Healthcare analytics, AI solutions for biological big data, providing an AI platform for the biotech, life sciences, medical and pharmaceutical industries, as well as for related technological approaches, i.e., curation and text analysis with machine learning and other activities related to AI applications to these industries.
Lasker~Koshland
Special Achievement Award in Medical Science
Award Description
Mary-Claire King For bold, imaginative, and diverse contributions to medical science and human rights — she discovered the BRCA1 gene locus that causes hereditary breast cancer and deployed DNA strategies that reunite missing persons or their remains with their families.
The 2014 Lasker~Koshland Award for Special Achievement in Medical Science honors a scientist who has made bold, imaginative, and diverse contributions to medical science and human rights. Mary-Claire King(University of Washington, Seattle) discovered the BRCA1 gene locus that causes hereditary breast cancer and deployed DNA strategies that reunite missing persons or their remains with their families. Her work has touched families around the world.
As a statistics graduate student in the late 1960s, King took the late Curt Stern’s genetics course just for fun. The puzzles she encountered there—problems posed by Stern—enchanted her. She was delighted to learn that people could be paid to solve such problems, and that mathematics holds their key. She decided to study genetics and never looked back.
During her Ph.D. work with the late Allan Wilson (University of California, Berkeley), King discovered that the sequences of human and chimpanzee proteins are, on average, more than 99 percent identical; DNA sequences that do not code for proteins differ only a little more. The two primates therefore are much closer cousins than suggested by fossil studies of the time. The genetic resemblance seemed to contradict obvious distinctions: Human brains outsize those of chimps; their limbs dwarf ours; and modes of communication, food gathering, and other lifestyle features diverge dramatically. King and Wilson proposed that these contrasts arise not from disparities in DNA sequences that encode proteins, but from a small number of differences in DNA sequences that turn the protein-coding genes on and off.
Just as genetic changes drive species in new directions, they also can propel cells toward malignancy. From an evolutionary perspective, the topic of breast cancer began to intrigue King. The illness runs in families and is clearly inherited, yet many affected women have no close relatives with the disease. It is especially deadly for women whose mothers succumbed to it—and risk increases for those who have a mother or sister with breast cancer, particularly if the cancer struck bilaterally or before menopause. Unlike the situation with lung cancer, no environmental exposure distinguishes sisters who get breast cancer from those who remain disease free.
By studying a rare familial cancer, Alfred Knudsen (Lasker Clinical Medical Research Award, 1998) had shown in the early 1970’s how an inherited genetic defect could increase vulnerability to cancer. In the model he advanced, some families harbor a damaged version of a gene that normally encourages proper cellular behavior. Genetic mishaps occur during a person’s lifetime, and a second “hit” in a cell with the first physiological liability nudges the injured cell toward malignancy. A similar story might play out in families with a high incidence of breast cancer, King reasoned. She began to hunt for the theoretical pernicious gene in 1974.
The hunt
Many geneticists doubted that susceptibility to breast cancer would map to a single gene; even if it did, finding the culprit seemed unlikely for numerous reasons. First, most cases are not familial and the disease is common—so common that inherited and non-inherited cases could occur in the same families. Furthermore, the malady might not strike all women who carry a high-risk gene, and different families might carry different high-risk genes. Prevailing views held that the ailment arises from the additive effects of multiple undefined genetic and environmental insults and from complicated interactions among them. No one had previously tacked such complexities, and an attempt to unearth a breast cancer gene seemed woefully naïve.
To test whether she could find evidence that particular genes increase the odds of getting breast cancer, King applied mathematical methods to data from more than 1500 families of women younger than 55 years old with newly diagnosed breast cancer. The analysis, published in 1988, suggested that four percent of the families carry a single gene that predisposes individuals to the illness.
The most convincing way to validate this idea was to track down the gene. Toward this end, King analyzed DNA from 329 participating relatives with 146 cases of invasive breast cancer. In many of the 23 families to which the participants belonged, the scourge struck young women, often in both breasts, and in some families, even men.
In late 1990, King (by then a professor at the University of California, Berkeley) hit her quarry. She had zeroed in on a suspicious section of chromosome 17 that carried particular genetic markers in women with breast cancer in the most severely affected families. Somewhere in that stretch of DNA lay the gene, which she named BRCA1.
This discovery spurred an international race to find the gene. Four years later, scientists at Myriad Genetics, Inc. isolated it. Alterations in either BRCA1 or a second breast-cancer susceptibility gene, BRCA2, found by Michael Stratton and colleagues (Institute of Cancer Research, UK) increase risk of ovarian as well as breast cancer. The proteins encoded by these genes help maintain cellular health by repairing marred DNA. When theBRCA1 or BRCA2 proteins fail to perform their jobs, genetic integrity is compromised, thus setting the stage for cancer.
About 12 percent of women in the general population get breast cancer at some point in their lives. In contrast, 65 percent of women who inherit an abnormal version of BRCA1 and about 45 percent of women who inherit an abnormal version of BRCA2 develop breast cancer by the time they are 70 years old. Individuals with troublesome forms of BRCA1 and BRCA2 can now be identified, monitored, counseled, and treated appropriately.
Harmful versions of other genes also predispose women to breast cancer, ovarian cancer, or both. Several years ago, King devised a scheme to screen for all of these genetic miscreants. This strategy allows genetic testing and risk determination for breast and ovarian cancer; it is already in clinical practice.
Genetic tools, human rights
King has applied her expertise to aid people who suffer from ills perpetrated by humans as well as genes. She helped find the “lost children” of Argentina—those who had been kidnapped as infants or born while their mothers were in prison during the military regime of the late 1970s and early 1980s. Some of these youngsters had been illegally adopted, many by military families. In 1983, King began identifying individuals, first with a technique that was originally designed to match potential organ transplant donors and recipients. She then developed an approach that relies on analysis of DNA from mitochondria—a cellular component that passes specifically from mother to child, and is powerful for connecting people to their female forebears. King helped prove genetic relationships and thus facilitated the reunion of more than 100 of the children with their families.
Later, the Argentinian government asked if she could help identify dead bodies of individuals thought to have been murdered. King harnessed the same method to figure out who had been buried in mass graves. She established that teeth, whose enamel coating protects DNA in the dental pulp from degradation, offer a valuable resource when attempting to trace remains in situations where long periods have elapsed since the time of death.
This and related approaches have been used to identify soldiers who went missing in action, including the remains of an American serviceman who was buried beneath the Tomb of the Unknowns in Arlington National Cemetery for 14 years, as well as victims of natural disasters and man-made tragedies such as 9/11.
Mary-Claire King has employed her intellect, dedication, and ethical sensibilities to generate knowledge that has catalyzed profound changes in health care, and she has applied her expertise to promote justice where nefarious governments have terrorized their citizens.
