Statistical models for discerning protein structures containing the DNA-binding helix-turn-helix motif

William A. McLaughlin; Helen M. Berman

doi:10.1016/S0022-2836(03)00532-1

Statistical models for discerning protein structures containing the DNA-binding helix-turn-helix motif

William A. McLaughlin, Helen M. Berman

SAS - Chem & Chemical Biology

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

15 Scopus citations

Abstract

A method for discerning protein structures containing the DNA-binding helix-turn-helix (HTH) motif has been developed. The method uses statistical models based on geometrical measurements of the motif. With a decision tree model, key structural features required for DNA binding were identified. These include a high average solvent-accessibility of residues within the recognition helix and a conserved hydrophobic interaction between the recognition helix and the second alpha helix preceding it. The Protein Data Bank was searched using a more accurate model of the motif created using the Adaboost algorithm to identify structures that have a high probability of containing the motif, including those that had not been reported previously.

Original language	English (US)
Pages (from-to)	43-55
Number of pages	13
Journal	Journal of molecular biology
Volume	330
Issue number	1
DOIs	https://doi.org/10.1016/S0022-2836(03)00532-1
State	Published - Jun 27 2003

All Science Journal Classification (ASJC) codes

Structural Biology
Molecular Biology

Keywords

DNA-binding
Helix-turn-helix motif
Machine learning
Structure classification

Access to Document

10.1016/S0022-2836(03)00532-1

Fingerprint Dive into the research topics of 'Statistical models for discerning protein structures containing the DNA-binding helix-turn-helix motif'. Together they form a unique fingerprint.

Cite this

@article{a7a6f7ca58d04f129096b0b10ece40e5,

title = "Statistical models for discerning protein structures containing the DNA-binding helix-turn-helix motif",

abstract = "A method for discerning protein structures containing the DNA-binding helix-turn-helix (HTH) motif has been developed. The method uses statistical models based on geometrical measurements of the motif. With a decision tree model, key structural features required for DNA binding were identified. These include a high average solvent-accessibility of residues within the recognition helix and a conserved hydrophobic interaction between the recognition helix and the second alpha helix preceding it. The Protein Data Bank was searched using a more accurate model of the motif created using the Adaboost algorithm to identify structures that have a high probability of containing the motif, including those that had not been reported previously.",

keywords = "DNA-binding, Helix-turn-helix motif, Machine learning, Structure classification",

author = "McLaughlin, {William A.} and Berman, {Helen M.}",

note = "Funding Information: We thank Professor Craig Nevill-Manning for his advice on machine learning methods and lending technical support for the Weka machine learning software. We are grateful to Professor Wilma K. Olson, Dr Catherine Lawson and Christine Zardecki for help with manuscript preparation, Professor Kevin Karplus for advice on developing the test and training sets used, Professor Jannette Carey for fruitful discussions, and Dr John Westbrook for a discussion regarding data mining with protein structures containing the DNA-binding HTH motif. We thank Professor Janet Thornton for a critical review of the manuscript and for helpful comments and suggestions. A Department of Energy Grant (DE-FG02-96ER62166) and an NIH Training Grant (GM08319) supported this work. ",

year = "2003",

month = jun,

day = "27",

doi = "10.1016/S0022-2836(03)00532-1",

language = "English (US)",

volume = "330",

pages = "43--55",

journal = "Journal of Molecular Biology",

issn = "0022-2836",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Statistical models for discerning protein structures containing the DNA-binding helix-turn-helix motif

AU - McLaughlin, William A.

AU - Berman, Helen M.

N1 - Funding Information: We thank Professor Craig Nevill-Manning for his advice on machine learning methods and lending technical support for the Weka machine learning software. We are grateful to Professor Wilma K. Olson, Dr Catherine Lawson and Christine Zardecki for help with manuscript preparation, Professor Kevin Karplus for advice on developing the test and training sets used, Professor Jannette Carey for fruitful discussions, and Dr John Westbrook for a discussion regarding data mining with protein structures containing the DNA-binding HTH motif. We thank Professor Janet Thornton for a critical review of the manuscript and for helpful comments and suggestions. A Department of Energy Grant (DE-FG02-96ER62166) and an NIH Training Grant (GM08319) supported this work.

PY - 2003/6/27

Y1 - 2003/6/27

N2 - A method for discerning protein structures containing the DNA-binding helix-turn-helix (HTH) motif has been developed. The method uses statistical models based on geometrical measurements of the motif. With a decision tree model, key structural features required for DNA binding were identified. These include a high average solvent-accessibility of residues within the recognition helix and a conserved hydrophobic interaction between the recognition helix and the second alpha helix preceding it. The Protein Data Bank was searched using a more accurate model of the motif created using the Adaboost algorithm to identify structures that have a high probability of containing the motif, including those that had not been reported previously.

AB - A method for discerning protein structures containing the DNA-binding helix-turn-helix (HTH) motif has been developed. The method uses statistical models based on geometrical measurements of the motif. With a decision tree model, key structural features required for DNA binding were identified. These include a high average solvent-accessibility of residues within the recognition helix and a conserved hydrophobic interaction between the recognition helix and the second alpha helix preceding it. The Protein Data Bank was searched using a more accurate model of the motif created using the Adaboost algorithm to identify structures that have a high probability of containing the motif, including those that had not been reported previously.

KW - DNA-binding

KW - Helix-turn-helix motif

KW - Machine learning

KW - Structure classification

UR - http://www.scopus.com/inward/record.url?scp=0038681269&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038681269&partnerID=8YFLogxK

U2 - 10.1016/S0022-2836(03)00532-1

DO - 10.1016/S0022-2836(03)00532-1

M3 - Article

C2 - 12818201

AN - SCOPUS:0038681269

VL - 330

SP - 43

EP - 55

JO - Journal of Molecular Biology

JF - Journal of Molecular Biology

SN - 0022-2836

IS - 1

ER -