Propensity vectors of low-ASA residue pairs in the distinction of protein interactions

Liu, Q; Li, J

Propensity vectors of low-ASA residue pairs in the distinction of protein interactions

Liu, Q Li, J

Permalink

Publication Type:: Journal Article
Citation:: Proteins: Structure, Function and Bioinformatics, 2010, 78 (3), pp. 589 - 602
Issue Date:: 2010-02-15

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download full textAdobe PDF (756.73 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Liu, Q	en_US
dc.contributor.author	Li, J https://orcid.org/0000-0003-1833-7413	en_US
dc.date.issued	2010-02-15	en_US
dc.identifier.citation	Proteins: Structure, Function and Bioinformatics, 2010, 78 (3), pp. 589 - 602	en_US
dc.identifier.issn	0887-3585	en_US
dc.identifier.uri	http://hdl.handle.net/10453/17545
dc.description.abstract	We introduce low-ASA residue pairs as classification features for distinguishing the different types of protein interactions. A low-ASA residue pair is defined as two contact residues each from one chain that have a small solvent accessible surface area (ASA). This notion of residue pairs is novel as it first combines residue pairs with the O-ring theory, an influential proposition stating that the binding hot spots at the interface are often surrounded by a ring of energetically less important residues. As binding hot spots lie in the core of the stability for protein interactions, we believe that low-ASA residue pairs can sharpen the distinction of protein interactions. The main part of our feature vector is 210-dimensional, consisting of all possible low-ASA residue pairs; the value of every feature is determined by a propensity measure. Our classification method is called OringPV, which uses propensity vectors of protein interactions for support vector machine. OringPV is tested on three benchmark datasets for a variety of classification tasks such as the distinction between crystal packing and biological interactions, the distinction between two different types of biological interactions, etc. The evaluation frameworks include within-dataset, crossdataset comparison, and leave-one-out crossvalidation. The results show that low-ASA residue pairs and the propensity vector description of protein interactions are truly strong in the distinction. In particular, many cross-dataset generalization capability tests have achieved excellent recalls and overall accuracies, much outperforming existing benchmark methods. © 2009 Wiley-Liss, Inc.	en_US
dc.relation.ispartof	Proteins: Structure, Function and Bioinformatics	en_US
dc.relation.isbasedon	10.1002/prot.22583	en_US
dc.subject.classification	Bioinformatics	en_US
dc.subject.mesh	Proteins	en_US
dc.subject.mesh	Statistics, Nonparametric	en_US
dc.subject.mesh	ROC Curve	en_US
dc.subject.mesh	Protein Conformation	en_US
dc.subject.mesh	Surface Properties	en_US
dc.subject.mesh	Algorithms	en_US
dc.subject.mesh	Models, Chemical	en_US
dc.subject.mesh	Models, Molecular	en_US
dc.subject.mesh	Protein Interaction Domains and Motifs	en_US
dc.title	Propensity vectors of low-ASA residue pairs in the distinction of protein interactions	en_US
dc.type	Journal Article
utslib.citation.volume	3	en_US
utslib.citation.volume	78	en_US
utslib.for	080301 Bioinformatics Software	en_US
utslib.for	01 Mathematical Sciences	en_US
utslib.for	06 Biological Sciences	en_US
utslib.for	08 Information and Computing Sciences	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
pubs.organisational-group	/University of Technology Sydney/Strength - CHT - Health Technologies
utslib.copyright.status	open_access
pubs.issue	3	en_US
pubs.publication-status	Published	en_US
pubs.volume	78	en_US

Abstract:

We introduce low-ASA residue pairs as classification features for distinguishing the different types of protein interactions. A low-ASA residue pair is defined as two contact residues each from one chain that have a small solvent accessible surface area (ASA). This notion of residue pairs is novel as it first combines residue pairs with the O-ring theory, an influential proposition stating that the binding hot spots at the interface are often surrounded by a ring of energetically less important residues. As binding hot spots lie in the core of the stability for protein interactions, we believe that low-ASA residue pairs can sharpen the distinction of protein interactions. The main part of our feature vector is 210-dimensional, consisting of all possible low-ASA residue pairs; the value of every feature is determined by a propensity measure. Our classification method is called OringPV, which uses propensity vectors of protein interactions for support vector machine. OringPV is tested on three benchmark datasets for a variety of classification tasks such as the distinction between crystal packing and biological interactions, the distinction between two different types of biological interactions, etc. The evaluation frameworks include within-dataset, crossdataset comparison, and leave-one-out crossvalidation. The results show that low-ASA residue pairs and the propensity vector description of protein interactions are truly strong in the distinction. In particular, many cross-dataset generalization capability tests have achieved excellent recalls and overall accuracies, much outperforming existing benchmark methods. © 2009 Wiley-Liss, Inc.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/17545