Assessment of protein disorder region predictions in CASP10

Bohdan Monastyrskyy; Andriy Kryshtafovych; John Moult; Anna Tramontano; Krzysztof Fidelis

doi:10.1002/prot.24391

Assessment of protein disorder region predictions in CASP10

Bohdan Monastyrskyy, Andriy Kryshtafovych, John Moult, Anna Tramontano, Krzysztof Fidelis

Research output: Contribution to journal › Article › peer-review

138 Scopus citations

Abstract

The article presents the assessment of disorder region predictions submitted to CASP10. The evaluation is based on the three measures tested in previous CASPs: (i) balanced accuracy, (ii) the Matthews correlation coefficient for the binary predictions, and (iii) the area under the curve in the receiver operating characteristic (ROC) analysis of predictions using probability annotation. We also performed new analyses such as comparison of the submitted predictions with those obtained with a Naïve disorder prediction method and with predictions from the disorder prediction databases D2P2 and MobiDB. On average, the methods participating in CASP10 demonstrated slightly better performance than those in CASP9.

Original language	English (US)
Pages (from-to)	127-137
Number of pages	11
Journal	Proteins: Structure, Function, and Bioinformatics
Volume	82
Issue number	SUPPL.2
DOIs	https://doi.org/10.1002/prot.24391
State	Published - Nov 22 2013
Externally published	Yes

Bibliographical note

KAUST Repository Item: Exported on 2020-10-01
Acknowledged KAUST grant number(s): KUK-I1–012-43
Acknowledgements: Grant sponsor: NIGMS/NIH; Grant number: R01GM100482 (to KF); Grant sponsor:King Abdullah University of Science and Technology (KAUST); Grant number:Award No. KUK-I1–012-43 (to AT); Grant sponsor: EMBO.
This publication acknowledges KAUST support, but has no KAUST affiliated authors.

Access to Document

10.1002/prot.24391

Cite this

@article{84d966491aa24f0996f3db4019d3d3dc,

title = "Assessment of protein disorder region predictions in CASP10",

abstract = "The article presents the assessment of disorder region predictions submitted to CASP10. The evaluation is based on the three measures tested in previous CASPs: (i) balanced accuracy, (ii) the Matthews correlation coefficient for the binary predictions, and (iii) the area under the curve in the receiver operating characteristic (ROC) analysis of predictions using probability annotation. We also performed new analyses such as comparison of the submitted predictions with those obtained with a Na{\"i}ve disorder prediction method and with predictions from the disorder prediction databases D2P2 and MobiDB. On average, the methods participating in CASP10 demonstrated slightly better performance than those in CASP9.",

author = "Bohdan Monastyrskyy and Andriy Kryshtafovych and John Moult and Anna Tramontano and Krzysztof Fidelis",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledged KAUST grant number(s): KUK-I1–012-43 Acknowledgements: Grant sponsor: NIGMS/NIH; Grant number: R01GM100482 (to KF); Grant sponsor:King Abdullah University of Science and Technology (KAUST); Grant number:Award No. KUK-I1–012-43 (to AT); Grant sponsor: EMBO. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2013",

month = nov,

day = "22",

doi = "10.1002/prot.24391",

language = "English (US)",

volume = "82",

pages = "127--137",

journal = "Proteins: Structure, Function, and Bioinformatics",

issn = "0887-3585",

publisher = "Wiley-Liss Inc.",

number = "SUPPL.2",

}

TY - JOUR

T1 - Assessment of protein disorder region predictions in CASP10

AU - Monastyrskyy, Bohdan

AU - Kryshtafovych, Andriy

AU - Moult, John

AU - Tramontano, Anna

AU - Fidelis, Krzysztof

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledged KAUST grant number(s): KUK-I1–012-43 Acknowledgements: Grant sponsor: NIGMS/NIH; Grant number: R01GM100482 (to KF); Grant sponsor:King Abdullah University of Science and Technology (KAUST); Grant number:Award No. KUK-I1–012-43 (to AT); Grant sponsor: EMBO. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2013/11/22

Y1 - 2013/11/22

N2 - The article presents the assessment of disorder region predictions submitted to CASP10. The evaluation is based on the three measures tested in previous CASPs: (i) balanced accuracy, (ii) the Matthews correlation coefficient for the binary predictions, and (iii) the area under the curve in the receiver operating characteristic (ROC) analysis of predictions using probability annotation. We also performed new analyses such as comparison of the submitted predictions with those obtained with a Naïve disorder prediction method and with predictions from the disorder prediction databases D2P2 and MobiDB. On average, the methods participating in CASP10 demonstrated slightly better performance than those in CASP9.

AB - The article presents the assessment of disorder region predictions submitted to CASP10. The evaluation is based on the three measures tested in previous CASPs: (i) balanced accuracy, (ii) the Matthews correlation coefficient for the binary predictions, and (iii) the area under the curve in the receiver operating characteristic (ROC) analysis of predictions using probability annotation. We also performed new analyses such as comparison of the submitted predictions with those obtained with a Naïve disorder prediction method and with predictions from the disorder prediction databases D2P2 and MobiDB. On average, the methods participating in CASP10 demonstrated slightly better performance than those in CASP9.

UR - http://hdl.handle.net/10754/597613

UR - http://doi.wiley.com/10.1002/prot.24391

UR - http://www.scopus.com/inward/record.url?scp=84892954999&partnerID=8YFLogxK

U2 - 10.1002/prot.24391

DO - 10.1002/prot.24391

M3 - Article

C2 - 23946100

SN - 0887-3585

VL - 82

SP - 127

EP - 137

JO - Proteins: Structure, Function, and Bioinformatics

JF - Proteins: Structure, Function, and Bioinformatics

IS - SUPPL.2

ER -

Assessment of protein disorder region predictions in CASP10

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this