1:00PM 11/13/2014 – 10th Annual Personalized Medicine Conference at the Harvard Medical School, Boston
REAL TIME Coverage of this Conference by Dr. Aviva Lev-Ari, PhD, RN – Director and Founder of LEADERS in PHARMACEUTICAL BUSINESS INTELLIGENCE, Boston http://pharmaceuticalintelligence.com
1:00 p.m. Panel Discussion Genomics in Prenatal and Childhood Disorders
Genetics: embryo – implant only the healthy embryo – newborn comprehensive genetics testing in the medical record integrated – Standard language of GENE-DRUG interaction not only drug-drug interaction
Potential Harms: May or may not happen disease – stigma issues
Explaining to parents the conditions is very difficult for MDs
Prenatal screening and diagnosis – chromosomal abnormality – Down Syndrome, testing is more precise 70% fewer procedures to correct defects due to screening prenatally.
Prenatal diagnostics — patient is not in front of us, ultrasound examination, options to terminate pregnancies, genetic counseling — changed due to Genomics
Prenatal treatment to down syndrome before the birth – Transcriptomic approach, treat the fetus prebirth
Standard of care – all pregnant women – must receive from MD the option for screening for down syndrome, it is a test positive or negative
NOW – DNA allows to test for fetal sex, chromosome in maternal circulation fetal and maternal genetics — Mother may have chromosomal variation
high false positive – DNA for Down Syndrome, 97% effective Micro duplication only 5%
genetics information protection act – sue prospective employer using Genome, life insurance issues
most data available is on Down Syndrome, of all parents informed of a fetus with Down Syndrome – 40% continues the pregnancy
accuracy in testing, offering choice and treatment are LEADING principles NOT elimination of a disease (i.e. down syndromes)
in ten years — GENOME OF EVERY FETUS TO BE SEQUENCE
Small population in Lancaster, PA – risk for untreatable disease 52,000 screens 4.2 millions in US are screened Target mutation analysis, diagnosis very effectively. Harrisburg, PA – small scale natural history studies
Carrier testing offered in 70s. Discourages from marriage, culture reaction is different. Working in the community, clinical practice using exon sequencing, combine population genetics and molecular biology.Translate Genomics to Clinical, small number of risk factors
History of genetics in population important to establish treatment
Upon birth, affected newborns get matching bone marrow transplant, thus, bypass stem cells – Gene therapy is another thing
Longer term, statistical model in asthma research, rigorous process on patient consent, life insurance, mutation that parents also have. Consequences: actionable findings are communicated
135 Genes – sequencing for some conditions
100,000 deliveries 10% ENTER THE STUDY, CASE BY CASE BASIS O PARTICIPATE, WHO SHOULD BE TESTED
REAL TIME Coverage of the Conference by Dr. Aviva Lev-Ari, PhD, RN – Director and Founder of LEADERS in PHARMACEUTICAL BUSINESS INTELLIGENCE, Boston http://pharmaceuticalintelligence.com
Speakers
Raju Kucherlapati, Ph.D. Paul C. Cabot Professor of Genetics, Professor of Medicine, Harvard Medical School
Welcome all attendees, discussing Personalized Medicine, what happened and looking forward — the potential of this approach to Medicine. Event organized with Partner, National Council Cancer Research. Organizing committee and Sponsors made the event possible.
AND
Scott Weiss, M.D., M.S. Scientific Director, Partners Personalized Medicine;
Associate Director, Channing Laboratory, Professor of Medicine.
Greetings
Greetings from the Institute of Medicine
Victor Dzau, M.D. — ABSENT — By Voice addressing the Audience
President, Institute of Medicine
Advisor on Genomics – In 1996 returned from Stanford to Harvard. What role Genetics and Genomics will play in Medicine.
Boston is a very special place for that endeavor. Harvard allocated $100 Million to study this topic. 10th year of the Conference. I am 100 days at IOM, Genomics and personalized medicine (PM) and Translation Medicine are the center. Spin off in Software development to solicit application in PM. Scientists, payers, technologists — the economics of PM navigate the regulatory. Looking forward for the next 10 years in PM
It is estimated that the medical imaging market will exceed $30 billion in 2014 (FierceMedicalImaging). To put this amount in perspective; the global pharmaceutical market size for the same year is expected to be ~$1 trillion (IMS) while the global health care spending as a percentage of Gross Domestic Product (GDP) will average 10.5% globally in 2014 (Deloitte); it will reach ~$3 trillion in the USA.
Recent technology-advances, mainly miniaturization and improvement in electronic-processing components is driving increased introduction of innovative medical-imaging devices into critical nodes of major-diseases’ management pathways. Consequently, in contrast to it’s very small contribution to global health costs, medical imaging bears outstanding potential to reduce the future growth in spending on major segments in this market mainly: Drugs development and regulation (e.g. companion diagnostics and imaging surrogate markers); Disease management (e.g. non-invasive diagnosis, guided treatment and non-invasive follow-ups); and Monitoring aging-population (e.g. Imaging-based domestic sensors).
In; The Role of Medical Imaging in Personalized Medicine I discussed in length the role medical imaging assumes in drugs development. Integrating imaging into drug development processes, specifically at the early stages of drug discovery, as well as for monitoring drug delivery and the response of targeted processes to the therapy is a growing trend. A nice (and short) review highlighting the processes, opportunities, and challenges of medical imaging in new drug development is: Medical imaging in new drug clinical development.
The following is dedicated to the role of imaging in guiding treatment.
Precise treatment is a major pillar of modern medicine. An important aspect to enable accurate administration of treatment is complementing the accurate identification of the organ location that needs to be treated with a system and methods that ensure application of treatment only, or mainly to, that location. Imaging is off-course, a major component in such composite systems. Amongst the available solution, functional-imaging modalities are gaining traction. Specifically, molecular imaging (e.g. PET, MRS) allows the visual representation, characterization, and quantification of biological processes at the cellular and subcellular levels within intact living organisms. In oncology, it can be used to depict the abnormal molecules as well as the aberrant interactions of altered molecules on which cancers depend. Being able to detect such fundamental finger-prints of cancer is key to improved matching between drugs-based treatment and disease. Moreover, imaging-based quantified monitoring of changes in tumor metabolism and its microenvironment could provide real-time non-invasive tool to predict the evolution and progression of primary tumors, as well as the development of tumor metastases.
A recent review-paper: Image-guided interventional therapy for cancer with radiotherapeutic nanoparticles nicely illustrates the role of imaging in treatment guidance through a comprehensive discussion of; Image-guided radiotherapeutic using intravenous nanoparticles for the delivery of localized radiation to solid cancer tumors.
Abstract
One of the major limitations of current cancer therapy is the inability to deliver tumoricidal agents throughout the entire tumor mass using traditional intravenous administration. Nanoparticles carrying beta-emitting therapeutic radionuclides[DN: radioactive isotops that emits electrons as part of the decay process a list of β-emitting radionuclides used in radiotherapeutic nanoparticle preparation is given in table1 of this paper.) that are delivered using advanced image-guidance have significant potential to improve solid tumor therapy. The use of image-guidance in combination with nanoparticle carriers can improve the delivery of localized radiation to tumors. Nanoparticles labeled with certain beta-emitting radionuclides are intrinsically theranostic agents that can provide information regarding distribution and regional dosimetry within the tumor and the body. Image-guided thermal therapy results in increased uptake of intravenous nanoparticles within tumors, improving therapy. In addition, nanoparticles are ideal carriers for direct intratumoral infusion of beta-emitting radionuclides by convection enhanced delivery, permitting the delivery of localized therapeutic radiation without the requirement of the radionuclide exiting from the nanoparticle. With this approach, very high doses of radiation can bedelivered to solid tumors while sparing normal organs. Recent technological developments in image-guidance, convection enhanced delivery and newly developed nanoparticles carrying beta-emitting radionuclides will be reviewed. Examples will be shown describing how this new approach has promise for the treatment of brain, head and neck, and other types of solid tumors.
