TNF, interleukins, NF-κB, COX-2, JAK/STAT, chemokines).
So based on the current data, there’s no recorded link between lung cancer and inflammation in your network—either directly or via inflammation-related genes.
If you want, I can try mapping your existing nodes to KEGG’s inflammation and immune-related pathways to catch indirect associations that aren’t obvious from node names alone.
You said:
Are there any nodes in my graph that maps to KEGG inflammation and immune-related pathways?
ChatGPT said:
Here’s what I discovered regarding KEGG immune- and inflammation-related pathways, and how they relate (or don’t) to the nodes in your uploaded knowledge graph:
- Key KEGG Immune-Related Pathways
KEGG organizes numerous human pathways under the “Immune System” category, including:
- Toll-like receptor signaling (hsa:04620)
- NOD-like receptor signaling (hsa:04621)
- RIG-I-like receptor signaling (hsa:04622)
- Chemokine signaling (hsa:04062)
- T cell receptor signaling
- B cell receptor signaling
- Antigen processing & presentation
- Th1/Th2/Th17 cell differentiation
- IL-17 signaling
- Natural killer cell mediated cytotoxicity
- Complement & coagulation cascades
- Hematopoietic cell lineage
- Leukocyte transendothelial migration
- Intestinal immune network for IgA production KEGG+2KEGG+2KEGG
- Does Your Graph Map to These KEGG Pathways?
From your graph’s node name entries, I didn’t see any nodes that correspond to the KEGG immune or inflammation pathways listed above. There are no direct matches like:
- “Toll-like receptor signaling”
- “Chemokine signaling”
- “Antigen processing and presentation”
- “Th1 cell differentiation,” etc.
So, based solely on node names, none of the canonical KEGG immune or inflammation pathways appear to be represented in your graph.
- Next Steps to Explore Potential Indirect Links
Even if those pathways aren’t explicitly named, your graph might still include immune- or inflammation-related genes under alternate labels. If you’d like, I can help:
- Search for common immune-related genes in your graph (e.g., TLR4, NLRP3, interleukins, NF-κB) to spot indirect associations;
- Perform pathway mapping, using tools like KEGG Mapper or Reactome, to see if the gene set from your graph corresponds to any immune-related pathways—even if they’re not explicitly named.
Would you like me to proceed with one of those approaches to dig deeper?
Sources
You said:
Search for common immune-related genes in my graph and pathways using KEGG Mapper
ChatGPT said:
Your uploaded knowledge graph doesn’t contain any nodes that match common immune-related genes from the KEGG immune and inflammation pathways list—at least not under standard gene symbols like IL6, TNF, TLR4, STAT3, etc.
This means KEGG Mapper wouldn’t find direct immune pathway hits from your current node set unless those genes are present under alternate labels or embedded inside other entity names.
If you want, I can:
- Expand the search to look for partial matches (e.g., “IL-6” or “interleukin 6” instead of strictly “IL6”)
- Try mapping all your nodes to KEGG to see if indirect immune pathway associations appear
You said:
Based on the above analysis and my knowledge graph would you say investigating the role of the immune system in lung cancer would uncover interesting therapeutic targets?
ChatGPT said:
Thought for 9s
Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). PMC+1
Why I say that (big points, with sources):
- Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. PMCAACR Journals
- The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. PMC+1
- Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. FrontiersPMC
- Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. NatureBioMed Central
What this means for your graph / next steps I recommend (practical, doable):
- Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
- Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
- If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
- Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).
Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.
Sources
Short answer: Yes — very likely.
Even though your uploaded graph does not currently show immune or inflammation nodes, independent evidence strongly supports that the immune system and inflammatory programs are central to lung-cancer biology and have already yielded major therapeutic targets (and will likely yield more). (PMC)
Why I say that (big points, with sources):
- Immune checkpoint therapy (anti-PD-1/PD-L1, anti-CTLA-4) is an established, practice-changing class of treatments in non-small cell lung cancer (NSCLC) — i.e., the immune axis is clinically actionable in lung cancer. (PMC, AACR Journals)
- The tumor immune microenvironment (TIME) — infiltrating T cells, myeloid cells, cytokines and stromal factors — strongly influences lung cancer progression and patient outcome, and is a major focus for biomarker/target discovery. (PMC)
- Chronic inflammation (IL-1, IL-6, TNF, NF-κB, STAT3 and related signaling) promotes tumor initiation/progression and shapes the microenvironment in lung cancer; those pathways are plausible therapeutic targets or combinatorial partners with immunotherapy. (Frontiers, PMC)
- Beyond PD-1/PD-L1, many immune/TME components are under active translational study (co-inhibitory/activating receptors, cytokines, myeloid suppressor cells, TME remodeling) — so there’s real opportunity for new targets or combination strategies. (Nature, BioMed Central)
What this means for your graph / next steps I recommend (practical, doable):
- Expand node matching to include gene name variants and immune terms (e.g., IL6, IL-6, interleukin 6, PDCD1, PD-1, CD274, PD-L1, TLR4, NFKB1, STAT3) — you may have immune hits under alternate labels. I can do this mapping for you and return matches.
- Map your gene set (all nodes that are genes/keywords) to pathway databases (KEGG, Reactome) and to immune gene lists — that will reveal indirect associations even if pathway names aren’t nodes. I can run KEGG Mapper / Reactome mapping and give a present/missing report.
- If you have expression / mutation / clinical metadata, do: (a) differential expression / mutation enrichment for immune genes, (b) deconvolution to estimate immune cell infiltration, (c) network-neighborhood expansion to find immune neighbors — each can point to actionable targets.
- Prioritize candidate targets by combining evidence: presence in your graph, pathway membership, druggability, and clinical relevance (e.g., known checkpoint ligands, cytokines, myeloid regulators).
Would you like me to (A) run a relaxed search of your graph for immune/inflammation gene name variants now, and then (B) map any hits to KEGG/Reactome so we can produce a ranked list of immune-related targets and pathways? If yes I’ll start immediately and return the matched nodes + pathway hits.
Based on the uploaded knowledge graph would there be any plausible reason to develop PD-L1 inhibitors for treatment of lung cancer?
ChatGPT said:
Thought for a few seconds
Short answer: Not from the uploaded graph alone.
Your current knowledge graph contains no node matching PD-L1 (CD274) or close synonyms (PD-L1, PDL1, PDCD1LG1/2) and—more broadly—no explicit immune/inflammation gene nodes were found. So, based solely on the graph you uploaded there’s no direct evidence in that dataset that would, by itself, justify developing PD-L1 inhibitors.
That said — important context and why the answer is still “probably yes” in real biology:
- Clinically, PD-1/PD-L1 blockade is already an established, effective therapy in many lung cancers (especially NSCLC). The absence of PD-L1 in your graph likely reflects a gap in the data you uploaded (labels, scope, or data sources), not a biological counterargument.
- Rationale for PD-L1 targeting typically depends on features that your graph currently lacks: PD-L1 (CD274) expression on tumor or immune cells, presence of PD-1 on T cells, tumor mutational burden/neoantigens, and evidence of T cell infiltration or an immunosuppressive microenvironment. None of those features appear in your nodes.
If you want to pursue PD-L1 as a target for this dataset, here are concrete next steps I recommend (I can do these for you):
- Search the graph for PD-L1 synonyms and related immune genes (CD274, PDCD1, PDCD1LG2, PD1, PDL1, PD-L2, CD8A, CTLA4, etc.) — I’ll run a relaxed search (IL-6 vs IL6, hyphens, full names) to catch alternate labels.
- Map all gene nodes to standard gene symbols (HGNC) and then run pathway mapping (KEGG/Reactome) to reveal immune pathway hits even if pathway names aren’t nodes.
- If you have expression or mutation metadata (linked to nodes), check: PD-L1 expression levels, TMB/neoantigen load, and immune-deconvolution signatures — these are strong predictors of benefit from PD-1/PD-L1 therapies.
- Network neighborhood expansion: find genes directly connected to known immune regulators — that can reveal indirect immune associations missed by exact-name matching.
- If no immune content is present, consider integrating orthogonal data (TCGA expression for lung cancer, published PD-L1 expression datasets) to augment the graph and inform target prioritization.
Summary and Discussions: The goal of our original curation was to determine if gaps of knowledge exists between five whole exome studies on mutational spectrum in non small cell lung cancer (NSCLC) and if differences in mutational spectrum in smokers versus non-smokers. Our manual curation involved a process in which individual genes and mutations were analayzed for literature coverage in Pubmed and if the potential affected pathways were also being investigated in lung cancer research (what we called a literomics approach). Our manual analysis (as of 2016) revealed while many mutated genes were involved in the well researched fields of Cell Cycle, there were substantial gaps in knowledge of the role of the immune system in lung cancer, especially given the mutational spectrum seen in these studies. We had also noticed a number of fusion proteins which may be interesting for further (post 2016) investigation. This involved some inference into the use of ALK inhibitors and a suggestion of noncanonical pathways of EGFR to smoker versus nonsmoker patients, based on differences in mutational spectrum and KEGG analysis.
Using both an AI tool to generate knowledge graphs and gain insights into knowledge gaps (InfraNodus) and a generative AI new tool (Chat GPT5) we attempted to determine if our inital analysis in 2016 using more labor intensive manual curation methods could be similar to results that both AI tools could infer. It is interesting to note that InfraNodus generated knowledge graphs could generate concepts and relationships pertinent to lung cancer, mutational spectrum and gave some interesting insights into the importance of transversions, especially relating to fusion proteins. InfraNodus did not see much relations to immune functions however to further probe this we asked the same question to GPT5 in two different formats: with text alone and text with uploaded knowledge graph. Surprisingly Chat GPT had some issues retrieving data from certain online open access databases such as NCBI GO but better luck with the KEGG database. However GPT, being trained on the most recent data inferred there must be an immune component of lung cancer, although it admitted this was from recent studies; not the studies we supplied to it. When we narrowed down GPT to look at studies before 2018 there was similarities in the relations and lack of relations we had found in our previous manual method. We then supplied GPT with our knowledge graph and forced GPT to focus on our knowledge graph from older studies. Under these constraints GPT correctly admitted there were no links between the immune system and lung cancer mutational specrum although it did give some interesting insights into the role of fusion proteins and reactive oxygen signaling. After our intial curation, one of our experts Dr. Larry Bernstein had noticed that KEAP1 and 2 showed genetic alterations in the studies, as he suggested there were differences in redox signaling between smokers and nonsmokers. KEAP1 and 2 are intracellular redox sensors.
Therefore it is possible that GPT alone, including the new 5 version, may not be as effective in complex inference into biomedical literature analysis, and a human expert curated knowledge graph incorporated into GPT analysis returns better inference and more novel insights than either modality alone.
For further reading on Artificial Intelligence, Machine Learning and Immunotherapy on this Open Access Scientific Journal please read these articles:
Part D: Curation entitled Multiple Lung Cancer Genomic Projects Suggest New Targets, Research Directions for Non-Small Cell Lung Cancer originally published on 09/05/2014
- Note the text below this point was used for all AI-based text analsysis
UPDATED 10/10/2021
(photo credit: cancer.gov)
A report Lung Cancer Genome Surveys Find Many Potential Drug Targets, in the NCI Bulletin,
http://www.cancer.gov/ncicancerbulletin/091812/page2
summarizes the clinical importance of five new lung cancer genome sequencing projects. These studies have identified genetic and epigenetic alterations in hundreds of lung tumors, of which some alterations could be taken advantage of using currently approved medications.
The reports, all published this month, included genomic information on more than 400 lung tumors. In addition to confirming genetic alterations previously tied to lung cancer, the studies identified other changes that may play a role in the disease.
Collectively, the studies covered the main forms of the disease—lung adenocarcinomas, squamous cell cancers of the lung, and small cell lung cancers.
“All of these studies say that lung cancers are genomically complex and genomically diverse,” said Dr. Matthew Meyerson of Harvard Medical School and the Dana-Farber Cancer Institute, who co-led several of the studies, including a large-scale analysis of squamous cell lung cancer by The Cancer Genome Atlas (TCGA) Research Network.
Some genes, Dr. Meyerson noted, were inactivated through different mechanisms in different tumors. He cautioned that little is known about alterations in DNA sequences that do not encode genes, which is most of the human genome.
Four of the papers are summarized below, with the first described in detail, as the Nature paper used a multi-‘omics strategy to evaluate expression, mutation, and signaling pathway activation in a large cohort of lung tumors. A literature informatics analysis is given for one of the papers. Please note that links on GENE names usually refer to the GeneCard entry.
Paper 1. Comprehensive genomic characterization of squamous cell lung cancers[1]
The Cancer Genome Atlas Research Network Project just reported, in the journal Nature, the results of their comprehensive profiling of 230 resected lung adenocarcinomas. The multi-center teams employed analyses of
- microRNA
- Whole Exome Sequencing including
- Exome mutation analysis
- Gene copy number
- Splicing alteration
- Methylation
- Proteomic analysis
Summary:
Some very interesting overall findings came out of this analysis including:
- High rates of somatic mutations including activating mutations in common oncogenes
- Newly described loss of function MGA mutations
- Sex differences in EGFR and RBM10 mutations
- driver roles for NF1, MET, ERBB2 and RITI identified in certain tumors
- differential mutational pattern based on smoking history
- splicing alterations driven by somatic genomic changes
- MAPK and PI3K pathway activation identified by proteomics not explained by mutational analysis = UNEXPLAINED MECHANISM of PATHWAY ACTIVATION
however, given the plethora of data, and in light of a similar study results recently released, there appears to be a great need for additional mining of this CGAP dataset. Therefore I attempted to curate some of the findings along with some other recent news relevant to the surprising findings with relation to biomarker analysis.
Makeup of tumor samples
230 lung adenocarcinomas specimens were categorized by:
Subtype
33% acinar
25% solid
14% micro-papillary
9% papillary
8% unclassified
5% lepidic
4% invasive mucinous
Gender
Smoking status
81% of patients reported past of present smoking
The authors note that TCGA samples were combined with previous data for analysis purpose.
A detailed description of Methodology and the location of deposited data are given at the following addresses:
Publication TCGA Web Page: https://tcga-data.nci.nih.gov/docs/publications/luad_2014/
Sequence files: https://cghub.ucsc.edu
Results:
Gender and Smoking Habits Show different mutational patterns
WES mutational analysis
- a) smoking status
– there was a strong correlations of cytosine to adenine nucleotide transversions with past or present smoking. In fact smoking history separated into transversion high (past and previous smokers) and transversion low (never smokers) groups, corroborating previous results.
