Exploiting heterogeneous sequence properties improves prediction of protein disorder

Zoran Obradovic, Kang Peng, Slobodan Vucetic, Predrag Radivojac, A. Dunker

Research output: Contribution to journalArticle

345 Citations (Scopus)

Abstract

During the past few years we have investigated methods to improve predictors of intrinsically disordered regions longer than 30 consecutive residues. Experimental evidence, however, showed that these predictors were less successful on short disordered regions, as observed two years ago during the fifth Critical Assessment of Techniques for Protein Structure Prediction (CASP5). To address this shortcoming, we developed a two-level model called VSL1 (CASP6 id: 193-1). At the first level, VSL1 consists of two specialized predictors, one of which was optimized for long disordered regions (>30 residues) and the other for short disordered regions (≥30 residues). At the second level, a meta-predictor was built to assign weights for combining the two first-level predictors. As the results of the CASP6 experiment showed, this new predictor has achieved the highest accuracy yet and significantly improved performance on short disordered regions, while maintaining high performance on long disordered regions.

Original languageEnglish
Pages (from-to)176-182
Number of pages7
JournalProteins: Structure, Function and Genetics
Volume61
Issue numberSUPPL. 7
DOIs
StatePublished - 2005

Fingerprint

Weights and Measures
Proteins
Experiments

Keywords

  • Disorder prediction
  • Intrinsically disordered
  • Length dependent predictors

ASJC Scopus subject areas

  • Genetics
  • Structural Biology
  • Biochemistry

Cite this

Exploiting heterogeneous sequence properties improves prediction of protein disorder. / Obradovic, Zoran; Peng, Kang; Vucetic, Slobodan; Radivojac, Predrag; Dunker, A.

In: Proteins: Structure, Function and Genetics, Vol. 61, No. SUPPL. 7, 2005, p. 176-182.

Research output: Contribution to journalArticle

Obradovic, Zoran ; Peng, Kang ; Vucetic, Slobodan ; Radivojac, Predrag ; Dunker, A. / Exploiting heterogeneous sequence properties improves prediction of protein disorder. In: Proteins: Structure, Function and Genetics. 2005 ; Vol. 61, No. SUPPL. 7. pp. 176-182.
@article{f78daba6d3e646eea3904b221bd5f26e,
title = "Exploiting heterogeneous sequence properties improves prediction of protein disorder",
abstract = "During the past few years we have investigated methods to improve predictors of intrinsically disordered regions longer than 30 consecutive residues. Experimental evidence, however, showed that these predictors were less successful on short disordered regions, as observed two years ago during the fifth Critical Assessment of Techniques for Protein Structure Prediction (CASP5). To address this shortcoming, we developed a two-level model called VSL1 (CASP6 id: 193-1). At the first level, VSL1 consists of two specialized predictors, one of which was optimized for long disordered regions (>30 residues) and the other for short disordered regions (≥30 residues). At the second level, a meta-predictor was built to assign weights for combining the two first-level predictors. As the results of the CASP6 experiment showed, this new predictor has achieved the highest accuracy yet and significantly improved performance on short disordered regions, while maintaining high performance on long disordered regions.",
keywords = "Disorder prediction, Intrinsically disordered, Length dependent predictors",
author = "Zoran Obradovic and Kang Peng and Slobodan Vucetic and Predrag Radivojac and A. Dunker",
year = "2005",
doi = "10.1002/prot.20735",
language = "English",
volume = "61",
pages = "176--182",
journal = "Proteins: Structure, Function and Genetics",
issn = "0887-3585",
publisher = "Wiley-Liss Inc.",
number = "SUPPL. 7",

}

TY - JOUR

T1 - Exploiting heterogeneous sequence properties improves prediction of protein disorder

AU - Obradovic, Zoran

AU - Peng, Kang

AU - Vucetic, Slobodan

AU - Radivojac, Predrag

AU - Dunker, A.

PY - 2005

Y1 - 2005

N2 - During the past few years we have investigated methods to improve predictors of intrinsically disordered regions longer than 30 consecutive residues. Experimental evidence, however, showed that these predictors were less successful on short disordered regions, as observed two years ago during the fifth Critical Assessment of Techniques for Protein Structure Prediction (CASP5). To address this shortcoming, we developed a two-level model called VSL1 (CASP6 id: 193-1). At the first level, VSL1 consists of two specialized predictors, one of which was optimized for long disordered regions (>30 residues) and the other for short disordered regions (≥30 residues). At the second level, a meta-predictor was built to assign weights for combining the two first-level predictors. As the results of the CASP6 experiment showed, this new predictor has achieved the highest accuracy yet and significantly improved performance on short disordered regions, while maintaining high performance on long disordered regions.

AB - During the past few years we have investigated methods to improve predictors of intrinsically disordered regions longer than 30 consecutive residues. Experimental evidence, however, showed that these predictors were less successful on short disordered regions, as observed two years ago during the fifth Critical Assessment of Techniques for Protein Structure Prediction (CASP5). To address this shortcoming, we developed a two-level model called VSL1 (CASP6 id: 193-1). At the first level, VSL1 consists of two specialized predictors, one of which was optimized for long disordered regions (>30 residues) and the other for short disordered regions (≥30 residues). At the second level, a meta-predictor was built to assign weights for combining the two first-level predictors. As the results of the CASP6 experiment showed, this new predictor has achieved the highest accuracy yet and significantly improved performance on short disordered regions, while maintaining high performance on long disordered regions.

KW - Disorder prediction

KW - Intrinsically disordered

KW - Length dependent predictors

UR - http://www.scopus.com/inward/record.url?scp=30344485673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30344485673&partnerID=8YFLogxK

U2 - 10.1002/prot.20735

DO - 10.1002/prot.20735

M3 - Article

C2 - 16187360

AN - SCOPUS:30344485673

VL - 61

SP - 176

EP - 182

JO - Proteins: Structure, Function and Genetics

JF - Proteins: Structure, Function and Genetics

SN - 0887-3585

IS - SUPPL. 7

ER -