The challenges this review discusses
intravenously administered drugs are inhibited in their intratumoral penetration by high interstitial pressures which prevent diffusion of drugs from the blood circulation into the tumor tissue [1–5].
relatively rapid clearance of intravenously administered drugs from the blood circulation by kidneys and liver.
drugs that do reach the solid tumor by diffusion are inhomogeneously distributed at the micro-scale – This cannot be overcome by simply administering larger systemic doses as toxicity to normal organs is generally the dose limiting factor.
even nanoparticulate drugs have poor penetration from the vascular compartment into the tumor and the nanoparticles that do penetrate are most often heterogeneously distributed
How imaging could mitigate the above mentioned challenges
The inclusion of an imaging probe during drug development can aid in determining the clearance kinetics and tissue distribution of the drug non-invasively. Such probe can also be used to determine the likelihood of the drug reaching the tumor and to what extent.
Note:Drugs that have increased accumulation within the targeted site are likely to be more effective as compared with others. In that respect, Nanoparticle-based drugs have an additional advantage over free drugs with their potential to be multifunctional carriers capable of carrying both therapeutic and diagnostic imaging probes (theranostic) in the same nanocarrier. These multifunctional nanoparticles can serve as theranostic agents and facilitate personalized treatment planning.
Imaging can also be used for localization of the tumor to improve the placement of a catheter or external device within tumors to cause cell death through thermal ablation or oxidative stress secondary to reactive oxygen species.
Note: Image guided thermal ablation methods include radiofrequency (RF) ablation, microwave ablation or high intensity focused ultrasound (HIFU). Photodynamic therapy methods using external light devices to activate photosensitizing agents can also be used to treat superficial tumors or deeper tumors when used with endoscopic catheters.
Quality control during and post treatment
For example: The use of high intensity focused ultrasound (HIFU) combined with nanoparticle therapeutics: HIFU is applied to improve drug delivery and to trigger drug release from nanoparticles. Gas-bubbles are playing the role of the drug’s nano-carrier. These are used both to increase the drug transport into the cell and as ultrasound-imaging contrast material. The ultrasound is also used for processes of drug-release and ablation.
Additional example; Multifunctional nanoparticles for tracking CED (convection enhanced delivery) distribution within tumors: Nanoparticle that could serve as a carrier not only for the therapeutic radionuclides but simultaneously also for a therapeutic drug and 4 different types of imaging contrast agents including an MRI contrast agent, PET and SPECT nuclear diagnostic imaging agents and optical contrast agents as shown below. The ability to perform multiple types of imaging on the same nanoparticles will allow studies investigating the distribution and retention of nanoparticles initially in vivo using non-invasive imaging and later at the histological level using optical imaging.
Conclusions
Image-guided radiotherapeutic nanoparticles have significant potential for solid tumor cancer therapy. The current success of this therapy in animals is most likely due to the improved accumulation, retention and dispersion of nanoparticles within solid tumor following image-guided therapies as well as the micro-field of the β-particle which reduces the requirement of perfectly homogeneous tumor coverage. It is also possible that the intratumoral distribution of nanoparticles may benefit from their uptake by intratumoral macrophages although more research is required to determine the importance of this aspect of intratumoral radionuclide nanoparticle therapy. This new approach to cancer therapy is a fertile ground for many new technological developments as well as for new understandings in the basic biology of cancer therapy. The clinical success of this approach will depend on progress in many areas of interdisciplinary research including imaging technology, nanoparticle technology, computer and robot assisted image-guided application of therapies, radiation physics and oncology. Close collaboration of a wide variety of scientists and physicians including chemists, nanotechnologists, drug delivery experts, radiation physicists, robotics and software experts, toxicologists, surgeons, imaging physicians, and oncologists will best facilitate the implementation of this novel approach to the treatment of cancer in the clinical environment. Image-guided nanoparticle therapies including those with β-emission radionuclide nanoparticles have excellent promise to significantly impact clinical cancer therapy and advance the field of drug delivery.
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
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.
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
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
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
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)
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).
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
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.
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.
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.
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.
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.
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:
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
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.
“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:
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]
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.
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.
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
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]
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 Postson 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
RymaBenayed, MichaelOffin, KerryMullaney, PurvilSukhadia, KellyRios, PatriceDesmeules, RyanPtashkin, HelenWon, JasonChang, DarraghHalpenny, Alison M.Schram, Charles M.Rudin, David M.Hyman, Maria E.Arcila, Michael F.Berger, AhmetZehir, Mark G.Kris, AlexanderDrilon and MarcLadanyi
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.
Wake Up and Smell the Fusions: Single-Modality Molecular Testing Misses Drivers
by Kurtis D.Davies and Dara L.Aisner
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.
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).
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.
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.
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:
The Society for Immunotherapy of Cancer (SITC) is a 501 (c)(3) non-profit society of medical professionals. Recent advances in immunology and biology have opened up new horizons in the field of cancer therapy, with an upsurge in the integration of new biologic agents into clinical practice. With several high-caliber scientific meetings with a focus on clinical and translational aspects of biologic approaches to cancer treatment and numerous networking opportunities unique to this organization, the Society for Immunotherapy of Cancer (SITC) has developed into the premier destination for interaction and innovation in the cancer biologics community.
Portland, OR – Friday, October 3, 2014 Charlotte, NC – Friday, October 3, 2014
Tampa, FL – Friday, December 5, 2014
September 2014
Hematologic Malignancies: Translating Discoveries to Novel Therapies September 20-23, 2014 • Sheraton Philadelphia Downtown • Philadelphia, PA
The AACR is proud to announce our conference focused on the blood-based cancers and associated disorders categorized as hematologic malignancies. Sessions will include presentations on leukemia, lymphoma, myeloma, myelodysplastic syndrome, and myeloproliferative neoplasms.
Advances in Melanoma: From Biology to Therapy
Loews Philadelphia • Philadelphia, PA • September 20-23, 2014
With so many recent advances in treating metastatic melanoma, including approaches like immunotherapies, targeted therapies, and combination therapies, melanoma research is at a critical point where it is extremely important for the field to have a continuous exchange of information. Despite the success of various “targeted” inhibitors, therapeutic responses in melanoma patients are often short-lived due to rapidly acquired drug resistance. Therefore, it is essential that melanoma researchers translate the novel understanding of melanoma biology to decipher the mechanisms of innate and acquired drug resistance for the development of improved therapeutic options. To bridge the gap between scientists and clinician-scientists’ professional practice, this conference will provide a platform for discussion and potential collaborations for the discovery of new therapeutic targets.
