Chainsaw: protein domain segmentation with fully convolutional neural networks
Bioinformatics · 02.05.2024 · 40 (5)
DOI: 10.1093/bioinformatics/btae296 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 08.05.2024. Verfasst von Jude Wells und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Artificial Intelligence, University College London, WC1E 6BT, United Kingdom. Hauptthemen laut MEDLINE: Neural Networks, Computer, Proteins, Algorithms, Protein Domains. Die Arbeit wurde bisher 57-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC.
Abstract (Originalsprache)
Motivation Protein domains are fundamental units of protein structure and play a pivotal role in understanding folding, function, evolution, and design. The advent of accurate structure prediction techniques has resulted in an influx of new structural data, making the partitioning of these structures into domains essential for inferring evolutionary relationships and functional classification. Results This article presents Chainsaw, a supervised learning approach to domain parsing that achieves accuracy that surpasses current state-of-the-art methods. Chainsaw uses a fully convolutional neural network which is trained to predict the probability that each pair of residues is in the same domain. Domain predictions are then derived from these pairwise predictions using an algorithm that searches for the most likely assignment of residues to domains given the set of pairwise co-membership probabilities. Chainsaw matches CATH domain annotations in 78% of protein domains versus 72% for the next closest method. When predicting on AlphaFold models, expert human evaluators were twice as likely to prefer Chainsaw’s predictions versus the next best method. Availability and implementation github.com/JudeWells/Chainsaw.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Centre for Artificial Intelligence, University College London, WC1E 6BT, United Kingdom.
- Institute of Structural and Molecular Biology, University College London, WC1E 6BT, United Kingdom.
ORCID-Profile: Jude Wells, Nicola Bordin, Ian Sillitoe
Förderung
- EPSRC
Zitieren
APA
Wells, J., Hawkins-Hooker, A., Bordin, N., Sillitoe, I., Paige, B., & Orengo, C. (2024). Chainsaw: protein domain segmentation with fully convolutional neural networks. Bioinformatics, 40(5). https://doi.org/10.1093/bioinformatics/btae296
Vancouver
Wells J, Hawkins-Hooker A, Bordin N, Sillitoe I, Paige B, Orengo C. Chainsaw: protein domain segmentation with fully convolutional neural networks. Bioinformatics. 2024;40(5). doi:10.1093/bioinformatics/btae296
BibTeX
@article{Wells2024,
author = {Wells, Jude and Hawkins-Hooker, Alex and Bordin, Nicola and Sillitoe, Ian and Paige, Brooks and Orengo, Christine},
title = {Chainsaw: protein domain segmentation with fully convolutional neural networks},
journal = {Bioinformatics},
year = {2024},
volume = {40},
number = {5},
doi = {10.1093/bioinformatics/btae296}
}
EUVIMED