ProteinUnet—An efficient alternative to SPIDER3‐single for sequence‐based prediction of protein secondary structures

Predicting protein function and structure from sequence remains an unsolved problem in bioinformatics. The best performing methods rely heavily on evolutionary information from multiple sequence alignments, which means their accuracy deteriorates for sequences with a few homologs, and given the incr...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of computational chemistry 2021-01, Vol.42 (1), p.50-59
Hauptverfasser:	Kotowski, Krzysztof, Smolarczyk, Tomasz, Roterman‐Konieczna, Irena, Stapor, Katarzyna
Format:	Artikel
Sprache:	eng
Schlagworte:	Accuracy backbone angles estimation Bioinformatics Computer architecture deep learning Homology Predictions protein structure prediction Proteins Recurrent neural networks secondary structure prediction Sequences solvent accessibility prediction
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!