MétaCan
Menu
← Back to cohort

Abstract A019: A fully transparent and automatable form of AI for biomarker and new target discovery using diverse multi-omics data

2025· article· en· W4412163815 on OpenAlexaboutno aff
Jedidiah Gaetz, Timothy R. Wall, Eleni S. Stylianou, Ehab M. Khalil, Oren Levy, Douglas W. Selinger

Bibliographic record

VenueClinical Cancer Research · 2025
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicBioinformatics and Genomic Networks
Canadian institutionsnot available
Fundersnot available
KeywordsBiomarkerBiomarker discoveryComputational biologyOmicsComputer scienceBioinformaticsMedicineBiologyProteomicsGeneticsGene

Abstract

fetched live from OpenAlex

Abstract Modern chemical biology and multi-omics approaches capture far more data than can be digested in human readable form, creating an opportunity for machine-based methods to significantly expand the boundaries of scientific knowledge. Artificial intelligence (AI) methods promise to fill this gap, however significant challenges remain to adapt machine learning (ML) based approaches to data that is noisy, complex, and bespoke while still preserving the transparency required for scientific and regulatory decision making. Herein we describe a novel approach combining knowledge graphs and centrality algorithms, allowing the construction of systems that are scalable, robust to noise, concise, and perhaps most importantly, highly transparent. The central construct, which we have termed a “focal graph”, can seamlessly integrate information across multiple, diverse, complex data sets, including large-scale chemical biology and multi-omics data. Focal graphs can be combined with agentic large language models (LLMs) as part of retrieval-augmented generation (RAG) strategies to build intelligent, autonomous workflows for discovery of new targets, biomarkers, and combination treatment strategies. Importantly, unlike ML methods, our focal graph approach preserves the provenance of the underlying experimental data, allowing the processes and conclusions to be examined and evaluated in tremendous detail by human or machine-based methods. Using focal graphs combined with agentic LLMs and workflow automation, we can plan and execute research programs that lead to the discovery of entirely novel biological insights, including new potential biomarkers, original drug targets, drug repurposing strategies, and combination therapy hypotheses. Here we present the theoretical underpinnings of focal graphs and their automation, as well as sharing selected findings related to novel disease therapeutic and biomarker strategies. These results derive their support from multiple, diverse, large-scale experimental data sets, with full transparency with respect to the experimental basis of the discoveries. As these autonomous systems become more sophisticated and are given access to more data and computational power, they can be expected to generate insights with increasing levels of novelty and experimental support. More information is available at www.plexresearch.com. Citation Format: Jedidiah Gaetz, Timothy R. Wall, Eleni S. Stylianou, Ehab Khalil, Oren Levy, Douglas W. Selinger. A fully transparent and automatable form of AI for biomarker and new target discovery using diverse multi-omics data [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Artificial Intelligence and Machine Learning; 2025 Jul 10-12; Montreal, QC, Canada. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(13_Suppl):Abstract nr A019.

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 imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.006
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.009
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0010.003
Scholarly communication0.0030.004
Open science0.0020.004
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0060.002

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.

Opus teacher head0.370
GPT teacher head0.526
Teacher spread0.156 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueClinical Cancer Research→Same topicBioinformatics and Genomic Networks→French-language works237,207→