Litcius/Paper detail

ISPRED-SEQ: Deep Neural Networks and Embeddings for Predicting Interaction Sites in Protein Sequences

Matteo Manfredi, Castrense Savojardo, Pier Luigi Martelli, Rita Casadio

2023Journal of Molecular Biology24 citationsDOIOpen Access PDF

Abstract

The knowledge of protein-protein interaction sites (PPIs) is crucial for protein functional annotation. Here we address the problem focusing on the prediction of putative PPIs considering as input protein sequences. The issue is important given the huge volume of protein sequences compared to experimental and/or computed structures. Taking advantage of protein language models, recently developed, and Deep Neural networks, here we describe ISPRED-SEQ, which overpasses state-of-the-art predictors addressing the same problem. ISPRED-SEQ is freely available for testing at https://ispredws.biocomp.unibo.it.

Topics & Concepts

Computer scienceArtificial neural networkComputational biologyArtificial intelligenceProtein Interaction NetworksAnnotationProtein–protein interactionDeep neural networksDeep learningMachine learningBiologyGeneticsRNA and protein synthesis mechanismsMachine Learning in BioinformaticsProtein Structure and Dynamics