Join leaders in the immunogenicity field for a two day conference to learn what constitutes a successful strategy for managing immunogenicity risk, and explore the business case for introducing immunogenicity assessment into your program.
Learn about the latest strategies and exciting new technologies
Discuss current and developing challenges and exchange new ideas
Improve the outcome of your R&D programs
Our 4th Mastering Immunogenicity Conference will continue to have a strong focus on immunogenicity sciences, particularly on what basic research needs to be carried out to improve our understanding of immune regulation to biotherapeutics. We will review progress made in correlating data from pre-clinical predictive tools to clinical outcomes, as well as continuing our discussions surrounding the benefits that Quality by Design has on reduced immunogenicity, considering subsequent patient benefits as well as competitive advantage. Presentations by experts will provide an overview of the wide range of technologies currently used for immunogenicity risk management and how they can be incorporated for a ‘quality by design’ approach.
HudsonAlpha Biotechnology Campus
Huntsville, Alabama, USA
The HudsonAlpha-Science Conference on Immunogenomics will bring together preeminent leaders and thinkers at the intersection of genomics and immunology.
October 2014
Cancer Immunotherapy: Out of the Gate
October 06, 2014 Grand Hyatt New York Hotel at Grand Central, New York, NY
The Cancer Research Institute (CRI) will host its 22nd Annual International Cancer Immunotherapy Symposium October 6-8, 2014 at The Grand Hyatt in New York City. Attracting clinicians, laboratory scientists, postdoctoral fellows, and graduate students, the symposium will feature plenary presentations from leaders in immunology and cancer immunotherapy, a poster session, and numerous networking opportunities.
This year’s CRI symposium, entitled Cancer Immunotherapy: Out of the Gate, will harness the excitement and enthusiasm generated by recent clinical successes to explore new and emerging areas of basic, translational, and clinical research. Topics such as the use of genomic methods to catalogue cancer heterogeneity, mechanistic studies of checkpoint blockage antibodies, new views on immunosurveillance and immunoregulation, and emerging therapies that are altering the landscape of cancer treatment will be discussed.
CSHL, UCLA & Einstein to Lead Roundtable Discussions on Single-Cell Sequencing
Interactive discussions on three of the key questions researchers are facing when considering single-cell analysis will be held on the second day of the Single-Cell Sequencing Conference at Next Generation Dx Summit, taking place August 20-21, 2014 in Washington, DC. For full program details and to register, please visit NextGenerationDx.com/Single-Cell-Sequencing.Making Single-Cell Analysis Cost Effective for Clinical Use
Moderator: James Hicks, Ph.D., Research Professor, Cancer Genomics, Cold Spring Harbor Laboratory
Methods for capture: What are the tradeoffs?
Combining RNA, DNA and protein analysis
What genomic assays are most informative?
Can assays be certifiable?
Finding a Needle in a Haystack: Towards Diagnosing Rare Soft Tissue Cancer Stem Cells (CSCs) Moderator: Michael Masterman-Smith, Ph.D., Entrepreneurial Scientist, UCLA California NanoSystems Institute
Rethinking companion diagnostics for cancer to incorporate analysis of CSCs
Current direct methodologies of CSC detection/isolation
Current proxy methodologies of CSC detection/isolation
The hope and promise of single-cell assay tools and technologies
Why Single-Cell Sequencing? Moderator: Jan Vijg, Ph.D., Professor and Chairman, Genetics, Albert Einstein College of Medicine
Sample limitations, e.g., prenatal diagnostics and CTCs
Sample limitations, e.g., prenatal diagnostics and CTCs
To study cell-to-cell variation, e.g., in tumors as well as normal tissues
To overcome technological constraints, e.g., detecting somatic mutations
Cell-to-cell fluctuations in gene expression can easily impair function, yet can be undetectable by measuring averages
Sequencing data from bulk DNA or RNA from multiple cells provide global information on average states of cell populations. But with whole-genome amplification and NGS, researchers can detect variation in individual cancer cells and dissect tumor evolution. Such cancer genome sequencing will improve oncology by detecting rare tumor cells early, measuring intra-/intertumor heterogeneity, guiding chemotherapy and controlling drug resistance. The Single-Cell Sequencing conference explores the latest strategies, data analyses and clinical considerations that influence and aid cancer diagnosis, prognosis and prediction and will lead to individualized cancer therapy.
Sessions include presentations spanning the opportunities of clinical single-cell analysis from:
Sunney Xie, Ph.D., Mallinckrodt Professor. Chemistry and Chemical Biology, Harvard University
Maximilian Diehn, M.D., Ph.D., Assistant Professor, Radiation Oncology, Stanford Cancer Institute, Institute for Stem Cell Biology & Regenerative Medicine, Stanford University
Denis Smirnov, Associate Scientific Director, US Biomarker Oncology, Janssen R&D US
James Hicks, Ph.D., Research Professor, Cancer Genomics, Cold Spring Harbor Laboratory
Jan Vijg, Ph.D., Professor and Chairman, Genetics, Albert Einstein College of Medicine
John F. Zhong, Ph.D., Associate Professor, Pathology, University of Southern California School of Medicine
Mark Hills, Ph.D., Research Scientist, Peter M. Lansdorp Laboratory, BC Cancer Research Centre
Michael Masterman-Smith, Ph.D., Entrepreneurial Scientist, UCLA California NanoSystems Institute
Parveen Kumar, Research Scientist, Thierry Voet Laboratory, Human Genetics, University of Leuven
Peter Nemes, Ph.D., Assistant Professor, Chemistry, George Washington University
Theresa Zhang, Ph.D., Vice President, Research Services, Personal Genome Diagnostics
Yong Wang, Ph.D., Senior Postdoctoral Fellow, Nicholas E. Navin Laboratory, Genetics, Bioinformatics, MD Anderson Cancer Center
Zivana Tezak, Ph.D., Associate Director, Science and Technology, Personalized Medicine, Office of In Vitro Diagnostic Device Evaluation and Safety (OIVD), Center for Devices and Radiological Health (CDRH), FDA
Recommended Pre-Conference Courses
NGS Data Analysis – Determining Clinical Utility of Genome Variants Monday, August 18 | 9:00am – 12:00pm This course will explore the strategies of genomic data analysis and interpretation, an emergent discipline that seeks to deliver better answers from NGS data so that patients and their physicians can determine informed healthcare decisions. View Details
NGS as a Diagnostics Platform Monday, August 18 | 2:00pm – 5:00pm The focus of this short course will be on understanding the use of NGS in clinical diagnosis, practical implementation of NGS in clinical laboratories and analysis of large data sets by using bioinformatics tools to parse and interpret data in relation to the clinical phenotype. The concluding presentation will be dedicated to quality and standardization of NGS assays. View Details
Summary – Volume 4, Part 2: Translational Medicine in Cardiovascular Diseases
Author and Curator: Larry H Bernstein, MD, FCAP
We have covered a large amount of material that involves
the development,
application, and
validation of outcomes of medical and surgical procedures
that are based on translation of science from the laboratory to the bedside, improving the standards of medical practice at an accelerated pace in the last quarter century, and in the last decade. Encouraging enabling developments have been:
1. The establishment of national and international outcomes databases for procedures by specialist medical societies
2. The identification of problem areas, particularly in activation of the prothrombotic pathways, infection control to an extent, and targeting of pathways leading to progression or to arrythmogenic complications.
