Artificial General Intelligence Is the Boost for The Drug Development

Drug discovery is a systematic scientific process that aims to identify, design, and develop novel therapeutic agents to cure, ameliorate or prevent diseases and medical conditions. The process is, in fact, iterative in nature, multi-faceted, and complex, integration of the multiome datasets includes genome, transcriptome (including single-cell transcriptomics), proteome, metabolome, phenome, radiome, and the human interactome.

Statistical systems and computational models are too weak to associate all these data and difficult to find causal mechanisms. Also, convenient AI-systems are not able to create new usable knowledge out of the collected material.

In contrary to “normal” AI, with few neural networks, limited deep learning methods, small datasets, isolated analysis and constant human intervention, AGI (Artificial General Intelligence) with thousands of neural networks and huge datasets can autonomously connect all stages of drug development and automatically solve the problems like a human does. AGI could change the whole market in the pharmaceutical industry.

In this talk, I will cover foundation models in molecular biology, medicine and drug discovery applications, generative AI applications across the entire drug discovery pipeline—from target identification to lead optimization, LLM as a new coding language for multi-modal analysis, AGI agent for automating many of the tedious and labor-intensive activities associated with drug development, digital twins for combining vast amounts of data about the workings of genes, proteins, cells and whole-body systems with patients’ personal data to create virtual models of cells, organs, brain – and eventually, potentially their entire body, developing selective state space models and control strategies for identifying interventions that maintain or restore a person’s health based on their individual biology, and graphical learning and causal inference for drug repurposing. I hope that that this talk will stimulate discussion and applications of AGI to drug development.

About

Momiao Xiong, is a professor in the Department of Biostatistics and Data Science, University of Texas School of Public Health, and a regular member in the Genetics & Epigenetics (G&E) Graduate Program at The University of Texas MD Anderson Cancer Center, UTHealth Graduate School of Biomedical Science. His interests are artificial intelligence, causal inference, bioinformatics and genomics.