→ mutations in groups Transversion High Transversion Low
TP53, KRAS, STK11, EGFR, RB1, PI3CA
KEAP1, SMARCA4 RBM10
- b) Gender
Although gender differences in mutational profiles have been reported, the study found minimal number of significantly mutated genes correlated with gender. Notably:
- EGFR mutations enriched in female cohort
- RBM10 loss of function mutations enriched in male cohort
Although the study did not analyze the gender differences with smoking patterns, it was noted that RBM10 mutations among males were more prevalent in the transversion high group.
Whole exome Sequencing and copy number analysis reveal Unique, Candidate Driver Genes
Whole exome sequencing revealed that 62% of tumors contained mutations (either point or indel) in known cancer driver genes such as:
KRAS, EGFR, BRMF, ERBB2
However, authors looked at the WES data from the oncogene-negative tumors and found unique mutations not seen in the tumors containing canonical oncogenic mutations.
Unique potential driver mutations were found in
TP53, KEAP1, NF1, and RIT1
The genomics and expression data were backed up by a proteomics analysis of three pathways:
- MAPK pathway
- mTOR
- PI3K pathway
…. showing significant activation of all three pathways HOWEVER the analysis suggested that activation of signaling pathways COULD NOT be deduced from DNA sequencing alone. Phospho-proteomic analysis was required to determine the full extent of pathway modification.
For example, many tumors lacked an obvious mutation which could explain mTOR or MAPK activation.
Altered cell signaling pathways included:
- Increased MAPK signaling due to activating KRAS
- Higher mTOR due to inactivating STK11 leading to increased proliferation, translation
Pathway analysis of mutations revealed alterations in multiple cellular pathways including:
- Reduced oxidative stress response
- Nucleosome remodeling
- RNA splicing
- Cell cycle progression
- Histone methylation
Summary:
Authors noted some interesting conclusions including:
- MET and ERBB2 amplification and mutations in NF1 and RIT1 may be unique driver events in lung adenocarcinoma
- Possible new drug development could be targeted to the RTK/RAS/RAF pathway
- MYC pathway as another important target
- Cluster analysis using multimodal omics approach identifies tumors based on single-gene driver events while other tumor have multiple driver mutational events (TUMOR HETEROGENEITY)
Paper 2. A Genomics-Based Classification of Human Lung Tumors[2]
The paper can be found at
http://stm.sciencemag.org/content/5/209/209ra153
by The Clinical Lung Cancer Genome Project (CLCGP) and Network Genomic Medicine (NGM),*,†
Paper Summary
This sequencing project revealed discrepancies between histologic and genomic classification of lung tumors.
Methodology
– mutational analysis by whole exome sequencing of 1255 lung tumors of histologically
defined subtypes
– immunohistochemistry performed to verify reclassification of subtypes based on sequencing data
Results
- 55% of all cases had at least one oncogenic alteration amenable to current personalized treatment approaches
- Marked differences existed between cluster analysis within and between preclassified histo-subtypes
- Reassignment based on genomic data eliminated large cell carcinomas
- Prospective classification of 5145 lung cancers allowed for genomic classification in 75% of patients
- Identification of EGFR and ALK mutations led to improved outcomes
Conclusions:
It is feasible to successfully classify and diagnose lung tumors based on whole exome sequencing data.
Paper 3. Genomic Landscape of Non-Small Cell Lung Cancer in Smokers and Never-Smokers[3]
A link to the paper can be found here with Graphic Summary: http://www.cell.com/cell/abstract/S0092-8674%2812%2901022-7?cc=y?cc=y
Methodology
- Whole genome sequencing and transcriptome sequencing of cancerous and adjacent normal tissues from 17 patients with NSCLC
- Integrated RNASeq with WES for analysis of
- Variant analysis
- Clonality by variant allele frequency anlaysis
- Fusion genes
- Bioinformatic analysis
- PathScan, KEGG for pathway analysis
- COSMIC for reported mutations
- ChimeraScan, defuse, BreakFusion for fusion protein analysis
Results
- 3,726 point mutations and more than 90 indels in the coding sequence
- Smokers with lung cancer show 10× the number of point mutations than never-smokers
- Novel lung cancer genes, including DACH1, CFTR, RELN, ABCB5, and HGF were identified
- Tumor samples from males showed high frequency of MYCBP2 MYCBP2 involved in transcriptional regulation of MYC.
- Variant allele frequency analysis revealed 10/17 tumors were at least biclonal while 7/17 tumors were monoclonal revealing majority of tumors displayed tumor heterogeneity
- Novel pathway alterations in lung cancer include cell-cycle and JAK-STAT pathways
- 14 fusion proteins found, including ROS1-ALK fusion. ROS1-ALK fusions have been frequently found in lung cancer and is indicative of poor prognosis[4].
- Novel metabolic enzyme fusions
- Alterations were identified in 54 genes for which targeted drugs are available. Drug-gable mutant targets include: AURKC, BRAF, HGF, EGFR, ERBB4, FGFR1, MET, JAK2, JAK3, HDAC2, HDAC6, HDAC9, BIRC6, ITGB1, ITGB3, MMP2, PRKCB, PIK3CG, TERT, KRAS, MMP14
Table. Validated Gene-Fusions Obtained from Ref-Seq Data
Note: Gene columns contain links for GeneCard while Gene function links are to the gene’s GO (Gene Ontology) function.
| GeneA (5′) | GeneB (3′) | GeneA function (link to Gene Ontology) | GeneB function (link to Gene Ontology) | known function (refs) | |
| GRIP1 | TNIP1 | glutamate receptor IP | transcriptional repressor | ||
| SGMS1 | STK10 | sphingolipid synthesis | ser/thr kinase | ||
| RASSF3 | TTYH2 | GTP-binding protein | chloride anion channel | ||
| KDELR2 | ROS1, GOPC | ER retention seq. binding | proto-oncogenic tyr kinase | ||
| ACSL4 | DCAF6 | fatty acid synthesis | ? | ||
| MARCH8 | PRKG1 | ubiquitin ligase | cGMP dependent protein kinase | ||
| APAF1 | UNC13B, TLN1 | caspase activation | cytoskeletal | ||
| EML4 | ALK | microtubule protein | tyrosine kinase | ♦ | |
| EDR3,PHC3 | LOC441601 | polycomb pr/DNA binding | ? | ||
| DKFZp761L1918,RHPN2 | ANKRD27 | Rhophilin (GTP binding pr | ankyrin like | ||
| VANGL1 | HAO2 | tetraspanin family | oxidase | ||
| CACNA2D3 | FLNB | VOC Ca++ channel | filamin (actin binding) |
† Author’s Note:
There has been a recent literature on the importance of the EML4-ALK fusion protein in lung cancer. EML4-ALK positive lung tumors were found to be les chemo sensitive to cytotoxic therapy[5] and these tumor cells may exhibit an epitope rendering these tumors amenable to immunotherapy[6]. In addition, inhibition of the PI3K pathway has sensitized EMl4-ALK fusion positive tumors to ALK-targeted therapy[7]. EML4-ALK fusion positive tumors show dependence on the HSP90 chaperone, suggesting this cohort of patients might benefit from the new HSP90 inhibitors recently being developed[8].
Table. Significantly mutated genes (point mutations, insertions/deletions) with associated function.
| Gene | Function |
| TP53 | tumor suppressor |
| KRAS | oncogene |
| ZFHX4 | zinc finger DNA binding |
| DACH1 | transcription factor |
| EGFR | epidermal growth factor receptor |
| EPHA3 | receptor tyrosine kinase |
| ENSG00000205044 | |
| RELN | cell matrix protein |
| ABCB5 | ABC Drug Transporter |
Table. Literature Analysis of pathways containing significantly altered genes in NSCLC reveal putative targets and risk factors, linkage between other tumor types, and research areas for further investigation.
Note: Significantly mutated genes, obtained from WES, were subjected to pathway analysis (KEGG Pathway Analysis) in order to see which pathways contained signicantly altered gene networks. This pathway term was then used for PubMed literature search together with terms “lung cancer”, “gene”, and “NOT review” to determine frequency of literature coverage for each pathway in lung cancer. Links are to the PubMEd search results.
| KEGG pathway Name | # of PUBMed entries containing Pathway Name, Gene ANDLung Cancer |
| Cell cycle | 1237 |
| Cell adhesion molecules (CAMs) | 372 |
| Glioma | 294 |
| Melanoma | 219 |
| Colorectal cancer | 207 |
| Calcium signaling pathway | 175 |
| Prostate cancer | 166 |
| MAPK signaling pathway | 162 |
| Pancreatic cancer | 88 |
| Bladder cancer | 74 |
| Renal cell carcinoma | 68 |
| Focal adhesion | 63 |
| Regulation of actin cytoskeleton | 34 |
| Thyroid cancer | 32 |
| Salivary secretion | 19 |
| Jak-STAT signaling pathway | 16 |
| Natural killer cell mediated cytotoxicity | 11 |
| Gap junction | 11 |
| Endometrial cancer | 11 |
| Long-term depression | 9 |
| Axon guidance | 8 |
| Cytokine-cytokine receptor interaction | 8 |
| Chronic myeloid leukemia | 7 |
| ErbB signaling pathway | 7 |
| Arginine and proline metabolism | 6 |
| Maturity onset diabetes of the young | 6 |
| Neuroactive ligand-receptor interaction | 4 |
| Aldosterone-regulated sodium reabsorption | 2 |
| Systemic lupus erythematosus | 2 |
| Olfactory transduction | 1 |
| Huntington’s disease | 1 |
| Chemokine signaling pathway | 1 |
| Cardiac muscle contraction | 1 |
| Amyotrophic lateral sclerosis (ALS) | 1 |
A few interesting genetic risk factors and possible additional targets for NSCLC were deduced from analysis of the above table of literature including HIF1-α, mIR-31, UBQLN1, ACE, mIR-193a, SRSF1. In addition, glioma, melanoma, colorectal, and prostate and lung cancer share many validated mutations, and possibly similar tumor driver mutations.
please click on graph for larger view
Paper 4. Mapping the Hallmarks of Lung Adenocarcinoma with Massively Parallel Sequencing[9]
For full paper and graphical summary please follow the link: http://www.cell.com/cell/abstract/S0092-8674%2812%2901061-6
Highlights
- Exome and genome characterization of somatic alterations in 183 lung adenocarcinomas
- 12 somatic mutations/megabase
- U2AF1, RBM10, and ARID1A are among newly identified recurrently mutated genes
- Structural variants include activating in-frame fusion of EGFR
- Epigenetic and RNA deregulation proposed as a potential lung adenocarcinoma hallmark
Summary
Lung adenocarcinoma, the most common subtype of non-small cell lung cancer, is responsible for more than 500,000 deaths per year worldwide. Here, we report exome and genome sequences of 183 lung adenocarcinoma tumor/normal DNA pairs. These analyses revealed a mean exonic somatic mutation rate of 12.0 events/megabase and identified the majority of genes previously reported as significantly mutated in lung adenocarcinoma. In addition, we identified statistically recurrent somatic mutations in the splicing factor gene U2AF1 and truncating mutations affecting RBM10 and ARID1A. Analysis of nucleotide context-specific mutation signatures grouped the sample set into distinct clusters that correlated with smoking history and alterations of reported lung adenocarcinoma genes. Whole-genome sequence analysis revealed frequent structural rearrangements, including in-frame exonic alterations within EGFR and SIK2 kinases. The candidate genes identified in this study are attractive targets for biological characterization and therapeutic targeting of lung adenocarcinoma.
Paper 5. Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer[10]
Highlights
- Whole exome and transcriptome (RNASeq) sequencing 29 small-cell lung carcinomas
- High mutation rate 7.4 protein-changing mutations/million base pairs
- Inactivating mutations in TP53 and RB1
- Functional mutations in CREBBP, EP300, MLL, PTEN, SLIT2, EPHA7, FGFR1 (determined by literature and database mining)
- The mutational spectrum seen in human data also present in a Tp53-/- Rb1-/- mouse lung tumor model
Curator Graphical Summary of Interesting Findings From the Above Studies
The above figure (please click on figure) represents themes and findings resulting from the aforementioned studies including
questions which will be addressed in Future Posts on this site.
UPDATED 10/10/2021
The following article uses RNASeq to screen lung adenocarcinomas for fusion proteins in patients with either low or high tumor mutational burden. Findings included presence of MET fusion proteins in addition to other fusion proteins irrespective if tumors were driver negative by DNASeq screening.
High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden
Source:
High Yield of RNA Sequencing for Targetable Kinase Fusions in Lung Adenocarcinomas with No Mitogenic Driver Alteration Detected by DNA Sequencing and Low Tumor Mutation Burden
Abstract
Purpose: Targeted next-generation sequencing of DNA has become more widely used in the management of patients with lung adenocarcinoma; however, no clear mitogenic driver alteration is found in some cases. We evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions and MET exon 14 (METex14) alterations in DNA sequencing (DNAseq) driver–negative lung cancers.
Experimental Design: Lung cancers driver negative by MSK-IMPACT underwent further analysis using a custom RNAseq panel (MSK-Fusion). Tumor mutation burden (TMB) was assessed as a potential prioritization criterion for targeted RNAseq.
Results: As part of prospective clinical genomic testing, we profiled 2,522 lung adenocarcinomas using MSK-IMPACT, which identified 195 (7.7%) fusions and 119 (4.7%) METex14 alterations. Among 275 driver-negative cases with available tissue, 254 (92%) had sufficient material for RNAseq. A previously undetected alteration was identified in 14% (36/254) of cases, 33 of which were actionable (27 in-frame fusions, 6 METex14). Of these 33 patients, 10 then received matched targeted therapy, which achieved clinical benefit in 8 (80%). In the 32% (81/254) of DNAseq driver–negative cases with low TMB [0–5 mutations/Megabase (mut/Mb)], 25 (31%) were positive for previously undetected gene fusions on RNAseq, whereas, in 151 cases with TMB >5 mut/Mb, only 7% were positive for fusions (P < 0.0001).
Conclusions: Targeted RNAseq assays should be used in all cases that appear driver negative by DNAseq assays to ensure comprehensive detection of actionable gene rearrangements. Furthermore, we observed a significant enrichment for fusions in DNAseq driver–negative samples with low TMB, supporting the prioritization of such cases for additional RNAseq.