5. This has become possible because of the advances in our knowledge of key related pathogenetic mechanisms involving gene expression and cellular regulation of complex mechanisms.
This completes what has been presented in Part 2, Vol 4 , and supporting references for the main points that are found in the Leaders in Pharmaceutical Intelligence Cardiovascular book. Part 1 was concerned with Posttranslational Modification of Proteins, vital for understanding cellular regulation and dysregulation. Part 2 was concerned with Translational Medical Therapeutics, the efficacy of medical and surgical decisions based on bringing the knowledge gained from the laboratory, and from clinical trials into the realm opf best practice. The time for this to occur in practice in the past has been through roughly a generation of physicians. That was in part related to the busy workload of physicians, and inability to easily access specialty literature as the volume and complexity increased. This had an effect of making access of a family to a primary care provider through a lifetime less likely than the period post WWII into the 1980s.
However, the growth of knowledge has accelerated in the specialties since the 1980’s so that the use of physician referral in time became a concern about the cost of medical care. This is not the place for or a matter for discussion here. It is also true that the scientific advances and improvements in available technology have had a great impact on medical outcomes. The only unrelated issue is that of healthcare delivery, which is not up to the standard set by serial advances in therapeutics, accompanied by high cost due to development costs, marketing costs, and development of drug resistance.
I shall identify continuing developments in cardiovascular diagnostics, therapeutics, and bioengineering that is and has been emerging.
Abstract:Genome-wide characterization of the in vivo cellular response to perturbation is fundamental to understanding how cells survive stress. Identifying the proteins and pathways perturbed by small molecules affects biology and medicine by revealing the mechanisms of drug action. We used a yeast chemogenomics platform that quantifies the requirement for each gene for resistance to a compound in vivo to profile 3250 small molecules in a systematic and unbiased manner. We identified 317 compounds that specifically perturb the function of 121 genes and characterized the mechanism of specific compounds. Global analysis revealed that the cellular response to small molecules is limited and described by a network of 45 major chemogenomic signatures. Our results provide a resource for the discovery of functional interactions among genes, chemicals, and biological processes.
In order to identify how chemical compounds target genes and affect the physiology of the cell, tests of the perturbations that occur when treated with a range of pharmacological chemicals are required. By examining the haploinsufficiency profiling (HIP) and homozygous profiling (HOP) chemogenomic platforms, Lee et al.(p. 208) analyzed the response of yeast to thousands of different small molecules, with genetic, proteomic, and bioinformatic analyses. Over 300 compounds were identified that targeted 121 genes within 45 cellular response signature networks. These networks were used to extrapolate the likely effects of related chemicals, their impact upon genetic pathways, and to identify putative gene functions
A team of cardiovascular researchers from the Cardiovascular Research Center at Icahn School of Medicine at Mount Sinai, Sanford-Burnham Medical Research Institute, and University of California, San Diego have identified a small, but powerful, new player in thIe onset and progression of heart failure. Their findings, published in the journal Nature on March 12, also show how they successfully blocked the newly discovered culprit.
Investigators identified a tiny piece of RNA called miR-25 that blocks a gene known as SERCA2a, which regulates the flow of calcium within heart muscle cells. Decreased SERCA2a activity is one of the main causes of poor contraction of the heart and enlargement of heart muscle cells leading to heart failure.
Using a functional screening system developed by researchers at Sanford-Burnham, the research team discovered miR-25 acts pathologically in patients suffering from heart failure, delaying proper calcium uptake in heart muscle cells. According to co-lead study authors Christine Wahlquist and Dr. Agustin Rojas Muñoz, developers of the approach and researchers in Mercola’s lab at Sanford-Burnham, they used high-throughput robotics to sift through the entire genome for microRNAs involved in heart muscle dysfunction.
Subsequently, the researchers at the Cardiovascular Research Center at Icahn School of Medicine at Mount Sinai found that injecting a small piece of RNA to inhibit the effects of miR-25 dramatically halted heart failure progression in mice. In addition, it also improved their cardiac function and survival.
“In this study, we have not only identified one of the key cellular processes leading to heart failure, but have also demonstrated the therapeutic potential of blocking this process,” says co-lead study author Dr. Dongtak Jeong, a post-doctoral fellow at the Cardiovascular Research Center at Icahn School of Medicine at Mount Sinai in the laboratory of the study’s co-senior author Dr. Roger J. Hajjar.
Publication: Inhibition of miR-25 improves cardiac contractility in the failing heart.Christine Wahlquist, Dongtak Jeong, Agustin Rojas-Muñoz, Changwon Kho, Ahyoung Lee, Shinichi Mitsuyama, Alain Van Mil, Woo Jin Park, Joost P. G. Sluijter, Pieter A. F. Doevendans, Roger J. : Hajjar & Mark Mercola. Nature (March 2014) http://www.nature.com/nature/journal/vaop/ncurrent/full/nature13073.html
“Junk” DNA Tied to Heart Failure
Deep RNA Sequencing Reveals Dynamic Regulation of Myocardial Noncoding RNAs in Failing Human Heart and Remodeling With Mechanical Circulatory Support
The myocardial transcriptome is dynamically regulated in advanced heart failure and after LVAD support. The expression profiles of lncRNAs, but not mRNAs or miRNAs, can discriminate failing hearts of different pathologies and are markedly altered in response to LVAD support. These results suggest an important role for lncRNAs in the pathogenesis of heart failure and in reverse remodeling observed with mechanical support.
Junk DNA was long thought to have no important role in heredity or disease because it doesn’t code for proteins. But emerging research in recent years has revealed that many of these sections of the genome produce noncoding RNA molecules that still have important functions in the body. They come in a variety of forms, some more widely studied than others. Of these, about 90% are called long noncoding RNAs (lncRNAs), and exploration of their roles in health and disease is just beginning.
The Washington University group performed a comprehensive analysis of all RNA molecules expressed in the human heart. The researchers studied nonfailing hearts and failing hearts before and after patients received pump support from left ventricular assist devices (LVAD). The LVADs increased each heart’s pumping capacity while patients waited for heart transplants.
In their study, the researchers found that unlike other RNA molecules, expression patterns of long noncoding RNAs could distinguish between two major types of heart failure and between failing hearts before and after they received LVAD support.
“The myocardial transcriptome is dynamically regulated in advanced heart failure and after LVAD support. The expression profiles of lncRNAs, but not mRNAs or miRNAs, can discriminate failing hearts of different pathologies and are markedly altered in response to LVAD support,” wrote the researchers. “These results suggest an important role for lncRNAs in the pathogenesis of heart failure and in reverse remodeling observed with mechanical support.”
‘Junk’ Genome Regions Linked to Heart Failure
In a recent issue of the journal Circulation, Washington University investigators report results from the first comprehensive analysis of all RNA molecules expressed in the human heart. The researchers studied nonfailing hearts and failing hearts before and after patients received pump support from left ventricular assist devices (LVAD). The LVADs increased each heart’s pumping capacity while patients waited for heart transplants.
