SC10: Applications of Artificial Intelligence & Machine Learning in Drug Discovery & Development
TUESDAY, SEPTEMBER 25, 6:00 - 8:30 PM
Room: Gardner 

This course aims to educate a diverse group of scientists-chemists, biologists, toxicologists, and those involved in translational and clinical research, about the growing use and applications of AI & ML. Talks start with explaining the basic terminology used and what it means, followed by discussions separating the hope from the hype. It goes into the caveats and limitations in AI and ML, while exploring ways in which it can be successfully applied in the drug discovery and development pipeline. There will be experts from various areas presenting case studies on how they have used AI/ML tools for lead optimization, target discovery, visualizing and classifying large datasets, patient stratification and more.

AI/ML Basics: What A Discovery Scientist Can Gain from Knowing

Arvind Rao, PhD, Assistant Professor, Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center

• AI/ML paradigms and applications: finding patterns in data, PCA, clustering, classification
• Modeling and predictions: regression and classification
• Understanding the caveats and limitations in AI/ML: interpretability, training-test equivalence

Data-driven Target discovery Using Relational Machine Learning

Jin Yao, PhD, Scientific Investigator, Computational Biology and Statistics, Target Sciences, GSK

• Introduction to statistical relational machine learning (SRML)
• Application of SRML on biological knowledge discovery and drug target identification

Machine Learning and AI on Electronic Health Records

Nicholas P. Tatonetti, PhD, Herbert Irving Assistant Professor of Biomedical Informatics and Director of Clinical Informatics

Herbert Irving Comprehensive Cancer Center, Columbia University

• Why ML/AI in health care data will never work; bias, missingness, and confounding in secondary data use
• Why ML/AI is our only hope to solve healthcare’s biggest problems; the power of scale, the complexity of medicine, and where the opportunities lie/li>

Instructor Biographies:

Arvind Rao, PhD, Associate Professor, Department of Computational Medicine and Bioinformatics, University of Michigan

Arvind Rao was until recently an Assistant Professor in the Department of Bioinformatics and Computational Biology at the UT MD Anderson Cancer Center since 2011. Prior to joining MD Anderson, he was a Lane Postdoctoral Fellow at Carnegie Mellon University, specializing in bioimage informatics. Arvind received his PhD in Electrical Engineering and Bioinformatics from the University of Michigan, specializing in transcriptional genomics. At MD Anderson, Arvind is working on using image analysis and machine learning methods to link image-derived phenotypes with genetic data, across biological scale (i.e. single cell, tissue and radiology data).

Jin Yao, PhD, Scientific Investigator, Computational Biology and Statistics, Target Sciences, GSK

Jin Yao is a Scientific Investigator in the group of Computational Biology at GlaxoSmithKline. Before joining GSK, he worked as a Postdoctoral Research Associate in the University of Buffalo Medical School where he studied the initiation of breast cancer using next-generation sequencing techniques. Jin Yao obtained his PhD in Electrical and Computer Engineering from the University of Florida, where his research focused on applying advanced computational methods to solve biological problems in cancer and microbial ecology. During his PhD, he developed a pipeline for 16s rRNA sequence analysis and completed his thesis on using machine learning techniques to model breast cancer progression. His research interests are developing and applying machine learning techniques for large-scale genetic and genomic data to understand human disease for personalized medicine.

Nicholas P. Tatonetti, PhD, Herbert Irving Assistant Professor of Biomedical Informatics and Director of Clinical Informatics, Herbert Irving Comprehensive Cancer Center, Columbia University

Dr. Nicholas Tatonetti is assistant professor of biomedical informatics in the Departments of Biomedical Informatics, Systems Biology, and Medicine and is Director of Clinical Informatics at the Institute for Genomic Medicine at Columbia University. He received his PhD from Stanford University where he focused on the development of novel statistical and computational methods for observational data mining. He applied these methods to drug safety surveillance and the discovery of dangerous drug-drug interactions. His lab at Columbia is focused on expanding upon his previous work in detecting, explaining, and validating drug effects and drug interactions from large-scale observational data. Widely published in both clinical and bioinformatics, Dr. Tatonetti is passionate about the integration of hospital data (stored in the electronic health records) and high-dimensional biological data (captured using next-generation sequencing, high-throughput screening, and other "omics" technologies).