Abstract A018: Accelerating drug discovery at an HBCU with AI/ML: Text mining, computational modeling, and drug repurposing approaches
Bibliographic record
Abstract
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
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 teacher head, 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".