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.
Preface to Metabolomics as a Discipline in Medicine
Author: Larry H. Bernstein, MD, FCAP
The family of ‘omics fields has rapidly outpaced its siblings over the decade since
the completion of the Human Genome Project. It has derived much benefit from
the development of Proteomics, which has recently completed a first draft of the
human proteome. Since genomics, transcriptomics, and proteomics, have matured
considerably, it has become apparent that the search for a driver or drivers of cellular signaling and metabolic pathways could not depend on a full clarity of the genome. There have been unresolved issues, that are not solely comprehended from assumptions about mutations.
The most common diseases affecting mankind are derangements in metabolic
pathways, develop at specific ages periods, and often in adulthood or in the
geriatric period, and are at the intersection of signaling pathways. Moreover,
the organs involved and systemic features are heavily influenced by physical
activity, and by the air we breathe and the water we drink.
The emergence of the new science is also driven by a large body of work
on protein structure, mechanisms of enzyme action, the modulation of gene
expression, the pH dependent effects on protein binding and conformation.
Beyond what has just been said, a significant portion of DNA has been
designated as “dark matter”. It turns out to have enormous importance in
gene regulation, even though it is not transcriptional, effected in a
modulatory way by “noncoding RNAs. Metabolomics is the comprehensive
analysis of small molecule metabolites. These might be substrates of
sequenced enzyme reactions, or they might be “inhibiting” RNAs just
mentioned. In either case, they occur in the substructures of the cell
called organelles, the cytoplasm, and in the cytoskeleton.
The reactions are orchestrated, and they can be modified with respect to
the flow of metabolites based on pH, temperature, membrane structural
modifications, and modulators. Since most metabolites are generated by
enzymatic proteins that result from gene expression, and metabolites give
organisms their biochemical characteristics, the metabolome links
genotype with phenotype.
Metabolomics is still developing, and the continued development has
relied on two major events. The first is chromatographic separation and
mass spectroscopy (MS), MS/MS, as well as advances in fluorescence
ultrasensitive optical photonic methods, and the second, as crucial,
is the developments in computational biology. The continuation of
this trend brings expectations of an impact on pharmaceutical and
on neutraceutical developments, which will have an impact on medical
practice. What has lagged behind, and may continue to contribute to the
lag is the failure to develop a suitable electronic medical record to
assist the physician in decisions confronted with so much as yet,
hidden data, the ready availability of which could guide more effective
diagnosis and management of the patient. Put all of this together, and
we can meet series challenges as the research community
interprets and integrates the complex data they are acquiring.
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:
CRACKING THE CODE OF HUMAN LIFE: The Birth of BioInformatics & Computational Genomics
Author and Curator: Larry H Bernstein, MD, FCAP
The previous Part II: Cracking the Code of Human Life,
Part II From Molecular Biology to Translational Medicine:How Far Have We Come, and Where Does It Lead Us? Is broken into a three part series.
Part II A. “CRACKING THE CODE OF HUMAN LIFE: Milestones along the Way” reviews the Human Genome Project and the decade beyond.
Part IIB. “CRACKING THE CODE OF HUMAN LIFE: The Birth of BioInformatics & Computational Genomics” lays the manifold multivariate systems analytical tools that has moved the science forward to a groung that ensures clinical application.
Part IIC. “CRACKING THE CODE OF HUMAN LIFE: Recent Advances in Genomic Analysis and Disease “ extends the discussion to advances in the management of patients as well as providing a roadmap for pharmaceutical drug targeting.
Part III concludes with Ubiquitin, it’s role in Signaling and Regulatory Control.
This article is a continuation of a previous discussion on the role of genomics in discovery of therapeutic targets titled, Directions for Genomics in Personalized Medicine, which focused on: key drivers of cellular proliferation, stepwise mutational changes coinciding with cancer progression, and potential therapeutic targets for reversal of the process. And it is a direct extension of Cracking the Code of Human Life (Part I): “the initiation phase of molecular biology”.
These articles review a web-like connectivity between inter-connected scientific discoveries, as significant findings have led to novel hypotheses and many expectations over the last 75 years. This largely post WWII revolution has driven our understanding of biological and medical processes at an exponential pace owing to successive discoveries of chemical structure,
the basic building blocks of DNA and proteins,
of nucleotide and protein-protein interactions,
protein folding, allostericity,
genomic structure,
DNA replication,
nuclear polyribosome interaction, and
metabolic control.
In addition, the emergence of methods
for copying,
removal and
insertion, and
improvements in structural analysis as well as
developments in applied mathematics have transformed the research framework.
CRACKING THE CODE OF HUMAN LIFE: The Birth of BioInformatics & Computational Genomics Computational Genomics I. Three-Dimensional Folding and Functional Organization Principles of The Drosophila Genome Sexton T, Yaffe E, Kenigeberg E, Bantignies F,…Cavalli G. Institute de Genetique Humaine, Montpelliere GenomiX, and Weissman Institute, France and Israel. Cell 2012; 148(3): 458-472. http://dx.doi.org/10.1016/j.cell.2012.01.010/
Chromosomes are the physical realization of genetic information and thus
form the basis for its readout and propagation.
Here we present a high-resolution chromosomal contact map derived from
a modified genome-wide chromosome conformation capture approach
applied to Drosophila embryonic nuclei.
the entire genome is linearly partitioned into
well-demarcated physical domains that
overlap extensively with
active and repressive epigenetic marks.
Chromosomal contacts are hierarchically organized between domains.
Global modeling of contact density and clustering of domains show
that inactive domains are condensed and
confined to their chromosomal territories, whereas
active domains reach out of the territory to form
remote intra- and interchromosomal contacts.
Moreover, we systematically identify specific
long-range intrachromosomal contacts between
Polycomb-repressed domains.
Together, these observations allow for
quantitative prediction of the Drosophila chromosomal contact map,
laying the foundation for detailed studies of
chromosome structure and function in
a genetically tractable system.
Insert pictures
profiles validate the Hi-C Genome wide map
IIC. “Mr. President; The Genome is Fractal !” Eric Lander
(Science Adviser to the President and Director of Broad Institute) et al.
delivered the message on Science Magazine cover (Oct. 9, 2009) and
generated interest in this by the International HoloGenomics Society at
a Sept meeting.
First, it may seem to be trivial to rectify the statement in “About cover”
of Science Magazine by AAAS. The statement “the Hilbert curve is a
one-dimensional fractal trajectory” needs mathematical clarification.
While the paper itself does not make this statement, the new Editorship
of the AAAS Magazine might be even more advanced if the previous
Editorship did not reject (without review) a Manuscript by 20+ Founders
of (formerly) International PostGenetics Society in December, 2006.
Second, it may not be sufficiently clear for the reader that the
reasonable requirement for the DNA polymerase to crawl along
a “knot-free” (or “low knot”) structure does not need fractals. A
“knot-free” structure could be spooled by an ordinary “knitting globule”
(such that the DNA polymerase does not bump into a “knot” when
duplicating the strand; just like someone knitting can go through
the entire thread without encountering an annoying knot): Just to
be “knot-free” you don’t need fractals.
Note, however, that the “strand” can be accessed only at its beginning –
it is impossible to e.g.
to pluck a segment from deep inside the “globulus”.
This is where certain fractals provide a major advantage – that could be
the “Eureka” moment for many readers.
For instance, the mentioned Hilbert-curve is not only “knot free” – but
provides an easy access to “linearly remote” segments of the strand.
If the Hilbert curve starts from the lower right corner and ends at the lower left corner,
for instance the path shows the very easy access of what would be the mid-point
if the Hilbert-curve is measured by
the Euclidean distance along the zig-zagged path.
Likewise, even the path from the beginning of the Hilbert-curve is about equally easy to access –
easier than to reach from the origin a point that is about 2/3 down the path.
The Hilbert-curve provides an easy access between two points
within the “spooled thread”;
from a point that is about 1/5 of the overall length
to about 3/5 is also in a “close neighborhood”.
This may be the “Eureka-moment” for some readers, to realize that
the strand of “the Double Helix” requires quite a finess to fold into
the densest possible globuli (the chromosomes) in a clever way
that various segments can be easily accessed.
Moreover, in a way that distances
between various segments are minimized.
This marvelous fractal structure
is illustrated by the 3D rendering of the Hilbert-curve.
Once you observe such fractal structure, you’ll never again think of
a chromosome as a “brillo mess”, would you?
It will dawn on you that the genome is orders of magnitudes more
finessed than we ever thought so.
Insert picture
profiles validate the Hi-C Genome wide map
Those embarking at a somewhat complex review of some
historical aspects of the power of fractals may wish to consult
the ouvre of Mandelbrot (also, to celebrate his 85th birthday).
For the more sophisticated readers, even the fairly simple
Hilbert-curve (a representative of the Peano-class) becomes
even more stunningly brilliant than just some “see through density”.
Those who are familiar with the classic “Traveling Salesman Problem”
know that “the shortest path along which every given n locations can
be visited once, and only once” requires fairly sophisticated algorithms
(and tremendous amount of computation if n>10 (or much more).
Some readers will be amazed, therefore, that for n=9 the underlying Hilbert-curve
Briefly, the significance of the above realization, that the (recursive)
Fractal Hilbert Curve is intimately connected to the
(recursive) solution of TravelingSalesman Problem,
a core-concept of Artificial Neural Networks summarized below.
Accomplished physicist John Hopfield aroused great excitement in 1982
(already a member of the National Academy of Science)
with his (recursive) design of artificial neural networks and learning algorithms
which were able to find reasonable solutions to combinatorial problems
such as the Traveling SalesmanProblem.
(Book review Clark Jeffries, 1991; 1. J. Anderson, R. Rosenfeld, and
A. Pellionisz (eds.), Neurocomputing 2: Directions for research, MIT
Press, Cambridge, MA, 1990):
“Perceptions were modeled chiefly with neural connections in a
“forward” direction: A -> B -* C — D.
The analysis of networks with strong
backward coupling proved intractable.
All our interesting results arise as consequences of the strong
back-coupling” (Hopfield, 1982).
The Principle of Recursive Genome Function surpassed obsolete
axioms that blocked, for half a Century,
entry of recursive algorithms to interpretation
of the structure-and function of (Holo)Genome.
This breakthrough, by uniting the two largely separate fields of
Neural Networks and Genome Informatics,
is particularly important for those who focused on
Biological (actually occurring) Neural Networks
(rather than abstract algorithms that may not, or
because of their core-axioms, simply could not
represent neural networks under the governance of DNA information).
IIIA. The FractoGene Decade from Inception in 2002 to Proofs of Concept and Impending Clinical Applications by 2012
Junk DNA Revisited (SF Gate, 2002)
The Future of Life, 50th Anniversary of DNA (Monterey, 2003)
Mandelbrot and Pellionisz (Stanford, 2004)
Morphogenesis, Physiology and Biophysics (Simons, Pellionisz 2005)
PostGenetics; Genetics beyond Genes (Budapest, 2006)
ENCODE-conclusion (Collins, 2007)
The Principle of Recursive Genome Function (paper, YouTube, 2008)
You Tube Cold Spring Harbor presentation of FractoGene (Cold Spring Harbor, 2009)
Mr. President, the Genome is Fractal! (2009)
HolGenTech, Inc. Founded (2010)
Pellionisz on the Board of Advisers in the USA and India (2011)
ENCODE – final admission (2012)
Recursive Genome Function is Clogged by Fractal Defects in Hilbert-Curve (2012)
Geometric Unification of Neuroscience and Genomics (2012)
US Patent Office issues FractoGene 8,280,641 to Pellionisz (2012)
When the human genome was first sequenced in June 2000, there were two pretty big surprises.
The first was that humans have only about 30,000-40,000 identifiable genes,
not the 100,000 or more many researchers were expecting.
The lower –and more humbling — number
means humans have just one-third
more genes than a common species of worm.
The second stunner was how much human genetic material — more than 90 percent —
is made up of what scientists were calling “junk DNA.”
The term was coined to describe similar but
not completely identical repetitive sequences of amino acids
(the same substances that make genes),
which appeared to have no function or purpose.
The main theory at the time was that these apparently
non-working sections of DNA were
just evolutionary leftovers, much like our earlobes.
If biophysicist Andras Pellionisz is correct, genetic science
may be on the verge of yielding its third — and
by far biggest — surprise.
With a doctorate in physics, Pellionisz is the holder of Ph.D.’s
in computer sciences and experimental biology from the
prestigious Budapest Technical University and
the Hungarian National Academy of Sciences.
A biophysicist by training, the 59-year-old is a former research
associate professor of physiology and biophysics at New York University,
author of numerous papers in respected scientific journals and textbooks,
a past winner of the prestigious Humboldt Prize for scientific research,
a former consultant to NASA and
holder of a patent on the world’s first artificial cerebellum,
a technology that has already been integrated into research
on advanced avionics systems.
Because of his background, the Hungarian-born brain researcher might
also become one of the first people to successfully launch a new company
by using the Internet to gather momentum for a novel scientific idea.
The genes we know about today, Pellionisz says, can be thought of as something
similar to machines that make bricks (proteins, in the case of genes), with certain
junk-DNA sections providing a blueprint for the
different ways those proteins are assembled.
The notion that at least certain parts of junk DNA might have a purpose for example,
many researchers now refer to
with a far less derogatory term: introns.
Insert picture
3-d-genome-map
In a provisional patent application filed July 31, Pellionisz claims to have
unlocked a key to the hidden role junk DNA plays in growth — and in life itself.
His patent application covers all attempts to
count,
measure and
compare
the fractal properties of introns
for diagnostic and therapeutic purposes.
IIIB. The Hidden Fractal Language of Intron DNA
To fully understand Pellionisz’ idea,
one must first know what a fractal is.
Fractals are a way that nature organizes matter.
Fractal patterns can be found
in anything that has a nonsmooth surface (unlike a billiard ball),
such as coastal seashores,
the branches of a tree or
the contours of a neuron (a nerve cell in the brain).
Some, but not all, fractals are self-similar and
stop repeating their patterns at some stage
the branches of a tree, for example,
can get only so small.
Because they are geometric, meaning they have a shape,
fractals can be described in mathematical terms.
It’s similar to the way a circle can be described
by using a number to represent its radius
(the distance from its center to its outer edge).
When that number is known, it’s possible to draw the circle it represents
without ever having seen it before.
Although the math is much more complicated,
the same is true of fractals.
If one has the formula for a given fractal,
it’s possible to use that formula to construct, or reconstruct,
an image of whatever structure it represents,
no matter how complicated.
The mysteriously repetitive but not identical strands of genetic material
are in reality building instructions organized in
a special type of pattern known as a fractal.
It’s this pattern of fractal instructions, he says, that tells genes what they
must do in order to form living tissue,
everything from the wings of a fly to the entire body of a full-grown human.
In a move sure to alienate some scientists,
Pellionisz has chosen the unorthodox route of
making his initial disclosures online on his own Web site.
He picked that strategy, he says, because
it is the fastest way he can document his claims
and find scientific collaborators and investors.
Most mainstream scientists usually blanch at such approaches,
preferring more traditionally credible methods, such as
publishing articles in peer-reviewed journals.
Basically, Pellionisz’ idea is that
a fractal set of building instructions in the DNA
plays a similar role in organizing life itself.
Decode the way that language works, he says, and
in theory it could be reverse engineered.
Just as knowing the radius of a circle lets one create that circle,
the more complicated fractal-based formula
would allow us to understand how nature creates a heart or
simpler structures, such as disease-fighting antibodies.
At a minimum, we’d get a far better understanding of
how nature gets that job done.
The complicated quality of the idea is helping encourage
new collaborations across the boundaries that sometimes
separate the increasingly intertwined disciplines of
biology, mathematics and computer sciences.