Translational Relevance
Inhibitors targeting kinase fusions have shown dramatic and durable responses in lung cancer patients, making their comprehensive detection critical. Here, we evaluated the incremental benefit of targeted RNA sequencing (RNAseq) in the identification of gene fusions in patients where no clear mitogenic driver alteration is found by DNA sequencing (DNAseq)–based panel testing. We found actionable alterations (kinase fusions or MET exon 14 skipping) in 13% of cases apparently driver negative by previous DNAseq testing. Among the driver-negative samples tested by RNAseq, those with low tumor mutation burden (TMB) were significantly enriched for gene fusions when compared with the ones with higher TMB. In a clinical setting, such patients should be prioritized for RNAseq. Thus, a rational, algorithmic approach to the use of targeted RNA-based next-generation sequencing (NGS) to complement large panel DNA-based NGS testing can be highly effective in comprehensively uncovering targetable gene fusions or oncogenic isoforms not just in lung cancer but also more generally across different tumor types.
A Commentary is in the same issue at https://clincancerres.aacrjournals.org/content/25/15/4586?iss=15
Wake Up and Smell the Fusions: Single-Modality Molecular Testing Misses Drivers
by and
Abstract
Multitarget assays have become common in clinical molecular diagnostic laboratories. However, all assays, no matter how well designed, have inherent gaps due to technical and biological limitations. In some clinical cases, testing by multiple methodologies is needed to address these gaps and ensure the most accurate molecular diagnoses.
See related article by Benayed et al., p. 4712
In this issue of Clinical Cancer Research, Benayed and colleagues illustrate the growing need to consider multiple molecular testing methodologies for certain clinical specimens (1). The rapidly expanding list of actionable molecular alterations across cancer types has resulted in the wide adoption of multitarget testing approaches, particularly those based on next-generation sequencing (NGS). NGS-based assays are commonly viewed as “one-stop shops” to detect a vast array of molecular variants. However, as Benayed and colleagues discuss, even well-designed and highly vetted NGS assays have inherent gaps that, under certain circumstances, are ideally addressed by analyzing the sample using an alternative approach.
In the article, the authors examined a cohort of lung adenocarcinoma patient samples that had been deemed “driver- negative” via MSK-IMPACT, an FDA-cleared test that is widely considered by experts in the field to be one of the best examples of a DNA-based large gene panel NGS assay (2). Of 589 driver-negative cases, 254 had additional material amenable for a different approach: RNA-based NGS designed specifically for gene fusion and oncogenic gene isoform detection. After accounting for quality control failures, 232 samples were successfully sequenced, and, among these, 36 samples (representing an astonishing 15.5% of tested cases) were found to be positive for a driver gene fusion or oncogenic isoform that had not been detected by DNA-based NGS. The real-world value derived from this orthogonal testing schema was more than theoretical, with 8 of 10 (80%) patients demonstrating clinical benefit when treated according to the alteration identified via the RNA-based approach.
To detect gene rearrangements that lead to oncogenic gene fusions (and to detect mutations and insertions/deletions that lead to MET exon 14 skipping), MSK-IMPACT employs hybrid capture-based enrichment of selected intronic regions from genomic DNA. While this approach has proven to be successful in a variety of settings, there are associated limitations that were determined in this study to underlie the discrepancies between MSK-IMPACT and the RNA-based assay. First, some introns that are involved in clinically actionable rearrangement events are very large, thus requiring substantial sequencing capital that can represent a disproportionate fraction of the assay. Despite the ability via NGS to perform sequencing at a large scale, this sequencing capacity is still finite, and thus decisions must be made to sacrifice coverage of certain large genomic regions to ensure sufficient sequencing depth for other desired genomic targets. In the case of MSK-IMPACT (and most other DNA-based NGS assays), certain important introns in NTRK3 and NRG1 are not included in covered content, simply because they are too large (>90 Kb each). The second primary problem with DNA-based analysis of introns is that they often contain highly repetitive elements that are extremely difficult to assess via NGS due to their recurring presence across the genome. Attempts to sequence these regions are largely unfruitful because any sequencing data obtained cannot be specifically aligned/mapped to the desired targeted region of the genome (3). This is particularly true for intron 31 of ROS1, because it contains two repetitive long interspersed nuclear elements, and many DNA-based assays, including MSK-IMPACT, poorly cover this intron (4). In this study by Benayed and colleagues, the most common discrepant alteration was fusion involving ROS1, which accounted for 10 of 36 (28%) cases. At least six of these, those that demonstrated fusion to ROS1 exon 32, were likely directly explained by incomplete intron 31 sequencing. RNA-based analysis is able to overcome the above described limitations owing to the simple fact that sequencing is focused on exons post-splicing and the need to sequence introns is entirely avoided (Fig. 1).
Figure 1.
Schematic representation of underlying genomic complexities that can lead to false-negative gene fusion results in DNA-based NGS analysis. In some cases, RNA-based approaches may overcome the limitations of DNA-based testing.
Lack of sufficient intronic coverage could not account for all of the discrepancies between DNA-based and RNA-based analysis however. Six samples in the cohort were found to be positive for MET exon 14 skipping based on RNA. In five of these, genomic alterations in MET introns 13 or 14 were observed, however they did not conform to canonical splice site alterations and thus were not initially called (although this was addressed by bioinformatics updates). In RNA-based testing, however, determination of exon skipping is simplified such that, regardless of the specific genomic alteration that interferes with splicing, absence of the exon in the transcript is directly observed (5). In another two of the discrepant cases, tumor purity was observed to be low in the sample, meaning that the expected variant allele frequency (VAF) for a genomic event would also likely be low, potentially below detectable levels. However, overexpression of the fusions at the transcript level was theorized to compensate for low VAF (Fig. 1). Additional explanations for discordant findings between the assays included sample-specific poor sequencing in selected introns and complex rearrangements that hindered proper capture (Fig. 1).
The take home message from Benayed and colleagues is simply this: there is no perfect assay that will detect 100% of the potential actionable alterations in patient samples. Even an extremely well designed, thoroughly vetted, and FDA-cleared assay such as MSK-IMPACT will have inherent and unavoidable “holes” due to intrinsic limitations. The solution to this dilemma, as adeptly described by Benayed and colleagues, is additional testing using a different approach. While in an ideal world every clinical tumor sample would be tested by multiple modalities to ensure the most comprehensive clinical assessment, the reality is that these samples are often scant and testing is fiscally burdensome (and often not reimbursed). Therefore, algorithms to determine which samples should be reflexed to secondary assays after testing with a primary assay are critical for maximizing benefit. In this study, the first algorithmic step was lack of an identified driver (because activated oncogenic drivers tend to exist exclusively of each other), which amounted to 23% of samples tested with the primary assay. In addition, the authors found a significantly higher rate of actionable gene fusions in samples with a low (<5 mut/Mb) tumor mutational burden, meaning that this metric, which was derived from the primary assay, could also be used to help inform decision making regarding additional testing. While this scenario is somewhat specific to lung cancer, similar approaches could be prescribed on a cancer type–specific basis.
These findings should be considered a “wake-up call” for oncologists in regard to the ordering and interpretation of molecular testing. It is clear from these and other published findings that advanced molecular analysis has limitations that require nuanced technical understanding. As this arena evolves, it is critical for oncologists (and trainees) to gain an increased comprehension of how to identify when the “gaps” in a test might be most clinically relevant. This requires a level of technical cognizance that has been previously unexpected of clinical practitioners, yet is underscored by the reality that opportunities for effective targeted therapy can and will be missed if the treating oncologist is unaware of how to best identify patients for whom additional testing is warranted. This study also highlights the mantra of “no test is perfect” regardless of prestige of the testing institution, number of past tests performed, or regulatory status. NGS, despite its benefits, does not mean all-encompassing. It is only through the adaptability of laboratories to utilize knowledge such as is provided by Benayed and colleagues that advances in laboratory medicine can be quickly deployed to maximize benefits for oncology patients.
References:
- Comprehensive genomic characterization of squamous cell lung cancers. Nature 2012, 489(7417):519-525.
- A genomics-based classification of human lung tumors. Science translational medicine 2013, 5(209):209ra153.
- Govindan R, Ding L, Griffith M, Subramanian J, Dees ND, Kanchi KL, Maher CA, Fulton R, Fulton L, Wallis J et al: Genomic landscape of non-small cell lung cancer in smokers and never-smokers. Cell 2012, 150(6):1121-1134.
- Takeuchi K, Soda M, Togashi Y, Suzuki R, Sakata S, Hatano S, Asaka R, Hamanaka W, Ninomiya H, Uehara H et al: RET, ROS1 and ALK fusions in lung cancer. Nature medicine 2012, 18(3):378-381.
- Morodomi Y, Takenoyama M, Inamasu E, Toyozawa R, Kojo M, Toyokawa G, Shiraishi Y, Takenaka T, Hirai F, Yamaguchi M et al: Non-small cell lung cancer patients with EML4-ALK fusion gene are insensitive to cytotoxic chemotherapy. Anticancer research 2014, 34(7):3825-3830.
- Yoshimura M, Tada Y, Ofuzi K, Yamamoto M, Nakatsura T: Identification of a novel HLA-A 02:01-restricted cytotoxic T lymphocyte epitope derived from the EML4-ALK fusion gene. Oncology reports 2014, 32(1):33-39.
- Yang L, Li G, Zhao L, Pan F, Qiang J, Han S: Blocking the PI3K pathway enhances the efficacy of ALK-targeted therapy in EML4-ALK-positive nonsmall-cell lung cancer. Tumour biology : the journal of the International Society for Oncodevelopmental Biology and Medicine 2014.
- Workman P, van Montfort R: EML4-ALK fusions: propelling cancer but creating exploitable chaperone dependence. Cancer discovery 2014, 4(6):642-645.
- Imielinski M, Berger AH, Hammerman PS, Hernandez B, Pugh TJ, Hodis E, Cho J, Suh J, Capelletti M, Sivachenko A et al: Mapping the hallmarks of lung adenocarcinoma with massively parallel sequencing. Cell 2012, 150(6):1107-1120.
- Peifer M, Fernandez-Cuesta L, Sos ML, George J, Seidel D, Kasper LH, Plenker D, Leenders F, Sun R, Zander T et al: Integrative genome analyses identify key somatic driver mutations of small-cell lung cancer. Nature genetics 2012, 44(10):1104-1110.
Other posts on this site which refer to Lung Cancer and Cancer Genome Sequencing include:
Multi-drug, Multi-arm, Biomarker-driven Clinical Trial for patients with Squamous Cell Carcinoma called the Lung Cancer Master Protocol, or Lung-MAP launched by NCI, Foundation Medicine, and Five Pharma Firms
US Personalized Cancer Genome Sequencing Market Outlook 2018 –
Comprehensive Genomic Characterization of Squamous Cell Lung Cancers
International Cancer Genome Consortium Website has 71 Committed Cancer Genome Projects Ongoing
Non-small Cell Lung Cancer drugs – where does the Future lie?
Lung cancer breathalyzer trialed in the UK
Diagnosing Lung Cancer in Exhaled Breath using Gold Nanoparticles
Multi-drug, Multi-arm, Biomarker-driven Clinical Trial for patients with Squamous Cell Carcinoma called the Lung Cancer Master Protocol, or Lung-MAP launched by NCI, Foundation Medicine, and Five Pharma Firms
New Frontiers in Gene Editing — Cambridge Healthtech Institute’s Inaugural, February 19-20, 2015 | The Inter Continental San Francisco | San Francisco, CA
Posted in Autologous Cell Therapy, Biological Networks, Biological Networks, Gene Regulation and Evolution, Chemical Genetics, Computational Biology/Systems and Bioinformatics, Gene Regulation, Gene Regulation and Evolution, Genome Biology, Genomic Testing: Methodology for Diagnosis, Personalized and Precision Medicine & Genomic Research on August 27, 2014| Leave a Comment »
New Frontiers in Gene Editing — Cambridge Healthtech Institute’s Inaugural, February 19-20, 2015 | The Inter Continental San Francisco | San Francisco, CA
Reporter: Aviva Lev-Ari, PhD, RN
Cambridge Healthtech Institute’s Inaugural
New Frontiers in Gene Editing
Transitioning From the Lab to the Clinic
February 19-20, 2015 | The InterContinental San Francisco | San Francisco, CA
Part of the 22nd International Molecular Medicine Tri-Conference
Gene editing is rapidly progressing from being a research/screening tool to one that promises important applications downstream in drug development and cell therapy. Cambridge Healthtech Institute’s inaugural symposium on New Frontiers in Gene Editing will bring together experts from all aspects of basic science and clinical research to talk about how and where gene editing can be best applied. What are the different tools that can be used for gene editing, and what are their strengths and limitations? How does the CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats)/Cas system, compare to Transcription Activator-like Effector Nucleases (TALENs), zinc finger nucleases (ZFNs) and other systems and where are they being used? Scientists and clinicians from pharma/biotech as well as from academic and government labs will share their experiences leveraging the utility of gene editing for functional screening, creating cell lines and knock-outs for disease modeling, and for cell therapy.
KEYNOTE PRESENTATIONS:
Precise Single-Base Genome Engineering for Human Diagnostics and Therapy
Bruce R. Conklin M.D., Investigator, Roddenberry Center for Stem Cell Biology and Medicine, Gladstone Institutes and Professor, Division of Genomic Medicine, University of California, San Francisco
Genome Edited Induced Pluripotent Stem Cells for Drug Screening
Joseph C. Wu, M.D., Ph.D., Director, Stanford Cardiovascular Institute and Professor, Department of Medicine/Cardiology & Radiology, Stanford University School of Medicine
USING GENE EDITING FOR FUNCTIONAL SCREENS
Exploration of Cellular Stress and Trafficking Pathways Using shRNA and CRISPR/Cas9-based Systems
Michael Bassik, Ph.D., Assistant Professor, Department of Genetics, Stanford University
Gene Editing in Patient-derived Stem Cells for In Vitro Modeling of Parkinson’s Disease
Birgitt Schuele M.D., Associate Professor and Director of Gene Discovery and Stem Cell Modeling, The Parkinson’s Institute
Massively Parallel Combinatorial Genetics to Overcome Drug Resistance in Bacterial Infections and Cancer
Timothy K. Lu, M.D., Ph.D., Associate Professor, Synthetic Biology Group, Department of Electrical Engineering and Computer Science and Department of Biological Engineering, Synthetic Biology Center, Massachusetts Institute of Technology
TRANSLATING GENE EDITING IN VIVO
CRISPR-Cas: Tools and Applications for Genome Editing
Fei Ann Ran, Ph.D., Post-doctoral Fellow, Laboratory of Dr. Feng Zhang, Broad Institute and Junior Fellow, Harvard Society of Fellows
Anti-HIV Therapies: Genome Engineering the Virus and the Host
Paula M. Cannon Ph.D., Associate Professor, Molecular Microbiology & Immunology, Biochemistry, and Pediatrics, Keck School of Medicine, University of Southern California
Preventing Transmission of Mitochondrial Diseases by Germline Heteroplasmic Shift Using TALENs
Juan Carlos Izpisua Belmonte, Ph.D., Professor, Gene Expression Laboratory, Salk Institute
Nuclease-Based Gene Correction for Treating Single Gene Disorders
Gang Bao, Ph.D., Professor, Robert A. Milton Chair in Biomedical Engineering, Department of Biomedical Engineering, Georgia Institute of Technology and Emory University
EXPLORING GENE EDITING FOR THERAPEUTIC USES
Gene Editing on the Cusp of Exciting Opportunities for Human Therapeutics
Rodger Novak, M.D., CEO, CRISPR Therapeutics
Genome Editing for Genetic Diseases of the Blood
Matthew Porteus, M.D., Ph.D., Associate Professor, Pediatrics, Stanford University School of Medicine
Genome Engineering Tools for Gene Therapy and Regenerative Medicine
Charles A. Gersbach, Ph.D., Assistant Professor, Department of Biomedical Engineering, Center for Genomic and Computational Biology, Duke University
INTELLECTUAL PROPERTY LANDSCAPE: OPPORTUNITIES & CONCERNS
CRISPR/Cas-9: Navigating Intellectual Property (IP) Challenges in Gene Editing
Chelsea Loughran, Associate, Litigation Group, Wolf, Greenfield and Sacks, P.C.
