While data science is driving breakthroughs in countless areas, the lack of availability of experimental training data has limited its impact on drug discovery.

As the Structural Genomics Consortium launches a large-scale initiative to generate experimental screening data to train ML models, the Galvanizing Data Science Applications in Early Stage Drug Discovery, a Data Sciences Institute Emergent Data Science Program, will offer quarterly workshops on data science for hit-finding that include interactive sessions and lab visits where data scientists will learn about data generation and experimentalists will learn about data analysis.

Led by Pr. Matthieu Schapira, the program will include workshops to explain the chemical library screening process and associated data, followed by challenges modelled after Cache Challenges in which participants use their machine learning models to retrospectively retrieve blinded hits. Successful participants will be invited to prospectively predict novel molecules from commercial catalogs for disease-associated proteins that will be tested experimentally and published. The aim is for one or more start-up(s) to emerge from among the most successful and entrepreneurial participants.

The goal of this training program is to lead to the development of innovative data science methodologies in early-stage drug discovery at University of Toronto and beyond.

It will build necessary bridges between data scientists and drug discovery experimentalists, two communities that typically do not speak the same language.

If you are interested, please contact matthieu.schapira@utoronto.ca