Protein alignment based on higher order conditional random fields for template-based modeling.

The query-template alignment of proteins is one of the most critical steps of template-based modeling methods used to predict the 3D structure of a query protein. This alignment can be interpreted as a temporal classification or structured prediction task and first order Conditional Random Fields ha...

Full description

Bibliographic Details
Main Authors: Juan A Morales-Cordovilla, Victoria Sanchez, Martin Ratajczak
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2018-01-01
Series:PLoS ONE
Online Access:http://europepmc.org/articles/PMC5983487?pdf=render
_version_ 1819151938560720896
author Juan A Morales-Cordovilla
Victoria Sanchez
Martin Ratajczak
author_facet Juan A Morales-Cordovilla
Victoria Sanchez
Martin Ratajczak
author_sort Juan A Morales-Cordovilla
collection DOAJ
description The query-template alignment of proteins is one of the most critical steps of template-based modeling methods used to predict the 3D structure of a query protein. This alignment can be interpreted as a temporal classification or structured prediction task and first order Conditional Random Fields have been proposed for protein alignment and proven to be rather successful. Some other popular structured prediction problems, such as speech or image classification, have gained from the use of higher order Conditional Random Fields due to the well known higher order correlations that exist between their labels and features. In this paper, we propose and describe the use of higher order Conditional Random Fields for query-template protein alignment. The experiments carried out on different public datasets validate our proposal, especially on distantly-related protein pairs which are the most difficult to align.
first_indexed 2024-12-22T14:41:21Z
format Article
id doaj.art-f4dd2c8d8a224b3b84c088cb6375c5bb
institution Directory Open Access Journal
issn 1932-6203
language English
last_indexed 2024-12-22T14:41:21Z
publishDate 2018-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj.art-f4dd2c8d8a224b3b84c088cb6375c5bb2022-12-21T18:22:32ZengPublic Library of Science (PLoS)PLoS ONE1932-62032018-01-01136e019791210.1371/journal.pone.0197912Protein alignment based on higher order conditional random fields for template-based modeling.Juan A Morales-CordovillaVictoria SanchezMartin RatajczakThe query-template alignment of proteins is one of the most critical steps of template-based modeling methods used to predict the 3D structure of a query protein. This alignment can be interpreted as a temporal classification or structured prediction task and first order Conditional Random Fields have been proposed for protein alignment and proven to be rather successful. Some other popular structured prediction problems, such as speech or image classification, have gained from the use of higher order Conditional Random Fields due to the well known higher order correlations that exist between their labels and features. In this paper, we propose and describe the use of higher order Conditional Random Fields for query-template protein alignment. The experiments carried out on different public datasets validate our proposal, especially on distantly-related protein pairs which are the most difficult to align.http://europepmc.org/articles/PMC5983487?pdf=render
spellingShingle Juan A Morales-Cordovilla
Victoria Sanchez
Martin Ratajczak
Protein alignment based on higher order conditional random fields for template-based modeling.
PLoS ONE
title Protein alignment based on higher order conditional random fields for template-based modeling.
title_full Protein alignment based on higher order conditional random fields for template-based modeling.
title_fullStr Protein alignment based on higher order conditional random fields for template-based modeling.
title_full_unstemmed Protein alignment based on higher order conditional random fields for template-based modeling.
title_short Protein alignment based on higher order conditional random fields for template-based modeling.
title_sort protein alignment based on higher order conditional random fields for template based modeling
url http://europepmc.org/articles/PMC5983487?pdf=render
work_keys_str_mv AT juanamoralescordovilla proteinalignmentbasedonhigherorderconditionalrandomfieldsfortemplatebasedmodeling
AT victoriasanchez proteinalignmentbasedonhigherorderconditionalrandomfieldsfortemplatebasedmodeling
AT martinratajczak proteinalignmentbasedonhigherorderconditionalrandomfieldsfortemplatebasedmodeling