An FDA Artificial Intelligence (AI) Program for Toxicology
Weida Tong, Ph.D., Director, Division of Bioinformatics and Biostatistics
AI4TOX is a program that aims to apply the most advanced AI methods to develop new tools to support FDA regulatory science and strengthen the safety review of FDA-regulated products. The program consists of 4 initiatives:
AnimalGAN: To predict animal toxicology data for untested chemicals through learning models that leverage existing animal data in support of the 3Rs approach (replace, reduce, and/or refine animal studies) in the safety evaluation of FDA-regulated products.
SafetAI: To develop novel deep learning methods for toxicological endpoints that are critical to the safety review of drug candidates before entering clinical trials.
BERTox: To develop the most advanced AI-powered Natural Language Processing (NLP) to facilitate analysis of FDA documents and public literature for improved efficiency and accuracy of information retrieval and toxicity assessment.
PathologAI: To develop an effective and accurate framework for analysis of histopathological data from animal studies to facilitate digital pathology in preclinical application.