Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM

Congzhong Cai; Hanguang Xiao; Qianfei Yuan; Xinghua Liu; Yufeng Wen

doi:10.2174/092986608784567528

Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM

Congzhong Cai^*, Hanguang Xiao, Qianfei Yuan, Xinghua Liu, Yufeng Wen

^*Corresponding author for this work

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

7 Citations (Scopus)

Abstract

This paper explores the use of support vector machine (SVM) for protein function prediction. Studies are conducted on several groups of proteins with different functions including DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors, drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins. The computed accuracy for the prediction of these proteins is found to be in the range of 82.32% to 99.7%, which illustrates the potential of SVM in facilitating protein function prediction.

Original language	English
Pages (from-to)	463-468
Number of pages	6
Journal	Protein and peptide letters
Volume	15
Issue number	5
DOIs	https://doi.org/10.2174/092986608784567528
Publication status	Published - Jun 2008
Externally published	Yes
Event	3rd International Conference on Intelligent Computing - Qingdao, China Duration: 21 Aug 2007 → 24 Aug 2007

Keywords

protein function prediction
DNA-binding proteins
RNA-binding proteins
G-protein coupled receptors (GPCRs)
drug absorption proteins
drug metabolizing enzymes
drug distribution and excretion proteins
support vector machine (SVM)
SUPPORT VECTOR MACHINES
SECONDARY STRUCTURE PREDICTION
AMINO-ACID-COMPOSITION
GENE-EXPRESSION
SEQUENCE
CLASSIFICATION
RECOGNITION
ALIGNMENT
NETWORKS
DATABASE

Access to Document

10.2174/092986608784567528

Cite this

@article{ae8af09ab6414f19a7138731bd41f0d4,

title = "Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM",

abstract = "This paper explores the use of support vector machine (SVM) for protein function prediction. Studies are conducted on several groups of proteins with different functions including DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors, drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins. The computed accuracy for the prediction of these proteins is found to be in the range of 82.32% to 99.7%, which illustrates the potential of SVM in facilitating protein function prediction.",

keywords = "protein function prediction, DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors (GPCRs), drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins, support vector machine (SVM), SUPPORT VECTOR MACHINES, SECONDARY STRUCTURE PREDICTION, AMINO-ACID-COMPOSITION, GENE-EXPRESSION, SEQUENCE, CLASSIFICATION, RECOGNITION, ALIGNMENT, NETWORKS, DATABASE",

author = "Congzhong Cai and Hanguang Xiao and Qianfei Yuan and Xinghua Liu and Yufeng Wen",

year = "2008",

month = jun,

doi = "10.2174/092986608784567528",

language = "English",

volume = "15",

pages = "463--468",

journal = "Protein and peptide letters",

issn = "0929-8665",

publisher = "BENTHAM SCIENCE PUBL LTD",

number = "5",

note = "3rd International Conference on Intelligent Computing ; Conference date: 21-08-2007 Through 24-08-2007",

}

TY - JOUR

T1 - Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM

AU - Cai, Congzhong

AU - Xiao, Hanguang

AU - Yuan, Qianfei

AU - Liu, Xinghua

AU - Wen, Yufeng

PY - 2008/6

Y1 - 2008/6

N2 - This paper explores the use of support vector machine (SVM) for protein function prediction. Studies are conducted on several groups of proteins with different functions including DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors, drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins. The computed accuracy for the prediction of these proteins is found to be in the range of 82.32% to 99.7%, which illustrates the potential of SVM in facilitating protein function prediction.

AB - This paper explores the use of support vector machine (SVM) for protein function prediction. Studies are conducted on several groups of proteins with different functions including DNA-binding proteins, RNA-binding proteins, G-protein coupled receptors, drug absorption proteins, drug metabolizing enzymes, drug distribution and excretion proteins. The computed accuracy for the prediction of these proteins is found to be in the range of 82.32% to 99.7%, which illustrates the potential of SVM in facilitating protein function prediction.

KW - protein function prediction

KW - DNA-binding proteins

KW - RNA-binding proteins

KW - G-protein coupled receptors (GPCRs)

KW - drug absorption proteins

KW - drug metabolizing enzymes

KW - drug distribution and excretion proteins

KW - support vector machine (SVM)

KW - SUPPORT VECTOR MACHINES

KW - SECONDARY STRUCTURE PREDICTION

KW - AMINO-ACID-COMPOSITION

KW - GENE-EXPRESSION

KW - SEQUENCE

KW - CLASSIFICATION

KW - RECOGNITION

KW - ALIGNMENT

KW - NETWORKS

KW - DATABASE

U2 - 10.2174/092986608784567528

DO - 10.2174/092986608784567528

M3 - Article

C2 - 18537735

SN - 0929-8665

VL - 15

SP - 463

EP - 468

JO - Protein and peptide letters

JF - Protein and peptide letters

IS - 5

T2 - 3rd International Conference on Intelligent Computing

Y2 - 21 August 2007 through 24 August 2007

ER -

Function prediction for DNA-/RNA-binding proteins, GPCRs, and drug ADME-associated proteins by SVM

Abstract

Keywords

Access to Document

Fingerprint

Cite this