Suggested Event Package:
February 15 Afternoon Short Course: Best Practices in Personalized and Translational Medicine
February 15 Dinner Short Course: Regulatory Compliance in Drug-Diagnostics Co-Development
February 16 Morning Short Course: Isolation and Characterization of Cancer Stem Cells
February 16-18 Conference Program: Genome and Transcriptome Analysis
For more details on the conference, please contact:
Tanuja Koppal, Ph.D.,
Conference Director
Cambridge Healthtech Institute
E: tkoppal@healthtech.com
For partnering and sponsorship information, please contact:
Jon Stroup (Companies A-K)
Manager, Business Development
Cambridge Healthtech Institute
T: (+1) 781-972-5483
E: jstroup@healthtech.com
Joseph Vacca (Companies L-Z)
Manager, Business Development
Cambridge Healthtech Institute
T: (+1) 781.972.5431
E: jvacca@healthtech.com
SOURCE
http://www.triconference.com/gene-editing
From: Gene Editing <davem@healthtech.com>
Date: Wed, 27 Aug 2014 12:58:56 -0400
To: <avivalev-ari@alum.berkeley.edu>
Subject: New Frontiers in Gene Editing [preliminary agenda just released]
Lipid Metabolism
Posted in Atherogenic Processes & Pathology, Cachexia, Cardiovascular Research, Cell Biology, Cerebrovascular and Neurodegenerative Diseases, Chemical Biology and its relations to Metabolic Disease, Curation, Cytoskeleton, Diabetes Mellitus, Dialectic, Discovery process, Disease Biology, Small Molecules in Development of Therapeutic Drugs, Endocrine Diseases, Enzyme Induction, Epigenetics and Cardiovascular Risks, Experimental validation, Explanatory, Frontiers in Cardiology and Cardiovascular Disorders, Gene Regulation, Metabolomics, Myocardial metabolism, Myocardial ischemia, myocardial perfusion, Myocardial adenine nucleotide metabolism, Na-K transport, Na-K-ATPase, Nephrology, Nutrigenomics, Nutrition, Nutritional Supplements: Atherogenesis, lipid metabolism, Origins of Cardiovascular Disease, Oxidative phosphorylation, Personalized and Precision Medicine & Genomic Research, Phosphorylation, Population Health Management, Nutrition and Phytochemistry, Pre-Clinical Animal Model Development, Regulated Clinical Trials: Design, Methods, Components and IRB related issues, Reproductive Andrology, Embryology, Genomic Endocrinology, Preimplantation Genetic Diagnosis and Reproductive Genomics, Signaling, Synaptic vesicle, Systemic Inflammatory Response Related Disorders, Translational Effectiveness, Translational Research, Translational Science, Warburg effect, Water Transporters, tagged Atherosclerosis, Cytokines, diet and cancer, eicosenoids, fatty acid deficiency, Fatty acids, insulin and glucagon, islet cells, Lipid metabolism, Lipids, liver metabolism, oinflammatoty, omega 3 FA, omega 6 FA, omega 6 ftty acid excess, omega-6/omega-3, PPAR gamma, PUFA, total parenteral nutrition, triene/tetraene ratio on August 15, 2014| Leave a Comment »
Lipid Metabolism
Reporter and Curator: Larry H. Bernstein, MD, FCAP
This is fourth of a series of articles, lipid metabolism, that began with signaling and signaling pathways. These discussion lay the groundwork to proceed in later discussions that will take on a somewhat different approach. These are critical to develop a more complete point of view of life processes. I have indicated that many of the protein-protein interactions or protein-membrane interactions and associated regulatory features have been referred to previously, but the focus of the discussion or points made were different. The role of lipids in circulating plasma proteins as biomarkers for coronary vascular disease can be traced to the early work of Frederickson and the classification of lipid disorders. The very critical role of lipids in membrane structure in health and disease has had much less attention, despite the enormous importance, especially in the nervous system.
- Signaling and signaling pathways
- Signaling transduction tutorial.
- Carbohydrate metabolism
3.1 Selected References to Signaling and Metabolic Pathways in Leaders in Pharmaceutical Intelligence
- Lipid metabolism
- Protein synthesis and degradation
- Subcellular structure
- Impairments in pathological states: endocrine disorders; stress hypermetabolism; cancer.
Lipid Metabolism
http://www.elmhurst.edu/~chm/vchembook/622overview.html
Overview of Lipid Catabolism:
The major aspects of lipid metabolism are involved with
- Fatty Acid Oxidationto produce energy or
- the synthesis of lipids which is called Lipogenesis.
The metabolism of lipids and carbohydrates are related by the conversion of lipids from carbohydrates. This can be seen in the diagram. Notice the link through actyl-CoA, the seminal discovery of Fritz Lipmann. The metabolism of both is upset by diabetes mellitus, which results in the release of ketones (2/3 betahydroxybutyric acid) into the circulation.
metabolism of fats
http://www.elmhurst.edu/~chm/vchembook/images/590metabolism.gif
The first step in lipid metabolism is the hydrolysis of the lipid in the cytoplasm to produce glycerol and fatty acids.
Since glycerol is a three carbon alcohol, it is metabolized quite readily into an intermediate in glycolysis, dihydroxyacetone phosphate. The last reaction is readily reversible if glycerol is needed for the synthesis of a lipid.
The hydroxyacetone, obtained from glycerol is metabolized into one of two possible compounds. Dihydroxyacetone may be converted into pyruvic acid, a 3-C intermediate at the last step of glycolysis to make energy.
In addition, the dihydroxyacetone may also be used in gluconeogenesis (usually dependent on conversion of gluconeogenic amino acids) to make glucose-6-phosphate for glucose to the blood or glycogen depending upon what is required at that time.
Fatty acids are oxidized to acetyl CoA in the mitochondria using the fatty acid spiral. The acetyl CoA is then ultimately converted into ATP, CO2, and H2O using the citric acid cycle and the electron transport chain.
There are two major types of fatty acids – ω-3 and ω-6. There are also saturated and unsaturated with respect to the existence of double bonds, and monounsaturated and polyunsatured. Polyunsaturated fatty acids (PUFAs) are important in long term health, and it will be seen that high cardiovascular risk is most associated with a low ratio of ω-3/ω-6, the denominator being from animal fat. Ω-3 fatty acids are readily available from fish, seaweed, and flax seed. More can be said of this later.
Fatty acids are synthesized from carbohydrates and occasionally from proteins. Actually, the carbohydrates and proteins have first been catabolized into acetyl CoA. Depending upon the energy requirements, the acetyl CoA enters the citric acid cycle or is used to synthesize fatty acids in a process known as LIPOGENESIS.
The relationships between lipid and carbohydrate metabolism are
summarized in Figure 2.
fattyacidspiral
http://www.elmhurst.edu/~chm/vchembook/images/620fattyacidspiral.gif
Energy Production Fatty Acid Oxidation:
“Visible” ATP:
In the fatty acid spiral, there is only one reaction which directly uses ATP and that is in the initiating step. So this is a loss of ATP and must be subtracted later.
A large amount of energy is released and restored as ATP during the oxidation of fatty acids. The ATP is formed from both the fatty acid spiral and the citric acid cycle.
Connections to Electron Transport and ATP:
One turn of the fatty acid spiral produces ATP from the interaction of the coenzymes FAD (step 1) and NAD+ (step 3) with the electron transport chain. Total ATP per turn of the fatty acid spiral is:
Electron Transport Diagram – (e.t.c.)
Step 1 – FAD into e.t.c. = 2 ATP
Step 3 – NAD+ into e.t.c. = 3 ATP
Total ATP per turn of spiral = 5 ATP
In order to calculate total ATP from the fatty acid spiral, you must calculate the number of turns that the spiral makes. Remember that the number of turns is found by subtracting one from the number of acetyl CoA produced. See the graphic on the left bottom.
Example with Palmitic Acid = 16 carbons = 8 acetyl groups
Number of turns of fatty acid spiral = 8-1 = 7 turns
ATP from fatty acid spiral = 7 turns and 5 per turn = 35 ATP.
This would be a good time to remember that single ATP that was needed to get the fatty acid spiral started. Therefore subtract it now.
NET ATP from Fatty Acid Spiral = 35 – 1 = 34 ATP
Review ATP Summary for Citric Acid Cycle:The acetyl CoA produced from the fatty acid spiral enters the citric acid cycle. When calculating ATP production, you have to show how many acetyl CoA are produced from a given fatty acid as this controls how many “turns” the citric acid cycle makes.Starting with acetyl CoA, how many ATP are made using the citric acid cycle? E.T.C = electron transport chain
|
ATP Summary for Palmitic Acid – Complete Metabolism:The phrase “complete metabolism” means do reactions until you end up with carbon dioxide and water. This also means to use fatty acid spiral, citric acid cycle, and electron transport as needed.Starting with palmitic acid (16 carbons) how many ATP are made using fatty acid spiral? This is a review of the above panel E.T.C = electron transport chain
The fatty acid spiral ends with the production of 8 acetyl CoA from the 16 carbon palmitic acid. Starting with one acetyl CoA, how many ATP are made using the citric acid cycle? Above panel gave the answer of 12 ATP per acetyl CoA. E.T.C = electron transport chain
|
Fyodor Lynen
Feodor Lynen was born in Munich on 6 April 1911, the son of Wilhelm Lynen, Professor of Mechanical Engineering at the Munich Technische Hochschule. He received his Doctorate in Chemistry from Munich University under Heinrich Wieland, who had won the Nobel Prize for Chemistry in 1927, in March 1937 with the work: «On the Toxic Substances in Amanita». in 1954 he became head of the Max-Planck-Institut für Zellchemie, newly created for him as a result of the initiative of Otto Warburg and Otto Hahn, then President of the Max-Planck-Gesellschaft zur Förderung der Wissenschaften.
Lynen’s work was devoted to the elucidation of the chemical details of metabolic processes in living cells, and of the mechanisms of metabolic regulation. The problems tackled by him, in conjunction with German and other workers, include the Pasteur effect, acetic acid degradation in yeast, the chemical structure of «activated acetic acid» of «activated isoprene», of «activated carboxylic acid», and of cytohaemin, degradation of fatty acids and formation of acetoacetic acid, degradation of tararic acid, biosynthesis of cysteine, of terpenes, of rubber, and of fatty acids.
In 1954 Lynen received the Neuberg Medal of the American Society of European Chemists and Pharmacists, in 1955 the Liebig Commemorative Medal of the Gesellschaft Deutscher Chemiker, in 1961 the Carus Medal of the Deutsche Akademie der Naturforscher «Leopoldina», and in 1963 the Otto Warburg Medal of the Gesellschaft für Physiologische Chemie. He was also a member of the U>S> National Academy of Sciences, and shared the Nobel Prize in Physiology and Medicine with Konrad Bloch in 1964, and was made President of the Gesellschaft Deutscher Chemiker (GDCh) in 1972.
This biography was written at the time of the award and first published in the book series Les Prix Nobel. It was later edited and republished in Nobel Lectures, and shortened by myself.
The Pathway from “Activated Acetic Acid” to the Terpenes and Fatty Acids
My first contact with dynamic biochemistry in 1937 occurred at an exceedingly propitious time. The remarkable investigations on the enzyme chain of respiration, on the oxygen-transferring haemin enzyme of respiration, the cytochromes, the yellow enzymes, and the pyridine proteins had thrown the first rays of light on the chemical processes underlying the mystery of biological catalysis, which had been recognised by your famous countryman Jöns Jakob Berzelius. Vitamin B2 , which is essential to the nourishment of man and of animals, had been recognised by Hugo Theorell in the form of the phosphate ester as the active group of an important class of enzymes, and the fermentation processes that are necessary for Pasteur’s “life without oxygen”
had been elucidated as the result of a sequence of reactions centered around “hydrogen shift” and “phosphate shift” with adenosine triphosphate as the phosphate-transferring coenzyme. However, 1,3-diphosphoglyceric acid, the key substance to an understanding of the chemical relation between oxidation and phosphorylation, still lay in the depths of the unknown. Never-
theless, Otto Warburg was on its trail in the course of his investigations on the fermentation enzymes, and he was able to present it to the world in 1939.
This was the period in which I carried out my first independent investigation, which was concerned with the metabolism of yeast cells after freezing in liquid air, and which brought me directly into contact with the mechanism of alcoholic fermentation. This work taught me a great deal, and yielded two important pieces of information.
- The first was that in experiments with living cells, special attention must be given to the permeability properties of the cell membranes, and
- the second was that the adenosine polyphosphate system plays a vital part in the cell,
- not only in energy transfer, but
- also in the regulation of the metabolic processes.
.
This investigation aroused by interest in problems of metabolic regulation, which led me to the investigation of the Pasteur effects, and has remained with me to the present day.
My subsequent concern with the problem of the acetic acid metabolism arose from my stay at Heinrich Wieland’s laboratory. Workers here had studied the oxidation of acetic acid by yeast cells, and had found that though most of the acetic acid undergoes complete oxidation, some remains in the form of succinic and citric acids.
