AI in Drug Development, Presented by the ATOM Consortium

Topic: Building data-driven small molecule property prediction models with AMPL

This talk introduces basic concepts in building small molecule property prediction using machine learning models trained on data collected from experimental assays. Practical challenges are considered, starting with limitations in data collection and curation through to model selection for property prediction applications.

This talk uses the ATOM (Accelerating Therapeutics for Opportunities in Medicine) Modeling PipeLine (AMPL) to provide concrete examples for building models and data visualization.