Linkedin

Become a Member >

CrossTALK: Cross-Training in AI and Laboratory Knowledge for Drug Discovery

As part of the Emerging Data Science program, the Data Sciences Institute is launching the CrossTALK: Cross-Training in AI and Laboratory Knowledge for Drug Discovery.

Open to University of Toronto and research funding partner students, postdoctoral fellows and staff with a computer or biological sciences background, CrossTALK is an opportunity to work alongside peers from complementary disciplines. The free 9-week bootcamp will run from February to April, in person at the DSI and in research labs.

Join us for the launch on January 31, 2025
3:30p.m.
Welcome
Matthieu Schapira, Professor, Department of Pharmacology and Toxicology, Temerty Faculty of Medicine, University of Toronto PI, Structural Genomics Consortium
3:40p.m.
Intro to Machine Learning
Dr. Benjamin Sanchez-Lengeling, Assistant Professor, Department of Chemical Engineering and Applied Chemistry, Faculty of Applied Science & Engineering, University of Toronto, and Vector Institute
4:20p.m.
Intro to experimental data generation and testing of predictions
Rachel J. Harding, Assistant Professor, Leslie Dan Faculty of Pharmacy, University of Toronto and Principal Investigator Structural Genomics Consortium
4:40p.m.
Reception
 
Workshop Sessions [approximately 21 hours] February-April, 2025:
  • Week 1-3 [3 hours]: Screening chemical libraries in the lab to generate training data for machine learning
  • Week 4-6 [15 hours]: Building machine learning models and predicting drug candidates
  • Week 7-9 [3 hours]: Testing predicted molecules in the lab in partnership with the Structural Genomics Consortium (SGC)

    • Launch
    January 31, 2025
    10th floor, 700 University Avenue, Toronto 
    Register

    Bootcamp
    Apply by
    January 12, 2025
    tinyurl.com/crosstalk-apply

    Most successful teams will be invited to prospectively predict unknown hits.
    Predicted compounds will be purchased and validated in the lab!

    Train

    Trainees are offered practical
    bootcamps to learn how experimental data are generated and how machine learning models are trained to predict bioactive molecules     

     

    Challenge

    Teams of students with computational and experimental backgrounds are given a dataset with which to develop a method to retrieve known but hidden target hits

    Co-Leads

    Matthieu Schapira

    Professor, Department of Pharmacology and Toxicology, Temerty Faculty of Medicine, University of Toronto PI, Structural Genomics Consortium

    Rachel Harding

    Assistant Professor, Department of Pharmacology and Toxicology, Temerty Faculty of Medicine, University of Toronto PI, Structural Genomics Consortium

    Mohamed Moosavi

    Assistant Professor, Department of Chemical Engineering & Applied Science, Faculty of Engineering, University of Toronto

    Chris Maddison

    Assistant Professor, Department of Computer Science and Deptartment of Statistical Sciences, Faculty of Arts & Science, University of Toronto Faculty Member, Vector Institute

    Hui Peng

    Associate Professor, Department of Chemistry, Faculty of Arts & Science, University of Toronto