Discovery and Basic Research
Tudor Oprea, MD, PhD
CEO
Expert Systems Inc
San Diego, California
Sudip Das, PhD (he/him/his)
Professor of Pharmaceutics & Drug Delivery
Butler University, College of Pharmacy & Health Sciences
Indianapolis, Indiana
In the rapidly evolving drug discovery and repurposing field, leveraging cutting-edge machine learning (ML) and artificial intelligence (AI) tools is critical for simultaneously optimizing multiple properties. Both early drug discovery and drug repurposing share a series of complex, multi-property optimization challenges. To accelerate this process, an integrated computational and experimental suite of tools that can work synergistically and provide mutually informative insights is needed.
Our research integrates large language models (LLMs) with state-of-the-art ML techniques to enhance drug discovery anr repurposing. Specifically, we have explored the potential of multitask models, which have recently demonstrated significant promise in predicting multiple drug-related properties. Recently, we combined multitask models with Combinatorial Fusion Analysis (CFA), a technique that aggregates and refines predictive outputs to improve accuracy and robustness.
Our investigation into integrating these methodologies has yielded promising results, suggesting that the combined LLM / ML approach could offer a powerful new platform, suitable for optimizing drug candidates across multiple parameters and for addressing novel approved drug-disease combinations. This presentation will discuss our platform, with case studies in oncology target identification and drug repurposing evaluation.