Abstract LB395: NetraAI-driven discovery of novel biomarkers in MSI-high colon cancer for precision immunotherapy
Bibliographic record
Abstract
Abstract By leveraging NetraAI, a novel machine learning (ML) approach, we identify potential biomarkers in microsatellite instability-high (MSI-H) colon cancer. MSI, marked by DNA mismatch repair (MMR) defects characterizes 5-20% of colorectal cancers (CRCs). MSI-H tumors harbor higher mutational burdens, produce neoantigens, and enhance immune recognition and responsiveness to immunotherapy. The innovative Sub-Insight Learning approach of NetraAI, allows us to overcome challenges associated with smaller data sets not reflecting the totality of the disease they represent. This approach utilizes a set of validated mathematical methods to identify sub-insights about patients even from small data sets. This allows the system to decompose the data sets into high and low confidence patient subpopulations, enhancing predictive model accuracy and reducing overfitting. Further, the system explains what variables are driving the etiology defining the subpopulations of patients. Utilizing a small data set consisting of 141 RNA expression profiles of CRC samples (E-GEOD-41258) with MSI-H and MSI-low colon cancer, we were able to derive several unique insights into patients’ molecular profiles. NetraAI analysis identified several unique variables, including CATSPERB, FUT8, PLLP, DUSP4, and MLPH that may play significant roles in MSI-H colon cancer pathology. These markers hold potential for personalizing clinical trials as well as potential therapeutic targets. Furthermore, protein-protein interaction (PPI) networks revealed co-expression and co-localizations that exist amongst these genes, suggesting a complex interplay among these genes, particularly in the context of spermatogenesis. The application of NetraAI and its Sub-Insight Learning paradigm has revealed novel insights into the molecular profile of MSI-H colon cancer. These findings pave the way for more targeted and effective precision immunotherapy strategies, demonstrating the power of AI in advancing the understanding and treatment of complex cancers. Citation Format: Bessi Qorri, Mike J. Tsay, Paul Leonchyk, Larry Alphs, Luca Pani, Joseph Geraci. NetraAI-driven discovery of novel biomarkers in MSI-high colon cancer for precision immunotherapy [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB395.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".