Keyword search (3,448 papers available)


Deep convolutional networks for quality assessment of protein folds

Author(s): Georgy Derevyanko

MOTIVATION: The computational prediction of a protein structure from its sequence generally relies on a method to assess the quality of protein models. Most assessment methods rank candidate models using heavily engineered structural features, defined as co...

Article GUID: 29931128
Title:Deep convolutional networks for quality assessment of protein folds
Authors:Georgy Derevyanko
Link:https://pubmed.ncbi.nlm.nih.gov/29931128/
DOI:10.1093/bioinformatics/bty494
Category:Bioinformatics
PMID:29931128
Dept Affiliation: CERMM
1 Department of Chemistry and Biochemistry and Centre for Research in Molecular Modeling (CERMM), Concordia University, Montréal, Québec, Canada.
2 Inria, Université Grenoble Alpes, CNRS, Grenoble INP, LJK, Grenoble, France.
3 Department of Computer Science and Operations Research, Université de Montréal, Montréal, Québec, Canada.

Description:

MOTIVATION: The computational prediction of a protein structure from its sequence generally relies on a method to assess the quality of protein models. Most assessment methods rank candidate models using heavily engineered structural features, defined as complex functions of the atomic coordinates. However, very few methods have attempted to learn these features directly from the data.