Hal Plotkin, Special to SF Gate. Thursday, November 21, 2002.
An effective strategy to elucidate the signal transduction cascades
activated by a transcription factor is to compare the transcriptional profiles
of wild type and transcription factor knockout models.
Many statistical tests have been proposed for analyzing gene expression data,
but most tests are based on pair-wise comparisons.
Since the analysis of micro-arrays involves the testing of
multiple hypotheses within one study, it is generally accepted that one should
control for false positives by the false discovery rate (FDR).
However, it has been reported that
this may be an inappropriate metric for
comparing data across different experiments.
Here we propose an approach that addresses the above mentioned problem
by the simultaneous testing and integration of the three hypotheses (contrasts)
using the cell means ANOVA model.
These three contrasts test for the effect of a treatment in
wild type,
gene knockout, and
globally over all experimental groups.
We illustrate our approach on microarray experiments that focused
on the identification of candidate target genes and biological processes
governed by the fatty acid sensing transcription factor PPARα in liver.
Compared to the often applied FDR based across experiment comparison,
our approach identified a conservative
but less noisy set of candidate genes
with same sensitivity and specificity.
However, our method had the advantage of properly adjusting for
multiple testing while integrating data from two experiments,
and was driven by biological inference.
We present a simple, yet efficient strategy to compare
differential expression of genes across experiments
while controlling for multiple hypothesis testing.
B. Managing biological complexity across orthologs with a visual knowledge-base
of documented biomolecular interactions Vincent VanBuren & Hailin Chen
Scientific Reports 2, Article number: 1011 http://dx.doi.org:/10.1038/srep01011
Received 02 October 2012 Accepted 04 December 2012
The complexity of biomolecular interactions and influences
is a major obstacle to their comprehension and elucidation.
Visualizing knowledge of biomolecular interactions
increases comprehension and
facilitates the development of new hypotheses.
The rapidly changing landscape of high-content experimental results
also presents a challenge for the maintenance of comprehensive knowledgebases.
Distributing the responsibility for maintenance of a knowledgebase
to a community of subject matter experts is an effective strategy
for large, complex and rapidly changing knowledgebases.
Cognoscente serves these needs by building visualizations for queries
of biomolecular interactions on demand,
by managing the complexity of those visualizations, and by
crowdsourcing to promote the incorporation of current knowledge
from the literature.
Imputing functional associations between
biomolecules and imputing directionality of regulation for those predictions
each require a corpus of existing knowledge as a framework to build upon.
Comprehension of the complexity of this corpus of knowledge
will be facilitated by effective visualizations of
the corresponding biomolecular interaction networks.
was designed and implemented to serve these roles as a knowledgebase
and as an effective visualization tool for systems biology research and education.
Cognoscente currently contains over 413,000 documented interactions,
with coverage across multiple species.
Perl, HTML, GraphViz1, and a MySQL database were used in the development of Cognoscente.
Cognoscente was motivated by the need to update the knowledgebase
of biomolecular interactions at the user level, and
flexibly visualize multi-molecule query results for
heterogeneous interaction types across different orthologs.
Satisfying these needs provides a strong foundation for
developing new hypotheses about regulatory and metabolic pathway topologies.
Several existing tools provide functions that are similar to Cognoscente, so we selected several popular alternatives to assess how their feature sets compare with Cognoscente ( Table 1 ). All databases assessed had easily traceable documentation for each interaction, and included protein-protein interactions in the database.
Most databases, with the exception of BIND, provide an open-access database that can be downloaded as a whole.
Most databases, with the exceptions of EcoCyc and HPRD, provide
support for multiple organisms.
Most databases support web services for
interacting with the database contents programmatically,
whereas this is a planned feature for Cognoscente.
INT, STRING, IntAct, EcoCyc, DIP and Cognoscente provide built-in
visualizations of query results, which we consider
among the most important features for facilitating comprehension of query results.
BIND supports visualizations via Cytoscape.
Cognoscente is among a few other tools that support
multiple organisms in the same query,
protein->DNA interactions, and
multi-molecule queries.
Cognoscente has planned support for
small molecule interactants (i.e. pharmacological agents).
MINT, STRING, and IntAct provide a prediction (i.e. score)
of functional associations, whereas
Cognoscente does not currently support this.
Cognoscente provides support for multiple edge encodings
to visualize different types of interactions in the same display,
a crowdsourcing web portal that allows users to submit
interactions that are then automatically incorporated in the knowledgebase,
and displays orthologs as compound nodes
to provide clues about potential orthologous interactions.
The main strengths of Cognoscente are that it provides a combined feature set that is superior to any existing database, it provides a unique visualization feature for orthologous molecules, and relatively unique support for multiple edge encodings, crowdsourcing, and connectivity parameterization. The current weaknesses of Cognoscente relative to these other tools are that it does not fully support web service interactions with the database, it does not fully support small molecule interactants, and it does not score interactions to predict functional associations. Web services and support for small molecule interactants are currently under development.
Related references from Leaders in Pharmaceutical Intelligence:
Larry, in a series of papers, Fertil, Deschavannes and colleagues have done beautiful analyses of fractal diagrams of Genome sequences in a series of papers.[Deschavanne PJ, Giron A, Vilain J, Fagot G, Fertil B (1999) Mol Biol Evol 16: 1391-1399; Fertil B, Massin M, Lespinats S, Devic C, Dumee P, Giron A (2005) GENSTYLE: exploration and analysis of DNA sequences with genomic signature. Nucleic Acids Res 33(Web Server issue):W512-5]. Clearly this gives an extraordinary insight in the specificity of positional sequence clusters. While fractals work well with octanucleotide clusters, longer the oligonucleotide tracks, higher the resolution. I feel that high resolution fractal maps of fentanucleotide sequences will provide something truely different and may be used as a tool to compare normal cellular DNA sequences to those from cancer cell lines and provide an operational window for manipulations.
Reporter and Curator: Larry H. Bernstein, MD, FCAP
This is the FIRST discussion of a several part series leading from the genome, to protein synthesis (1), posttranslational modification of proteins (2), examples of protein effects on metabolism and signaling pathways (3), and leading to disruption of signaling pathways in disease (4), and effects leading to mutagenesis.
DNA carries the information for making all of the cell’s proteins. These proteins implement all of the functions of a living organism and determine the organism’s characteristics. When the cell reproduces, it has to pass all of this information on to the daughter cells.
Before a cell can reproduce, it must first replicate, or make a copy of, its DNA. Where DNA replication occurs depends upon whether the cells is a prokaryote or a eukaryote (see the RNA sidebar on the previous page for more about the types of cells). DNA replication occurs in the cytoplasm of prokaryotes and in the nucleus of eukaryotes. Regardless of where DNA replication occurs, the basic process is the same.
The structure of DNA lends itself easily to DNA replication. Each side of the double helix runs in opposite (anti-parallel) directions. The beauty of this structure is that it can unzip down the middle and each side can serve as a pattern or template for the other side (called semi-conservative replication). However, DNA does not unzip entirely. It unzips in a small area called a replication fork, which then moves down the entire length of the molecule.
Eukaryotic DNA replication (Wikipedia), is a conserved mechanism that restricts DNA replication to only once per cell cycle. Eukaryotic DNA replication of chromosomalDNA is central for the duplication of a cell and is necessary for the maintenance of the eukaryotic genome.
DNA replication is the action of DNA polymerases synthesizing a DNA strand complementary to the original template strand. To synthesize DNA, the double-stranded DNA is unwound by DNA helicases ahead of polymerases, forming a replication fork containing two single-stranded templates.
Replication processes permit the copying of a single DNA double helix into two DNA helices, which are divided into the daughter cells at mitosis. The major enzymatic functions carried out at the replication fork are well conserved from prokaryotes to eukaryotes, but the replication machinery in eukaryotic DNA replication is a much larger complex, coordinating many proteins at the site of replication, forming the replisome.[1]
The replisome is responsible for copying the entirety of genomic DNA in each proliferative cell. This process allows for the high-fidelity passage of hereditary/genetic information from parental cell to daughter cell and is thus essential to all organisms. Much of the cell cycle is built around ensuring that DNA replication occurs without errors.[1]
In G1 phase of the cell cycle, many of the DNA replication regulatory processes are initiated. In eukaryotes, the vast majority of DNA synthesis occurs during S phase of the cell cycle, and the entire genome must be unwound and duplicated to form two daughter copies. During G2, any damaged DNA or replication errors are corrected. Finally, one copy of the genomes is segregated to each daughter cell at mitosis or M phase.[2] These daughter copies each contain one strand from the parental duplex DNA and one nascent antiparallel strand.
This mechanism is conserved from prokaryotes to eukaryotes and is known as semiconservative DNA replication. The process of semiconservative replication for the site of DNA replication is a fork-like DNA structure, the replication fork, where the DNA helix is open, or unwound, exposing unpaired DNA nucleotides for recognition and base pairing for the incorporation of free nucleotides into double-stranded DNA.[3]
Let’s look at the details:
An enzyme called DNA gyrase makes a nick in the double helix and each side separates
An enzyme called helicase unwinds the double-stranded DNA
Several small proteins called single strand binding proteins(SSB) temporarily bind to each side and keep them separated
An enzyme complex called DNA polymerase“walks” down the DNA strands and adds new nucleotides to each strand. The nucleotides pair with the complementary nucleotides on the existing stand (A with T, G with C).
A subunit of the DNA polymerase proofreads the new DNA
An enzyme called DNA ligaseseals up the fragments into one long continuous strand
The new copies automatically wind up again
Different types of cells replicated their DNA at different rates. Some cells constantly divide, like those in your hair and fingernails and bone marrow cells. Other cells go through several rounds of cell division and stop (including specialized cells, like those in your brain, muscle and heart). Finally, some cells stop dividing, but can be induced to divide to repair injury (such as skin cells and liver cells). In cells that do not constantly divide, the cues for DNA replication/cell division come in the form of chemicals. These chemicals can come from other parts of the body (hormones) or from the environment.
Pre-replicative_complex
Diagram of the formation of the pre-replicative complex transforming into an active replisome. Mcm 2-7 complex loads onto DNA at replication origins during G1 and unwinds DNA ahead of replicative polymerases.Cdc6 and Cdt1 bring Mcm complexes to replication origins. CDK/DDK-dependent phosphorylation of pre-replicative proteins leads toreplisome assembly and origin firing. Cdc6 and Cdt1 are no longer required and are removed from the nucleus or degraded. Mcms and associated proteins, GINS and Cdc45, unwind DNA to expose template DNA. At this point replisome assembly is completed and replication is initiated. “P” represents phosphorylation.
The assembly of the minichromosome maintenance (Mcm) proteins function together as a complex in the cell. The assembly of the Mcm proteins onto chromatin requires the coordinated function of the Origin Recognition Complex (ORC), Cdc6, and Cdt1.[18] Once the Mcm proteins have been loaded onto the chromatin, ORC and Cdc6 can be removed from the chromatin without preventing subsequent DNA replication. This suggests that the primary role of the pre-replication complex is to correctly load the Mcm proteins.[19]
The Mcm proteins support roles both in the initiation and elongation steps of DNA synthesis.[20] Each Mcm protein is highly related to all others, but unique sequences distinguishing each of the subunit types are conserved across eukaryotes. All eukaryotes have exactly six Mcm protein analogs that each fall into one of the existing classes (Mcm2-7), which suggests that each Mcm protein has a unique and important function.[21]
Minichromosome maintenance proteins have been found to be required for DNA helicase activity and inactivation of any of the six Mcm proteins prevents further progression of the replication fork. This is consistent with the requirement of ORC, Cdc6, and Cdt1 function to assemble the Mcm proteins at the origin of replication.[22] The complex containing all six Mcm proteins creates a hexameric, doughnut like structure with a central cavity.[23] The helicase activity of the Mcm protein complex raises the question of how the ring-like complex is loaded onto the single-stranded DNA. One possibility is that the helicase activity of the Mcm protein complex can oscillate between an open and a closed ring formation to allow single-stranded DNA loading.[6]
Along with the minichromosome maintenance protein complex helicase activity, the complex also has associated ATPase activity.[24] A mutation in any one of the six Mcm proteins reduces the conserved ATP binding sites, which indicates that ATP hydrolysis is a coordinated event involving all six subunits of the Mcm complex.[25] Studies have shown that within the Mcm protein complex are specific catalytic pairs of Mcm proteins that function together to coordinate ATP hydrolysis. For example, Mcm3 but not Mcm6 can activate Mcm6 activity. These studies suggest that the structure for the Mcm complex is a hexamer with Mcm3 next to Mcm7, Mcm2 next to Mcm6, and Mcm4 next to Mcm5. Both members of the catalytic pair contribute to the conformation that allows ATP binding and hydrolysis and the mixture of active and inactive subunits create a coordinated ATPase activity that allows the Mcm protein complex to complete ATP binding and hydrolysis as a whole.[26]
The nuclear localization of the minichromosome maintenance proteins is regulated in budding yeast cells. The Mcm proteins are present in the nucleus in G1 stage and S phase of the cell cycle, but are exported to the cytoplasm during the G2 stage and M phase. A complete and intact six subunit Mcm complex is required to enter into the cell nucleus.[27] InS. cerevisiae, nuclear export is promoted by cyclin-dependent kinase (CDK) activity. Mcm proteins that are associated with chromatin are protected from CDK export machinery due to the lack of accessibility to CDK.[28]
During the G1 stage of the cell cycle, the replication initiation factors, origin recognition complex (ORC), Cdc6, Cdt1, and minichromosome maintenance (Mcm) protein complex, bind sequentially to DNA to form the pre-replication complex (pre-RC). At the transition of the G1 stage to the S phase of the cell cycle, S phase–specific cyclin-dependent protein kinase (CDK) and Cdc7/Dbf4 kinase (DDK) transform the pre-RC into an active replication fork. During this transformation, the pre-RC is disassembled with the loss of Cdc6, creating the initiation complex. In addition to the binding of the Mcm proteins, cell division cycle 45 (Cdc45) protein is also essential for initiating DNA replication.[29][30] Studies have shown that Mcm is critical for the loading of Cdc45 onto chromatin and this complex containing both Mcm and Cdc45 is formed at the onset of the S phase of the cell cycle.[31][32] Cdc45 targets the Mcm protein complex, which has been loaded onto the chromatin, as a component of the pre-RC at the origin of replication during the G1 stage of the cell cycle.[20]
The six minichromosome maintenance proteins and Cdc45 are essential during initiation and elongation for the movement of replication forks and for unwinding of the DNA. GINS are essential for the interaction of Mcm and Cdc45 at the origins of replication during initiation and then at DNA replication forks as the replisome progresses.[37][38] The GINS complex is composed of four small proteins Sld5 (Cdc105), Psf1 (Cdc101), Psf2 (Cdc102) and Psf3 (Cdc103), GINS represents ‘go, ichi, ni, san’ which means ‘5, 1, 2, 3’ in Japanese.[39]
Mcm10 is essential for chromosome replication and interacts with the minichromosome maintenance 2-7 helicase that is loaded in an inactive form at origins of DNA replication. Mcm10 chaperones the catalytic DNA polymerase α and helps stabilize the polymerase.[40]
At the onset of S phase, the pre-replicative complex must be activated by two S phase-specific kinases in order to form an initiation complex at an origin of replication. One kinase is the Cdc7-Dbf4 kinase called Dbf4-dependent kinase (DDK) and the other is cyclin-dependent kinase (CDK).[41] Chromatin-binding assays of Cdc45 in yeast and Xenopus have shown that a downstream event of CDK action is loading of Cdc45 onto chromatin.[30][31]Cdc6 has been speculated to be a target of CDK action, because of the association between Cdc6 and CDK, and the CDK-dependent phosphorylation of Cdc6. The CDK-dependent phosphorylation of Cdc6 has been considered to be required for entry into the S phase.[42]
Eukaryotic replisome complex and associated proteins.
