Target 2035 Fellow (Postdoctoral Researcher): The Hospital for Sick Children (SickKids) and the Structural Genomics Consortium (SGC) are seeking a highly motivated Post-Doctoral Fellow to advance machine learning methodologies for predicting small-molecule binding affinities. This multi-year project, part of the Target 2035 initiative, will tackle the challenges of data scarcity in drug discovery.
Target 2035 Fellow (Postdoctoral Researcher – Machine Learning for Drug Discovery)
Designation:
Postdoctoral Researcher
Location:
Toronto, Ontario, Canada
(Split between The Hospital for Sick Children and the Structural Genomics Consortium)
Research Area:
Machine Learning for Drug Discovery
Eligibility/Qualification:
- Education: PhD in Computational Chemistry, Computer Science, Bioinformatics, or a related field.
- Technical Expertise: Strong background in representation learning, foundation models, and multi-fidelity optimization.
- Domain Knowledge: Familiarity with physics-based molecular modeling (e.g., FEP).
- Skills: Experience with large-scale ML training and handling noisy experimental data (like DEL).
Job Description:
Core Objectives:
- Develop multi-fidelity binding affinity prediction pipelines.
- Create novel foundation ML models using DNA-encoded library (DEL) and affinity selection mass spectrometry (ASMS) data.
Role Responsibilities:
- Benchmark existing models (e.g., Boltz-2, AQAffinity, Uni-Mol) for binding affinity prediction.
- Develop fine-tuning strategies for DEL/ASMS datasets.
- Implement iterative workflows where ML predictions guide compound selection for optimization.
- Produce at least two peer-reviewed publications.
- Assemble an open-source computational library integrating ML models and optimization components.
How to Apply:
Interested candidates can apply through the SickKids career page: Apply Here
Last Date for Apply:
Until position filled
For more information and ongoing updates, please visit the SickKids and SGC websites.
