Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts

Patrik Björkholm; Pawel Daniluk; Andriy Kryshtafovych; Krzysztof Fidelis; Robin Andersson; Torgeir R Hvidsten

doi:10.1093/bioinformatics/btp149

Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts

Patrik Björkholm, Pawel Daniluk, Andriy Kryshtafovych, Krzysztof Fidelis, Robin Andersson, Torgeir R Hvidsten

28 Citations (Scopus)

Abstract

Correct prediction of residue-residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail.

Original language	English
Journal	Bioinformatics (Online)
Volume	25
Issue number	10
Pages (from-to)	1264-70
Number of pages	7
ISSN	1367-4811
DOIs	https://doi.org/10.1093/bioinformatics/btp149
Publication status	Published - 15 May 2009
Externally published	Yes

Keywords

Computational Biology
Databases, Protein
Markov Chains
Models, Molecular
Protein Folding
Protein Structure, Secondary
Proteins

Access to Document

10.1093/bioinformatics/btp149

Cite this

@article{8acf15fb34c1445b9b5a2dfd6a2bcfdc,

title = "Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts",

abstract = "Correct prediction of residue-residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail.",

keywords = "Computational Biology, Databases, Protein, Markov Chains, Models, Molecular, Protein Folding, Protein Structure, Secondary, Proteins",

author = "Patrik Bj{\"o}rkholm and Pawel Daniluk and Andriy Kryshtafovych and Krzysztof Fidelis and Robin Andersson and Hvidsten, {Torgeir R}",

year = "2009",

month = may,

day = "15",

doi = "10.1093/bioinformatics/btp149",

language = "English",

volume = "25",

pages = "1264--70",

journal = "Bioinformatics (Online)",

issn = "1367-4811",

publisher = "Oxford University Press",

number = "10",

}

TY - JOUR

T1 - Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts

AU - Björkholm, Patrik

AU - Daniluk, Pawel

AU - Kryshtafovych, Andriy

AU - Fidelis, Krzysztof

AU - Andersson, Robin

AU - Hvidsten, Torgeir R

PY - 2009/5/15

Y1 - 2009/5/15

N2 - Correct prediction of residue-residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail.

AB - Correct prediction of residue-residue contacts in proteins that lack good templates with known structure would take ab initio protein structure prediction a large step forward. The lack of correct contacts, and in particular long-range contacts, is considered the main reason why these methods often fail.

KW - Computational Biology

KW - Databases, Protein

KW - Markov Chains

KW - Models, Molecular

KW - Protein Folding

KW - Protein Structure, Secondary

KW - Proteins

U2 - 10.1093/bioinformatics/btp149

DO - 10.1093/bioinformatics/btp149

M3 - Journal article

C2 - 19289446

SN - 1367-4811

VL - 25

SP - 1264

EP - 1270

JO - Bioinformatics (Online)

JF - Bioinformatics (Online)

IS - 10

ER -

Using multi-data hidden Markov models trained on local neighborhoods of protein structure to predict residue-residue contacts

Abstract

Keywords

Access to Document

Fingerprint

Cite this