The formation of the pre-replicative complex (pre-RC) marks the potential sites for the initiation of DNA replication. Consistent with the minichromosome maintenance complex encircling double stranded DNA, formation of the pre-RC does not lead to the immediate unwinding of origin DNA or the recruitment of DNA polymerases. Instead, the pre-RC that is formed during the G1 of the cell cycle is only activated to unwind the DNA and initiate replication after the cells pass from the G1 to the S phase of the cell cycle.[2]
Once the initiation complex is formed and the cells pass into the S phase, the complex then becomes a replisome. The eukaryotic replisome complex is responsible for coordinating DNA replication. Replication on the leading and lagging strands is performed by DNA polymerase ε and DNA polymerase δ. Many replisome factors including Claspin, And1, replication factor C clamp loader and the fork protection complex are responsible for regulating polymerase functions and coordinating DNA synthesis with the unwinding of the template strand by Cdc45-Mcm-GINS complex. As the DNA is unwound the twist number decreases. To compensate for this the writhe number increases, introducing positive supercoils in the DNA. These supercoils would cause DNA replication to halt if they were not removed. Topoisomerases are responsible for removing these supercoils ahead of the replication fork.
The replication fork is the junction the between the newly separated template strands, known as the leading and lagging strands, and the double stranded DNA. Since duplex DNA is antiparallel, DNA replication occurs in opposite directions between the two new strands at the replication fork, but all DNA polymerases synthesize DNA in the 5′ to 3′ direction with respect to the newly synthesized strand. Further coordination is required during DNA replication. Two replicative polymerases synthesize DNA in opposite orientations. Polymerase ε synthesizes DNA on the “leading” DNA strand continuously as it is pointing in the same direction as DNA unwinding by the replisome. In contrast, polymerase δ synthesizes DNA on the “lagging” strand, which is the opposite DNA template strand, in a fragmented or discontinuous manner.
The discontinuous stretches of DNA replication products on the lagging strand are known as Okazaki fragments and are about 100 to 200 bases in length at eukaryotic replication forks. The lagging strand usually contains longer stretches of single-stranded DNA that is coated with single-stranded binding proteins, which help stabilize the single-stranded templates by preventing a secondary structure formation. In eukaryotes, these single-stranded binding proteins are a heterotrimeric complex known as replication protein A(RPA).[56]
Each Okazaki fragment is preceded by an RNA primer, which is displaced by the procession of the next Okazaki fragment during synthesis. RNAse H recognizes the DNA:RNA hybrids that are created by the use of RNA primers and is responsible for removing these from the replicated strand, leaving behind a primer:template junction. DNA polymerase α, recognizes these sites and elongates the breaks left by primer removal. In eukaryotic cells,
Depiction of DNA replication at replication fork. a: template strands, b: leading strand, c: lagging strand, d: replication fork, e: RNA primer, f: Okazaki fragment
Leading Strand
Lagging Strand
Replicative DNA Polymerases
After the replicative helicase has unwound the parental DNA duplex, exposing two single-stranded DNA templates, replicative polymerases are needed to generate two copies of the parental genome. DNA polymerase function is highly specialized and accomplish replication on specific templates and in narrow localizations. At the eukaryotic replication fork, there are three distinct replicative polymerase complexes that contribute to DNA replication: Polymerase α, Polymerase δ, and Polymerase ε. These three polymerases are essential for viability of the cell.[66]
Because DNA polymerases require a primer on which to begin DNA synthesis, polymerase α (Pol α) acts as a replicative primase. Pol α is associated with an RNA primase and this complex accomplishes the priming task by synthesizing a primer that contains a short 10 nucleotide stretch of RNA followed by 10 to 20 DNA bases.[3] Importantly, this priming action occurs at replication initiation at origins to begin leading-strand synthesis and also at the 5′ end of each Okazaki fragment on the lagging strand.
However, Pol α is not able to continue DNA replication and must be replaced with another polymerase to continue DNA synthesis.[67] Polymerase switching requires clamp loaders and it has been proven that normal DNA replication requires the coordinated actions of all three DNA polymerases: Pol α for priming synthesis, Pol ε for leading-strand replication, and the Pol δ, which is constantly loaded, for generating Okazaki fragments during lagging-strand synthesis.[68]
The DNA helicases and polymerases must remain in close contact at the replication fork. If unwinding occurs too far in advance of synthesis, large tracts of single-stranded DNA are exposed. This can activate DNA damage signaling or induce DNA repair processes. To thwart these problems, the eukaryotic replisome contains specialized proteins that are designed to regulate the helicase activity ahead of the replication fork. These proteins also provide docking sites for physical interaction between helicases and polymerases, thereby ensuring that duplex unwinding is coupled with DNA synthesis.[73]
To strengthen the interaction between the polymerase and the template DNA, DNA sliding clamps associate with the polymerase to promote the processivity of the replicative polymerase. In eukaryotes, the sliding clamp is a homotrimer ring structure known as the proliferating cell nuclear antigen (PCNA). The PCNA ring has polarity with surfaces that interact with DNA polymerases and tethers them securely to the DNA template. PCNA-dependent stabilization of DNA polymerases has a significant effect on DNA replication because PCNAs are able to enhance the polymerase processivity up to 1,000-fold.[85][86] PCNA is an essential cofactor and has the distinction of being one of the most common interaction platforms in the replisome to accommodate multiple processes at the replication fork, and so PCNA is also viewed as a regulatory cofactor for DNA polymerases.[87)
PCNA loading is accomplished by the replication factor C (RFC) complex. The RFC complex is composed of five ATPases: Rfc1, Rfc2, Rfc3, Rfc4 and Rfc5.[88] RFC recognizes primer-template junctions and loads PCNA at these sites.[89][90] The PCNA homotrimer is opened by RFC by ATP hydrolysis and is then loaded onto DNA in the proper orientation to facilitate its association with the polymerase.[91][92] Clamp loaders can also unload PNCA from DNA; a mechanism needed when replication must be terminated.[92]
Termination
The end replication problem is handled in eukaryotic cells by telomere regions and telomerase. Telomeres extend the 3′ end of the parental chromosome beyond the 5′ end of the daughter strand. This single-stranded DNA structure can act as an origin of replication that recruits telomerase. Telomerase is a specialized DNA polymerase that consists of multiple protein subunits and an RNA component. The RNA component of telomerase anneals to the single stranded 3′ end of the template DNA and contains 1.5 copies of the telomeric sequence.[60] Telomerase contains a protein subunit that is a reverse transcriptase called telomerase reverse transcriptase or TERT. TERT synthesizes DNA until the end of the template telomerase RNA and then disengages.[60] This process can be repeated as many times as needed with the extension of the 3′ end of the parental DNA molecule. This 3′ addition provides a template for extension of the 5′ end of the daughter strand by lagging strand DNA synthesis. Regulation of telomerase activity is handled by telomere-binding proteins.
A depiction of telomerase progressively elongating telomeric DNA.
DNA replication is a tightly orchestrated process that is controlled within the context of the cell cycle. Progress through the cell cycle and in turn DNA replication is tightly regulated by the formation and activation of pre-replicative complexs (pre-RCs) which is achieved through the activation and inactivation of cyclin-dependent kinases (Cdks). Specifically it is the interactions of cyclins and cyclin dependent kinases that are responsible for the transition from G1 into S-phase.
Cell_Cycle_
– G-quadruplex
It will be exactly 60 years ago in February that James Watson and Francis Crick famously burst into the pub next to their Cambridge laboratory to announce the discovery of the “secret of life”.
What they had actually done was describe the way in which two long chemical chains wound up around each other to encode the information cells need to build and maintain our bodies.
Today, the pair’s modern counterparts in the university city continue to work on DNA’s complexities.
Balasubramanian’s group has been pursuing a four-stranded version of the molecule that scientists have produced in the test tube now for a number of years.
It is called the G-quadruplex. The “G” refers to guanine, one of the four chemical groups, or “bases”, that hold DNA together and which encode our genetic information (the others being adenine, cytosine, and thymine).
The G-quadruplex seems to form in DNA where guanine exists in substantial quantities.
And although ciliates, relatively simple microscopic organisms, have displayed evidence for the incidence of such DNA, the new research is said to be the first to firmly pinpoint the quadruple helix in human cells.
‘Funny target’
The team, led by Giulia Biffi, a researcher in Balasubramaninan’s lab, produced antibody proteins that were designed specifically to track down and bind to regions of human DNA that were rich in the quadruplex structure. The antibodies were tagged with a fluorescence marker so that the time and place of the structures’ emergence in the cell cycle could be noted and imaged.
This revealed the four-stranded DNA arose most frequently during the so-called “s-phase” when a cell copies its DNA just prior to dividing.
Prof Balasubramaninan said that was of key interest in the study of cancers, which were usually driven by genes, or oncogenes, that had mutated to increase DNA replication.
If the G-quadruplex could be implicated in the development of some cancers, it might be possible, he said, to make synthetic molecules that contained the structure and blocked the runaway cell proliferation at the root of tumours.
If the first and core mission of the genetic code is to faithfully replicate the “genetic material” encoded in the DNA and RNA nucleic acids, then every metabolic process must be functioning in a synchronous 24/7 manner. The only way to do this is to use all the purine and pyrmidine nucleotide, nucleoside and bases (ATUIXGC) =7 necessary and sufficient to make RNA first and then with the assistance of Thioredoxin i.e. ferredoxin purple sulphur bacteria to oxidize rna to dna.
In regards to purine metabolism which is my major area of focus. The two purine nucleotides left out of the current genetic code i.e. IMP and XMP have the following functions through their enzymes.1. Begin purine nucleotide synthesis de novo by IMPDH cyclodehydrogenase the last step in closing the purine ring and the current foundation molecular structure for DNA and RNA; 2. HPRT is the main enzyme is purine salvage for IMP and GMP; APRT provides same service for AMP; 3. Finally the last step in purine metabolism is by xanthine oxidase with the assistance of FES and molybendum. In essence the IMP and XMP families were the first to build the nucleic acid molecular structure; design a process to recycle functional side groups while keeping the purine ring intact and finally developing the biochemical pathway to eliminate toxic ammonia NH3 from the CNS and liver/kidneys.
I believe the 7 nucleotide Novagon DNA triplex genetic code should be called the epigenetic code since it works not only in protein metabolism which is 2% of the genome but noncoding intronic regions ie. rna editing, RNAi, piRNA, snMRN, long noncoding RNA and many other small rnas which operate above the level of the dna and rna base pair i.e. epigenesis suppressing or enhancing whole genes and networks of genes which control protein,lipid,carbohydrate and nucleic acid metabolism.
I am in the process of deveoping a 7 code epigenetic primer to control the gene switches which in turn allows the genetic material to be inherited from generation to generation as the species constantly adapts to external and internal stressors and competitive antagonist.
A Conserved Structural Core in Type II Restriction Enzymes.
ultraviolet rays, especially the UV-C rays (~260 nm) that are absorbed strongly by DNA but also the longer-wavelength UV-B that penetrates the ozone shield [Link].
Highly-reactive oxygen radicals produced during normal cellular respiration as well as by other biochemical pathways. [Link to further discussion.]
Chemicals in the environment
many hydrocarbons, including some found in cigarette smoke
One of the most frequent is the loss of an amino group(“deamination”) — resulting, for example, in a C being converted to a U.
Mismatchesof the normal bases because of a failure of proofreading during DNA replication.
Common example: incorporation of the pyrimidineU (normally found only in RNA) instead of T.
Breaksin the backbone.
Can be limited to one of the two strands (a single-stranded break, SSB) or
on both strands(a double-stranded break (DSB).
Ionizing radiation is a frequent cause, but some chemicals produce breaks as well.
CrosslinksCovalent linkagescan be formed between bases
on the same DNA strand (“intrastrand”) or
on the opposite strand (“interstrand”).
Several chemotherapeutic drugs used against cancers crosslink DNA [Link].
Repairing Damaged Bases
Damaged or inappropriate bases can be repaired by several mechanisms:
Direct chemical reversal of the damage
Excision Repair, in which the damaged base or bases are removed and then replaced with the correct ones in a localized burst of DNA synthesis. There are three modes of excision repair, each of which employs specialized sets of enzymes.
Base Excision Repair (BER)
Nucleotide Excision Repair (NER)
Mismatch Repair (MMR)
Gene expression profiles associated with acute myocardial infarction and risk of cardiovascular death
Background: Genetic risk scores have been developed for coronary artery disease and atherosclerosis, but are not predictive of adverse cardiovascular events. We asked whether peripheral blood expression profiles may be predictive of acute myocardial infarction (AMI) and/or cardiovascular death.
Methods: Peripheral blood samples from 338 subjects aged 62 ± 11 years with coronary artery disease (CAD) were analyzed in two phases (discovery N = 175, and replication N = 163), and followed for a mean 2.4 years for cardiovascular death. Gene expression was measured on Illumina HT-12 microarrays with two different normalization procedures to control technical and biological covariates. Whole genome genotyping was used to support comparative genome-wide association studies of gene expression. Analysis of variance was combined with receiver operating curve and survival analysis to define a transcriptional signature of cardiovascular death.
Results: In both phases, there was significant differential expression between healthy and AMI groups with overall down-regulation of genes involved in T-lymphocyte signaling and up-regulation of inflammatory genes. Expression quantitative trait loci analysis provided evidence for altered local genetic regulation of transcript abundance in AMI samples. On follow-up there were 31 cardiovascular deaths. A principal component (PC1) score capturing covariance of 238 genes that were differentially expressed between deceased and survivors in the discovery phase significantly predicted risk of cardiovascular death in the replication and combined samples (hazard ratio = 8.5, P< 0.0001) and improved the C-statistic (area under the curve 0.82 to 0.91, P= 0.03) after adjustment for traditional covariates.
Conclusions: A specific blood gene expression profile is associated with a significant risk of death in Caucasian subjects with CAD. This comprises a subset of transcripts that are also altered in expression during acute myocardial infarction.
Lecture Contents delivered at Koch Institute for Integrative Cancer Research, Summer Symposium 2014: RNA Biology, Cancer and Therapeutic Implications, June 13, 2014 @MIT
TDP-43 is a transcriptional repressor that binds to chromosomally integrated TAR DNA and represses HIV-1 transcription. In addition, this protein regulates alternate splicing of the CFTR gene. In particular, TDP-43 is a splicing factor binding to the intron8/exon9 junction of the CFTR gene and to the intron2/exon3 region of the apoA-II gene.[2] A similar pseudogene is present on chromosome 20.[3]
TDP-43 has been shown to bind both DNA and RNA and have multiple functions in transcriptional repression, pre-mRNA splicing and translational regulation.
TDP-43 was originally identified as a transcriptional repressor that binds to chromosomally integrated trans-activation response element (TAR) DNA and represses HIV-1 transcription.[1] It was also reported to regulate alternate splicing of theCFTR gene and the apoA-II gene.
In spinal motor neurons TDP-43 has also been shown in humans to be a low molecular weight microfilament (hNFL) mRNA-binding protein.[4] It has also shown to be a neuronal activity response factor in the dendrites of hippocampal neurons suggesting possible roles in regulating mRNA stability, transport and local translation in neurons.[5]
HIV-1, the causative agent of acquired immunodeficiency syndrome (AIDS), contains an RNAgenome that produces a chromosomally integrated DNA during the replicative cycle. Activation of HIV-1 gene expression by the transactivator “Tat” is dependent on an RNA regulatory element (TAR) located “downstream” (i.e. to-be transcribed at a later point in time) of the transcription initiation site.