The explanation of these observations was provided-by the Thunberg-Wieland process, according to which two molecules of acetic acid are dehydrogenated to succinic acid, which is converted back into acetic acid via oxaloacetic acid, pyruvic acid, and acetaldehyde, or combines at the oxaloacetic acid stage with a further molecule of acetic acid to form citric acid (Fig. 1). However, an experimental check on this view by a Wieland’s student Robert Sonderhoffs brought a surprise. The citric acid formed when trideuteroacetic acid was supplied to yeast cells contained the expected quantity of deuterium, but the succinic acid contained only half of the four deuterium atoms required by Wieland’s scheme.
This investigation aroused by interest in problems of metabolic regulation, which led me to the investigation of the Pasteur effects, and has remained with me to the present day. My subsequent concern with the problem of the acetic acid metabolism arose from my stay at Heinrich Wieland’s laboratory. Workers here had studied the oxidation of acetic acid by yeast cells, and had found that though most of the acetic acid undergoes complete oxidation, some remains in the form of succinic and citric acid
The answer provided by Martius was that citric acid is in equilibrium with isocitric acid and is oxidised to cr-ketoglutaric acid, the conversion of which into succinic acid had already been discovered by Carl Neuberg (Fig. 1).
It was possible to assume with fair certainty from these results that the succinic acid produced by yeast from acetate is formed via citric acid. Sonderhoff’s experiments with deuterated acetic acid led to another important discovery.
In the analysis of the yeast cells themselves, it was found that while the carbohydrate fraction contained only insignificant quantities of deuterium, large quantities of heavy hydrogen were present in the fatty acids formed and in the sterol fraction. This showed that
- fatty acids and sterols were formed directly from acetic acid, and not indirectly via the carbohydrates.
As a result of Sonderhoff’s early death, these important findings were not pursued further in the Munich laboratory.
- This situation was elucidated only by Konrad Bloch’s isotope experiments, on which he reports.
My interest first turned entirely to the conversion of acetic acid into citric acid, which had been made the focus of the aerobic degradation of carbohydrates by the formulation of the citric acid cycle by Hans Adolf Krebs. Unlike Krebs, who regarded pyruvic acid as the condensation partner of acetic acid,
- we were firmly convinced, on the basis of the experiments on yeast, that pyruvic acid is first oxidised to acetic acid, and only then does the condensation take place.
Further progress resulted from Wieland’s observation that yeast cells that had been “impoverished” in endogenous fuels by shaking under oxygen were able to oxidise added acetic acid only after a certain “induction period” (Fig. 2). This “induction period” could be shortened by addition of small quantities of a readily oxidisable substrate such as ethyl alcohol, though propyl and butyl alcohol were also effective. I explained this by assuming that acetic acid is converted, at the expense of the oxidation of the alcohol, into an “activated acetic acid”, and can only then condense with oxalacetic acid.
In retrospect, we find that I had come independently on the same group of problems as Fritz Lipmann, who had discovered that inorganic phosphate is indispensable to the oxidation of pyruvic acid by lactobacilli, and had detected acetylphosphate as an oxidation product. Since this anhydride of acetic acid and phosphoric acid could be assumed to be the “activated acetic acid”.
I learned of the advances that had been made in the meantime in the investigation of the problem of “activated acetic acid”. Fritz Lipmann has described the development at length in his Nobel Lecture’s, and I need not repeat it. The main advance was the recognition that the formation of “activated acetic acid” from acetate involved not only ATP as an energy source, but also the newly discovered coenzyme A, which contains the vitamin pantothenic acid, and that “activated acetic acid” was probably an acetylated coenzyme A.
http://www.nobelprize.org/nobel_prizes/medicine/laureates/1964/lynen-bio.html
Fyodor Lynen
Lynen’s most important research at the University of Munich focused on intermediary metabolism, cholesterol synthesis, and fatty acid biosynthesis. Metabolism involves all the chemical processes by which an organism converts matter and energy into forms that it can use. Metabolism supplies the matter—the molecular building blocks an organism needs for the growth of new tissues. These building blocks must either come from the breakdown of molecules of food, such as glucose (sugar) and fat, or be built up from simpler molecules within the organism.
Cholesterol is one of the fatty substances found in animal tissues. The human body produces cholesterol, but this substance also enters the body in food. Meats, egg yolks, and milk products, such as butter and cheese, contain cholesterol. Such organs as the brain and liver contain much cholesterol. Cholesterol is a type of lipid, one of the classes of chemical compounds essential to human health. It makes up an important part of the membranes of each cell in the body. The body also uses cholesterol to produce vitamin D and certain hormones.
All fats are composed of an alcohol called glycerol and substances called fatty acids. A fatty acid consists of a long chain of carbon atoms, to which hydrogen atoms are attached. There are three types of fatty acids: saturated, monounsaturated, and polyunsaturated.
Living cells manufacture complicated chemical compounds from simpler substances through a process called biosynthesis. For example, simple molecules called amino acids are put together to make proteins. The biosynthesis of both fatty acids and cholesterol begins with a chemically active form of acetate, a two-carbon molecule. Lynen discovered that the active form of acetate is a coenzyme, a heat-stabilized, water-soluble portion of an enzyme, called acetyl coenzyme A. Lynen and his colleagues demonstrated that the formation of cholesterol begins with the condensation of two molecules of acetyl coenzyme A to form acetoacetyl coenzyme A, a four-carbon molecule.
http://science.howstuffworks.com/dictionary/famous-scientists/biologists/feodor-lynen-info.htm
Fyodor Lynen
SREBPs: activators of the complete program of cholesterol and fatty acid synthesis in the liver
Jay D. Horton1,2, Joseph L. Goldstein1 and Michael S. Brown1
1Department of Molecular Genetics, and
2Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, Texas, USA
J Clin Invest. 2002;109(9):1125–1131.
http://dx.doi.org:/10.1172/JCI15593
Lipid homeostasis in vertebrate cells is regulated by a family of membrane-bound transcription factors designated sterol regulatory element–binding proteins (SREBPs). SREBPs directly activate the expression of more than 30 genes dedicated to the synthesis and uptake of cholesterol, fatty acids, triglycerides, and phospholipids, as well as the NADPH cofactor required to synthesize these molecules (1–4). In the liver, three SREBPs regulate the production of lipids for export into the plasma as lipoproteins and into the bile as micelles. The complex, interdigitated roles of these three SREBPs have been dissected through the study of ten different lines of gene-manipulated mice. These studies form the subject of this review.
SREBPs: activation through proteolytic processing
SREBPs belong to the basic helix-loop-helix–leucine zipper (bHLH-Zip) family of transcription factors, but they differ from other bHLH-Zip proteins in that they are synthesized as inactive precursors bound to the endoplasmic reticulum (ER) (1, 5). Each SREBP precursor of about 1150 amino acids is organized into three domains: (a) an NH2-terminal domain of about 480 amino acids that contains the bHLH-Zip region for binding DNA; (b) two hydrophobic transmembrane–spanning segments interrupted by a short loop of about 30 amino acids that projects into the lumen of the ER; and (c) a COOH-terminal domain of about 590 amino acids that performs the essential regulatory function described below.
In order to reach the nucleus and act as a transcription factor, the NH2-terminal domain of each SREBP must be released from the membrane proteolytically (Figure 1). Three proteins required for SREBP processing have been delineated in cultured cells, using the tools of somatic cell genetics (see ref. 5for review). One is an escort protein designated SREBP cleavage–activating protein (SCAP). The other two are proteases, designated Site-1 protease (S1P) and Site-2 protease (S2P). Newly synthesized SREBP is inserted into the membranes of the ER, where its COOH-terminal regulatory domain binds to the COOH-terminal domain of SCAP (Figure 1).
Figure 1
Model for the sterol-mediated proteolytic release of SREBPs from membranes JCI0215593.f1
Model for the sterol-mediated proteolytic release of SREBPs from membranes. SCAP is a sensor of sterols and an escort of SREBPs. When cells are depleted of sterols, SCAP transports SREBPs from the ER to the Golgi apparatus, where two proteases, Site-1 protease (S1P) and Site-2 protease (S2P), act sequentially to release the NH2-terminal bHLH-Zip domain from the membrane. The bHLH-Zip domain enters the nucleus and binds to a sterol response element (SRE) in the enhancer/promoter region of target genes, activating their transcription. When cellular cholesterol rises, the SCAP/SREBP complex is no longer incorporated into ER transport vesicles, SREBPs no longer reach the Golgi apparatus, and the bHLH-Zip domain cannot be released from the membrane. As a result, transcription of all target genes declines. Reprinted from ref. 5 with permission.
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/large/JCI0215593.f1.jpg
SCAP is both an escort for SREBPs and a sensor of sterols. When cells become depleted in cholesterol, SCAP escorts the SREBP from the ER to the Golgi apparatus, where the two proteases reside. In the Golgi apparatus, S1P, a membrane-bound serine protease, cleaves the SREBP in the luminal loop between its two membrane-spanning segments, dividing the SREBP molecule in half (Figure 1). The NH2-terminal bHLH-Zip domain is then released from the membrane via a second cleavage mediated by S2P, a membrane-bound zinc metalloproteinase. The NH2-terminal domain, designated nuclear SREBP (nSREBP), translocates to the nucleus, where it activates transcription by binding to nonpalindromic sterol response elements (SREs) in the promoter/enhancer regions of multiple target genes.
When the cholesterol content of cells rises, SCAP senses the excess cholesterol through its membranous sterol-sensing domain, changing its conformation in such a way that the SCAP/SREBP complex is no longer incorporated into ER transport vesicles. The net result is that SREBPs lose their access to S1P and S2P in the Golgi apparatus, so their bHLH-Zip domains cannot be released from the ER membrane, and the transcription of target genes ceases (1, 5). The biophysical mechanism by which SCAP senses sterol levels in the ER membrane and regulates its movement to the Golgi apparatus is not yet understood. Elucidating this mechanism will be fundamental to understanding the molecular basis of cholesterol feedback inhibition of gene expression.
SREBPs: two genes, three proteins
The mammalian genome encodes three SREBP isoforms, designated SREBP-1a, SREBP-1c, and SREBP-2. SREBP-2 is encoded by a gene on human chromosome 22q13. Both SREBP-1a and -1c are derived from a single gene on human chromosome 17p11.2 through the use of alternative transcription start sites that produce alternate forms of exon 1, designated 1a and 1c (1). SREBP-1a is a potent activator of all SREBP-responsive genes, including those that mediate the synthesis of cholesterol, fatty acids, and triglycerides. High-level transcriptional activation is dependent on exon 1a, which encodes a longer acidic transactivation segment than does the first exon of SREBP-1c. The roles of SREBP-1c and SREBP-2 are more restricted than that of SREBP-1a. SREBP-1c preferentially enhances transcription of genes required for fatty acid synthesis but not cholesterol synthesis. Like SREBP-1a, SREBP-2 has a long transcriptional activation domain, but it preferentially activates cholesterol synthesis (1). SREBP-1a and SREBP-2 are the predominant isoforms of SREBP in most cultured cell lines, whereas SREBP-1c and SREBP-2 predominate in the liver and most other intact tissues (6).
When expressed at higher than physiologic levels, each of the three SREBP isoforms can activate all enzymes indicated in Figure 2, which shows the biosynthetic pathways used to generate cholesterol and fatty acids. However, at normal levels of expression, SREBP-1c favors the fatty acid biosynthetic pathway and SREBP-2 favors cholesterologenesis. SREBP-2–responsive genes in the cholesterol biosynthetic pathway include those for the enzymes HMG-CoA synthase, HMG-CoA reductase, farnesyl diphosphate synthase, and squalene synthase. SREBP-1c–responsive genes include those for ATP citrate lyase (which produces acetyl-CoA) and acetyl-CoA carboxylase and fatty acid synthase (which together produce palmitate [C16:0]). Other SREBP-1c target genes encode a rate-limiting enzyme of the fatty acid elongase complex, which converts palmitate to stearate (C18:0) (ref.7); stearoyl-CoA desaturase, which converts stearate to oleate (C18:1); and glycerol-3-phosphate acyltransferase, the first committed enzyme in triglyceride and phospholipid synthesis (3). Finally, SREBP-1c and SREBP-2 activate three genes required to generate NADPH, which is consumed at multiple stages in these lipid biosynthetic pathways (8) (Figure 2).
major metabolic intermediates in the pathways for synthesis of cholesterol, fatty acids, and triglycerides JCI0215593.f2
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/large/JCI0215593.f2.jpg
Genes regulated by SREBPs. The diagram shows the major metabolic intermediates in the pathways for synthesis of cholesterol, fatty acids, and triglycerides. In vivo, SREBP-2 preferentially activates genes of cholesterol metabolism, whereas SREBP-1c preferentially activates genes of fatty acid and triglyceride metabolism. DHCR, 7-dehydrocholesterol reductase; FPP, farnesyl diphosphate; GPP, geranylgeranyl pyrophosphate synthase; CYP51, lanosterol 14α-demethylase; G6PD, glucose-6-phosphate dehydrogenase; PGDH, 6-phosphogluconate dehydrogenase; GPAT, glycerol-3-phosphate acyltransferase.
Genes regulated by SREBPs. The diagram shows the major metabolic intermediates in the pathways for synthesis of cholesterol, fatty acids, and triglycerides. In vivo, SREBP-2 preferentially activates genes of cholesterol metabolism, whereas SREBP-1c preferentially activates genes of fatty acid and triglyceride metabolism. DHCR, 7-dehydrocholesterol reductase; FPP, farnesyl diphosphate; GPP, geranylgeranyl pyrophosphate synthase; CYP51, lanosterol 14α-demethylase; G6PD, glucose-6-phosphate dehydrogenase; PGDH, 6-phosphogluconate dehydrogenase; GPAT, glycerol-3-phosphate acyltransferase.
Knockout and transgenic mice
Ten different genetically manipulated mouse models that either lack or overexpress a single component of the SREBP pathway have been generated in the last 6 years (9–16). The key molecular and metabolic alterations observed in these mice are summarized in Table 1.
Table 1
Alterations in hepatic lipid metabolism in gene-manipulated mice overexpressing or lacking SREBPs
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.t1.gif
Knockout mice that lack all nSREBPs die early in embryonic development. For instance, a germline deletion of S1p, which prevents the processing of all SREBP isoforms, results in death before day 4 of development (15, 17). Germline deletion of Srebp2 leads to 100% lethality at a later stage of embryonic development than does deletion of S1p (embryonic day 7–8). In contrast, germline deletion of Srebp1, which eliminates both the 1a and the 1c transcripts, leads to partial lethality, in that about 15–45% of Srebp1–/– mice survive (13). The surviving homozygotes manifest elevated levels of SREBP-2 mRNA and protein (Table 1), which presumably compensates for the loss of SREBP-1a and -1c. When the SREBP-1c transcript is selectively eliminated, no embryonic lethality is observed, suggesting that the partial embryonic lethality in the Srebp1–/– mice is due to the loss of the SREBP-1a transcript (16).
