PONDR-FIT: A meta-predictor of intrinsically disordered amino acids

Bin Xue, Roland L. Dunbrack, Robert W. Williams, A. Keith Dunker, Vladimir N. Uversky

Research output: Contribution to journalArticle

560 Citations (Scopus)

Abstract

Protein intrinsic disorder is becoming increasingly recognized in proteomics research. While lacking structure, many regions of disorder have been associated with biological function. There are many different experimental methods for characterizing intrinsically disordered proteins and regions; nevertheless, the prediction of intrinsic disorder from amino acid sequence remains a useful strategy especially for many large-scale proteomic investigations. Here we introduced a consensus artificial neural network (ANN) prediction method, which was developed by combining the outputs of several individual disorder predictors. By eight-fold cross-validation, this meta-predictor, called PONDR-FIT, was found to improve the prediction accuracy over a range of 3 to 20% with an average of 11% compared to the single predictors, depending on the datasets being used. Analysis of the errors shows that the worst accuracy still occurs for short disordered regions with less than ten residues, as well as for the residues close to order/disorder boundaries. Increased understanding of the underlying mechanism by which such meta-predictors give improved predictions will likely promote the further development of protein disorder predictors. Access to PONDR-FIT is available at www.disprot.org.

Original languageEnglish (US)
Pages (from-to)996-1010
Number of pages15
JournalBiochimica et Biophysica Acta - Proteins and Proteomics
Volume1804
Issue number4
DOIs
StatePublished - Apr 1 2010

Fingerprint

Proteomics
Intrinsically Disordered Proteins
Amino Acids
Amino Acid Sequence
Proteins
Order disorder transitions
Research
Neural networks
Datasets

Keywords

  • Highly dynamic
  • Highly flexible
  • Intrinsically disordered
  • Intrinsically unstructured
  • Natively unfolded
  • PONDR
  • Predictor
  • Structurally disordered

ASJC Scopus subject areas

  • Biochemistry
  • Biophysics
  • Analytical Chemistry
  • Molecular Biology

Cite this

PONDR-FIT : A meta-predictor of intrinsically disordered amino acids. / Xue, Bin; Dunbrack, Roland L.; Williams, Robert W.; Dunker, A. Keith; Uversky, Vladimir N.

In: Biochimica et Biophysica Acta - Proteins and Proteomics, Vol. 1804, No. 4, 01.04.2010, p. 996-1010.

Research output: Contribution to journalArticle

Xue, Bin ; Dunbrack, Roland L. ; Williams, Robert W. ; Dunker, A. Keith ; Uversky, Vladimir N. / PONDR-FIT : A meta-predictor of intrinsically disordered amino acids. In: Biochimica et Biophysica Acta - Proteins and Proteomics. 2010 ; Vol. 1804, No. 4. pp. 996-1010.
@article{0f557ec1454b4bf3be26d1a68d130bdf,
title = "PONDR-FIT: A meta-predictor of intrinsically disordered amino acids",
abstract = "Protein intrinsic disorder is becoming increasingly recognized in proteomics research. While lacking structure, many regions of disorder have been associated with biological function. There are many different experimental methods for characterizing intrinsically disordered proteins and regions; nevertheless, the prediction of intrinsic disorder from amino acid sequence remains a useful strategy especially for many large-scale proteomic investigations. Here we introduced a consensus artificial neural network (ANN) prediction method, which was developed by combining the outputs of several individual disorder predictors. By eight-fold cross-validation, this meta-predictor, called PONDR-FIT, was found to improve the prediction accuracy over a range of 3 to 20{\%} with an average of 11{\%} compared to the single predictors, depending on the datasets being used. Analysis of the errors shows that the worst accuracy still occurs for short disordered regions with less than ten residues, as well as for the residues close to order/disorder boundaries. Increased understanding of the underlying mechanism by which such meta-predictors give improved predictions will likely promote the further development of protein disorder predictors. Access to PONDR-FIT is available at www.disprot.org.",
keywords = "Highly dynamic, Highly flexible, Intrinsically disordered, Intrinsically unstructured, Natively unfolded, PONDR, Predictor, Structurally disordered",
author = "Bin Xue and Dunbrack, {Roland L.} and Williams, {Robert W.} and Dunker, {A. Keith} and Uversky, {Vladimir N.}",
year = "2010",
month = "4",
day = "1",
doi = "10.1016/j.bbapap.2010.01.011",
language = "English (US)",
volume = "1804",
pages = "996--1010",
journal = "Biochimica et Biophysica Acta - Proteins and Proteomics",
issn = "1570-9639",
publisher = "Elsevier",
number = "4",

}

TY - JOUR

T1 - PONDR-FIT

T2 - A meta-predictor of intrinsically disordered amino acids

AU - Xue, Bin

AU - Dunbrack, Roland L.

AU - Williams, Robert W.

AU - Dunker, A. Keith

AU - Uversky, Vladimir N.

PY - 2010/4/1

Y1 - 2010/4/1

N2 - Protein intrinsic disorder is becoming increasingly recognized in proteomics research. While lacking structure, many regions of disorder have been associated with biological function. There are many different experimental methods for characterizing intrinsically disordered proteins and regions; nevertheless, the prediction of intrinsic disorder from amino acid sequence remains a useful strategy especially for many large-scale proteomic investigations. Here we introduced a consensus artificial neural network (ANN) prediction method, which was developed by combining the outputs of several individual disorder predictors. By eight-fold cross-validation, this meta-predictor, called PONDR-FIT, was found to improve the prediction accuracy over a range of 3 to 20% with an average of 11% compared to the single predictors, depending on the datasets being used. Analysis of the errors shows that the worst accuracy still occurs for short disordered regions with less than ten residues, as well as for the residues close to order/disorder boundaries. Increased understanding of the underlying mechanism by which such meta-predictors give improved predictions will likely promote the further development of protein disorder predictors. Access to PONDR-FIT is available at www.disprot.org.

AB - Protein intrinsic disorder is becoming increasingly recognized in proteomics research. While lacking structure, many regions of disorder have been associated with biological function. There are many different experimental methods for characterizing intrinsically disordered proteins and regions; nevertheless, the prediction of intrinsic disorder from amino acid sequence remains a useful strategy especially for many large-scale proteomic investigations. Here we introduced a consensus artificial neural network (ANN) prediction method, which was developed by combining the outputs of several individual disorder predictors. By eight-fold cross-validation, this meta-predictor, called PONDR-FIT, was found to improve the prediction accuracy over a range of 3 to 20% with an average of 11% compared to the single predictors, depending on the datasets being used. Analysis of the errors shows that the worst accuracy still occurs for short disordered regions with less than ten residues, as well as for the residues close to order/disorder boundaries. Increased understanding of the underlying mechanism by which such meta-predictors give improved predictions will likely promote the further development of protein disorder predictors. Access to PONDR-FIT is available at www.disprot.org.

KW - Highly dynamic

KW - Highly flexible

KW - Intrinsically disordered

KW - Intrinsically unstructured

KW - Natively unfolded

KW - PONDR

KW - Predictor

KW - Structurally disordered

UR - http://www.scopus.com/inward/record.url?scp=76849087968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76849087968&partnerID=8YFLogxK

U2 - 10.1016/j.bbapap.2010.01.011

DO - 10.1016/j.bbapap.2010.01.011

M3 - Article

C2 - 20100603

AN - SCOPUS:76849087968

VL - 1804

SP - 996

EP - 1010

JO - Biochimica et Biophysica Acta - Proteins and Proteomics

JF - Biochimica et Biophysica Acta - Proteins and Proteomics

SN - 1570-9639

IS - 4

ER -