Mutations in the TARDBP gene are associated with neurodegenerative disorders including frontotemporal lobar degeneration and amyotrophic lateral sclerosis (ALS).[9] In particular, the TDP-43 mutants M337V and Q331K are being studied for their roles in ALS.[10][11] Cytoplasmic TDP-43 pathology is the dominant histopathological feature of multisystem proteinopathy.[12]
General annotation (Comments)
Function
DNA and RNA-binding protein which regulates transcription and
splicing. Involved in the regulation of CFTR splicing. It promotes
CFTR exon 9 skipping by binding to the UG repeated motifs in the
polymorphic region near the 3′-splice site of this exon. The resulting
aberrant splicing is associated with pathological features typical of
cystic fibrosis. May also be involved in microRNA biogenesis,
apoptosis and cell division. Can repress HIV-1 transcription by
binding to the HIV-1 long terminal repeat. Stabilizes the low
molecular weight neurofilament (NFL) mRNA through a direct
interaction with the 3′ UTR. Ref.2Ref.12
Subunit structure
Homodimer. Interacts with BRDT By similarity. Binds specifically to
pyrimidine-rich motifs of TAR DNA and to single stranded TG
repeated sequences. Binds to RNA, specifically to UG repeated
sequences with a minimun of six contiguous repeats. Interacts with
ATNX2; the interaction is RNA-dependent. Ref.16
Subcellular location
Nucleus. Note: In patients with frontotemporal lobar degeneration
and amyotrophic lateral sclerosis, it is absent from the nucleus of
affected neurons but it is the primary component of cytoplasmic
ubiquitin-positive inclusion bodies. Ref.2Ref.11
Tissue specificity
Ubiquitously expressed. In particular, expression is high in pancreas,
placenta, lung, genital tract and spleen.
Domain
The RRM domains can bind to both DNA and RNA By similarity.
Post-translational modification
Hyperphosphorylated in hippocampus, neocortex, and spinal cord
from individuals affected with ALS and FTLDU. Ref.11Ubiquitinated in hippocampus, neocortex, and spinal cord from
individuals affected with ALS and FTLDU. Ref.2Ref.11 Cleaved to
generate C-terminal fragments in hippocampus, neocortex, and
spinal cord from individuals affected with ALS and FTLDU.
Involvement in disease
Amyotrophic lateral sclerosis 10 (ALS10) [MIM:612069]: A
neurodegenerative disorder affecting upper motor neurons in the
brain and lower motor neurons in the brain stem and spinal cord,
resulting in fatal paralysis. Sensory abnormalities are absent. The
pathologic hallmarks of the disease include pallor of the corticospinal
tract due to loss of motor neurons, presence of ubiquitin-positive
inclusions within surviving motor neurons, and deposition of
pathologic aggregates. The etiology of amyotrophic lateral sclerosis is likely to be multifactorial, involving both genetic and environmental factors. The disease is inherited in 5-10% of the cases. Note: The disease is caused by mutations affecting the gene represented in this
entry.
Deoxyribonucleic acid (DNA) synthesis is a process by which copies of nucleic acid strands are made. In nature, DNA synthesis takes place in cells by a mechanism known as DNA replication. Using genetic engineering and enzyme chemistry, scientists have developed man-made methods for synthesizing DNA. The most important of these is poly-merase chain reaction (PCR). First developed in the early 1980s, PCR has become a multi-billion dollar industry with the original patent being sold for $300 million dollars.
History
DNA was discovered in 1951 by Francis Crick, James Watson, and Maurice Wilkins. Using x-ray crystallography data generated by Rosalind Franklin, Watson and Crick determined that the structure of DNA was that of a double helix. For this work, Watson, Crick, and Wilkins received the Nobel Prize in Physiology or Medicine in 1962. Over the years, scientists worked with DNA trying to figure out the “code of life.” They found that DNA served as the instruction code for protein sequences. They also found that every organism has a unique DNA sequence and it could be used for screening, diagnostic, and identification purposes. One thing that proved limiting in these studies was the amount of DNA available from a single source.
After the nature of DNA was determined, scientists were able to examine the composition of the cellular genes. A gene is a specific sequence of DNA base pairs that provide the code for the construction of a protein. These proteins determine the traits of an organism, such as eye color or blood type. When a certain gene was isolated, it became desirable to synthesize copies of that molecule. One of the first ways in which a large amount of a specific DNA was synthesized was though genetic engineering.
Genetic engineering begins by combining a gene of interest with a bacterial plasmid. A plasmid is a small stretch of DNA that is found in many bacteria. The resulting hybrid DNA is called recombinant DNA. This new recombinant DNA plasmid is then injected into bacterial cells. The cells are then cloned by allowing it to grow and multiply in a culture. As the cells multiply so do copies of the inserted gene. When the bacteria has multiplied enough, the multiple copies of the inserted gene can then be isolated. This method of DNA synthesis can produce billions of copies of a gene in a couple of weeks.
In 1983, the time required to produce copies of DNA was significantly reduced when Kary Mullis developed a process for synthesizing DNA called polymerase chain reaction (PCR). This method is much faster than previous known methods producing billions of copies of a DNA strand in just a few hours. It begins by putting a small section of double stranded DNA in a solution containing DNA polymerase, nucleotides and primers. The solution is heated to separate the DNA strands. When it is cooled, the polymerase creates a copy of each strand. The process is repeated every five minutes until the desired amount of DNA is produced. In 1993, Mullis’s development of PCR earned him the Nobel Prize in Chemistry.
Background
The key to understanding DNA synthesis is understanding its structure. Typically, DNA exists as two chains of chemically linked nucleotides. These links follow specific patterns dictated by the base pairing rules. Each nucleotide is made up of a deoxyribose sugar molecule, a phosphate group, and one of four nitrogen containing bases. The bases include the pyrimidines thymine (T) and cytosine (C)and the purines adenine (A) and guanine (G). In DNA, adenine generally links with thymine and guanine with cytosine. The molecule is arranged in a structure called a double helix which can be imagined by picturing a twisted ladder or spiral staircase. The bases make up the rungs of the ladder while the sugar and phosphate portions make up the ladder sides. The order in which the nucleotides are linked, called the sequence, is determined by a process known as DNA sequencing.
In a eukaryotic cell, DNA synthesis occurs just prior to cell division through a process called replication. When replication begins the two strands of DNA are separated by a variety of enzymes. Thus opened, each strand serves as a template for producing new strands. This whole process is catalyzed by an enzyme called DNA polymerase. This molecule brings corresponding, or complementary, nucleotides in line with each of the DNA strands. The nucleotides are then chemically linked to form new DNA strands which are exact copies of the original strand. These copies, called the daughter strands, contain half of the parent DNA molecule and half of a whole new molecule. Replication by this method is known as semiconservative replication.
Raw Materials
The primary raw materials used for DNA synthesis include DNA starting materials, taq DNA polymerase, primers, nucleotides, and the buffer solution. Each of these play an important role in the production of millions of DNA molecules.
Controlled DNA synthesis begins by identifying a small segment of DNA to copy. This is typically a specific sequence of DNA that contains the code for a desired protein. Called template DNA, this material must be highly purified.
While the process of DNA replication was known before 1980, PCR was not possible because there were no known heat stable DNA polymerases. In the early 1980s, scientists found bacteria living around natural steam vents. It turned out that these organisms, called thermus aquaticus, had a DNA polymerase that was stable and functional at extreme levels of heat. This taq DNA polymerase became the cornerstone for modern DNA synthesis techniques. During a typical PCR process, 2-3 micrograms of taq DNA polymerase is needed.
The polymerase builds the DNA strands by combining corresponding nucleotides on each DNA strand. Chemically speaking, nucleotides are made up of three types of molecular groups including a sugar structure, a phosphate group, and a cyclic base. The sugar portion provides the primary structure for all nucleotides. In general, the sugars are composed of five carbon atoms with a number of hydroxy (-OH) groups attached. For DNA, the sugar is 2-deoxy-D-ribose. The defining part of a nucleotide is the hetero-cyclic base that is covalently bound to the sugar. These bases are either pyrimidine or purine groups, and they form the basis for the nucleic acid code. Two types of purine bases are found including adenine and guanine. In DNA, two types of pyrimidine bases are present, thymine and cytosine. A phosphate group makes up the final portion of a nucleotide. This group is derived from phosphoric acid and is covalently bonded to the sugar structure on the fifth carbon.
The first phase of polymerase chain reaction (PCR) involves the denaturation of DNA. This “opening up” of the DNA molecule provides the template for the next DNA molecule from which to be produced. With the DNA split into separate strands, the temperature is lowered—the primer annealing step. During the next phase, the DNA polymerase interacts with the strands and adds complementary nucleotides along the entire length. The time required at this phase is about one minute for every 1,000 base pairs.
To initiate DNA synthesis, short primer sections of DNA must be used. These primer sections, called oligo fragments, are about 18-25 nucleotides in length and correspond to a section on the template DNA. They typically have a C and G nucleotide concentration of about 60% with even distribution. This provides the maximum efficiency in the synthesis process.
The buffer solution provides the medium in which DNA synthesis can occur. This is an aqueous solution which contains MgCl2, HCI, EDTA, and KCI. The MgCl2 concentration is important because the Mg2+ ions interact with the DNA and the primers creating crucial complexes for DNA synthesis. The pH of this system is critical so it may also be buffered with ammonium sulfate. To energize the reaction, various energy molecules are added such as ATP, GTP, and NTP.
DNA synthesis involves three distinct processes, typically done in separate areas to avoid contamination, including sample preparation, DNA synthesis reaction cycle and DNA isolation. Following these procedures scientists are able to convert a few strands of DNA into millions and millions of exact copies.
Preparation of the samples
1 Typically, all of the starting solutions except the primers, polymerases and the dNTPs are put in an autoclave to kill off any contaminating organism. Two separate solutions are made. One contains the buffer, primers and the polymerase. The other contains the MgCl2 and the template DNA. These solutions are all put into small tubes to begin the reaction.
Kary Banks Mullis.
Kary Banks Mullis was born in Lenoir, North Carolina, in 1944. Upon graduation from Georgia Tech in 1966 with a B.S. in chemistry, Muilis entered the biochemistry doctoral program at the University of California, Berkeley. Earning his Ph.D. in 1973, he accepted a teaching position at the University of Kansas Medical School in Kansas City. In 1977, he assumed a postdoctoral fellowship at the University of California, San Francisco.
Muilis accepted a position as a research scientist in 1979 with a growing biotech firm—Cetus Corporation, in Emeryville, California—that synthesized chemicals used by other scientists in genetic cloning. While there, he designed polymerase chain reaction (PCR), a fast and effective technique for reproducing specific genes or DNA (deoxyribonucleic acid) fragments that can create billions of copies in a few hours. The most effective way to reproduce DNA was by cloning, but it was problematic. It took time to convince Mullis’s colleagues of the importance of this discovery but soon PCR became the focus of intensive research. Scientists at Cetus developed a commercial version of the process and a machine called the Thermal Cycler (with the addition of the chemical building blocks of DNA [nucleotides] and a biochemical catalyst [polymerase], the machine would perform the process automatically on a target piece of DNA).
This is the third discussion of a several part series leading from the genome, to protein synthesis (1), posttranslational modification of proteins (2), examples of protein effects on metabolism and signaling pathways (3), and leading to disruption of signaling pathways in disease (4), and effects leading to mutagenesis.
This discussion is the beginning of a diversion away from the routine discussion of a specific sequence and pairing of nucleotides in the classic model, to explore the interaction between proteins, or folded proteins and RNA or hidtones that reside in the nucleus and contribute to induction or inactivation of gene expression. The basic text document is rigid, inflexible, and resides in all cells. Yet, in bacteria, yeast, and eukaryotic cells, there are models of gene expression, and in eukaryotes, there is the development of expressed organ systems. These systems have similar proteins or enzymes that are functionally identical, but they have isoforms that bind with proteins, membranes, lipopolysaccharides, and lipoproteins – which has an impact on the catabolic and anabolic activity of the cells, and they are affected by oxidative stress, and they are often dependent on the energy of binding with metal ions,i.e., Mn, Cu, Cd, Zn,..,Fe, and in other cases anionic ligands, such as I, and they may transiently act through a nucleotide or influenced by a hormone.
This will be presented as a group of predetermined articles to follow:
1. Scientists discover a broad spectrum of alternatively spliced human protein variants within a well-studied family of genes.
2. Thyroid Hormone Key to Lipid Kinase Regulation
3. Mammalian Target of Rapamycin Complex 1 Orchestrates Invariant NKT Cell Differentiation and Effector Function
4 The E3 ligase PARC mediates the degradation of cytosolic cytochrome c to promote survival in neurons and cancer cells
5. Nf k-beta signaling pathway
6. P181 cAMP-mediated Rac1 activation regulates the re-establishment of endothelial adherens junctions and barrier restoration during inflammation.
7. Structure of the DDB1–CRBN E3 ubiquitin ligase in complex with thalidomide
8. Protein misfolding, congophilia, oligomerization, and defective amyloid processing in preeclampsia
9. Removing parts of shape-shifting protein explains how blood clots
1. Added Layers of Proteome Complexity
Scientists discover a broad spectrum of alternatively spliced human protein variants within a well-studied family of genes.
By Anna Azvolinsky | July 17, 2014
added layers of proteome
There may be more to the human proteome than previously thought. Some genes are known to have several different alternatively spliced protein variants, but the Scripps Research Institute’s Paul Schimmel and his colleagues have now uncovered almost 250 protein splice variants of an essential, evolutionarily conserved family of human genes. The results were published today (July 17) in Science.
Focusing on the 20-gene family of aminoacyl tRNA synthetases (AARSs), the team captured AARS transcripts from human tissues—some fetal, some adult—and showed that many of these messenger RNAs (mRNAs) were translated into proteins. Previous studies have identified several splice variants of these enzymes that have novel functions, but uncovering so many more variants was unexpected, Schimmel said. Most of these new protein products lack the catalytic domain but retain other AARS non-catalytic functional domains.
“The main point is that a vast new area of biology, previously missed, has been uncovered,” said Schimmel.
“This is an incredible study that fundamentally changes how we look at the protein-synthesis machinery,” Michael Ibba, a protein translation researcher at Ohio State University who was not involved in the work, told The Scientist in an e-mail. “The unexpected and potentially vast expanded functional networks that emerge from this study have the potential to influence virtually any aspect of cell growth.”
The team—including researchers at the Hong Kong University of Science and Technology, Stanford University, and aTyr Pharma, a San Diego-based biotech company that Schimmel co-founded—comprehensively captured and sequenced the AARS mRNAs from six human tissue types using high-throughput deep sequencing. While many of the transcripts were expressed in each of the tissues, there was also some tissue specificity.
Next, the team showed that a proportion of these transcripts, including those missing the catalytic domain, indeed resulted in stable protein products: 48 of these splice variants associated with polysomes. In vitro translation assays and the expression of more than 100 of these variants in cells confirmed that many of these variants could be made into stable protein products.
The AARS enzymes—of which there’s one for each of the 20 amino acids—bring together an amino acid with its appropriate transfer RNA (tRNA) molecule. This reaction allows a ribosome to add the amino acid to a growing peptide chain during protein translation. AARS enzymes can be found in all living organisms and are thought to be among the first proteins to have originated on Earth.
To understand whether these non-catalytic proteins had unique biological activities, the researchers expressed and purified recombinant AARS fragments, testing them in cell-based assays for proliferation, cell differentiation, and transcriptional regulation, among other phenotypes. “We screened through dozens of biological assays and found that these variants operate in many signaling pathways,” said Schimmel.
“This is an interesting finding and fits into the existing paradigm that, in many cases, a single gene is processed in various ways [in the cell] to have alternative functions,” said Steven Brenner, a computational genomics researcher at the University of California, Berkeley.