“We took an unbiased approach to investigating which types of RNA might be linked to heart failure,” said senior author Jeanne Nerbonne, the Alumni Endowed Professor of Molecular Biology and Pharmacology. “We were surprised to find that long noncoding RNAs stood out.
In the new study, the investigators found that unlike other RNA molecules, expression patterns of long noncoding RNAs could distinguish between two major types of heart failure and between failing hearts before and after they received LVAD support.
“We don’t know whether these changes in long noncoding RNAs are a cause or an effect of heart failure,” Nerbonne said. “But it seems likely they play some role in coordinating the regulation of multiple genes involved in heart function.”
Nerbonne pointed out that all types of RNA molecules they examined could make the obvious distinction: telling the difference between failing and nonfailing hearts. But only expression of the long noncoding RNAs was measurably different between heart failure associated with a heart attack (ischemic) and heart failure without the obvious trigger of blocked arteries (nonischemic). Similarly, only long noncoding RNAs significantly changed expression patterns after implantation of left ventricular assist devices.
Heart failure is a complex disease with a broad spectrum of pathological features. Despite significant advancement in clinical diagnosis through improved imaging modalities and hemodynamic approaches, reliable molecular signatures for better differential diagnosis and better monitoring of heart failure progression remain elusive. The few known clinical biomarkers for heart failure, such as plasma brain natriuretic peptide and troponin, have been shown to have limited use in defining the cause or prognosis of the disease.1,2 Consequently, current clinical identification and classification of heart failure remain descriptive, mostly based on functional and morphological parameters. Therefore, defining the pathogenic mechanisms for hypertrophic versus dilated or ischemic versus nonischemic cardiomyopathies in the failing heart remain a major challenge to both basic science and clinic researchers. In recent years, mechanical circulatory support using left ventricular assist devices (LVADs) has assumed a growing role in the care of patients with end-stage heart failure.3 During the earlier years of LVAD application as a bridge to transplant, it became evident that some patients exhibit substantial recovery of ventricular function, structure, and electric properties.4 This led to the recognition that reverse remodeling is potentially an achievable therapeutic goal using LVADs. However, the underlying mechanism for the reverse remodeling in the LVAD-treated hearts is unclear, and its discovery would likely hold great promise to halt or even reverse the progression of heart failure.
Efficacy and Safety of Dabigatran Compared With Warfarin in Relation to Baseline Renal Function in Patients With Atrial Fibrillation: A RE-LY (Randomized Evaluation of Long-term Anticoagulation Therapy) Trial Analysis
In patients with atrial fibrillation, impaired renal function is associated with a higher risk of thromboembolic events and major bleeding. Oral anticoagulation with vitamin K antagonists reduces thromboembolic events but raises the risk of bleeding. The new oral anticoagulant dabigatran has 80% renal elimination, and its efficacy and safety might, therefore, be related to renal function. In this prespecified analysis from the Randomized Evaluation of Long-Term Anticoagulant Therapy (RELY) trial, outcomes with dabigatran versus warfarin were evaluated in relation to 4 estimates of renal function, that is, equations based on creatinine levels (Cockcroft-Gault, Modification of Diet in Renal Disease (MDRD), Chronic Kidney Disease Epidemiology Collaboration [CKD-EPI]) and cystatin C. The rates of stroke or systemic embolism were lower with dabigatran 150 mg and similar with 110 mg twice daily irrespective of renal function. Rates of major bleeding were lower with dabigatran 110 mg and similar with 150 mg twice daily across the entire range of renal function. However, when the CKD-EPI or MDRD equations were used, there was a significantly greater relative reduction in major bleeding with both doses of dabigatran than with warfarin in patients with estimated glomerular filtration rate ≥80 mL/min. These findings show that dabigatran can be used with the same efficacy and adequate safety in patients with a wide range of renal function and that a more accurate estimate of renal function might be useful for improved tailoring of anticoagulant treatment in patients with atrial fibrillation and an increased risk of stroke.
Aldosterone Regulates MicroRNAs in the Cortical Collecting Duct to Alter Sodium Transport.
ABSTRACT A role for microRNAs (miRs) in the physiologic regulation of sodium transport in the kidney has not been established. In this study, we investigated the potential of aldosterone to alter miR expression in mouse cortical collecting duct (mCCD) epithelial cells. Microarray studies demonstrated the regulation of miR expression by aldosterone in both cultured mCCD and isolated primary distal nephron principal cells.
Aldosterone regulation of the most significantly downregulated miRs, mmu-miR-335-3p, mmu-miR-290-5p, and mmu-miR-1983 was confirmed by quantitative RT-PCR. Reducing the expression of these miRs separately or in combination increased epithelial sodium channel (ENaC)-mediated sodium transport in mCCD cells, without mineralocorticoid supplementation. Artificially increasing the expression of these miRs by transfection with plasmid precursors or miR mimic constructs blunted aldosterone stimulation of ENaC transport.
Using a newly developed computational approach, termed ComiR, we predicted potential gene targets for the aldosterone-regulated miRs and confirmed ankyrin 3 (Ank3) as a novel aldosterone and miR-regulated protein.
A dual-luciferase assay demonstrated direct binding of the miRs with the Ank3-3′ untranslated region. Overexpression of Ank3 increased and depletion of Ank3 decreased ENaC-mediated sodium transport in mCCD cells. These findings implicate miRs as intermediaries in aldosterone signaling in principal cells of the distal kidney nephron.
2. Diagnostic Biomarker Status
A prospective study of the impact of serial troponin measurements on the diagnosis of myocardial infarction and hospital and 6-month mortality in patients admitted to ICU with non-cardiac diagnoses.
ABSTRACT Troponin T (cTnT) elevation is common in patients in the Intensive Care Unit (ICU) and associated with morbidity and mortality. Our aim was to determine the epidemiology of raised cTnT levels and contemporaneous electrocardiogram (ECG) changes suggesting myocardial infarction (MI) in ICU patients admitted for non-cardiac reasons.
cTnT and ECGs were recorded daily during week 1 and on alternate days during week 2 until discharge from ICU or death. ECGs were interpreted independently for the presence of ischaemic changes. Patients were classified into 4 groups: (i) definite MI (cTnT >=15 ng/L and contemporaneous changes of MI on ECG), (ii) possible MI (cTnT >=15 ng/L and contemporaneous ischaemic changes on ECG), (iii) troponin rise alone (cTnT >=15 ng/L), or (iv) normal. Medical notes were screened independently by two ICU clinicians for evidence that the clinical teams had considered a cardiac event.
Data from 144 patients were analysed [42% female; mean age 61.9 (SD 16.9)]. 121 patients (84%) had at least one cTnT level >=15 ng/L. A total of 20 patients (14%) had a definite MI, 27% had a possible MI, 43% had a cTNT rise without contemporaneous ECG changes, and 16% had no cTNT rise. ICU, hospital and 180 day mortality were significantly higher in patients with a definite or possible MI.Only 20% of definite MIs were recognised by the clinical team. There was no significant difference in mortality between recognised and non-recognised events.At time of cTNT rise, 100 patients (70%) were septic and 58% were on vasopressors. Patients who were septic when cTNT was elevated had an ICU mortality of 28% compared to 9% in patients without sepsis. ICU mortality of patients who were on vasopressors at time of cTNT elevation was 37% compared to 1.7% in patients not on vasopressors.
