This interactive and hands on workshop will provide a set of tools to tools to improve discovery and decision making for well-specified questions with abundant, high-quality data. Featuring 2 case studies from Pfizer and Deep Biologics, we will detail how to apply machine learning in all stages of drug discovery including target validation, identification of prognostic biomarkers and analysis of digital pathology data in clinical trials; and antibody optimization. Here we will explore and solve challenges including lack of interpretability and repeatability of ML-generated results to prevent application limit.

Case Study A: Applications of Machine Learning for Antibody Optimization

The following subtopics will be covered:

• Applications of machine learning for predicting antigen specificity from massively diverse libraries
• Filtering of the identified leads for viscosity, clearance, solubility and immunogenicity
• Experimental validation of the in silico optimized hits and testing whether they retain specificity

In the second half of this workshop, Peter from Pfizer will lead a discussion around:

• Tools to improve discovery and decision making
• Machine learning applications in all stages of drug discovery
• Solving challenges in lack of interoperability and repeatability