The team is now investigating the potentially unique roles of these protein splice variants in greater detail—in both human tissue as well as in model organisms. For example, it is not yet clear whether any of these variants directly bind tRNAs.
“I do think [these proteins] will play some biological roles,” said Tao Pan, who studies the functional roles of tRNAs at the University of Chicago. “I am very optimistic that interesting biological functions will come out of future studies on these variants.”
Brenner agreed. “There could be very different biological roles [for some of these proteins]. Biology is very creative that way, [it’s] able to generate highly diverse new functions using combinations of existing protein domains.” However, the low abundance of these variants is likely to constrain their potential cellular functions, he noted.
Because AARSs are among the oldest proteins, these ancient enzymes were likely subject to plenty of change over time, said Karin Musier-Forsyth, who studies protein translational at the Ohio State University. According to Musier-Forsyth, synthetases are already known to have non-translational functions and differential localizations. “Like the addition of post-translational modifications, splicing variation has evolved as another way to repurpose protein function,” she said.
One of the protein variants was able to stimulate skeletal muscle fiber formation ex vivo and upregulate genes involved in muscle cell differentiation and metabolism in primary human skeletal myoblasts. “This was really striking,” said Musier-Forsyth. “This suggests that, perhaps, peptides derived from these splice variants could be used as protein-based therapeutics for a variety of diseases.”
Published: Jul 16, 2014 | Updated: Jul 17, 2014
By Salynn Boyles, Contributing Writer, MedPage Today
Reviewed by Zalman S. Agus, MD; Emeritus Professor, Perelman School of Medicine at the University of Pennsylvania and
Dorothy Caputo, MA, BSN, RN, Nurse Planner
Action Points
Thyroid hormone is an essential regulator of human growth, brain maturation, and adult cognition and metabolism.
This study provides evidence that cytoplasmic thyroid hormone signaling through phosphatidylinositol 3-kinase appears to be an essential mechanism underlying normal synaptic maturation and plasticity in the postnatal mouse hippocampus
Thyroid hormones are key for brain development and synaptic maturation, and researchers have identified a specific molecular mechanism for rapid lipid kinase activation by the thyroid hormone receptor beta (TR-beta) that involves a cytoplasmic complex of the gene.
Many effects of the thyroid hormone on mammalian cells in vitro have been shown to be mediated by the phosphatidylinositol 3-kinase (PI3K), but the molecular mechanism of PI3K regulation and its relevance to brain development have not been clear, according to David L. Armstrong, PhD, of the National Institute of Environmental Health and Development in Research Triangle, N.C., and colleagues.
They identified a specific molecular mechanism for rapid PI3 kinase activation by TR-beta which involves a cytoplasmic complex of TR-beta, the p85 regulatory subunit of PI3 kinase and the Src family kinase, Lyn, they wrote in Endocrinology.Armstrong’s co-authors are from Duke University and Loyola University in Chicago.
This complex provides a unique mechanism for integrating growth signals through thyroid hormone and receptor tyrosine kinases, they explained.
“Most everyone agrees that thyroid hormones are essential for brain development and synaptic maturation, but we didn’t know how exactly,” Armstrong told MedPage Today. “We show that nongenomic signaling in TR-beta through PI3 kinase is essential for one of its physiological actions.”
The Role of T3 Hormone
The recognition that many hormones regulate gene expression through receptor proteins that bind to DNA is a major biological discovery over the past 50 years, the researchers noted.
“More recently, it has become clear that in many cases the same hormones produce rapid effects on cell physiology though the same receptors signaling in the cytoplasm,” they wrote. “However, testing the relative importance of the genomic and nongenomic mechanisms in vivo has been prevented by the absence of specific molecular mechanisms for the nongenomic effects that could be blocked by mutation of the receptor without disrupting its direct effects on gene expression.”
The thyroid hormone T3 has been shown to be a regulator of many physiological effects, including human growth, brain maturation, and adult cognition and metabolism.
Many of these effects have been found to be mediated through the regulation of gene expression by zinc-finger nuclear receptor proteins that are encoded by the THRA and THRB genes. But many in vitro effects of T3 are too rapid to be explained by transcriptional regulation, Armstrong and colleagues noted.
In earlier work, they identified PI3 kinase as a key player in these rapid effects. Like thyroid hormone, PI3 kinase activity has been identified as essential for growth, metabolism, and brain development.
PI3 kinase is regulated primarily by receptor tyrosine kinases, and an integrin receptor has been identified that mediates some of the PI3 kinase-dependent effects of thyroxine (T4), the widely circulated precursor of T3.
Both TR-alpha and TR-beta have also been reported to associate with PI3 kinase and stimulate its activity in many cell types. In a 2006 study in the Proceedings of the National Academy of Sciences, Armstrong and colleagues demonstrated that TRis required to reconstitute T3 and PI3 kinase-dependent regulation of Kv11.1 channels in cell-free membrane patches from Chinese hamster ovary (CHO) cells.
Based on that research, they concluded that TR-beta signaling through PI3K “provides a molecular explanation for the essential role of thyroid hormone in human brain development and adult lipid metabolism.”
Measuring PIP3 Production
In the newly reported series of experiments, the researchers used fluorescent PIP3 indicator to directly measure PIP3 production in response to thyroid hormone on the same time scale as the electrophysiological measurements in the CHO cells expressing recombinant human thyroid hormone receptors.
The research revealed that, in the absence of hormone, the nuclear receptor TR-beta forms a cytoplasmic complex with the p85 subunit of PI3 kinase and the Src family tyrosine kinase, Lyn, which depends on two canonical phosphotyrosine motifs in the second zinc finger of TR that are not conserved in TR-beta
“When hormone is added, [TR-beta] dissociates and moves to the nucleus, and PIP3production goes up rapidly,” the researchers wrote. “Mutating either tyrosine to a phenylalanine prevents rapid signaling through PI3 kinase but does not prevent hormone-dependent transcription of genes with a thyroid hormone response element.”
“It is only when you have both thyroid hormone and phosphotyrosine signaling that you get maximal stimulation of PI3 kinase,” Armstrong said, adding that the novel methodology of the study, which involved serum from thyroidectomized animals, led to the finding.
These experiments led to in vivo research to test the physiological relevance of thyroid hormone signaling through PI3 kinase for brain development in a novel mouse line created by the researchers.
“We reasoned that blocking binding of TR-beta to p85 by mutating Y171 might eliminate any dominant negative effect of the mutant, in much the same way that receptor knockdown proved much less deleterious to the organism than hormone withdrawal, presumably because many of the effects of the receptor on gene expression are mediated by binding of the unliganded receptor,” they wrote.
They created a novel mouse line with a targeted mutation knocked into the THRB gene to substitute phenylalanine for tyrosine at residue 147 of TR-beta-1, which prevents Lyn binding to the mutant receptor.
They confirmed that the mutation did not alter total circulating levels of thyroxine (T4) or T3 by mass spectrometry of serum samples from 4-month-old mice.
“When the rapid signaling mechanism was blocked chronically throughout development in mice by a targeted point mutation in both alleles of THRB, circulating hormone levels, TR-betaexpression, and direct gene regulation by TR-beta in the brain and liver were all unaffected,” the researchers wrote. “The mutation did significantly impair maturation and plasticity of the Schaffer collateral synapses on CA1 pyramidal neurons in the postnatal hippocampus. Thus, phosphotyrosine-dependent association of TR-betawith PI3K provides a potential mechanism for integrating regulation of development and metabolism by thyroid hormone and receptor tyrosine kinases.”
A Novel Finding
The finding that thyroid hormone signaling through PI3 kinase appears to be an essential mechanism underlying normal synaptic maturation and plasticity in the postnatal mouse hippocampus is novel.
The researchers noted that they could not formally exclude some more subtle effects of the mutation on the regulation of an unknown gene that plays as central a role in synaptic development as PI3K, but the added that “our results do categorically rule out a role for other thyroid hormone receptors in this particular aspect of synaptic maturation in the mouse hippocampus.
“In either case, given the importance of thyroid hormone signaling for human brain development and adult metabolism, future studies will need to investigate whether PI3 kinase stimulation by thyroid hormone is also susceptible to disruption by environmental toxicants,” they wrote.
Armstrong also pointed out that the tyrosine motifs in TR-beta, which were shown to be essential for signaling through PI3 kinase, are present in all mammals, but not in other species with known genome data, with the exception of the gecko and the axolotl (Mexican salamander).
“Mammals evolved from reptiles, and the thinking is that they survived by adopting a nocturnal niche,” he said. “This is exactly what thyroid hormone does, so it may be that this mutation contributed to the (evolutionary) success of mammals.”
ABSTRACT Invariant NKT (iNKT) cells play critical roles in bridging innate and adaptive immunity. The Raptor containing mTOR complex 1 (mTORC1) has been well documented to control peripheral CD4 or CD8 T cell effector or memory differentiation. However, the role of mTORC1 in iNKT cell development and function remains largely unknown. By using mice with T cell-restricted deletion of Raptor, we show that mTORC1 is selectively required for iNKT but not for conventional T cell development. Indeed, Raptor-deficient iNKT cells are mostly blocked at thymic stage 1-2, resulting in a dramatic decrease of terminal differentiation into stage 3 and severe reduction of peripheral iNKT cells. Moreover, residual iNKT cells in Raptor knockout mice are impaired in their rapid cytokine production upon αGalcer challenge. Bone marrow chimera studies demonstrate that mTORC1 controls iNKT differentiation in a cell-intrinsic manner. Collectively, our data provide the genetic evidence that iNKT cell development and effector functions are under the control of mTORC1 signaling.
4. PARC
The E3 ligase PARC mediates the degradation of cytosolic cytochrome c to promote survival in neurons and cancer cells
Vivian Gama1,2, Vijay Swahari1,2, Johanna Schafer1*, Adam J. Kole2, Allyson Evans2, Yolanda Huang2, Anna Cliffe1,2, Brian Golitz3,4, Noah Sciaky3,4, Xin-Hai Pei5,6, Yue Xiong5,6, and Mohanish Deshmukh1,2,5
1 Neuroscience Center, 2 Department of Cell Biology and Physiology, 3 UNC RNAi Screening Facility,4 Department of Pharmacology, 5 Lineberger Comprehensive Cancer Center, 6 Department of Biochemistry and Biophysics, University of North Carolina, Chapel Hill, NC 27599, USA.* Present address: Vanderbilt University, Nashville, TN 37232, USA. Present address: Cell Press, Cambridge, MA 02139, USA. Present address: Department of Anesthesiology, Columbia University Medical Center, New York, NY 10032, USA.
Abstract: The ability to withstand mitochondrial damage is especially critical for the survival of postmitotic cells, such as neurons. Likewise, cancer cells can also survive mitochondrial stress. We found that cytochrome c (Cyt c), which induces apoptosis upon its release from damaged mitochondria, is targeted for proteasome-mediated degradation in mouse neurons, cardiomyocytes, and myotubes and in human glioma and neuroblastoma cells, but not in proliferating human fibroblasts. In mouse neurons, apoptotic protease-activating factor 1 (Apaf-1) prevented the proteasome-dependent degradation of Cyt c in response to induced mitochondrial stress. An RNA interference screen in U-87 MG glioma cells identified p53-associated Parkin-like cytoplasmic protein (PARC, also known as CUL9) as an E3 ligase that targets Cyt c for degradation. The abundance of PARC positively correlated with differentiation in mouse neurons, and overexpression of PARC reduced the abundance of mitochondrially-released cytosolic Cyt c in various cancer cell lines and in mouse embryonic fibroblasts. Conversely, neurons from Parc-deficient mice had increased sensitivity to mitochondrial damage, and neuroblastoma or glioma cells in which PARC or ubiquitin was knocked down had increased abundance of mitochondrially-released cytosolic Cyt c and decreased viability in response to stress. These findings suggest that PARC-mediated ubiquitination and degradation of Cyt c is a strategy engaged by both neurons and cancer cells to prevent apoptosis during conditions of mitochondrial stress. Sci. Signal., 15 July 2014 Vol. 7, Issue 334, p. ra67 http://dx.doi.org:/10.1126/scisignal.2005309
Citation: V. Gama, V. Swahari, J. Schafer, A. J. Kole, A. Evans, Y. Huang, A. Cliffe, B. Golitz, N. Sciaky, X.-H. Pei, Y. Xiong, M. Deshmukh, The E3 ligase PARC mediates the degradation of cytosolic cytochrome c to promote survival in neurons and cancer cells. Sci. Signal.7, ra67 (2014).
Killing the Killer: PARC/CUL9 Promotes Cell Survival by Destroying Cytochrome c
Jonathan Lopez and Stephen W. G. Tait* Cancer Research UK Beatson Institute, Institute of Cancer Sciences, University of Glasgow, Garscube Estate, Switchback Road, Glasgow G61 1BD, UK.
Abstract: Balanced amounts of apoptotic cell death are essential for health; its deregulation plays key roles in neurodegeneration, autoimmunity, and cancer. Mitochondria orchestrate apoptosis through a process called mitochondrial outer-membrane permeabilization (MOMP). After MOMP, mitochondrial cytochrome c is released into the cytoplasm, where it binds the adaptor molecule APAF1, triggering caspase protease activation and cell death. In this issue of Science Signaling, Deshmukh and colleagues define a new survival mechanism downstream of mitochondrial permeabilization. Specifically, they identify proteasomal degradation of cytochrome c as a major determinant of cell survival. In an unbiased approach, PARC (also known as CUL9) was found to be the ubiquitin ligase responsible for the ubiquitination and proteasomal degradation of cytochrome c. The consequences of this survival process may be double-edged because both cancer cells and postmitotic cells use PARC/CUL9–mediated cytochrome c degradation to ensure cell survival. Ultimately, differential targeting of this process may promote survival of postmitotic tissue or enhance tumor-specific killing.
Citation: J. Lopez, S. W. G. Tait, Killing the Killer: PARC/CUL9 Promotes Cell Survival by Destroying Cytochrome c. Sci. Signal.7, pe17 (2014).
4. The WNK-SPAK/OSR1 pathway: Master regulator of cation-chloride cotransporters
Dario R. Alessi1, Jinwei Zhang1, Arjun Khanna2, Thomas Hochdörfer1, Yuze Shang3, and Kristopher T. Kahle2,3* 1 MRC Protein Phosphorylation and Ubiquitylation Unit, College of Life Sciences, University of Dundee, Dundee DD1 5EH, Scotland. 2 Department of Neurosurgery, Massachusetts General Hospital, and Harvard Medical School, 3 Manton Center for Orphan Disease Research, Boston Children’s Hospital, Boston, MA 02115, USA.
Abstract: The WNK-SPAK/OSR1 kinase complex is composed of the kinases WNK (with no lysine) and SPAK (SPS1-related proline/alanine-rich kinase) or the SPAK homolog OSR1 (oxidative stress–responsive kinase 1). The WNK family senses changes in intracellular Cl– concentration, extracellular osmolarity, and cell volume and transduces this information to sodium (Na+), potassium (K+), and chloride (Cl–) cotransporters [collectively referred to as CCCs (cation-chloride cotransporters)] and ion channels to maintain cellular and organismal homeostasis and affect cellular morphology and behavior. Several genes encoding proteins in this pathway are mutated in human disease, and the cotransporters are targets of commonly used drugs. WNKs stimulate the kinases SPAK and OSR1, which directly phosphorylate and stimulate Cl–-importing, Na+-driven CCCs or inhibit the Cl–-extruding, K+-driven CCCs. These coordinated and reciprocal actions on the CCCs are triggered by an interaction between RFXV/I motifs within the WNKs and CCCs and a conserved carboxyl-terminal docking domain in SPAK and OSR1. This interaction site represents a potentially druggable node that could be more effective than targeting the cotransporters directly. In the kidney, WNK-SPAK/OSR1 inhibition decreases epithelial NaCl reabsorption and K+ secretion to lower blood pressure while maintaining serum K+. In neurons, WNK-SPAK/OSR1 inhibition could facilitate Cl–extrusion and promote -aminobutyric acidergic (GABAergic) inhibition. Such drugs could have efficacy as K+-sparing blood pressure–lowering agents in essential hypertension, nonaddictive analgesics in neuropathic pain, and promoters of GABAergic inhibition in diseases associated with neuronal hyperactivity, such as epilepsy, spasticity, neuropathic pain, schizophrenia, and autism. Citation: D. R. Alessi, J. Zhang, A. Khanna, T. Hochdörfer, Y. Shang, K. T. Kahle, The WNK-SPAK/OSR1 pathway: Master regulator of cation-chloride cotransporters. Sci. Signal.7, re3 (2014).