The majority of critically ill patients (84%) had a cTnT rise and 41% met criteria for a possible or definite MI of whom only 20% were recognised clinically. Mortality up to 180 days was higher in patients with a cTnT rise.
Prognostic performance of high-sensitivity cardiac troponin T kinetic changes adjusted for elevated admission values and the GRACE score in an unselected emergency department population.
ABSTRACT To test the prognostic performance of rising and falling kinetic changes of high-sensitivity cardiac troponin T (hs-cTnT) and the GRACE score.
Rising and falling hs-cTnT changes in an unselected emergency department population were compared.
635 patients with a hs-cTnT >99th percentile admission value were enrolled. Of these, 572 patients qualified for evaluation with rising patterns (n=254, 44.4%), falling patterns (n=224, 39.2%), or falling patterns following an initial rise (n=94, 16.4%). During 407days of follow-up, we observed 74 deaths, 17 recurrent AMI, and 79 subjects with a composite of death/AMI. Admission values >14ng/L were associated with a higher rate of adverse outcomes (OR, 95%CI:death:12.6, 1.8-92.1, p=0.01, death/AMI:6.7, 1.6-27.9, p=0.01). Neither rising nor falling changes increased the AUC of baseline values (AUC: rising 0.562 vs 0.561, p=ns, falling: 0.533 vs 0.575, p=ns). A GRACE score ≥140 points indicated a higher risk of death (OR, 95%CI: 3.14, 1.84-5.36), AMI (OR,95%CI: 1.56, 0.59-4.17), or death/AMI (OR, 95%CI: 2.49, 1.51-4.11). Hs-cTnT changes did not improve prognostic performance of a GRACE score ≥140 points (AUC, 95%CI: death: 0.635, 0.570-0.701 vs. 0.560, 0.470-0.649 p=ns, AMI: 0.555, 0.418-0.693 vs. 0.603, 0.424-0.782, p=ns, death/AMI: 0.610, 0.545-0.676 vs. 0.538, 0.454-0.622, p=ns). Coronary angiography was performed earlier in patients with rising than with falling kinetics (median, IQR [hours]:13.7, 5.5-28.0 vs. 20.8, 6.3-59.0, p=0.01).
Neither rising nor falling hs-cTnT changes improve prognostic performance of elevated hs-cTnT admission values or the GRACE score. However, rising values are more likely associated with the decision for earlier invasive strategy.
ABSTRACT: Under normal circumstances, most intracellular troponin is part of the muscle contractile apparatus, and only a small percentage (< 2-8%) is free in the cytoplasm. The presence of a cardiac-specific troponin in the circulation at levels above normal is good evidence of damage to cardiac muscle cells, such as myocardial infarction, myocarditis, trauma, unstable angina, cardiac surgery or other cardiac procedures. Troponins are released as complexes leading to various cut-off values depending on the assay used. This makes them very sensitive and specific indicators of cardiac injury. As with other cardiac markers, observation of a rise and fall in troponin levels in the appropriate time-frame increases the diagnostic specificity for acute myocardial infarction. They start to rise approximately 4-6 h after the onset of acute myocardial infarction and peak at approximately 24 h, as is the case with creatine kinase-MB. They remain elevated for 7-10 days giving a longer diagnostic window than creatine kinase. Although the diagnosis of various types of acute coronary syndrome remains a clinical-based diagnosis, the use of troponin levels contributes to their classification. This Editorial elaborates on the nature of troponin, its classification, clinical use and importance, as well as comparing it with other currently available cardiac markers.
ABSTRACT: Although redefinition for acute myocardial infarction (AMI) has been proposed few years ago, to date it has not been universally adopted by many institutions. The purpose of this study is to evaluate the diagnostic, prognostic and economical impact of the new diagnostic criteria for AMI. Patients consecutively admitted to the emergency department with suspected acute coronary syndromes were enrolled in this study. Troponin T (cTnT) was measured in samples collected for routine CK-MB analyses and results were not available to physicians. Patients without AMI by traditional criteria and cTnT > or = 0.035 ng/mL were coded as redefined AMI. Clinical outcomes were hospital death, major cardiac events and revascularization procedures. In-hospital management and reimbursement rates were also analyzed. Among 363 patients, 59 (16%) patients had AMI by conventional criteria, whereas additional 75 (21%) had redefined AMI, an increase of 127% in the incidence. Patients with redefined AMI were significantly older, more frequently male, with atypical chest pain and more risk factors. In multivariate analysis, redefined AMI was associated with 3.1 fold higher hospital death (95% CI: 0.6-14) and a 5.6 fold more cardiac events (95% CI: 2.1-15) compared to those without AMI. From hospital perspective, based on DRGs payment system, adoption of AMI redefinition would increase 12% the reimbursement rate [3552 Int dollars per 100 patients evaluated]. The redefined criteria result in a substantial increase in AMI cases, and allow identification of high-risk patients. Efforts should be made to reinforce the adoption of AMI redefinition, which may result in more qualified and efficient management of ACS.
Acellular biomaterials can stimulate the local environment to repair tissues without the regulatory and scientific challenges of cell-based therapies. A greater understanding of the mechanisms of such endogenous tissue repair is furthering the design and application of these biomaterials. We discuss recent progress in acellular materials for tissue repair, using cartilage and cardiac tissues as examples of application with substantial intrinsic hurdles, but where human translation is now occurring.
Acellular Biomaterials: An Evolving Alternative to Cell-Based Therapies
Acellular biomaterials can stimulate the local environment to repair tissues without the regulatory and scientific challenges of cell-based therapies. A greater understanding of the mechanisms of such endogenous tissue repair is furthering the design and application of these biomaterials. We discuss recent progress in acellular materials for tissue repair, using cartilage and cardiac tissues as examples of applications with substantial intrinsic hurdles, but where human translation is now occurring.
Instructive Nanofiber Scaffolds with VEGF Create a Microenvironment for Arteriogenesis and Cardiac Repair
Angiogenic therapy is a promising approach for tissue repair and regeneration. However, recent clinical trials with protein delivery or gene therapy to promote angiogenesis have failed to provide therapeutic effects. A key factor for achieving effective revascularization is the durability of the microvasculature and the formation of new arterial vessels. Accordingly, we carried out experiments to test whether intramyocardial injection of self-assembling peptide nanofibers (NFs) combined with vascular endothelial growth factor (VEGF) could create an intramyocardial microenvironment with prolonged VEGF release to improve post-infarct neovascularization in rats. Our data showed that when injected with NF, VEGF delivery was sustained within the myocardium for up to 14 days, and the side effects of systemic edema and proteinuria were significantly reduced to the same level as that of control. NF/VEGF injection significantly improved angiogenesis, arteriogenesis, and cardiac performance 28 days after myocardial infarction. NF/VEGF injection not only allowed controlled local delivery but also transformed the injected site into a favorable microenvironment that recruited endogenous myofibroblasts and helped achieve effective revascularization. The engineered vascular niche further attracted a new population of cardiomyocyte-like cells to home to the injected sites, suggesting cardiomyocyte regeneration. Follow-up studies in pigs also revealed healing benefits consistent with observations in rats. In summary, this study demonstrates a new strategy for cardiovascular repair with potential for future clinical translation.
