Chapter 12 of Bioinformatics

Protein structure soon

Predicted structures (AlphaFold/ESMFold-style), confidence measures, and features derived from structure for downstream models.

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

What it will cover

• Reading predicted structures and confidence (pLDDT, PAE)
• Secondary structure, solvent accessibility and contacts
• Structure-derived features for machine learning
• Comparing structures: RMSD, TM-score
• Structure-aware splits
• Lab 12: from predicted structures to a structure-feature model

Planned learning outcomes

1. Load predicted protein structures and interpret their confidence measures.
2. Compute structure-derived features and use them in a model.
3. Compare structures quantitatively and avoid leakage through structural similarity.

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 sequence-identity splits here.

PreviousChapter 11 Omics dataNextChapter 13 Generative models for molecules

Edit this pageReport a problemLast updated 2026-11-02