Mentored Research ProjectsRepresentative program

Machine Learning and Molecular Docking for Kinase Inhibitor Discovery

Explore a reproducible computational drug-design workflow using protein structures, docking, and introductory machine learning.

Overview

This computational practicum examines how structural information and data-driven methods can inform hypotheses about molecular interactions. Learners document data sources, compare docking and modeling outputs, and discuss uncertainty. Computational rankings are research hypotheses, not validated evidence of clinical efficacy or safety.

Learning goals and possible work

Proposed learning outcomes for this program example:

  • Explain the data and structural assumptions behind a computational workflow.
  • Conduct and document a small computational comparison.
  • Interpret candidate rankings cautiously and identify validation needs.

Illustrative learning sequence

The sequence below illustrates how this program’s content can be organized. Topics, pacing, and project depth are adapted for each offering. This is not an archived record of a specific cohort’s weekly syllabus.

  1. 01Research questions in computational drug discovery
  2. 02Linux basics, files, and reproducible research records
  3. 03Protein structures and appropriate structural data sources
  4. 04Protein-ligand interactions and molecular representations
  5. 05Docking concepts and a small educational exercise
  6. 06Comparing poses and interpreting screening outputs
  7. 07Preparing molecular features and activity labels
  8. 08Introductory machine-learning models and validation
  9. 09Structure-activity hypotheses, uncertainty, and limitations
  10. 10Reproducible report and computational research presentation
Ask About This Program Back to the Program Portfolio

Related program examples