Using microenvironments to identify allosteric binding sites

Christopher Eric Foley, Sana Mohammad M Al Azwari, Mark Dufton, John Wilson

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

1 Citation (Scopus)

Abstract

Protein amino acid residues can be classified by their chemical properties and data mining can be used to make predictions about their structure and function. However, the properties of the surrounding residues contribute to the overall chemical context. This paper defines microenvironments as the spherical volume around a point in space and uses these volumes to determine average properties of the encompassed residues. The approach to index generation rapidly constructs microenvironment data. The averaged chemical properties are then employed in allosteric site prediction using support vector machines and neural networks. The results show that index generation performs best when microenvironment radius matches the granularity of the index and that microenvironments improve the classification accuracy.
LanguageEnglish
Title of host publication2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages411-415
Number of pages5
ISBN (Print)9781467325592
DOIs
Publication statusPublished - 4 Oct 2012
Event2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012) - Philadelphia, United States
Duration: 4 Oct 20127 Oct 2012

Conference

Conference2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012)
CountryUnited States
CityPhiladelphia
Period4/10/127/10/12

Fingerprint

Binding sites
Chemical properties
Support vector machines
Data mining
Amino acids
Neural networks
Proteins

Keywords

  • neural networks
  • microenvironments
  • allosteric binding sites
  • bioinformatics

Cite this

Foley, C. E., Al Azwari, S. M. M., Dufton, M., & Wilson, J. (2012). Using microenvironments to identify allosteric binding sites. In 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012) (pp. 411-415). Piscataway, NJ: IEEE. https://doi.org/10.1109/BIBM.2012.6392711
Foley, Christopher Eric ; Al Azwari, Sana Mohammad M ; Dufton, Mark ; Wilson, John. / Using microenvironments to identify allosteric binding sites. 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012). Piscataway, NJ : IEEE, 2012. pp. 411-415
@inproceedings{913ed4831c1f4520b387c9ed691a85c3,
title = "Using microenvironments to identify allosteric binding sites",
abstract = "Protein amino acid residues can be classified by their chemical properties and data mining can be used to make predictions about their structure and function. However, the properties of the surrounding residues contribute to the overall chemical context. This paper defines microenvironments as the spherical volume around a point in space and uses these volumes to determine average properties of the encompassed residues. The approach to index generation rapidly constructs microenvironment data. The averaged chemical properties are then employed in allosteric site prediction using support vector machines and neural networks. The results show that index generation performs best when microenvironment radius matches the granularity of the index and that microenvironments improve the classification accuracy.",
keywords = "neural networks, microenvironments, allosteric binding sites , bioinformatics",
author = "Foley, {Christopher Eric} and {Al Azwari}, {Sana Mohammad M} and Mark Dufton and John Wilson",
year = "2012",
month = "10",
day = "4",
doi = "10.1109/BIBM.2012.6392711",
language = "English",
isbn = "9781467325592",
pages = "411--415",
booktitle = "2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012)",
publisher = "IEEE",

}

Foley, CE, Al Azwari, SMM, Dufton, M & Wilson, J 2012, Using microenvironments to identify allosteric binding sites. in 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012). IEEE, Piscataway, NJ, pp. 411-415, 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012), Philadelphia, United States, 4/10/12. https://doi.org/10.1109/BIBM.2012.6392711

Using microenvironments to identify allosteric binding sites. / Foley, Christopher Eric; Al Azwari, Sana Mohammad M; Dufton, Mark; Wilson, John.

2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012). Piscataway, NJ : IEEE, 2012. p. 411-415.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Using microenvironments to identify allosteric binding sites

AU - Foley, Christopher Eric

AU - Al Azwari, Sana Mohammad M

AU - Dufton, Mark

AU - Wilson, John

PY - 2012/10/4

Y1 - 2012/10/4

N2 - Protein amino acid residues can be classified by their chemical properties and data mining can be used to make predictions about their structure and function. However, the properties of the surrounding residues contribute to the overall chemical context. This paper defines microenvironments as the spherical volume around a point in space and uses these volumes to determine average properties of the encompassed residues. The approach to index generation rapidly constructs microenvironment data. The averaged chemical properties are then employed in allosteric site prediction using support vector machines and neural networks. The results show that index generation performs best when microenvironment radius matches the granularity of the index and that microenvironments improve the classification accuracy.

AB - Protein amino acid residues can be classified by their chemical properties and data mining can be used to make predictions about their structure and function. However, the properties of the surrounding residues contribute to the overall chemical context. This paper defines microenvironments as the spherical volume around a point in space and uses these volumes to determine average properties of the encompassed residues. The approach to index generation rapidly constructs microenvironment data. The averaged chemical properties are then employed in allosteric site prediction using support vector machines and neural networks. The results show that index generation performs best when microenvironment radius matches the granularity of the index and that microenvironments improve the classification accuracy.

KW - neural networks

KW - microenvironments

KW - allosteric binding sites

KW - bioinformatics

UR - http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=6373898

UR - http://www.scopus.com/record/display.url?eid=2-s2.0-84872526650&origin=inward&txGid=F58F98FE25389759CA2C5FD5BBBB4640.53bsOu7mi7A1NSY7fPJf1g%3a1

U2 - 10.1109/BIBM.2012.6392711

DO - 10.1109/BIBM.2012.6392711

M3 - Conference contribution book

SN - 9781467325592

SP - 411

EP - 415

BT - 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012)

PB - IEEE

CY - Piscataway, NJ

ER -

Foley CE, Al Azwari SMM, Dufton M, Wilson J. Using microenvironments to identify allosteric binding sites. In 2012 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2012). Piscataway, NJ: IEEE. 2012. p. 411-415 https://doi.org/10.1109/BIBM.2012.6392711