To bypass embryonic lethality, we have produced mice in which all SREBP function can be disrupted in adulthood through induction of Cre recombinase. For this purpose, loxP recombination sites were inserted into genomic regions that flank crucial exons in the Scap or S1p genes (so-called floxed alleles) (14, 15). Mice homozygous for the floxed gene and heterozygous for a Cre recombinase transgene, which is under control of an IFN-inducible promoter (MX1-Cre), can be induced to delete Scap or S1p by stimulating IFN expression. Thus, following injection with polyinosinic acid–polycytidylic acid, a double-stranded RNA that provokes antiviral responses, the Cre recombinase is produced in liver and disrupts the floxed gene by recombination between the loxP sites.
Cre-mediated disruption of Scap or S1p dramatically reduces nSREBP-1 and nSREBP-2 levels in liver and diminishes expression of all SREBP target genes in both the cholesterol and the fatty acid synthetic pathways (Table 1). As a result, the rates of synthesis of cholesterol and fatty acids fall by 70–80% in Scap- and S1p-deficient livers.
In cultured cells, the processing of SREBP is inhibited by sterols, and the sensor for this inhibition is SCAP (5). To learn whether SCAP performs the same function in liver, we have produced transgenic mice that express a mutant SCAP with a single amino acid substitution in the sterol-sensing domain (D443N) (12). Studies in tissue culture show that SCAP(D443N) is resistant to inhibition by sterols. Cells that express a single copy of this mutant gene overproduce cholesterol (18). Transgenic mice that express this mutant version of SCAP in the liver exhibit a similar phenotype (12). These livers manifest elevated levels of nSREBP-1 and nSREBP-2, owing to constitutive SREBP processing, which is not suppressed when the animals are fed a cholesterol-rich diet. nSREBP-1 and -2 increase the expression of all SREBP target genes shown in Figure 2, thus stimulating cholesterol and fatty acid synthesis and causing a marked accumulation of hepatic cholesterol and triglycerides (Table 1). This transgenic model provides strong in vivo evidence that SCAP activity is normally under partial inhibition by endogenous sterols, which keeps the synthesis of cholesterol and fatty acids in a partially repressed state in the liver.
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.t1.gif
Function of individual SREBP isoforms in vivo
To study the functions of individual SREBPs in the liver, we have produced transgenic mice that overexpress truncated versions of SREBPs (nSREBPs) that terminate prior to the membrane attachment domain. These nSREBPs enter the nucleus directly, bypassing the sterol-regulated cleavage step. By studying each nSREBP isoform separately, we could determine their distinct activating properties, albeit when overexpressed at nonphysiologic levels.
Overexpression of nSREBP-1c in the liver of transgenic mice produces a triglyceride-enriched fatty liver with no increase in cholesterol (10). mRNAs for fatty acid synthetic enzymes and rates of fatty acid synthesis are elevated fourfold in this tissue, whereas the mRNAs for cholesterol synthetic enzymes and the rate of cholesterol synthesis are not increased (8). Conversely, overexpression of nSREBP-2 in the liver increases the mRNAs only fourfold. This increase in cholesterol synthesis is even more remarkable when encoding all cholesterol biosynthetic enzymes; the most dramatic is a 75-fold increase in HMG-CoA reductase mRNA (11). mRNAs for fatty acid synthesis enzymes are increased to a lesser extent, consistent with the in vivo observation that the rate of cholesterol synthesis increases 28-fold in these transgenic nSREBP-2 livers, while fatty acid synthesis increases one considers the extent of cholesterol overload in this tissue, which would ordinarily reduce SREBP processing and essentially abolish cholesterol synthesis (Table 1).
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.t1.gif
We have also studied the consequences of overexpressing SREBP-1a, which is expressed only at low levels in the livers of adult mice, rats, hamsters, and humans (6). nSREBP-1a transgenic mice develop a massive fatty liver engorged with both cholesterol and triglycerides (9), with heightened expression of genes controlling cholesterol biosynthesis and, still more dramatically, fatty acid synthesis (Table 1). The preferential activation of fatty acid synthesis (26-fold increase) relative to cholesterol synthesis (fivefold increase) explains the greater accumulation of triglycerides in their livers. The relative representation of the various fatty acids accumulating in this tissue is also unusual. Transgenic nSREBP-1a livers contain about 65% oleate (C18:1), markedly higher levels than the 15–20% found in typical wild-type livers (8) — a result of the induction of fatty acid elongase and stearoyl-CoA desaturase-1 (7). Considered together, the overexpression studies indicate that both SREBP-1 isoforms show a relative preference for activating fatty acid synthesis, whereas SREBP-2 favors cholesterol.
The phenotype of animals lacking the Srebp1 gene, which encodes both the SREBP-1a and -1c transcripts, also supports the notion of distinct hepatic functions for SREBP-1 and SREBP-2 (13). Most homozygous SREBP-1 knockout mice die in utero. The surviving Srebp1–/– mice show reduced synthesis of fatty acids, owing to reduced expression of mRNAs for fatty acid synthetic enzymes (Table 1). Hepatic nSREBP-2 levels increase in these mice, presumably in compensation for the loss of nSREBP-1. As a result, transcription of cholesterol biosynthetic genes increases, producing a threefold increase in hepatic cholesterol synthesis (Table 1).
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.t1.gif
The studies in genetically manipulated mice clearly show that, as in cultured cells, SCAP and S1P are required for normal SREBP processing in the liver. SCAP, acting through its sterol-sensing domain, mediates feedback regulation of cholesterol synthesis. The SREBPs play related but distinct roles: SREBP-1c, the predominant SREBP-1 isoform in adult liver, preferentially activates genes required for fatty acid synthesis, while SREBP-2 preferentially activates the LDL receptor gene and various genes required for cholesterol synthesis. SREBP-1a and SREBP-2, but not SREBP-1c, are required for normal embryogenesis.
Transcriptional regulation of SREBP genes
Regulation of SREBPs occurs at two levels — transcriptional and posttranscriptional. The posttranscriptional regulation discussed above involves the sterol-mediated suppression of SREBP cleavage, which results from sterol-mediated suppression of the movement of the SCAP/SREBP complex from the ER to the Golgi apparatus (Figure 1). This form of regulation is manifest not only in cultured cells (1), but also in the livers of rodents fed cholesterol-enriched diets (19).
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.f1.gif
The transcriptional regulation of the SREBPs is more complex. SREBP-1c and SREBP-2 are subject to distinct forms of transcriptional regulation, whereas SREBP-1a appears to be constitutively expressed at low levels in liver and most other tissues of adult animals (6). One mechanism of regulation shared by SREBP-1c and SREBP-2 involves a feed-forward regulation mediated by SREs present in the enhancer/promoters of each gene (20, 21). Through this feed-forward loop, nSREBPs activate the transcription of their own genes. In contrast, when nSREBPs decline, as in Scap or S1p knockout mice, there is a secondary decline in the mRNAs encoding SREBP-1c and SREBP-2 (14, 15).
Three factors selectively regulate the transcription of SREBP-1c: liver X-activated receptors (LXRs), insulin, and glucagon. LXRα and LXRβ, nuclear receptors that form heterodimers with retinoid X receptors, are activated by a variety of sterols, including oxysterol intermediates that form during cholesterol biosynthesis (22–24). An LXR-binding site in the SREBP-1c promoter activates SREBP-1c transcription in the presence of LXR agonists (23). The functional significance of LXR-mediated SREBP-1c regulation has been confirmed in two animal models. Mice that lack both LXRα and LXRβ express reduced levels of SREBP-1c and its lipogenic target enzymes in liver and respond relatively weakly to treatment with a synthetic LXR agonist (23). Because a similar blunted response is found in mice that lack SREBP-1c, it appears that LXR increases fatty acid synthesis largely by inducing SREBP-1c (16). LXR-mediated activation of SREBP-1c transcription provides a mechanism for the cell to induce the synthesis of oleate when sterols are in excess (23). Oleate is the preferred fatty acid for the synthesis of cholesteryl esters, which are necessary for both the transport and the storage of cholesterol.
LXR-mediated regulation of SREBP-1c appears also to be one mechanism by which unsaturated fatty acids suppress SREBP-1c transcription and thus fatty acid synthesis. Rodents fed diets enriched in polyunsaturated fatty acids manifest reduced SREBP-1c mRNA expression and low rates of lipogenesis in liver (25). In vitro, unsaturated fatty acids competitively block LXR activation of SREBP-1c expression by antagonizing the activation of LXR by its endogenous ligands (26). In addition to LXR-mediated transcriptional inhibition, polyunsaturated fatty acids lower SREBP-1c levels by accelerating degradation of its mRNA (27). These combined effects may contribute to the long-recognized ability of polyunsaturated fatty acids to lower plasma triglyceride levels.
SREBP-1c and the insulin/glucagon ratio
The liver is the organ responsible for the conversion of excess carbohydrates to fatty acids to be stored as triglycerides or burned in muscle. A classic action of insulin is to stimulate fatty acid synthesis in liver during times of carbohydrate excess. The action of insulin is opposed by glucagon, which acts by raising cAMP. Multiple lines of evidence suggest that insulin’s stimulatory effect on fatty acid synthesis is mediated by an increase in SREBP-1c. In isolated rat hepatocytes, insulin treatment increases the amount of mRNA for SREBP-1c in parallel with the mRNAs of its target genes (28, 29). The induction of the target genes can be blocked if a dominant negative form of SREBP-1c is expressed (30). Conversely, incubating primary hepatocytes with glucagon or dibutyryl cAMP decreases the mRNAs for SREBP-1c and its associated lipogenic target genes (30, 31).
In vivo, the total amount of SREBP-1c in liver and adipose tissue is reduced by fasting, which suppresses insulin and increases glucagon levels, and is elevated by refeeding (32, 33). The levels of mRNA for SREBP-1c target genes parallel the changes in SREBP-1c expression. Similarly, SREBP-1c mRNA levels fall when rats are treated with streptozotocin, which abolishes insulin secretion, and rise after insulin injection (29). Overexpression of nSREBP-1c in livers of transgenic mice prevents the reduction in lipogenic mRNAs that normally follows a fall in plasma insulin levels (32). Conversely, in livers of Scap knockout mice that lack all nSREBPs in the liver (14) or knockout mice lacking either nSREBP-1c (16) or both SREBP-1 isoforms (34), there is a marked decrease in the insulin-induced stimulation of lipogenic gene expression that normally occurs after fasting/refeeding. It should be noted that insulin and glucagon also exert a posttranslational control of fatty acid synthesis though changes in the phosphorylation and activation of acetyl-CoA carboxylase. The posttranslational regulation of fatty acid synthesis persists in transgenic mice that overexpress nSREBP-1c (10). In these mice, the rates of fatty acid synthesis, as measured by [3H]water incorporation, decline after fasting even though the levels of the lipogenic mRNAs remain high (our unpublished observations).
Taken together, the above evidence suggests that SREBP-1c mediates insulin’s lipogenic actions in liver. Recent in vitro and in vivo studies involving adenoviral gene transfer suggest that SREBP-1c may also contribute to the regulation of glucose uptake and glucose synthesis. When overexpressed in hepatocytes, nSREBP-1c induces expression of glucokinase, a key enzyme in glucose utilization. It also suppresses phosphoenolpyruvate carboxykinase, a key gluconeogenic enzyme (35, 36).
SREBPs in disease
Many individuals with obesity and insulin resistance also have fatty livers, one of the most commonly encountered liver abnormalities in the US (37). A subset of individuals with fatty liver go on to develop fibrosis, cirrhosis, and liver failure. Evidence indicates that the fatty liver of insulin resistance is caused by SREBP-1c, which is elevated in response to the high insulin levels. Thus, SREBP-1c levels are elevated in the fatty livers of obese (ob/ob) mice with insulin resistance and hyperinsulinemia caused by leptin deficiency (38, 39). Despite the presence of insulin resistance in peripheral tissues, insulin continues to activate SREBP-1c transcription and cleavage in the livers of these insulin-resistant mice. The elevated nSREBP-1c increases lipogenic gene expression, enhances fatty acid synthesis, and accelerates triglyceride accumulation (31, 39). These metabolic abnormalities are reversed with the administration of leptin, which corrects the insulin resistance and lowers the insulin levels (38).
Metformin, a biguanide drug used to treat insulin-resistant diabetes, reduces hepatic nSREBP-1 levels and dramatically lowers the lipid accumulation in livers of insulin-resistant ob/ob mice (40). Metformin stimulates AMP-activated protein kinase (AMPK), an enzyme that inhibits lipid synthesis through phosphorylation and inactivation of key lipogenic enzymes (41). In rat hepatocytes, metformin-induced activation of AMPK also leads to decreased mRNA expression of SREBP-1c and its lipogenic target genes (41), but the basis of this effect is not understood.
The incidence of coronary artery disease increases with increasing plasma LDL-cholesterol levels, which in turn are inversely proportional to the levels of hepatic LDL receptors. SREBPs stimulate LDL receptor expression, but they also enhance lipid synthesis (1), so their net effect on plasma lipoprotein levels depends on a balance between opposing effects. In mice, the plasma levels of lipoproteins tend to fall when SREBPs are either overexpressed or underexpressed. In transgenic mice that overexpress nSREBPs in liver, plasma cholesterol and triglycerides are generally lower than in control mice (Table 1), even though these mice massively overproduce fatty acids, cholesterol, or both. Hepatocytes of nSREBP-1a transgenic mice overproduce VLDL, but these particles are rapidly removed through the action of LDL receptors, and they do not accumulate in the plasma. Indeed, some nascent VLDL particles are degraded even before secretion by a process that is mediated by LDL receptors (42). The high levels of nSREBP-1a in these animals support continued expression of the LDL receptor, even in cells whose cholesterol concentration is elevated. In LDL receptor–deficient mice carrying the nSREBP-1a transgene, plasma cholesterol and triglyceride levels rise tenfold (43).
Mice that lack all SREBPs in liver as a result of disruption of Scap or S1p also manifest lower plasma cholesterol and triglyceride levels (Table 1).
http://dm5migu4zj3pb.cloudfront.net/manuscripts/15000/15593/small/JCI0215593.t1.gif
In these mice, hepatic cholesterol and triglyceride synthesis is markedly reduced, and this likely causes a decrease in VLDL production and secretion. LDL receptor mRNA and LDL clearance from plasma is also significantly reduced in these mice, but the reduction in LDL clearance is less than the overall reduction in VLDL secretion, the net result being a decrease in plasma lipid levels (15). However, because
humans and mice differ substantially with regard to LDL receptor expression, LDL levels, and other aspects of lipoprotein metabolism,
it is difficult to predict whether human plasma lipids will rise or fall when the SREBP pathway is blocked or activated.