Along with scientific and regulatory issues, the translation of cell and tissue therapies in the routine clinical practice needs to address standardization and cost-effectiveness through the definition of suitable manufacturing paradigms.
Heroes in Medical Research: Developing Models for Cancer Research
Author, Curator: Stephen J. Williams, Ph.D.
The current rapid progress in cancer research would have never come about if not for the dedication of past researchers who had developed many of the scientific tools we use today. In this issue of Heroes in Medical Research I would like to give tribute to the researchers who had developed the some of the in-vivo and in-vitro models which are critical for cancer research.
The Animal Modelers in Cancer Research
Helen Dean King, Ph.D. (1869-1955)
Helen Dean King, Ph.D. from www.ExplorePAhistory.com; photo Courtesy of the Wistar Institute Archive Collection, Philadelphia, PA
The work of Dr. Helen Dean King on rat inbreeding led to development of strains of laboratory animals. Dr. King taught at Bryn Mawr College, then worked at University of Pennsylvania and the Wistar Institute under famed geneticist Thomas Hunt Morgan, researching if inbreeding would produce harmful genetic traits. At University of Pennsylvania she examined environmental and genetic factors on gender determination.
Important papers include [1-6]as well as the following contributions:
“Studies in Inbreeding”, “Life Processes in Gray Norway Rats During Fourteen Years in Captivity”, doctoral thesis on embryologic development in toads (1899)
Milestones include:
1909 started albino rat breeding and bred 20 female and male from same litter (King colony) to 25
successive generations (inbreeding did not cause harmful traits)
1919 started to domesticate the wild Norwegian rats that ran thru Philadelphia (six pairs Norway rats
thru 28 generations)
A good reference for definitions of rat inbreeding versus line generation including a history of Dr. King’s work can be found at the site: Munificent Mischief Rattery and a brief history here.[7] In addition, Dr. King had investigated using rat strains as a possible recipient for tumor cells. The work was an important advent to the use of immunodeficient models for cancer research.
As shown below Philadelphia became a hotbed for research into embryology, development, genetics, and animal model development.
Beatrice Mintz, Ph.D.
(Beatrice Minz, Ph.D.; photo credit Fox Chase Cancer Center, www.pubweb.fccc.edu)
Dr. Mintz, an embryologist and cancer researcher from Fox Chase Cancer Center in Philadelphia, PA, contributed some of the most seminal discoveries leading to our current understanding of genetics, embryo development, cellular differentiation, and oncogenesis, especially melanoma, while pioneering techniques which allowed the development of genetically modified mice.
If you get the privilege of hearing her talk, take advantage of it. Dr. Mintz is one of those brilliant scientists who have the ability to look at a clinical problem from the viewpoint of a basic biological question and, at the same time, has the ability to approach the well-thought out questions with equally well thought out experimental design. For example, Dr. Mintz asked if a cell’s developmental fate was affected by location in the embryo. This led to her work by showing teratocarcinoma tumor cells in the developing embryo could revert to a more normal phenotype, essentially proving two important concepts in development and tumor biology:
The existence of pluripotent stem cells
That tumor cells are affected by their environment (which led to future concepts of the importance of tumor microenvironment on tumor growth
Other seminal discoveries included:
Development of the first mouse chimeras using novel cell fusion techniques
With Rudolf Jaenisch in 1974, showed integration of viral DNA from SV40, could be integrated into the DNA of developing mice and persist into adulthood somatic cells, the first transgenesis in mice which led ultimately to:
Development of the first genetically modified mouse model of human melanoma in 1993
Her current work, seen on the faculty webpage here, is developing mice with predisposition to melanoma to uncover risk factors associated with the early development of melanoma.
In keeping with the Philadelphia tradition another major mouse model which became seminal to cancer drug discovery was co-developed in the same city, same institute and described in the next section.
It is interesting to note that the first cloning of an animal, a frog, had taken place at the Institute for Cancer Research, later becoming Fox Chase Cancer Center, which was performed by Drs. Robert Briggs and Thomas J. King and reported in the 152 PNAS paper Transplantation of Living Nuclei From Blastula Cells into Enucleated Frogs’ Eggs.[8]
The Immunodeficient Animal as a Model System for Cancer Research – Dr. Mel Bosma, Ph.D.
In the summer of 1980 at Fox Chase Cancer Center, Dr. Melvin J. Bosma and his co-researcher wife Gayle discovered mice with deficiencies in common circulating antibodies and since, these mice were littermates, realized they had found a genetic defect which rendered the mice immunodeficient (upon further investigation these mice were unable to produce mature B and T cells). These mice were the first scid (severe combined immunodeficiency) colony. The scid phenotype was later found to be a result of a spontaneous mutation in the enzyme Prkdc {protein kinase, DNA activated, catalytic polypeptide} involved in DNA repair, and ultimately led to a defect in V(D)J recombination of immunoglobulins.
The emergence of this scid mouse was not only crucial for AIDS research but was another turning point in cancer research , as researchers now had a robust in-vivo recipient for human tumor cells. The orthotopic xenograft of human tumor cells now allowed for studies on genetic and microenvironmental factors affecting tumorigenicity, as well as providing a model for chemotherapeutic drug development (see Suggitt for review and references)[9]. A discussion of the pros and cons of the xenograft system for cancer drug discovery would be too voluminous for this post and would warrant a full review by itself. But before the advent of such scid mouse systems researchers relied on spontaneous and syngeneic mouse tumor models such as the B16 mouse melanoma and Lewis lung tumor model.
Two other in-vivo tumor models: Patient Derived Xenografts (PDX) and Genetically Engineered Mouse models (GEM) deserve their own separate discussion however the success of these new models can be attributed to the hard work of the aforementioned investigators. Therefore I will post separately and curate PDX and GEM models of cancer and highlight some new models which are having great impact on cancer drug development.
2. Lewis MR, Aptekman PM, King HD: Retarding action of adrenal gland on growth of sarcoma grafts in rats. J Immunol 1949, 61(4):315-319.
3. Aptekman PM, Lewis MR, King HD: Tumor-immunity induced in rats by subcutaneous injection of tumor extract. J Immunol 1949, 63(4):435-440.
4. Lewis MR, Aptekman PM, King HD: Inactivation of malignant tissue in tumor-immune rats. J Immunol 1949, 61(4):321-326.
5. Lewis MR, King HD, et al.: Further studies on oncolysis and tumor immunity in rats. J Immunol 1948, 60(4):517-528.
6. Aptekman PM, Lewis MR, King HD: A method of producing in inbred albino rats a high percentage of immunity from tumors native in their strain. J Immunol 1946, 52:77-86.
2012pharmaceutical
sjwilliamspa
