Back

FrustraPocket: A protein-ligand binding site predictor using energetic local frustration

Freiberger, M. I.; Clemente, C. M.; Valero, E.; Pombo, J. G.; Leonetti, C. O.; Ravetti, S.; Parra, R. G.; Ferreiro, D. U.

2022-12-14 bioinformatics
10.1101/2022.12.11.519349 bioRxiv
Show abstract

Proteins are evolved polymers that minimize their free energy upon folding to their native states. Still, many folded proteins display energetic conflict between residues in various regions that can be identified as highly frustrated, and these have been shown to be related to several physiological functions. Here we show that small-ligand binding sites are typically enriched in locally frustrated interactions in the unbound state. We built a tool using a simple machine learning algorithm named FrustraPocket that combines the notion of small-molecule binding pockets and the localization of clusters of highly frustrated interactions to identify potential protein-ligand binding sites solely from the unbound forms. Availability and implementation (github)https://github.com/CamilaClemente/FrustraPocket/ Docker containerhttps://hub.docker.com/r/proteinphysiologylab/frustrapocket

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.