MétaCan
Menu
Back to cohort

Abstract A018: Accelerating drug discovery at an HBCU with AI/ML: Text mining, computational modeling, and drug repurposing approaches

2025· article· en· W4412163772 on OpenAlexaboutno aff
Kevin P. Williams, Xiaojia Ji, Michael Tarpley, Weifan Zheng

Bibliographic record

VenueClinical Cancer Research · 2025
Typearticle
Languageen
FieldBiochemistry, Genetics and Molecular Biology
TopicBiomedical Text Mining and Ontologies
Canadian institutionsnot available
Fundersnot available
KeywordsDrug repositioningDrugRepurposingDrug discoveryComputer scienceMedicinePharmacologyBioinformaticsEngineeringBiology

Abstract

fetched live from OpenAlex

Abstract Advances in artificial intelligence (AI) and machine learning (ML) are transforming drug discovery by significantly reducing time and costs. This abstract highlights the AI/ML approaches employed in our lab at North Carolina Central University (NCCU), a Historically Black College and University (HBCU), to support drug repurposing efforts. Using Literature-Wide Association Studies (LWAS), a text-mining method, we analyzed over three million biomedical abstracts and identified 24 potential drugs as candidates for repurposing to treat inflammatory breast cancer (IBC), a rare and understudied disease. We also applied gene reversal rate (GRR) analysis—a computational approach that identifies drugs capable of reversing disease-associated gene expression profiles toward normal. By integrating disease gene expression profiles with drug-induced data from the Library of Integrated Network-based Cellular Signatures (LINCS), we predicted 19 additional candidate drugs for IBC. Currently, we are advancing our text-mining efforts by combining BioWordVec embeddings with LWAS to further expand our list of repurposing candidates for IBC. In parallel, we are utilizing the AIDDISON platform—an AI-driven tool that integrates generative AI, ML, and computer-aided drug design—to identify small-molecule inhibitors. Through similarity searches and molecular docking, we have discovered 23 potential inhibitors of the Hedgehog pathway transcription factor GLI1. Additionally, we employ artificial neural network (ANN) models for ligand discovery. These models were trained on more than 40,000 ligand–target pairs, incorporating IC50 and Ki values from BindingDB. The models link compound SMILES representations with target protein sequences to predict small molecules that may inhibit GLI1, a therapeutic target in several cancers. By leveraging AI/ML techniques, including LWAS, GRR, AIDDISON, and ANN, we aim to develop efficient, cost-effective, and rapid solutions for drug repurposing. These efforts support the discovery of new treatment options for rare diseases such as IBC and provide cutting-edge research and training opportunities for students and researchers at NCCU. Citation Format: Kevin P. Williams, Xiaojia Ji, Esraa Salim, Michael Tarpley, Weifan Zheng. Accelerating drug discovery at an HBCU with AI/ML: Text mining, computational modeling, and drug repurposing approaches [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 A018.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.597
Threshold uncertainty score0.541

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.226
GPT teacher head0.474
Teacher spread0.248 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreEmpirical

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 ResearchSame topicBiomedical Text Mining and OntologiesFrench-language works237,207