Struct-NB: Predicting protein-RNA binding sites using structural features

Fadi Towfic; Cornelia Caragea; David C. Gemperline; Drena Dobbs; Vasant Honavar

doi:10.1504/IJDMB.2010.030965

Struct-NB: Predicting protein-RNA binding sites using structural features

Fadi Towfic, Cornelia Caragea, David C. Gemperline, Drena Dobbs, Vasant Honavar

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

39 Scopus citations

Abstract

We analyse sequence and structural features of protein-RNA interfaces using RB-147, a non-redundant dataset of protein-RNA complexes extracted from the PDB. We train classifiers using machine learning algorithms to predict protein-RNA interfaces from sequence and structure-derived features of proteins. Our experiments show that Struct-NB, a Naïve Bayes classifier that exploits structural features, outperforms its counterparts that use only sequence features to predict protein-RNA binding residues.

Original language	English (US)
Pages (from-to)	21-43
Number of pages	23
Journal	International Journal of Data Mining and Bioinformatics
Volume	4
Issue number	1
DOIs	https://doi.org/10.1504/IJDMB.2010.030965
State	Published - Jan 2010

All Science Journal Classification (ASJC) codes

Information Systems
General Biochemistry, Genetics and Molecular Biology
Library and Information Sciences

Access to Document

10.1504/IJDMB.2010.030965

Cite this

@article{c31d4e93565745b4bf916639d1145d06,

title = "Struct-NB: Predicting protein-RNA binding sites using structural features",

abstract = "We analyse sequence and structural features of protein-RNA interfaces using RB-147, a non-redundant dataset of protein-RNA complexes extracted from the PDB. We train classifiers using machine learning algorithms to predict protein-RNA interfaces from sequence and structure-derived features of proteins. Our experiments show that Struct-NB, a Na{\"i}ve Bayes classifier that exploits structural features, outperforms its counterparts that use only sequence features to predict protein-RNA binding residues.",

author = "Fadi Towfic and Cornelia Caragea and Gemperline, {David C.} and Drena Dobbs and Vasant Honavar",

year = "2010",

month = jan,

doi = "10.1504/IJDMB.2010.030965",

language = "English (US)",

volume = "4",

pages = "21--43",

journal = "International Journal of Data Mining and Bioinformatics",

issn = "1748-5673",

publisher = "Inderscience Enterprises Ltd",

number = "1",

}

TY - JOUR

T1 - Struct-NB

T2 - Predicting protein-RNA binding sites using structural features

AU - Towfic, Fadi

AU - Caragea, Cornelia

AU - Gemperline, David C.

AU - Dobbs, Drena

AU - Honavar, Vasant

PY - 2010/1

Y1 - 2010/1

N2 - We analyse sequence and structural features of protein-RNA interfaces using RB-147, a non-redundant dataset of protein-RNA complexes extracted from the PDB. We train classifiers using machine learning algorithms to predict protein-RNA interfaces from sequence and structure-derived features of proteins. Our experiments show that Struct-NB, a Naïve Bayes classifier that exploits structural features, outperforms its counterparts that use only sequence features to predict protein-RNA binding residues.

AB - We analyse sequence and structural features of protein-RNA interfaces using RB-147, a non-redundant dataset of protein-RNA complexes extracted from the PDB. We train classifiers using machine learning algorithms to predict protein-RNA interfaces from sequence and structure-derived features of proteins. Our experiments show that Struct-NB, a Naïve Bayes classifier that exploits structural features, outperforms its counterparts that use only sequence features to predict protein-RNA binding residues.

UR - http://www.scopus.com/inward/record.url?scp=77951265973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77951265973&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2010.030965

DO - 10.1504/IJDMB.2010.030965

M3 - Article

C2 - 20300450

AN - SCOPUS:77951265973

SN - 1748-5673

VL - 4

SP - 21

EP - 43

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

IS - 1

ER -

Struct-NB: Predicting protein-RNA binding sites using structural features

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this