Karen E. Tkach, Jennifer E. Oyler, and Grégoire Altan-Bonnet* ImmunoDynamics Group, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA.
Abstract: The discovery of feedback loops between signaling and gene expression is ushering in new quantitative models of cellular regulation. In a recent issue of Science Signaling, Sung et al. showed how positive feedback downstream of nuclear factor B (NF-B) signaling enhances the capacity of macrophages to scale their antimicrobial responses to the dose of pathogen-associated molecular cues. This finding stemmed from analysis of cell-to-cell variability and computational modeling of time integration between signaling and transcriptional responses. Ultimately, such quantitative approaches challenge the oft-assumed time separation of “fast” signal transduction followed by “slow” gene expression, and they provide a better understanding of complex biological regulation over long time scales.
Citation: K. E. Tkach, J. E. Oyler, G. Altan-Bonnet, Cracking the NF-B Code. Sci. Signal.7, pe5 (2014).
Switching of the Relative Dominance Between Feedback Mechanisms in Lipopolysaccharide-Induced Nfk-B Signaling
Myong-Hee Sung1*, Ning Li2, Qizong Lao1, Rachel A. Gottschalk2, Gordon L. Hager1*, and Iain D. C. Fraser2* 1 Laboratory of Receptor Biology and Gene Expression, National Cancer Institute, 2 Laboratory of Systems Biology, National Institute of Allergy and Infectious Diseases, National Institutes of Health, Bethesda, MD 20892, USA.
Abstract: A fundamental goal in biology is to gain a quantitative understanding of how appropriate cell responses are achieved amid conflicting signals that work in parallel. Through live, single-cell imaging, we monitored both the dynamics of nuclear factor B (NF-B) signaling and inflammatory cytokine transcription in macrophages exposed to the bacterial product lipopolysaccharide (LPS). Our analysis revealed a previously uncharacterized positive feedback loop involving induction of the expression of Rela, which encodes the RelA (p65) NF-B subunit. This positive feedback loop rewired the regulatory network when cells were exposed to LPS above a distinct concentration. Paradoxically, this rewiring of NF-B signaling in macrophages (a myeloid cell type) required the transcription factor Ikaros, which promotes the development of lymphoid cells. Mathematical modeling and experimental validation showed that the RelA positive feedback overcame existing negative feedback loops and enabled cells to discriminate between different concentrations of LPS to mount an effective innate immune response only at higher concentrations. We suggest that this switching in the relative dominance of feedback loops (“feedback dominance switching”) may be a general mechanism in immune cells to integrate opposing feedback on a key transcriptional regulator and to set a response threshold for the host.
Citation: M.-H. Sung, N. Li, Q. Lao, R. A. Gottschalk, G. L. Hager, I. D. C. Fraser, Switching of the Relative Dominance Between Feedback Mechanisms in Lipopolysaccharide-Induced NF-B Signaling. Sci. Signal.7, ra6 (2014).
Drug development in the Alzheimer’s field has been riddled with failures, and most research efforts have focused on pinpointing genetic and environmental factors responsible for causing or accelerating the progression of the disease.
Now, researchers from Montreal’s Douglas Mental Health Institute and McGill University have identified a relatively frequent genetic variant that may provide protection against the devastating neurodegenerative disease.
“We found that specific genetic variants in a gene called HMG CoA reductase which normally regulates cholesterol production and mobilization in the brain can interfere with, and delay the onset of Alzheimer’s disease by nearly four years. This is an exciting breakthrough in a field where successes have been scarce these past few years,” said Dr. Judes Poirier, whose previous research led to the discovery that a genetic variant was formally associated with the common form of Alzheimer’s disease.
This variant may explain why some people who are carriers of predisposing genetic factors for the common form of Alzheimer’s do not develop the disease, living long lives without memory problems until their nineties.
6. P181 cAMP-mediated Rac1 activation regulates the re-establishment of endothelial adherens junctions and barrier restoration during inflammation.
ABSTRACT Inflammatory mediators like thrombin and TNFα disrupt endothelial junctions and barrier integrity, leading to edema formation. This increase in endothelial permeability is followed by slow restoration of the endothelial barrier, which is critical for the maintenance of basal endothelial permeability. However, the molecular mechanism of recovery of the endothelial barrier in response to inflammatory mediators has not yet been well delineated. The aim of the present study was to explore the mechanism of this barrier restoration. Specific emphasis was given to the role of Rac1 GTPase activation, which is an important regulator of endothelial adherens junction (AJ) integrity.
7.Thalidomide
Structure of the DDB1–CRBN E3 ubiquitin ligase in complex with thalidomide
In the 1950s, the drug thalidomide, administered as a sedative to pregnant women, led to the birth of thousands of children with multiple defects. Despite the teratogenicity of thalidomide and its derivatives lenalidomide and pomalidomide, these immunomodulatory drugs (IMiDs) recently emerged as effective treatments for multiple myeloma and 5q-deletion-associated dysplasia. IMiDs target the E3 ubiquitin ligase CUL4–RBX1–DDB1–CRBN (known as CRL4CRBN) and promote the ubiquitination of the IKAROS family transcription factors IKZF1 and IKZF3 by CRL4CRBN. Here we present crystal structures of the DDB1–CRBN complex bound to thalidomide, lenalidomide and pomalidomide. The structure establishes that CRBN is a substrate receptor within CRL4CRBN and enantioselectively binds IMiDs. Using an unbiased screen, we identified the homeobox transcription factor MEIS2 as an endogenous substrate of CRL4CRBN. Our studies suggest that IMiDs block endogenous substrates (MEIS2) from binding to CRL4CRBN while the ligase complex is recruiting IKZF1 or IKZF3 for degradation. This dual activity implies that small molecules can modulate an E3 ubiquitin ligase and thereby upregulate or downregulate the ubiquitination of proteins.
Figure 1: The overall structure of the DDB1–CRBN complex.
a, Cartoon representation of the structure of the complex of human DDB1, G. gallus CRBN and thalidomide: DDB1, highlighting the domains BPA (red), BPB (magenta), BPC (orange) and DDB1-CTD (grey); G. gallus CRBN, highlighting the domain…
a, Chemical structure of lenalidomide. b, Chemical structure of pomalidomide. c, Sketch of thalidomide and its interactions with G. gallus CRBN. Hydrogen bonds are shown as dashed lines, and hydrophobic interactions are indicated as gr
Figure 3: CRBN is a substrate receptor in the ligase CRL4CRBN.
a, Architecture of the CRL4DDB2 complex bound to DNA (PDB ID 4A0K). b, Model of CRL4CRBN bound to thalidomide. c, Firefly luciferase (Fluc) to Renillaluciferase (Rluc) ratios (Fluc:Rluc) of IKZF1-reporter-plasmid-transfected HEK 293T…
a, Thalidomide binds to CRBN at the canonical substrate-binding site. b, The potent anti-myeloma drug thalidomide and its derivatives lenalidomide and pomalidomide occupy the same site but with different solvent-exposed moieties. c, Bi…
8. Preeclampsia of pregnancyand protein misfolding
Protein misfolding, congophilia, oligomerization, and defective amyloid processing in preeclampsia
Irina A. Buhimschi1,2,*, Unzila A. Nayeri2, Guomao Zhao1, Lydia L. Shook2, Anna Pensalfini3, et al. 1Center for Perinatal Research, The Research Institute at Nationwide Children’s Hospital and Department of Pediatrics, 4Depart of ObGyn, The Ohio State University College of Medicine, Columbus, OH 2Depart of ObGyn and Reproductive Sciences, Yale University School of Medicine, New Haven, CT
3Center for Dementia Research, Nathan Kline Institute for Psychiatric Research and Department of Psychiatry, New York University School of Medicine, New York, NY 5Depart of ObGyn and Reproductive Sciences, University of Vermont College of Medicine, Burlington, VT . 6Department of Molecular Biology and Biochemistry, University of California, Irvine, Irvine, CA 92617, USA. 7Department of Biochemistry and Experimental Biochemistry Unit, King Abdulaziz Univ, Jeddah , Saudi Arabia.
Preeclampsia is a pregnancy-specific disorder of unknown etiology and a leading contributor to maternal and perinatal morbidity and mortality worldwide. Because there is no cure other than delivery, preeclampsia is the leading cause of iatrogenic preterm birth. We show that preeclampsia shares pathophysiologic features with recognized protein misfolding disorders. These features include urine congophilia (affinity for the amyloidophilic dye Congo red), affinity for conformational state–dependent antibodies, and dysregulation of prototype proteolytic enzymes involved in amyloid precursor protein (APP) processing. Assessment of global protein misfolding load in pregnancy based on urine congophilia (Congo red dot test) carries diagnostic and prognostic potential for preeclampsia. We used conformational state–dependent antibodies to demonstrate the presence of generic supramolecular assemblies (prefibrillar oligomers and annular protofibrils), which vary in quantitative and qualitative representation with preeclampsia severity. In the first attempt to characterize the preeclampsia misfoldome, we report that the urine congophilic material includes proteoforms of ceruloplasmin, immunoglobulin free light chains, SERPINA1, albumin, interferon-inducible protein 6-16, and Alzheimer’s β-amyloid. The human placenta abundantly expresses APP along with prototype APP-processing enzymes, of which the α-secretase ADAM10, the β-secretases BACE1 and BACE2, and the γ-secretase presenilin-1 were all up-regulated in preeclampsia. The presence of β-amyloid aggregates in placentas of women with preeclampsia and fetal growth restriction further supports the notion that this condition should join the growing list of protein conformational disorders. If these aggregates play a pathophysiologic role, our findings may lead to treatment for preeclampsia.
Citation: I. A. Buhimschi, U. A. Nayeri, G. Zhao, L. L. Shook, A. Pensalfini, E. F. Funai, I. M. Bernstein, C. G. Glabe, C. S. Buhimschi,Protein misfolding, congophilia, oligomerization, and defective amyloid processing in preeclampsia. Sci. Transl. Med. 6, 245ra92 (2014).
9. Blood Clotting
Removing parts of shape-shifting protein explains how blood clots
prothrombin (FII)
Using x-ray crystallography, SLU researchers published the first image of the important blood-clotting protein prothrombin (coagulation factor II). The protein’s flexible structure is key to the development of blood-clotting.In results recently published in Proceedings of the National Academy of Sciences (PNAS), Saint Louis University scientists have discovered that removal of disordered sections of a protein’s structure reveals the molecular mechanism of a key reaction that initiates blood clotting.
Enrico Di Cera, M.D., chair of the Edward A. Doisy department of biochemistry and molecular biology at Saint Louis University, studies thrombin, a key vitamin K-dependent blood-clotting protein, and its inactive precursor prothrombin (or coagulation factor II).
“Prothrombin is essential for life and is the most important clotting factor,” Di Cera said. “We are proud to report that our lab here at SLU has finally succeeded in crystallizing prothrombin for the first time.”
Blood-clotting has long ensured our survival, stopping blood loss after an injury. However, when triggered in the wrong circumstances, clotting can lead to debilitating or fatal conditions such as a heart attack, stroke or deep vein thrombosis.
Before thrombin becomes active, it circulates throughout the blood in the inactive (zymogen) form called prothrombin. When the active enzyme is needed (after a vascular injury, for example), the coagulation cascade is initiated and prothrombin is converted into the active enzyme thrombin that causes blood to clot.
X-ray crystallography is one tool in scientists’ toolbox for understanding processes at the molecular level. It offers a way to obtain a “snap shot” of a protein’s structure.
In this technique, scientists grow crystals of the protein they want to study, shoot x-rays at them and record data about the way the rays are scattered by crystals. Then they use computer programs to create an image of the protein based on that data.
Once scientists can visualize the three dimensional structure of a molecule, they can begin to piece together the way in which the protein functions and interacts with other molecules in the body, or with drugs.
Last year, Di Cera and colleagues published the first structure of prothrombin. This first structure lacked a domain responsible for interaction with membranes and certain other sections were not detected by x-ray analysis. Though the scientists were able to crystallize the protein, there were disordered regions in the structure that they could not see.
Within prothrombin there are two kringle domains (looped sections of a protein named after the Scandinavian pastry) connected by a “linker” region that intrigued the SLU investigators because of its intrinsic disorder.
“We deleted this linker and crystals grew in a few days instead of months, revealing for the first time the full architecture of prothrombin,” Di Cera said.
In addition to this remarkable discovery, Di Cera and colleagues found that the deleted version of prothrombin is activated to thrombin much faster than the intact prothrombin. The structure without the disordered linker is in fact optimized for conversion to thrombin and reveals key information on the mechanism of prothrombin activation.
For over four decades, scientists have tried to crystallize prothrombin but without success.
“It took us almost two years to discover that the disordered linker was the key,” Di Cera said. “Finally, prothrombin revealed its secrets and with that the molecular mechanism of a key reaction of blood clotting finally becomes amenable to rational drug design for therapeutic intervention.”
SLU researchers Nicola Pozzi, Ph.D., Zhiwei Chen, Leslie Pelc and Daniel Shropshire also are authors on the paper.
This article is a look at where the biomedical research sciences are in developing standards for development in the near term.
Let’s Not Wait for the FDA: Raising the Standards of Biomarker Development – A New Series
published by Theral Timpson on Tue, 07/01/2014 – 15:03
We talk a lot on this show about the potential of personalized medicine. Never before have we learned at such breakneck speed just how our bodies function. The pace of biological research staggers the mind and hints at a time when we will “crack the code” of the system that is homo sapiens, going from picking the low hanging fruit to a more rational approach. The high tech world has put at the fingertips of biologists just the tools to do it. There is plenty of compute, plenty of storage available to untangle, or decipher the human body. Yet still, we talk of potential.
Chat with anyone heavily involved in the life science industry–be it diagnostics or pharma– and you’ll quickly hear that we must have better biomarkers.
Next week we launch a series, Let’s Not Wait for the FDA: Raising the Standards of Biomarker Development, where we will pursue the “hotspots” that are haunting those in the field.
The National Biomarker Development Alliance (NBDA) is a non profit organization based at Arizona State University and led by the formidable Anna Barker, former deputy director of the NCI. The aim of the NBDA is to identify problem areas in biomarker development–from the biospecimen and sampling issues to experiment design to bioinformatics challenges–and raise the standards in each area. This series of interviews is based on their approach. We will purse each of these topics with a special guest.
The place to start is with samples. The majority of researchers who are working on biomarker assays don’t give much thought to the “story” of their samples. Yet the quality of their research will never exceed the quality of the samples with which they start–a very scary thought according toCarolyn Compton, a former pathologist, now professor of pathology at ASU and Johns Hopkins. Carolyn worked originally as a clinical pathologist and knows first hand the the issues around sample degradation. She left the clinic when she was recruited to the NCI with the mission of bringing more awareness to the issue of bio specimens. She joins us as our first guest in the series.
