Protein structure based prediction of catalytic residues

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Background: Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60% of these proteins have any sort of functional annotation.Results: We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63% and a precision of 17%), a performance competitive with that of other state-of-the-art methods.Conclusions: We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases.

Original languageEnglish (US)
Article number63
JournalBMC Bioinformatics
Volume14
Issue number1
DOIs
StatePublished - Feb 22 2013

Fingerprint

Protein Structure
Conservation
Proteins
Prediction
Amino acids
Barycentre
Databases
Amino Acids
Centrality
Entropy
Genomics
Neural networks
Discriminant Function
PageRank
Betweenness
Relative Entropy
Test Set
Graph in graph theory
Independent Set
Chemical analysis

Keywords

  • Catalytic residues
  • Feature selection
  • Functional site
  • Neural network
  • Structural genomics

ASJC Scopus subject areas

  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics
  • Structural Biology

Cite this

Protein structure based prediction of catalytic residues. / Fajardo, Jorge E.; Fiser, Andras.

In: BMC Bioinformatics, Vol. 14, No. 1, 63, 22.02.2013.

Research output: Contribution to journalArticle

@article{11b8aba2ff864442984fdd5a035cf2d6,
title = "Protein structure based prediction of catalytic residues",
abstract = "Background: Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60{\%} of these proteins have any sort of functional annotation.Results: We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63{\%} and a precision of 17{\%}), a performance competitive with that of other state-of-the-art methods.Conclusions: We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases.",
keywords = "Catalytic residues, Feature selection, Functional site, Neural network, Structural genomics",
author = "Fajardo, {Jorge E.} and Andras Fiser",
year = "2013",
month = "2",
day = "22",
doi = "10.1186/1471-2105-14-63",
language = "English (US)",
volume = "14",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Protein structure based prediction of catalytic residues

AU - Fajardo, Jorge E.

AU - Fiser, Andras

PY - 2013/2/22

Y1 - 2013/2/22

N2 - Background: Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60% of these proteins have any sort of functional annotation.Results: We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63% and a precision of 17%), a performance competitive with that of other state-of-the-art methods.Conclusions: We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases.

AB - Background: Worldwide structural genomics projects continue to release new protein structures at an unprecedented pace, so far nearly 6000, but only about 60% of these proteins have any sort of functional annotation.Results: We explored a range of features that can be used for the prediction of functional residues given a known three-dimensional structure. These features include various centrality measures of nodes in graphs of interacting residues: closeness, betweenness and page-rank centrality. We also analyzed the distance of functional amino acids to the general center of mass (GCM) of the structure, relative solvent accessibility (RSA), and the use of relative entropy as a measure of sequence conservation. From the selected features, neural networks were trained to identify catalytic residues. We found that using distance to the GCM together with amino acid type provide a good discriminant function, when combined independently with sequence conservation. Using an independent test set of 29 annotated protein structures, the method returned 411 of the initial 9262 residues as the most likely to be involved in function. The output 411 residues contain 70 of the annotated 111 catalytic residues. This represents an approximately 14-fold enrichment of catalytic residues on the entire input set (corresponding to a sensitivity of 63% and a precision of 17%), a performance competitive with that of other state-of-the-art methods.Conclusions: We found that several of the graph based measures utilize the same underlying feature of protein structures, which can be simply and more effectively captured with the distance to GCM definition. This also has the added the advantage of simplicity and easy implementation. Meanwhile sequence conservation remains by far the most influential feature in identifying functional residues. We also found that due the rapid changes in size and composition of sequence databases, conservation calculations must be recalibrated for specific reference databases.

KW - Catalytic residues

KW - Feature selection

KW - Functional site

KW - Neural network

KW - Structural genomics

UR - http://www.scopus.com/inward/record.url?scp=84874072821&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874072821&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-14-63

DO - 10.1186/1471-2105-14-63

M3 - Article

VL - 14

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - 1

M1 - 63

ER -