CDF it all

Consensus prediction of intrinsically disordered proteins based on various cumulative distribution functions

Bin Xue, Christopher J. Oldfield, A. Dunker, Vladimir N. Uversky

Research output: Contribution to journalArticle

83 Citations (Scopus)

Abstract

Many biologically active proteins are intrinsically disordered. A reasonable understanding of the disorder status of these proteins may be beneficial for better understanding of their structures and functions. The disorder contents of disordered proteins vary dramatically, with two extremes being fully ordered and fully disordered proteins. Often, it is necessary to perform a binary classification and classify a whole protein as ordered or disordered. Here, an improved error estimation technique was applied to develop the cumulative distribution function (CDF) algorithms for several established disorder predictors. A consensus binary predictor, based on the artificial neural networks, NN-CDF, was developed by using output of the individual CDFs. The consensus method outperforms the individual predictors by 4-5% in the averaged accuracy.

Original languageEnglish
Pages (from-to)1469-1474
Number of pages6
JournalFEBS Letters
Volume583
Issue number9
DOIs
StatePublished - May 6 2009

Fingerprint

Intrinsically Disordered Proteins
Distribution functions
Proteins
Error analysis
Neural networks

Keywords

  • Accuracy
  • CDF
  • Intrinsically disordered protein
  • Prediction

ASJC Scopus subject areas

  • Biochemistry
  • Biophysics
  • Cell Biology
  • Genetics
  • Molecular Biology
  • Structural Biology

Cite this

CDF it all : Consensus prediction of intrinsically disordered proteins based on various cumulative distribution functions. / Xue, Bin; Oldfield, Christopher J.; Dunker, A.; Uversky, Vladimir N.

In: FEBS Letters, Vol. 583, No. 9, 06.05.2009, p. 1469-1474.

Research output: Contribution to journalArticle

Xue, Bin ; Oldfield, Christopher J. ; Dunker, A. ; Uversky, Vladimir N. / CDF it all : Consensus prediction of intrinsically disordered proteins based on various cumulative distribution functions. In: FEBS Letters. 2009 ; Vol. 583, No. 9. pp. 1469-1474.
@article{d865e24ea9a84535a2c119e9e960449d,
title = "CDF it all: Consensus prediction of intrinsically disordered proteins based on various cumulative distribution functions",
abstract = "Many biologically active proteins are intrinsically disordered. A reasonable understanding of the disorder status of these proteins may be beneficial for better understanding of their structures and functions. The disorder contents of disordered proteins vary dramatically, with two extremes being fully ordered and fully disordered proteins. Often, it is necessary to perform a binary classification and classify a whole protein as ordered or disordered. Here, an improved error estimation technique was applied to develop the cumulative distribution function (CDF) algorithms for several established disorder predictors. A consensus binary predictor, based on the artificial neural networks, NN-CDF, was developed by using output of the individual CDFs. The consensus method outperforms the individual predictors by 4-5{\%} in the averaged accuracy.",
keywords = "Accuracy, CDF, Intrinsically disordered protein, Prediction",
author = "Bin Xue and Oldfield, {Christopher J.} and A. Dunker and Uversky, {Vladimir N.}",
year = "2009",
month = "5",
day = "6",
doi = "10.1016/j.febslet.2009.03.070",
language = "English",
volume = "583",
pages = "1469--1474",
journal = "FEBS Letters",
issn = "0014-5793",
publisher = "Elsevier",
number = "9",

}

TY - JOUR

T1 - CDF it all

T2 - Consensus prediction of intrinsically disordered proteins based on various cumulative distribution functions

AU - Xue, Bin

AU - Oldfield, Christopher J.

AU - Dunker, A.

AU - Uversky, Vladimir N.

PY - 2009/5/6

Y1 - 2009/5/6

N2 - Many biologically active proteins are intrinsically disordered. A reasonable understanding of the disorder status of these proteins may be beneficial for better understanding of their structures and functions. The disorder contents of disordered proteins vary dramatically, with two extremes being fully ordered and fully disordered proteins. Often, it is necessary to perform a binary classification and classify a whole protein as ordered or disordered. Here, an improved error estimation technique was applied to develop the cumulative distribution function (CDF) algorithms for several established disorder predictors. A consensus binary predictor, based on the artificial neural networks, NN-CDF, was developed by using output of the individual CDFs. The consensus method outperforms the individual predictors by 4-5% in the averaged accuracy.

AB - Many biologically active proteins are intrinsically disordered. A reasonable understanding of the disorder status of these proteins may be beneficial for better understanding of their structures and functions. The disorder contents of disordered proteins vary dramatically, with two extremes being fully ordered and fully disordered proteins. Often, it is necessary to perform a binary classification and classify a whole protein as ordered or disordered. Here, an improved error estimation technique was applied to develop the cumulative distribution function (CDF) algorithms for several established disorder predictors. A consensus binary predictor, based on the artificial neural networks, NN-CDF, was developed by using output of the individual CDFs. The consensus method outperforms the individual predictors by 4-5% in the averaged accuracy.

KW - Accuracy

KW - CDF

KW - Intrinsically disordered protein

KW - Prediction

UR - http://www.scopus.com/inward/record.url?scp=67349162535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349162535&partnerID=8YFLogxK

U2 - 10.1016/j.febslet.2009.03.070

DO - 10.1016/j.febslet.2009.03.070

M3 - Article

VL - 583

SP - 1469

EP - 1474

JO - FEBS Letters

JF - FEBS Letters

SN - 0014-5793

IS - 9

ER -