That Carolyn has straddled the world of the clinic and the world of research is key to her message. And it’s key to this series. As we see an increased push to “translate” research into clinical applications, we find that these two worlds do not work enough together.
Researchers spend a lot of time analyzing data and developing causal relationships from certain biological molecules to a disease. But how often do these researchers consider how the history of a sample might be altering their data?
“Garbage in, garbage out,” says Carolyn, who links low quality samples with the abysmal non-reproducable rate of most published research.
Two of our guests in the series have worked on the adaptive iSpy breast cancer trials. These are innovative clinical trials that have been designed to “adapt” to the specific biology of those in the trial. Using the latest advances in genetics, the iSPY trials aim to match experimental drugs with the molecular makeup of tumors most likely to respond to them. And the trials are testing multiple drugs at once.
Don Berry is known for bringing statistics to clinical trials. He designed the iSpy trials and joins us to explain how these new trials work and of the promise of the adaptive design.
Laura Esserman is the director of the breast cancer center at UCSC and has been heavily involved in the implementation of the iSpy trials. Esserman is concerned that “if we keep doing conventional clinical trials, people are going to give up on doing them.” An MBA as well as an MD, Esserman brings what she learned about innovation in the high-tech industry to treatment for breast cancer.
From there we turn to the topic of “systems biology” where we will chat with George Poste, a tour de force when it comes to considering all of the various aspects of biology. Anyone who has ever been present for one of George’s presentations has no doubt come away scratching your head wondering if we’ll ever really glimpse the whole system that is a human being. If there is one brain that has seen all the rooms and hallways of our complex system, it’s George Poste.
We’ll finish the series by interviewing David Haussler from UCSC of Genome Browser fame. Recently Haussler has worked extensively on an NCI project, The Cancer Genome Atlas, to bring together data sets and connect cancer researchers around the world. What is the promise and pitfalls David sees with the latest bioinformatics tools?
George Poste says that in the literature we have identified 150,000 biomarkers that have causal linkage to disease. Yet only 100 of these have been commercialized and are used in the clinic. Why is the number so low? We hope to come up with some answers in this series.
Why Hasn’t Clinical Genetics Taken Off? (part 2)
published by Sultan Meghji on Fri, 06/20/2014 – 14:49
In my previous post, I made the broad comment that education of the patient and front line doctors was the single largest barrier to entry for clinical genetics. Here I look at the steps in the scientific process and where the biggest opportunities lie:
The Sequencing (still)
PCR is a perfectly reasonable technology for sequencing in the research lab today, but the current configuration of technologies need to change. We need to move away from an expert level skill set and a complicated chemistry process in the lab to a disposable, consumer friendly set of technologies. I’m not convinced PCR is the right technology for that and would love to see nanopore be a serious contender, but lack of funding for a broad spectrum of both physics-only as well as physical-electrical startups have slowed the progress of these technologies. And waiting in the wings, other technologies are spinning up in research labs around the world. Price is no longer a serious problem in the space – reliable, repeatable, easy to use sequencing technologies are. The complexity of the current technology (both in terms of sample preparation and machine operation) is a big hurdle.
The Analysis (compute)
Over the last few years, quite a bit of commentary and effort has been put into making the case that the compute is a significant challenge (including more than a few comments by yours truly in that vein!). Today, it can be said with total confidence that compute is NOT a problem. Compute has been commoditized. Through excellent new software to advanced platforms and new hardware, it is a trivial exercise to do the analysis and costs tiny amounts of money ($<25 per sample on a cloud provider appears to be the going rate for a clinical exome in terms of platform & infrastructure cost). Integration with the sequencer and downstream medical middleware is the biggest opportunity.
The Analysis (value)
The bigger challenge on the analysis is the specific things being analyzed as mapped to the needs of the patient. We are still in a world where the vast majority of the sequencing work is being done in support of a specific patient with a specific disease. There isn’t even broad consensus yet in the scientific community about the basics of the pipeline (see my blog posthere for an attempt at capturing what I’m seeing in the market). A movement away from the recent trend in studying specific indications (esp. cancer) is called for. Broadening the sample population will allow us to pick simpler, clearer and easier pipelines which will then make them more adoptable. It would be a massive benefit to the world if the scientific, medical and regulatory communities would get together and start creating, in a crowdsourced manner, a small number of databases that are specifically useful to healthy people. Targeting things like nutrition, athletics, metabolism, and other normal aspects of daily life. A dataset that could, when any one person’s DNA is references, would find something useful. Including the regulators is key so that we can begin to move away from the old fashioned model of clearances that still permeate the industry.
The Regulators
Beyond the broader issues around education I referenced in my previous post, there is a massive upgrade in the regulation infrastructure that is needed. We still live in a world of fax machines, overnight shipping of paper documents and personal relationships all being more important than the quality of the science you as an innovator are bringing to bear.
Consider the recent massive growth in wearables, fitness trackers and other instrumentation local to the human body. Why must we treat clinical genetics simply as a diagnostic and not, as it should be, as a fundamental set of quantitative data about your body that you can leverage in a myriad of ways. Direct to consumer (DTC) genetics companies, most notably 23andme, have approached this problem poorly – instead of making it valuable to the average consumer, what they’ve done is attempted to straddle the line between medical and not. The Fitbit model has shown very clearly that lifestyle activities can be directly harnessed to build commercial value in scaling health related activities without becoming a regulatory issue. It’s time for genetics to do the same thing.
A few weeks back, we published a review about the development and role of the human reference genome. A key point of the reference genome is that it is not a single sequence. Instead it is an assembly of consensus sequences that are designed to deal with variation in the human population and uncertainty in the data. The reference is a map and like a geographical maps evolves though increased understanding over time.
From the Wiley On Line site:
Abstract
Genome maps, like geographical maps, need to be interpreted carefully. Although maps are essential to exploration and navigation they cannot be completely accurate. Humans have been mapping the world for several millennia, but genomes have been mapped and explored for just a single century with the greatest advancements in making a sequence reference map of the human genome possible in the past 30 years. After the deoxyribonucleic acid (DNA) sequence of the human genome was completed in 2003, the reference sequence underwent several improvements and today provides the underlying comparative resource for a multitude genetic assays and biochemical measurements. However, the ability to simplify genetic analysis through a single comprehensive map remains an elusive goal.
Key Concepts:
Maps are incomplete and contain errors.
DNA sequence data are interpreted through biochemical experiments or comparisons to other DNA sequences.
A reference genome sequence is a map that provides the essential coordinate system for annotating the functional regions of the genome and comparing differences between individuals’ genomes.
The reference genome sequence is always product of understanding at a set point in time and continues to evolve.
DNA sequences evolve through duplication and mutation and, as a result, contain many repeated sequences of different sizes, which complicates data analysis.
DNA sequence variation happens on large and small scales with respect to the lengths of the DNA differences to include single base changes, insertions, deletions, duplications and rearrangements.
DNA sequences within the human population undergo continual change and vary highly between individuals.
The current reference genome sequence is a collection of sequences, an assembly, that include sequences assembled into chromosomes, sequences that are part of structurally complex regions that cannot be assembled, patches (fixes) that cannot be included in the primary sequence, and high variability sequences that are organised into alternate loci.
Genetic analysis is error prone and the data require validation because the methods for collecting DNA sequences create artifacts and the reference sequence used for comparative analyses is incomplete.
Cells from most major human solid and hematologic malignancies exhibit abnormal cellular localization of a variety of oncogenic proteins, tumor suppressor proteins, and cell cycle regulators (Cronshaw et al. 2004, Falini et al 2006). For example, certain p53 mutations lead to localization in the cytoplasm rather than in the nucleus. This results in the loss of normal growth regulation, despite intact tumor suppressor function. In other tumors, wild-type p53 is sequestered in the cytoplasm or rapidly degraded, again leading to loss of its suppressor function. Restoration of appropriate nuclear localization of functional p53 protein can normalize some properties of neoplastic cells (Cai et al. 2008; Hoshino et al. 2008; Lain et al. 1999a; Lain et al. 1999b; Smart et al. 1999), can restore sensitivity of cancer cells to DNA damaging agents (Cai et al. 2008), and can lead to regression of established tumors (Sharpless & DePinho 2007, Xue et al. 2007). Similar data have been obtained for other tumor suppressor proteins such as forkhead (Turner and Sullivan 2008) and c-Abl (Vignari and Wang 2001). In addition, abnormal localization of several tumor suppressor and growth regulatory proteins may be involved in the pathogenesis of autoimmune diseases (Davis 2007, Nakahara 2009). CRMl inhibition may provide particularly interesting utility in familial cancer syndromes (e.g. , Li-Fraumeni Syndrome due to loss of one p53 allele,
BRCA1 or 2 cancer syndromes), where specific tumor suppressor proteins (TSP) are deleted or dysfunctional and where increasing TSP levels by systemic (or local) administration of CRMl inhibitors could help restore normal tumor suppressor function. Specific proteins and R As are carried into and out of the nucleus by specialized transport molecules, which are classified as importins if they transport molecules into the nucleus, and exportins if they transport molecules out of the nucleus (Terry et al. 2007;
Sorokin et al. 2007). Proteins that are transported into or out of the nucleus contain nuclear import/localization (NLS) or export (NES) sequences that allow them to interact with the relevant transporters. Chromosomal Region Maintenance 1 (Crml or CRM1), which is also called exportin-1 or Xpol, is a major exportin.
Overexpression of Crml has been reported in several tumors, including human ovarian cancer (Noske et al. 2008), cervical cancer (van der Watt et al. 2009), pancreatic cancer (Huang et al. 2009), hepatocellular carcinoma (Pascale et al. 2005) and osteosarcoma (Yao et al. 2009) and is independently correlated with poor clinical outcomes in these tumor types.
Inhibition of Crml blocks the exodus of tumor suppressor proteins and/or growth regulators such as p53, c-Abl, p21, p27, pRB, BRCA1, IkB, ICp27, E2F4, KLF5, YAP1, ZAP, KLF5, HDAC4, HDAC5 or forkhead proteins (e.g., FOX03a) from the nucleus that are associated with gene expression, cell proliferation, angiogenesis and epigenetics. Crml inhibitors have been shown to induce apoptosis in cancer cells even in the presence of activating oncogenic or growth stimulating signals, while sparing normal (untransformed) cells. Most studies of Crml inhibition have utilized the natural product Crml inhibitor Leptomycin B (LMB). LMB itself is highly toxic to neoplastic cells, but poorly tolerated with marked gastrointestinal toxicity in animals (Roberts et al. 1986) and humans (Newlands et al. 1996). Derivatization of LMB to improve drug-like properties leads to compounds that retain antitumor activity and are better tolerated in animal tumor models (Yang et al. 2007, Yang et al. 2008, Mutka et al. 2009). Therefore, nuclear export inhibitors could have beneficial effects in neoplastic and other proliferative disorders.
In addition to tumor suppressor proteins, Crml also exports several key proteins that are involved in many inflammatory processes. These include IkB, NF-kB, Cox-2, RXRa, Commdl, HIFl, HMGBl, FOXO, FOXP and others. The nuclear factor kappa B (NF-kB/rel) family of transcriptional activators, named for the discovery that it drives immunoglobulin kappa gene expression, regulate the mRNA expression of variety of genes involved in inflammation, proliferation, immunity and cell survival. Under basal conditions, a protein inhibitor of NF-kB, called IkB, binds to NF-kB in the nucleus and the complex IkB-NF-kB renders the NF-kB transcriptional function inactive. In response to inflammatory stimuli, IkB dissociates from the IkB-NF-kB complex, which releases NF-kB and unmasks its potent transcriptional activity. Many signals that activate NF-kB do so by targeting IkB for proteolysis (phosphorylation of IkB renders it “marked” for ubiquitination and then proteolysis). The nuclear IkBa-NF-kB complex can be exported to the cytoplasm by Crml where it dissociates and NF-kB can be reactivated. Ubiquitinated IkB may also dissociate from the NF-kB complex, restoring NF-kB transcriptional activity. Inhibition of Crml induced export in human neutrophils and macrophage like cells (U937) by LMB not only results in accumulation of transcriptionally inactive, nuclear IkBa-NF-kB complex but also prevents the initial activation of NF-kB even upon cell stimulation (Ghosh 2008, Huang 2000). In a different study, treatment with LMB inhibited IL-Ιβ induced NF-kB DNA binding (the first step in NF-kB transcriptional activation), IL-8 expression and intercellular adhesion molecule expression in pulmonary microvascular endothelial cells (Walsh 2008). COMMDl is another nuclear inhibitor of both NF-kB and hypoxia-inducible factor 1 (HIFl) transcriptional activity. Blocking the nuclear export of COMMDl by inhibiting Crml results in increased inhibition of NF-kB and HIFl transcriptional activity (Muller 2009).
Crml also mediates retinoid X receptor a (RXRa) transport. RXRa is highly expressed in the liver and plays a central role in regulating bile acid, cholesterol, fatty acid, steroid and xenobiotic metabolism and homeostasis. During liver inflammation, nuclear RXRa levels are significantly reduced, mainly due to inflammation-mediated nuclear export of RXRa by Crml . LMB is able to prevent IL-Ιβ induced cytoplasmic increase in RXRa levels in human liver derived cells (Zimmerman 2006).
The role of Crml -mediated nuclear export in NF-kB, HIF-1 and RXRa signalling suggests that blocking nuclear export can be potentially beneficial in many inflammatory processes across multiple tissues and organs including the vasculature (vasculitis, arteritis, polymyalgia rheumatic, atherosclerosis), dermatologic (see below), rheumatologic
(rheumatoid and related arthritis, psoriatic arthritis, spondyloarthropathies, crystal arthropathies, systemic lupus erythematosus, mixed connective tissue disease, myositis syndromes, dermatomyositis, inclusion body myositis, undifferentiated connective tissue disease, Sjogren’s syndrome, scleroderma and overlap syndromes, etc.).
CRM1 inhibition affects gene expression by inhibiting/activating a series of transcription factors like ICp27, E2F4, KLF5, YAP1, and ZAP.
Crml inhibition has potential therapeutic effects across many dermatologic syndromes including inflammatory dermatoses (atopy, allergic dermatitis, chemical dermatitis, psoriasis), sun-damage (ultraviolet (UV) damage), and infections. CRMl inhibition, best studied with LMB, showed minimal effects on normal keratinocytes, and exerted anti-inflammatory activity on keratinocytes subjected to UV, TNFa, or other inflammatory stimuli (Kobayashi & Shinkai 2005, Kannan & Jaiswal 2006). Crml inhibition also upregulates NRF2 (nuclear factor erythroid-related factor 2) activity, which protects keratinocytes (Schafer et al. 2010, Kannan & Jaiswal 2006) and other cell types (Wang et al. 2009) from oxidative damage. LMB induces apoptosis in keratinocytes infected with oncogenic human papillomavirus (HPV) strains such as HPV 16, but not in uninfected keratinocytes (Jolly et al. 2009).
Crml also mediates the transport of key neuroprotectant proteins that may be useful in neurodegenerative diseases including Parkinson’s disease (PD), Alzheimer’s disease, and amyotrophic lateral sclerosis (ALS). For example, by (1) forcing nuclear retention of key neuroprotective regulators such as NRF2 (Wang 2009), FOXA2 (Kittappa et al. 2007), parking in neuronal cells, and/or (2) inhibiting NFKB transcriptional activity by sequestering IKB to the nucleus in glial cells, Crml inhibition could slow or prevent neuronal cell death found in these disorders. There is also evidence linking abnormal glial cell proliferation to abnormalities in CRMl levels or CRMl function (Shen 2008).