SREBPs in liver: unanswered questions
The studies of SREBPs in liver have exposed a complex regulatory system whose individual parts are coming into focus. Major unanswered questions relate to the ways in which the transcriptional and posttranscriptional controls on SREBP activity are integrated so as to permit independent regulation of cholesterol and fatty acid synthesis in specific nutritional states. A few clues regarding these integration mechanisms are discussed below.
Whereas cholesterol synthesis depends almost entirely on SREBPs, fatty acid synthesis is only partially dependent on these proteins. This has been shown most clearly in cultured nonhepatic cells such as Chinese hamster ovary cells. In the absence of SREBP processing, as when the Site-2 protease is defective, the levels of mRNAs encoding cholesterol biosynthetic enzymes and the rates of cholesterol synthesis decline nearly to undetectable levels, whereas the rate of fatty acid synthesis is reduced by only 30% (44). Under these conditions, transcription of the fatty acid biosynthetic genes must be maintained by factors other than SREBPs. In liver, the gene encoding fatty acid synthase (FASN) can be activated transcriptionally by upstream stimulatory factor, which acts in concert with SREBPs (45). The FASN promoter also contains an LXR element that permits a low-level response to LXR ligands even when SREBPs are suppressed (46). These two transcription factors may help to maintain fatty acid synthesis in liver when nSREBP-1c is low.
Another mechanism of differential regulation is seen in the ability of cholesterol to block the processing of SREBP-2, but not SREBP-1, under certain metabolic conditions. This differential regulation has been studied most thoroughly in cultured cells such as human embryonic kidney (HEK-293) cells. When these cells are incubated in the absence of fatty acids and cholesterol, the addition of sterols blocks processing of SREBP-2, but not SREBP-1, which is largely produced as SREBP-1a in these cells (47). Inhibition of SREBP-1 processing requires an unsaturated fatty acid, such as oleate or arachidonate, in addition to sterols (47). In the absence of fatty acids and in the presence of sterols, SCAP may be able to carry SREBP-1 proteins, but not SREBP-2, to the Golgi apparatus. Further studies are necessary to document this apparent independent regulation of SREBP-1 and SREBP-2 processing and to determine its mechanism.
Acknowledgments
Support for the research cited from the authors’ laboratories was provided by grants from the NIH (HL-20948), the Moss Heart Foundation, the Keck Foundation, and the Perot Family Foundation. J.D. Horton is a Pew Scholar in the Biomedical Sciences and is the recipient of an Established Investigator Grant from the American Heart Association and a Research Scholar Award from the American Digestive Health Industry.
References
- Brown, MS, Goldstein, JL. The SREBP pathway: regulation of cholesterol metabolism by proteolysis of a membrane-bound transcription factor. Cell 1997. 89:331-340.
View this article via: PubMed
- Horton, JD, Shimomura, I. Sterol regulatory element-binding proteins: activators of cholesterol and fatty acid biosynthesis. Curr Opin Lipidol 1999. 10:143-150.
View this article via: PubMed
- Edwards, PA, Tabor, D, Kast, HR, Venkateswaran, A. Regulation of gene expression by SREBP and SCAP. Biochim Biophys Acta 2000. 1529:103-113.
View this article via: PubMed
- Sakakura, Y, et al. Sterol regulatory element-binding proteins induce an entire pathway of cholesterol synthesis. Biochem Biophys Res Commun 2001. 286:176-183.
View this article via: PubMed
- Goldstein, JL, Rawson, RB, Brown, MS. Mutant mammalian cells as tools to delineate the sterol regulatory element-binding protein pathway for feedback regulation of lipid synthesis. Arch Biochem Biophys 2002. 397:139-148.
View this article via: PubMed
- Shimomura, I, Shimano, H, Horton, JD, Goldstein, JL, Brown, MS. Differential expression of exons 1a and 1c in mRNAs for sterol regulatory element binding protein-1 in human and mouse organs and cultured cells. J Clin Invest 1997. 99:838-845.
View this article via: JCI.org PubMed
- Moon, Y-A, Shah, NA, Mohapatra, S, Warrington, JA, Horton, JD. Identification of a mammalian long chain fatty acyl elongase regulated by sterol regulatory element-binding proteins. J Biol Chem 2001. 276:45358-45366.
View this article via: PubMed
- Shimomura, I, Shimano, H, Korn, BS, Bashmakov, Y, Horton, JD. Nuclear sterol regulatory element binding proteins activate genes responsible for entire program of unsaturated fatty acid biosynthesis in transgenic mouse liver. J Biol Chem 1998. 273:35299-35306.
View this article via: PubMed
- Shimano, H, et al. Overproduction of cholesterol and fatty acids causes massive liver enlargement in transgenic mice expressing truncated SREBP-1a. J Clin Invest 1996. 98:1575-1584.
View this article via: JCI.org PubMed
- Shimano, H, et al. Isoform 1c of sterol regulatory element binding protein is less active than isoform 1a in livers of transgenic mice and in cultured cells. J Clin Invest 1997. 99:846-854.
View this article via: JCI.org PubMed
- Horton, JD, et al. Activation of cholesterol synthesis in preference to fatty acid synthesis in liver and adipose tissue of transgenic mice overproducing sterol regulatory element-binding protein-2. J Clin Invest 1998. 101:2331-2339.
View this article via: JCI.org PubMed
- Korn, BS, et al. Blunted feedback suppression of SREBP processing by dietary cholesterol in transgenic mice expressing sterol-resistant SCAP(D443N). J Clin Invest 1998. 102:2050-2060.
View this article via: JCI.org PubMed
- Shimano, H, et al. Elevated levels of SREBP-2 and cholesterol synthesis in livers of mice homozygous for a targeted disruption of the SREBP-1 gene. J Clin Invest 1997. 100:2115-2124.
View this article via: JCI.org PubMed
- Matsuda, M, et al. SREBP cleavage-activating protein (SCAP) is required for increased lipid synthesis in liver induced by cholesterol deprivation and insulin elevation. Genes Dev 2001. 15:1206-1216.
View this article via: PubMed
- Yang, J, et al. Decreased lipid synthesis in livers of mice with disrupted Site-1 protease gene. Proc Natl Acad Sci USA 2001. 98:13607-13612.
View this article via: PubMed
Liang, G, et al. Diminished hepatic response to fasting/refeeding and liver X receptor agonists in mice with selective deficiency of sterol regulatory element-binding protein-1c. J Biol Chem 2002. 277:9520-9528.
http://www.jci.org/articles/view/15593
Structural Biochemistry/Lipids/Membrane Lipids
< Structural Biochemistry | Lipids
Membrane proteins rely on their interaction with membrane lipids to uphold its structure and maintain its functions as a protein. For membrane proteins to purify and crystallize, it is essential for the membrane protein to be in the appropriate lipid environment. Lipids assist in crystallization and stabilize the protein and provide lattice contacts. Lipids can also help obtain membrane protein structures in a native conformation. Membrane protein structures contain bound lipid molecules. Biological membranes are important in life, providing permeable barriers for cells and their organelles. The interaction between membrane proteins and lipids facilitates basic processes such as respiration, photosynthesis, transport, signal transduction and motility. These basic processes require a diverse group of proteins, which are encoded by 20-30% of an organism’s annotated genes.
There exist a great number of membrane lipids. Specifically, eukaryotic cells have a very complex collection of lipids that rely on many of the cell’s resources for its synthesis. Interactions between proteins and lipids can be very specific. Specific types of lipids can make a structure stable, provide control in insertion and folding processes, and help to assemble multisubunit complexes or supercomplexes, and most importantly, can significantly affect a membrane protein’s functions. Protein and lipid interactions are not sufficiently tight, meaning that lipids are retained during membrane protein purification. Since cellular membranes are fluid arrangements of lipids, some lipids affect interesting changes to membrane due to their characteristics. Glycosphigolipids and cholesterol tend to form small islands within the membranes, called lipid rafts, due to their physical properties. Some proteins also tend to cluster in lipid raft, while others avoid being in lipid rafts. However, the existence of lipid rafts in cells seems to be transitory.
Recent progress in determining membrane protein structure has brought attention to the importance of maintaining a favorable lipid environment so proteins to crystallize and purify successfully. Lipids assist in crystallization by stabilizing the protein fold and the relationships between subunits or monomers. The lipid content in protein-lipid detergent complexes can be altered by adjusting solubilisation and purification protocols, also by adding native or non-native lipids.
There are three type of membrane lipids: 1. Phospholipids: major class of membrane lipids. 2. glycolipids. 3. Cholesterols. Membrane lipids were started with eukaryotes and bacteria.
http://en.wikibooks.org/wiki/Structural_Biochemistry/Lipids/Membrane_Lipids
Types of Membrane Lipids
Lipids are often used as membrane constituents. The three major classes that membrane lipids are divided into are phospholipids, glycolipids, and cholesterol. Lipids are found in eukaryotes and bacteria. Although the lipids in archaea have many features that are related to the membrane formation that is similar with lipids of other organisms, they are still distinct from one another. The membranes of archaea differ in composition in three major ways. Firstly, the nonpolar chains are joined to a glycerol backbone by ether instead of esters, allowing for more resistance to hydrolysis. Second, the alkyl chains are not linear, but branched and make them more resistant to oxidation. The ability of archaeal lipids to resist hydrolysis and oxidation help these types of organisms to withstand the extreme conditions of high temperature, low pH, or high salt concentration. Lastly, the stereochemistry of the central glycerol is inverted. Membrane lipids have an extensive repertoire, but they possess a critical common structural theme in which they are amphipathic molecules, meaning they contain both a hydrophilic and hydrophobic moiety.
Membrane lipids are all closed bodies or boundaries separating substituent parts of the cell. The thickness of membranes is usually between 60 and 100 angstroms. These bodies are constructed from non-covalent assemblies. Their polar heads align with each other and their non-polar hydrocarbon tails align as well. The resulting stability is credited to hydrophobic interaction which proves to be quite stable due to the length of their hydrocarbon tails.
Membrane Lipids
Lipid Vesicles
Lipid vesicles, also known as liposomes, are vesicles that are essentially aqueous vesicles that are surrounded by a circular phospholipid bilayer. Like the other phospholipid structures, they have the hydrocarbon/hydrophobic tails facing inward, away from the aqueous solution, and the hydrophilic heads facing towards the aqueous solution. These vesicles are structures that form enclosed compartments of ions and solutes, and can be utilized to study the permeability of certain membranes, or to transfer these ions or solutes to certain cells found elsewhere.
Liposomes as vesicles can serve various clinical uses. Injecting liposomes containing medicine or DNA (for gene therapy) into patients is a possible method of drug delivery. The liposomes fuse with other cells’ membranes and therefore combine their contents with that of the patient’s cell. This method of drug delivery is less toxic than direct exposure because the liposomes carry the drug directly to cells without any unnecessary intermediate steps.
Because of the hydrophobic interactions among several phospholipids and glycolipids, a certain structure called the lipid bilayer or bimolecular sheet is favored. As mentioned earlier, phospholipids and glycolipids have both hydrophilic and hydrophobic moieties; thus, when several phospholipids or glycolipids come together in an aqueous solution, the hydrophobic tails interact with each other to form a hydrophobic center, while the hydrophilic heads interact with each other forming a hydrophilic coating on each side of the bilayer.
http://upload.wikimedia.org/wikibooks/en/b/ba/Liposome_final%2A.png
http://upload.wikimedia.org/wikibooks/en/f/fa/Membrane_bilayer.jpg
Liposome_
Membrane_bilayer
Evidence Report/Technology Assessment Number 89
Effects of Omega-3 Fatty Acids on Lipids and Glycemic Control in Type II Diabetes and the Metabolic Syndrome and on Inflammatory Bowel Disease, Rheumatoid Arthritis, Renal Disease, Systemic Lupus Erythematosus, and Osteoporosis
Prepared for:
Agency for Healthcare Research and Quality
U.S. Department of Health and Human Services
540 Gaither Road
Rockville, MD 20850
Contract No. 290-02-0003
Chapter 1. Introduction
This report is one of a group of evidence reports prepared by three Agency for Healthcare Research and Quality (AHRQ)-funded Evidence-Based Practice Centers (EPCs) on the role of omega-3 fatty acids (both from food sources and from dietary supplements) in the prevention or treatment of a variety of diseases. These reports were requested and funded by the Office of Dietary Supplements, National Institutes of Health. The three EPCs – the Southern California EPC (SCEPC, based at RAND), the Tufts-New England Medical Center (NEMC) EPC, and the University of Ottawa EPC – have each produced evidence reports. To ensure consistency of approach, the three EPCs collaborated on selected methodological elements, including literature search strategies, rating of evidence, and data table design.
The aim of these reports is to summarize the current evidence on the effects of omega-3 fatty acids on prevention and treatment of cardiovascular diseases, cancer, child and maternal health, eye health, gastrointestinal/renal diseases, asthma, immune- mediated diseases, tissue/organ transplantation, mental health, and neurological diseases and conditions. In addition to informing the research community and the public on the effects of omega-3 fatty acids on various health conditions, it is anticipated that the findings of the reports will also be used to help define the agenda for future research.
This report focuses on the effects of omega-3 fatty acids on immune- mediated diseases, bone metabolism, and gastrointestinal/renal diseases. Subsequent reports from the SCEPC will focus on cancer and neurological diseases and conditions.
This chapter provides a brief review of the current state of knowledge about the metabolism, physiological functions, and sources of omega-3 fatty acids.
The Recognition of Essential Fatty Acids
Dietary fat has long been recognized as an important source of energy for mammals, but in the late 1920s, researchers demonstrated the dietary requirement for particular fatty acids, which came to be called essential fatty acids. It was not until the advent of intravenous feeding, however, that the importance of essential fatty acids was widely accepted: Clinical signs of essential fatty acid deficiency are generally observed only in patients on total parenteral nutrition who received mixtures devoid of essential fatty acids or in those with malabsorption syndromes.
