liveBook · Manning

Pconsc4

As explained in Build AI Drug Discovery Pipelines

Pconsc4 is a protein-contact prediction model that applies a U-Net architecture to features derived from multiple sequence alignments.

Pconsc4 predicts which residue pairs in a protein are physically close. It builds 72 features from a multiple sequence alignment (MSA), then uses a U-Net encoder-decoder with skip connections to produce a contact-probability matrix. section 11.3.1

The prediction pipeline connects evolutionary signals to a protein graph:

  • Search sequence databases for homologous proteins and align their sequences into an MSA. section 11.3.1
  • Calculate position-specific amino acid frequencies, mutual information, direct coupling statistics, and other features for residue positions. section 11.3.1
  • Predict contact probabilities, threshold them at 0.5, and use the resulting contact map as a graph adjacency matrix. 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 predicted residue contacts become a two-dimensional contact map and then a protein graph with residues as nodes and contacts as edges. section 11.3.1

How Build AI Drug Discovery Pipelines covers it

How deep it goes
Explains MSA features, U-Net processing, probability thresholding, and graph conversion without detailing training or optimization.
Examples
Uses 72 MSA-derived features, a 0.5 contact threshold, and residue-node graphs built from predicted contacts.
What it assumes
Assumes sequence-alignment concepts only lightly, while defining homologous proteins, MSAs, contact maps, and graph roles.
What you can do after
Apply it via DGraphDTA to construct protein graphs from sequences and predicted residue contacts.
How it connects
Links multiple sequence alignments, homologous proteins, U-Net architectures, contact maps, protein graphs, 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.