Intact nuclear export, primarily mediated through CRMl, is also required for the intact maturation of many viruses. Viruses where nuclear export, and/or CRMl itself, has been implicated in their lifecycle include human immunodeficiency virus (HIV), adenovirus, simian retrovirus type 1, Borna disease virus, influenza (usual strains as well as H1N1 and avian H5N1 strains), hepatitis B (HBV) and C (HCV) viruses, human papillomavirus (HPV), respiratory syncytial virus (RSV), Dungee, Severe Acute Respiratory Syndrome coronavirus, yellow fever virus, West Nile virus, herpes simplex virus (HSV), cytomegalovirus (CMV), and Merkel cell polyomavirus (MCV). (Bhuvanakantham 2010, Cohen 2010, Whittaker 1998). It is anticipated that additional viral infections reliant on intact nuclear export will be uncovered in the future.
The HIV-1 Rev protein, which traffics through nucleolus and shuttles between the nucleus and cytoplasm, facilitates export of unspliced and singly spliced HIV transcripts containing Rev Response Elements (RRE) RNA by the CRMl export pathway. Inhibition of Rev-mediated RNA transport using CRMl inhibitors such as LMBor PKF050-638 can arrest the HIV-1 transcriptional process, inhibit the production of new HIV-1 virions, and thereby reduce HIV-1 levels (Pollard 1998, Daelemans 2002). Dengue virus (DENV) is the causative agent of the common arthropod-borne viral disease, Dengue fever (DF), and its more severe and potentially deadly Dengue hemorrhagic fever (DHF). DHF appears to be the result of an over exuberant inflammatory response to DENV. NS5 is the largest and most conserved protein of DENV. CRMl regulates the transport of NS5 from the nucleus to the cytoplasm, where most of the NS5 functions are mediated. Inhibition of CRMl -mediated export of NS5 results in altered kinetics of virus production and reduces induction of the inflammatory chemokine interleukin-8 (IL-8), presenting a new avenue for the treatment of diseases caused by DENV and other medically important flaviviruses including hepatitis C virus (Rawlinson 2009).
Other virus-encoded RNA-binding proteins that use CRMl to exit the nucleus include the HSV type 1 tegument protein (VP 13/14, or hUL47), human CMV protein pp65, the SARS Coronavirus ORF 3b Protein, and the RSV matrix (M) protein (Williams 2008, Sanchez 2007, Freundt 2009, Ghildyal 2009).
Interestingly, many of these viruses are associated with specific types of human cancer including hepatocellular carcinoma (HCC) due to chronic HBV or HCV infection, cervical cancer due to HPV, and Merkel cell carcinoma associated with MCV. CRMl inhibitors could therefore have beneficial effects on both the viral infectious process as well as on the process of neoplastic transformation due to these viruses.
CRMl controls the nuclear localization and therefore activity of multiple DNA metabolizing enzymes including histone deacetylases (HDAC), histone acetyltransferases (HAT), and histone methyltransferases (HMT). Suppression of cardiomyocyte hypertrophy with irreversible CRMl inhibitors has been demonstrated and is believed to be linked to nuclear retention (and activation) of HDAC 5, an enzyme known to suppress a hypertrophic genetic program (Monovich et al. 2009). Thus, CRMl inhibition may have beneficial effects in hypertrophic syndromes, including certain forms of congestive heart failure and hypertrophic cardiomyopathies.
I came across a few recent articles on the subject of US Patent Office guidance on patentability as well as on Supreme Court ruling on claims. I filed several patents on clinical laboratory methods early in my career upon the recommendation of my brother-in-law, now deceased. Years later, after both brother-in-law and patent attorney are no longer alive, I look back and ask what I have learned over $100,000 later, with many trips to the USPTO, opportunities not taken, and a one year provisional patent behind me.
My conclusion is
(1) that patents are for the protection of the innovator, who might realize legal protection, but the cost and the time investment can well exceed the cost of startup and building a small startup enterprize, that would be the next step.
(2) The other thing to consider is the capability of the lawyer or firm that represents you. A patent that is well done can be expected to take 5-7 years to go through with due diligence. I would not expect it to be done well by a university with many other competing demands. I might be wrong in this respect, as the climate has changed, and research universities have sprouted engines for change. Experienced and productive faculty are encouraged or allowed to form their own such entities.
(3) The emergence of Big Data, computational biology, and very large data warehouses for data use and integration has changed the landscape. The resources required for an individual to pursue research along these lines is quite beyond an individuals sole capacity to successfully pursue without outside funding. In addition, the changed designated requirement of first to publish has muddied the water.
Of course, one can propose without anything published in the public domain. That makes it possible for corporate entities to file thousands of patents, whether there is actual validation or not at the time of filing. It would be a quite trying experience for anyone to pursue in the USPTO without some litigation over ownership of patent rights. At this stage of of technology development, I have come to realize that the organization of research, peer review, and archiving of data is still at a stage where some of the best systems avalailable for storing and accessing data still comes considerably short of what is needed for the most complex tasks, even though improvements have come at an exponential pace.
I shall not comment on the contested views held by physicists, chemists, biologists, and economists over the completeness of guiding theories strongly held. Only history will tell. Beliefs can hold a strong sway, and have many times held us back.
I am not an expert on legal matters, but it is incomprehensible to me that issues concerning technology innovation can be adjudicated in the Supreme Court, as has occurred in recent years. I have postgraduate degrees in Medicine, Developmental Anatomy, and post-medical training in pathology and laboratory medicine, as well as experience in analytical and research biochemistry. It is beyond the competencies expected for these type of cases to come before the Supreme Court, or even to the Federal District Courts, as we see with increasing frequency, as this has occurred with respect to the development and application of the human genome.
I’m not sure that the developments can be resolved for the public good without a more full development of an open-access system of publishing. Now I present some recent publication about, or published by the USPTO.
DR ANTHONY MELVIN CRASTO
Dr. Melvin Castro – Organic Chemistry and New Drug Development
YOU ARE FOLLOWING THIS BLOG You are following this blog, along with 1,014 other amazing people (manage).
USPTO Guidance On Patentable Subject Matter: Impediment to Biotech Innovation
Joanna T. Brougher, David A. FazzolareJ Commercial Biotechnology 2014 20(3):Brougher
jcbiotech-patents
Abstract In June 2013, the U.S. Supreme Court issued a unanimous decision upending more than three decades worth of established patent practice when it ruled that isolated gene sequences are no longer patentable subject matter under 35 U.S.C. Section 101.While many practitioners in the field believed that the USPTO would interpret the decision narrowly, the USPTO actually expanded the scope of the decision when it issued its guidelines for determining whether an invention satisfies Section 101.
The guidelines were met with intense backlash with many arguing that they unnecessarily expanded the scope of the Supreme Court cases in a way that could unduly restrict the scope of patentable subject matter, weaken the U.S. patent system, and create a disincentive to innovation. By undermining patentable subject matter in this way, the guidelines may end up harming not only the companies that patent medical innovations, but also the patients who need medical care. This article examines the guidelines and their impact on various technologies.
35 U.S.C. Section 101 states “Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
” Prometheus Laboratories, Inc. v. Mayo Collaborative Services, 566 U.S. ___ (2012)
Association for Molecular Pathology et al., v. Myriad Genetics, Inc., 569 U.S. ___ (2013).
Parke-Davis & Co. v. H.K. Mulford Co., 189 F. 95, 103 (C.C.S.D.N.Y. 1911)
USPTO. Guidance For Determining Subject Matter Eligibility Of Claims Reciting Or Involving Laws of Nature, Natural Phenomena, & Natural Products.
A 2013 Supreme Court decision that barred human gene patents is scrambling patenting policies.
PHOTO: MLADEN ANTONOV/AFP/GETTY IMAGES
A year after the U.S. Supreme Court issued a landmark ruling that human genes cannot be patented, the biotech industry is struggling to adapt to a landscape in which inventions derived from nature are increasingly hard to patent. It is also pushing back against follow-on policies proposed by the U.S. Patent and Trademark Office (USPTO) to guide examiners deciding whether an invention is too close to a natural product to deserve patent protection. Those policies reach far beyond what the high court intended, biotech representatives say.
“Everything we took for granted a few years ago is now changing, and it’s generating a bit of a scramble,” says patent attorney Damian Kotsis of Harness Dickey in Troy, Michigan, one of more than 15,000 people who gathered here last week for the Biotechnology Industry Organization’s (BIO’s) International Convention.
At the meeting, attorneys and executives fretted over the fate of patent applications for inventions involving naturally occurring products—including chemical compounds, antibodies, seeds, and vaccines—and traded stories of recent, unexpected rejections by USPTO. Industry leaders warned that the uncertainty could chill efforts to commercialize scientific discoveries made at universities and companies. Some plan to appeal the rejections in federal court.
USPTO officials, meanwhile, implored attendees to send them suggestions on how to clarify and improve its new policies on patenting natural products, and even announced that they were extending the deadline for public comment by a month. “Each and every one of you in this room has a moral duty … to provide written comments to the PTO,” patent lawyer and former USPTO Deputy Director Teresa Stanek Rea told one audience.
At the heart of the shake-up are two Supreme Court decisions: the ruling last year in Association for Molecular Pathology v. Myriad Genetics Inc. that human genes cannot be patented because they occur naturally (Science, 21 June 2013, p. 1387); and the 2012 Mayo v. Prometheus decision, which invalidated a patent on a method of measuring blood metabolites to determine drug doses because it relied on a “law of nature” (Science, 12 July 2013, p. 137).
Myriad and Mayo are already having a noticeable impact on patent decisions, according to a study released here. It examined about 1000 patent applications that included claims linked to natural products or laws of nature that USPTO reviewed between April 2011 and March 2014. Overall, examiners rejected about 40%; Myriad was the basis for rejecting about 23% of the applications, and Mayo about 35%, with some overlap, the authors concluded. That rejection rate would have been in the single digits just 5 years ago, asserted Hans Sauer, BIO’s intellectual property counsel, at a press conference. (There are no historical numbers for comparison.) The study was conducted by the news service Bloomberg BNA and the law firm Robins, Kaplan, Miller & Ciseri in Minneapolis, Minnesota.
USPTO is extending the decisions far beyond diagnostics and DNA?
The numbers suggest USPTO is extending the decisions far beyond diagnostics and DNA, attorneys say. Harness Dickey’s Kotsis, for example, says a client recently tried to patent a plant extract with therapeutic properties; it was different from anything in nature, Kotsis argued, because the inventor had altered the relative concentrations of key compounds to enhance its effect. Nope, decided USPTO, too close to nature.
In March, USPTO released draft guidance designed to help its examiners decide such questions, setting out 12 factors for them to weigh. For example, if an examiner deems a product “markedly different in structure” from anything in nature, that counts in its favor. But if it has a “high level of generality,” it gets dinged.
The draft has drawn extensive criticism. “I don’t think I’ve ever seen anything as complicated as this,” says Kevin Bastian, a patent attorney at Kilpatrick Townsend & Stockton in San Francisco, California. “I just can’t believe that this will be the standard.”
USPTO officials appear eager to fine-tune the draft guidance, but patent experts fear the Supreme Court decisions have made it hard to draw clear lines. “The Myriad decision is hopelessly contradictory and completely incoherent,” says Dan Burk, a law professor at the University of California, Irvine. “We know you can’t patent genetic sequences,” he adds, but “we don’t really know why.”
Get creative in using Draft Guidelines!
For now, Kostis says, applicants will have to get creative to reduce the chance of rejection. Rather than claim protection for a plant extract itself, for instance, an inventor could instead patent the steps for using it to treat patients. Other biotech attorneys may try to narrow their patent claims. But there’s a downside to that strategy, they note: Narrower patents can be harder to protect from infringement, making them less attractive to investors. Others plan to wait out the storm, predicting USPTO will ultimately rethink its guidance and ease the way for new patents.
Public comment period extended
USPTO has extended the deadline for public comment to 31 July, with no schedule for issuing final language. Regardless of the outcome, however, Stanek Rea warned a crowd of riled-up attorneys that, in the world of biopatents, “the easy days are gone.”
Manual of Patent Examining Procedure (MPEP)Ninth Edition, March 2014
The USPTO continues to offer an online discussion tool for commenting on selected chapters of the Manual. To participate in the discussion and to contribute your ideas go to: http://uspto-mpep.ideascale.com.
Manual of Patent Examining Procedure (MPEP)Ninth Edition, March 2014
The USPTO continues to offer an online discussion tool for commenting on selected chapters of the Manual. To participate in the discussion and to contribute your ideas go to:http://uspto-mpep.ideascale.com.
The documents updated in the Ninth Edition of the MPEP, dated March 2014, include changes that became effective in November 2013 or earlier.
All of the documents have been updated for the Ninth Edition except Chapters 800, 900, 1000, 1300, 1700, 1800, 1900, 2000, 2300, 2400, 2500, and Appendix P.
More information about the changes and updates is available from the “Blue Page – Introduction” of the Searchable MPEP or from the “Summary of Changes” link to the HTML and PDF versions provided below. Discuss the Manual of Patent Examining Procedure (MPEP) Welcome to the MPEP discussion tool!
We have received many thoughtful ideas on Chapters 100-600 and 1800 of the MPEP as well as on how to improve the discussion site. Each and every idea submitted by you, the participants in this conversation, has been carefully reviewed by the Office, and many of these ideas have been implemented in the August 2012 revision of the MPEP and many will be implemented in future revisions of the MPEP. The August 2012 revision is the first version provided to the public in a web based searchable format. The new search tool is available at http://mpep.uspto.gov. We would like to thank everyone for participating in the discussion of the MPEP.
We have some great news! Chapters 1300, 1500, 1600 and 2400 of the MPEP are now available for discussion. Please submit any ideas and comments you may have on these chapters. Also, don’t forget to vote on ideas and comments submitted by other users. As before, our editorial staff will periodically be posting proposed new material for you to respond to, and in some cases will post responses to some of the submitted ideas and comments.Recently, we have received several comments concerning the Leahy-Smith America Invents Act (AIA). Please note that comments regarding the implementation of the AIA should be submitted to the USPTO via email t aia_implementation@uspto.gov or via postal mail, as indicated at the America Invents Act Web site. Additional information regarding the AIA is available at www.uspto.gov/americainventsact We have also received several comments suggesting policy changes which have been routed to the appropriate offices for consideration. We really appreciate your thinking and recommendations!
After more than 5 years and two draft versions, the final version of the Guidance for
Industry (GfI) – “Electronic Source Data in Clinical Investigations” was published in
September 2013. This new FDA Guidance defines the FDA’s expectations for sponsors,
CROs, investigators and other persons involved in the capture, review and retention of
electronic source data generated in the context of FDA-regulated clinical trials.In an
effort to encourage the modernization and increased efficiency of processes in clinical
trials, the FDA clearly supports the capture of electronic source data and emphasizes
the agency’s intention to support activities aimed at ensuring the reliability, quality,
integrity and traceability of this source data, from its electronic source to the electronic
submission of the data in the context of an authorization procedure. The Guidance
addresses aspects as data capture, data review and record retention. When the
computerized systems used in clinical trials are described, the FDA recommends
that the description not only focus on the intended use of the system, but also on
data protection measures and the flow of data across system components and
interfaces. In practice, the pharmaceutical industry needs to meet significant
requirements regarding organisation, planning, specification and verification of
computerized systems in the field of clinical trials. The FDA also mentions in the
Guidance that it does not intend to apply 21 CFR Part 11 to electronic health records
(EHR). Author: Oliver Herrmann Q-Infiity Source: http://www.fda.gov/downloads/Drugs/GuidanceComplianceRegulatoryInformation/
Guidances/UCM328691.pdf Webinar: https://collaboration.fda.gov/p89r92dh8wc
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
2012pharmaceutical
sjwilliamspa
Sohan