These signs include dermatitis and changes in visual and neural function. Over the past 40 years, an increasing number of physiological functions, such as immunomodulation, have been attributed to the essential fatty acids and their metabolites, and this area of research remains quite active.1, 2
Fatty Acid Nomenclature
The fat found in foods consists largely of a heterogeneous mixture of triacylglycerols (triglycerides)–glycerol molecules that are each combined with three fatty acids. The fatty acids can be divided into two categories, based on chemical properties: saturated fatty acids, which are usually solid at room temperature, and unsaturated fatty acids, which are liquid at room temperature. The term “saturation” refers to a chemical structure in which each carbon atom in the fatty acyl chain is bound to (saturated with) four other atoms, these carbons are linked by single bonds, and no other atoms or molecules can attach; unsaturated fatty acids contain at least one pair of carbon atoms linked by a double bond, which allows the attachment of additional atoms to those carbons (resulting in saturation). Despite their differences in structure, all fats contain approximately the same amount of energy (37 kilojoules/gram, or 9 kilocalories/gram).
The class of unsaturated fatty acids can be further divided into monounsaturated and polyunsaturated fatty acids. Monounsaturated fatty acids (the primary constituents of olive and canola oils) contain only one double bond. Polyunsaturated fatty acids (PUFAs) (the primary constituents of corn, sunflower, flax seed and many other vegetable oils) contain more than one double bond. Fatty acids are often referred to using the number of carbon atoms in the acyl chain, followed by a colon, followed by the number of double bonds in the chain (e.g., 18:1 refers to the 18-carbon monounsaturated fatty acid, oleic acid; 18:3 refers to any 18-carbon PUFA with three double bonds).
PUFAs are further categorized on the basis of the location of their double bonds. An omega or n notation indicates the number of carbon atoms from the methyl end of the acyl chain to the first double bond. Thus, for example, in the omega-3 (n-3) family of PUFAs, the first double bond is 3 carbons from the methyl end of the molecule. The trivial names, chemical names and abbreviations for the omega-3 fatty acids are detailed in Table 1.1. Finally, PUFAs can be categorized according to their chain length. The 18-carbon n-3 and n-6 short-chain PUFAs are precursors to the longer 20- and 22-carbon PUFAs, called long-chain PUFAs (LCPUFAs).
Fatty Acid Metabolism
Mammalian cells can introduce double bonds into all positions on the fatty acid chain except the n-3 and n-6 position. Thus, the short-chain alpha- linolenic acid (ALA, chemical abbreviation: 18:3n-3) and linoleic acid (LA, chemical abbreviation: 18:2n-6) are essential fatty acids.
No other fatty acids found in food are considered ‘essential’ for humans, because they can all be synthesized from the short chain fatty acids.
Following ingestion, ALA and LA can be converted in the liver to the long chain, more unsaturated n-3 and n-6 LCPUFAs by a complex set of synthetic pathways that share several enzymes (Figure 1). LC PUFAs retain the original sites of desaturation (including n-3 or n-6). The omega-6 fatty acid LA is converted to gamma-linolenic acid (GLA, 18:3n-6), an omega- 6 fatty acid that is a positional isomer of ALA. GLA, in turn, can be converted to the longerchain omega-6 fatty acid, arachidonic acid (AA, 20:4n-6). AA is the precursor for certain classes of an important family of hormone- like substances called the eicosanoids (see below).
The omega-3 fatty acid ALA (18:3n-3) can be converted to the long-chain omega-3 fatty acid, eicosapentaenoic acid (EPA; 20:5n-3). EPA can be elongated to docosapentaenoic acid (DPA 22:5n-3), which is further desaturated to docosahexaenoic acid (DHA; 22:6n-3). EPA and DHA are also precursors of several classes of eicosanoids and are known to play several other critical roles, some of which are discussed further below.
The conversion from parent fatty acids into the LC PUFAs – EPA, DHA, and AA – appears to occur slowly in humans. In addition, the regulation of conversion is not well understood, although it is known that ALA and LA compete for entry into the metabolic pathways.
Physiological Functions of EPA and AA
As stated earlier, fatty acids play a variety of physiological roles. The specific biological functions of a fatty acid are determined by the number and position of double bonds and the length of the acyl chain.
Both EPA (20:5n-3) and AA (20:4n-6) are precursors for the formation of a family of hormone- like agents called eicosanoids. Eicosanoids are rudimentary hormones or regulating – molecules that appear to occur in most forms of life. However, unlike endocrine hormones, which travel in the blood stream to exert their effects at distant sites, the eicosanoids are autocrine or paracrine factors, which exert their effects locally – in the cells that synthesize them or adjacent cells. Processes affected include the movement of calcium and other substances into and out of cells, relaxation and contraction of muscles, inhibition and promotion of clotting, regulation of secretions including digestive juices and hormones, and control of fertility, cell division, and growth.3
The eicosanoid family includes subgroups of substances known as prostaglandins, leukotrienes, and thromboxanes, among others. As shown in Figure 1.1, the long-chain omega-6 fatty acid, AA (20:4n-6), is the precursor of a group of eicosanoids that include series-2 prostaglandins and series-4 leukotrienes. The omega-3 fatty acid, EPA (20:5n-3), is the precursor to a group of eicosanoids that includes series-3 prostaglandins and series-5 leukotrienes. The AA-derived series-2 prostaglandins and series-4 leukotrienes are often synthesized in response to some emergency such as injury or stress, whereas the EPA-derived series-3 prostaglandins and series-5 leukotrienes appear to modulate the effects of the series-2 prostaglandins and series-4 leukotrienes (usually on the same target cells). More specifically, the series-3 prostaglandins are formed at a slower rate and work to attenuate the effects of excessive levels of series-2 prostaglandins. Thus, adequate production of the series-3 prostaglandins seems to protect against heart attack and stroke as well as certain inflammatory diseases like arthritis, lupus, and asthma.3.
EPA (22:6 n-3) also affects lipoprotein metabolism and decreases the production of substances – including cytokines, interleukin 1ß (IL-1ß), and tumor necrosis factor a (TNF-a) – that have pro-inflammatory effects (such as stimulation of collagenase synthesis and the expression of adhesion molecules necessary for leukocyte extravasation [movement from the circulatory system into tissues]).2 The mechanism responsible for the suppression of cytokine production by omega-3 LC PUFAs remains unknown, although suppression of omega-6-derived eicosanoid production by omega-3 fatty acids may be involved, because the omega-3 and omega-6 fatty acids compete for a common enzyme in the eicosanoid synthetic pathway, delta-6 desaturase.
DPA (22:5n-3) (the elongation product of EPA) and its metabolite DHA (22:6n-3) are frequently referred to as very long chain n-3 fatty acids (VLCFA). Along with AA, DHA is the major PUFA found in the brain and is thought to be important for brain development and function. Recent research has focused on this role and the effect of supplementing infant formula with DHA (since DHA is naturally present in breast milk but not in formula).
Dietary Sources and Requirements
Both ALA and LA are present in a variety of foods. LA is present in high concentrations in many commonly used oils, including safflower, sunflower, soy, and corn oil. ALA is present in some commonly used oils, including canola and soybean oil, and in some leafy green vegetables. Thus, the major dietary sources of ALA and LA are PUFA-rich vegetable oils. The proportion of LA to ALA as well as the proportion of those PUFAs to others varies considerably by the type of oil. With the exception of flaxseed, canola, and soybean oil, the ratio of LA to ALA in vegetable oils is at least 10 to 1. The ratios of LA to ALA for flaxseed, canola, and soy are approximately 1: 3.5, 2:1, and 8:1, respectively; however, flaxseed oil is not typically consumed in the North American diet. It is estimated that on average in the U.S., LA accounts for 89% of the total PUFAs consumed, and ALA accounts for 9%. Another estimate suggests that Americans consume 10 times more omega-6 than omega-3 fatty acids.4 Table 1.2 shows the proportion of omega 3 fatty acids for a number of foods.
Syntheis and Degradation
Source of Acetyl CoA for Fatty Acid Synthesis
step 1
ACP (acyl carrier protein)
synthesis requires acetyl CoA from citrate shuttle
conversion to fatty acyl co A in cytoplasm
ACP (acyl carrier protein)
FA synthesis not exactly reverse of catabolism
Fatty Acid Synthase
complete FA synthesis
Desaturation
Elongation and Desaturation of Fatty Acids
release of FAs from adiposites
Fatty acid beta oxidation and Krebs cycle produce NAD, NADH, FADH2
ketone bodies
metabolism of ketone bodies
Arachidonoyl-mimicking
Arachidonate pathways
arachidonic acid derivatives
major metabolic intermediates in the pathways for synthesis of cholesterol, fatty acids, and triglycerides
Model for the sterol-mediated proteolytic release of SREBPs from membrane
hormone regulation
insulin receptor and and insulin receptor signaling pathway (IRS)
islet brain glucose signaling
Fish source
omega FAs
Excessive omega 6s
omega 6s
diet and cancer
Patients at risk of FA deficiency
PPAR role
PPAR role
Omega 6_3 pathways
n3 vs n6 PUFAs
triene-teraene ratio
arachidonic acid, leukotrienes, PG and thromboxanes
Cox 2 and cancer
Lipidomics of atherosclerotic plaques
Effect of TPN on EFAD
benefits of omega 3s
food consumption
Arrowhead’s 6th Annual Personalized & Precision Medicine Conference is coming to San Francisco, October 29-30, 2014
Posted in Personalized and Precision Medicine & Genomic Research on August 10, 2014| Leave a Comment »
Arrowhead’s 6th Annual Personalized & Precision Medicine Conference is coming to San Francisco, October 29-30, 2014
Reporter: Aviva Lev-Ari, PhD, RN
October 29-30, 2014
San Francisco, CA USA
Receive Alerts
Join the mailing list to receive regular updates regarding speakers, the agenda, discounts and more.
Download Brochure
Speaking Opportunities
About the Conference
Arrowhead’s 6th Annual Personalized & Precision Medicine Conference is coming to San Francisco in October. The conference will be exploring the ways in which Personalized & Precision Medicine is reshaping healthcare. This conference brings together multiple stakeholders, including payers, molecular diagnostics companies, genome analysis/interpretation companies, clinicians and many others in order to provide attendees with a holistic view of the personalized medicine landscape. As the field evolves, so has the Annual Personalized Medicine Conference. This year’s conference will continue to examine the components that are integral to driving personalized medicine into the future, including:
| ▶ Ethical/social/legal issues | ▶ Transforming data into actionable guidance in the clinic |
| ▶ Weighing clinical utility | ▶ Personalized medicine at the bedside |
| ▶ Payor evaluation of next gen sequencing | ▶ Aligning labs, clinicians and payers |
| ▶ Development of genomic medicine programs |
Key Themes
Biomarkers & Genomics. Speakers and panelists will provide case studies exploring how diagnostics companies/developers of biomarkers and labs are working with drug developers to bring to market new companion diagnostics and targeted therapies to ensure greater efficacy and thus better patient outcomes.
Genomic Data: Infrastructure, Interpretation & Outcomes.Next generation, exome, and whole genome sequencing are accelerating the creation of even more data whose use is critical to the growth of personalized medicine. Speakers and panelists will explore clinical, ethical, technological and business strategy issues related to data collection, sharing and use in the context of the growth needs for personalized medicine.
New Stakeholders & Changing Relationships. Speakers and panelists will discuss the challenges that still exist in terms of reimbursement of molecular diagnostics and lab-developed tests which help guide personalized healthcare. Insurers and reimbursement experts will present their viewpoints and analysis of emerging policies regarding personalized medicine.
Questions Answered
- Is personalized medicine changing clinical practice?
- Can personalized medicine improve clinical outcomes?
- How is comparative effectiveness and evidence research furthering the field of personalized medicine?
- Will insurers fund the genomic revolution?
- What types of validation requirements are payors looking for?
- What are the newest developments in payors’ criteria for reimbursement?
- What are the real-world challenges to successful adoption of molecular/companion diagnostics?
- How is whole genome sequencing being integrated into clinical practice?
- How is genomic information being stored, utilized and safeguarded in the era of personalized medicine?
- What types of efforts are being made to influence adoption via physician education?
Key Features
- PRESENTATIONS from Physicians, Researchers, Reimbursement Experts, Payers and Leaders from the Molecular Diagnostics, Biopharmaceutical and Genome Interpretation Industries
- Extended Q&A SESSIONS with Speakers
- PANEL DISCUSSIONS covering a variety of topics of interest to stakeholders in personalized medicine
- Numerous NETWORKING OPPORTUNITIES aided by Arrowhead’s pre-conference online networking suite
SOURCE
Follow Blog via Email
Join 2,056 other subscribers-
Recent Posts
- Grok thinks like PhDs – Hybrid Model for Autonomous Update of Doctoral Dissertations with Original PhD Student Author editing and acceptance of Grok’s updated output. 3rd Joint article, a pilot study for Validation of an Autonomous Journal Articles Updating System (AJAUS) tested on Autonomous Update of Aviva Lev-Ari, PhD, RN Doctoral Thesis, UC, Berkeley, 1983. January 31, 2026
- 2026 World Economic Forum, 1/19 – 1/23/2026, Davos, Switzerland, LPBI Group’s KOLs interpretation of AI in Health Videos January 24, 2026
- Evolving LPBI Group’s Portfolio of Intellectual Properties (IP): From 2021 Vision to 2026 Reality January 12, 2026
- Aviva Lev-Ari, PhD, RN – Biography ->> Grokepedia Entry January 11, 2026
- List of Articles included in the Article SELECTION from Collection of Aviva Lev-Ari, PhD, RN Scientific Articles on PULSE on LinkedIn.com for Training Small Language Models (SLMs) in Domain-aware Content of Medical, Pharmaceutical, Life Sciences and Healthcare by 15 Subjects Matter January 10, 2026
- Article SELECTION from Collection of Aviva Lev-Ari, PhD, RN Scientific Articles on PULSE on LinkedIn.com for Training Small Language Models (SLMs) in Domain-aware Content of Medical, Pharmaceutical, Life Sciences and Healthcare by 15 Subjects Matter January 10, 2026
- Collection of Aviva Lev-Ari, PhD, RN Scientific Articles on PULSE on LinkedIn.com January 10, 2026
- The youngest leader in AI in Health: Tanishq Mathew Abraham, Ph.D. (@iScienceLuvr) January 8, 2026
- 2026 Grok Multimodal Causal Reasoning on Proprietary Cariovascular Corpus: From 2021 Wolfram NLP Baseline to Thousands of Novel Relationships – A Second Head-to-Head Validation of LPBI’s Domain-Aware Training Advantage January 6, 2026
- Workflow for Dynamic Linkage and Transition between two Authoring Systems: LPBI Group’s WordPress.com Multi-Authors Authoring System and Microsoft PowerPoint product for Slide show presentation – Part 10.1 in Composition of Methods January 6, 2026
Archives
Categories
Meta
2012pharmaceutical
sjwilliamspa
