Ahmed Doghri Logo Image
Ahmed Doghri

foldcontact

A sequence can look protein-like and still ignore the fold. foldcontact makes every infilled residue answer to the contact map, lifting constraint satisfaction from 34.5% to 100%.

foldcontact reproduced benchmark result

Protein-Looking Is Not Fold-Aware

Masked sequence models are good at producing plausible amino acids. Plausible is not the same as compatible with the residues that must meet in three-dimensional space.

foldcontact builds paired residue constraints, masks one side of every contact, and asks two infillers to rebuild it. One samples from the amino-acid alphabet. The other must satisfy the contact class.

The Contact Map Gets A Vote

The guided decoder treats hydrophobic, charged, and polar compatibility as a hard selection signal. Every prediction remains inspectable; there is no checkpoint hiding the decision.

This is a small reproduction of a structure-aware design idea, not a structure predictor. It exists to isolate the value of geometric constraints before scaling the architecture.

The Number

Random infilling satisfies 34.5% of 1,440 held-out contacts. Contact-guided infilling satisfies 100%, a 65.5-point gain.

The controlled benchmark is educational and not a wet-lab claim. One deterministic test passes across the three-version GitHub Actions matrix.

Research Basis

Inspired by the 2025 AtomWorks and RosettaFold-3 release. The portfolio number above comes from this repository's own controlled benchmark, not from the paper.

Tools Used

Python
Protein Design
Contact Maps
Sequence Infilling
Structural Biology
unittest
GitHub Actions CI