Chapter 8 of Cheminformatics

Structure-based design soon

Proteins as structures: binding sites, molecular docking with AutoDock Vina, and machine-learned rescoring of poses.

soon This chapter is planned and not yet written. The outline below is the current plan; it may change.

What it will cover

• Protein structure files (PDB/mmCIF), chains, ligands and waters
• Finding and describing a binding site
• Preparing receptor and ligand; docking with AutoDock Vina
• Reading docking scores and poses critically
• ML rescoring and pose classification
• Lab 8: dock a small library into a kinase and rescore the poses

Planned learning outcomes

1. Prepare a protein and a ligand and run a docking calculation reproducibly.
2. Interpret docking poses and scores, including their well-known failure modes.
3. Train a simple rescoring model and evaluate it without leakage across protein families.

In the meantime

Everything here builds on Part I, in particular the evaluation habits of Chapter 2. Episode 2.6 already introduces the group splits that become scaffold splits here.

PreviousChapter 7 Graph neural networks for moleculesNextChapter 9 Biological sequences and databases

Edit this pageReport a problemLast updated 2026-11-02