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

Juan A. Morales-Cordovilla, Victoria Sanchez, Martin Ratajczak

Research output: Contribution to journalArticleResearchpeer-review

Abstract

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.

Original languageEnglish
Article numbere0197912
JournalPLoS ONE
Volume13
Issue number6
DOIs
Publication statusPublished - 1 Jun 2018

Fingerprint

Proteins
proteins
prediction
Image classification
Labels
Experiments
methodology
Datasets

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Protein alignment based on higher order conditional random fields for template-based modeling. / Morales-Cordovilla, Juan A.; Sanchez, Victoria; Ratajczak, Martin.

In: PLoS ONE, Vol. 13, No. 6, e0197912, 01.06.2018.

Research output: Contribution to journalArticleResearchpeer-review

Morales-Cordovilla, Juan A. ; Sanchez, Victoria ; Ratajczak, Martin. / Protein alignment based on higher order conditional random fields for template-based modeling. In: PLoS ONE. 2018 ; Vol. 13, No. 6.
@article{f1a606e374e14c2ebc854f0439a08bdb,
title = "Protein alignment based on higher order conditional random fields for template-based modeling",
abstract = "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.",
author = "Morales-Cordovilla, {Juan A.} and Victoria Sanchez and Martin Ratajczak",
year = "2018",
month = "6",
day = "1",
doi = "10.1371/journal.pone.0197912",
language = "English",
volume = "13",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

TY - JOUR

T1 - Protein alignment based on higher order conditional random fields for template-based modeling

AU - Morales-Cordovilla, Juan A.

AU - Sanchez, Victoria

AU - Ratajczak, Martin

PY - 2018/6/1

Y1 - 2018/6/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85048059039&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0197912

DO - 10.1371/journal.pone.0197912

M3 - Article

VL - 13

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 6

M1 - e0197912

ER -