Cargando…

Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning

De novo membrane protein structure prediction is limited to small proteins due to the conformational search space quickly expanding with length. Long-range contacts (24+ amino acid separation)–residue positions distant in sequence, but in close proximity in the structure, are arguably the most effec...

Descripción completa

Detalles Bibliográficos
Autores principales: Teixeira, Pedro L., Mendenhall, Jeff L., Heinze, Sten, Weiner, Brian, Skwark, Marcin J., Meiler, Jens
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5443516/
https://www.ncbi.nlm.nih.gov/pubmed/28542325
http://dx.doi.org/10.1371/journal.pone.0177866
_version_ 1783238581080293376
author Teixeira, Pedro L.
Mendenhall, Jeff L.
Heinze, Sten
Weiner, Brian
Skwark, Marcin J.
Meiler, Jens
author_facet Teixeira, Pedro L.
Mendenhall, Jeff L.
Heinze, Sten
Weiner, Brian
Skwark, Marcin J.
Meiler, Jens
author_sort Teixeira, Pedro L.
collection PubMed
description De novo membrane protein structure prediction is limited to small proteins due to the conformational search space quickly expanding with length. Long-range contacts (24+ amino acid separation)–residue positions distant in sequence, but in close proximity in the structure, are arguably the most effective way to restrict this conformational space. Inverse methods for co-evolutionary analysis predict a global set of position-pair couplings that best explain the observed amino acid co-occurrences, thus distinguishing between evolutionarily explained co-variances and these arising from spurious transitive effects. Here, we show that applying machine learning approaches and custom descriptors improves evolutionary contact prediction accuracy, resulting in improvement of average precision by 6 percentage points for the top 1L non-local contacts. Further, we demonstrate that predicted contacts improve protein folding with BCL::Fold. The mean RMSD100 metric for the top 10 models folded was reduced by an average of 2 Å for a benchmark of 25 membrane proteins.
format Online
Article
Text
id pubmed-5443516
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-54435162017-06-06 Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning Teixeira, Pedro L. Mendenhall, Jeff L. Heinze, Sten Weiner, Brian Skwark, Marcin J. Meiler, Jens PLoS One Research Article De novo membrane protein structure prediction is limited to small proteins due to the conformational search space quickly expanding with length. Long-range contacts (24+ amino acid separation)–residue positions distant in sequence, but in close proximity in the structure, are arguably the most effective way to restrict this conformational space. Inverse methods for co-evolutionary analysis predict a global set of position-pair couplings that best explain the observed amino acid co-occurrences, thus distinguishing between evolutionarily explained co-variances and these arising from spurious transitive effects. Here, we show that applying machine learning approaches and custom descriptors improves evolutionary contact prediction accuracy, resulting in improvement of average precision by 6 percentage points for the top 1L non-local contacts. Further, we demonstrate that predicted contacts improve protein folding with BCL::Fold. The mean RMSD100 metric for the top 10 models folded was reduced by an average of 2 Å for a benchmark of 25 membrane proteins. Public Library of Science 2017-05-24 /pmc/articles/PMC5443516/ /pubmed/28542325 http://dx.doi.org/10.1371/journal.pone.0177866 Text en © 2017 Teixeira et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Teixeira, Pedro L.
Mendenhall, Jeff L.
Heinze, Sten
Weiner, Brian
Skwark, Marcin J.
Meiler, Jens
Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title_full Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title_fullStr Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title_full_unstemmed Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title_short Membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
title_sort membrane protein contact and structure prediction using co-evolution in conjunction with machine learning
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5443516/
https://www.ncbi.nlm.nih.gov/pubmed/28542325
http://dx.doi.org/10.1371/journal.pone.0177866
work_keys_str_mv AT teixeirapedrol membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning
AT mendenhalljeffl membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning
AT heinzesten membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning
AT weinerbrian membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning
AT skwarkmarcinj membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning
AT meilerjens membraneproteincontactandstructurepredictionusingcoevolutioninconjunctionwithmachinelearning