liveBook · Manning

Contact prediction

As explained in Build AI Drug Discovery Pipelines

Contact prediction is the computational inference of spatially contacting residue pairs from protein sequence-derived information.

Contact prediction infers which residue pairs are spatially close from protein sequence information, enabling graph construction when experimental structures are unavailable. section 11.3.1

A practical contact-prediction workflow:

  • Collect homologous protein sequences and align them in a multiple sequence alignment (MSA). section 11.3.1
  • Detect correlated mutations, using compensatory evolutionary changes as evidence that residues interact physically. section 11.3.1
  • Use a deep-learning model trained on known Protein Data Bank structures to predict a contact map. section 11.3.1

From contact map to protein graph

A graph-building pipeline loads a predicted contact map, thresholds its entries into residue-to-residue edges, computes sequence-derived features from an alignment, and represents residues as graph nodes. section 11.3.1

Figure 11.5 Transforming a Protein's 3D Structure into a 2D Graph. Converting a protein's spatial information into a graph representation. (a) A simplified 3D protein structure with dashed lines connecting amino acid residues that are in close spatial proximity (a 'contact'). (b) Spatial information is translated into a contact map, which is a 2D matrix. A point at (i, j) is marked if residue i and residue j are in contact, serving as an adjacency matrix for the graph. (c) The contact map is used to construct a graph where the amino acid residues are the nodes and the contacts are the edges. This graph captures the key residue interactions in a format that is invariant to the protein's rotation and translation in 3D space.

Trace how three-dimensional residue proximity becomes a two-dimensional contact map and then a rotation- and translation-invariant protein graph. section 11.3.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains MSAs, evolutionary coupling, and predicted contact maps, then sketches threshold-based graph construction without detailing model training.
Examples
Uses residue-contact maps, homologous-sequence alignments, and thresholded protein graphs as concrete computational artifacts.
What it assumes
Assumes basic protein-sequence familiarity while defining homologs, MSAs, residue contacts, and evolutionary coupling.
What you can do after
Build protein graphs from sequence-derived contact maps and alignment features for downstream affinity modeling.
How it connects
Connects protein structure, contact maps, multiple sequence alignments, evolutionary coupling, and graph neural networks.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Build AI Drug Discovery Pipelines. The section links point to the parts of the book it draws on.