Prediction of compounds' biological function (metabolic pathways) based on functional group composition

被引：43

作者：

Cai, Yu-Dong ^{[1
,2
]}

Qian, Ziliang ^{[3
,4
]}

Lu, Lin ^{[5
]}

Feng, Kai-Yan ^{[2
]}

Meng, Xin ^{[1
]}

Niu, Bing ^{[6
]}

Zhao, Guo-Dong ^{[1
]}

Lu, Wen-Cong ^{[6
]}

机构：

[1] Chinese Acad Sci, Shanghai Inst Biol Sci, CAS MPG Partner Inst Computat Biol, Shanghai 200072, Peoples R China

[2] Univ Manchester, Inst Sci & Technol, Dept Math, Manchester M60 1QD, Lancs, England

[3] Chinese Acad Sci, Grad Sch, Beijing 100039, Peoples R China

[4] Chinese Acad Sci, Bioinformat Ctr, Key Lab Mol Syst Biol, Shanghai Inst Biol Sci, Shanghai 200031, Peoples R China

[5] Shanghai Jiao Tong Univ, Dept Biomed Engn, Shanghai 200240, Peoples R China

[6] Shanghai Univ, Sch Mat Sci & Engn, Shanghai 200072, Peoples R China

来源：

MOLECULAR DIVERSITY | 2008年 / 12卷 / 02期

关键词：

compound; biological functions; nearest neighbor algorithm; functional group composition; metabolic pathway;

D O I：

10.1007/s11030-008-9085-9

中图分类号：

Q5 [生物化学]; Q7 [分子生物学];

学科分类号：

071010 ; 081704 ;

摘要：

Efficient in silico screening approaches may provide valuable hints on biological functions of the compound-candidates, which could help to screen functional compounds either in basic researches on metabolic pathways or drug discovery. Here, we introduce a machine learning method (Nearest Neighbor Algorithm) based on functional group composition of compounds to the analysis of metabolic pathways. This method can quickly map small chemical molecules to the metabolic pathway that they likely belong to. A set of 2,764 compounds from 11 major classes of metabolic pathways were selected for study. The overall prediction rate reached 73.3%, indicating that functional group composition of compounds was really related to their biological metabolic functions.

引用

页码：131 / 137

页数：7

共 19 条

[1] Metabolic engineering - a genetic toolbox for small molecule organic synthesis
Burkart, MD
[J]. ORGANIC & BIOMOLECULAR CHEMISTRY, 2003, 1 (01) : 1 - 4
[2] Predicting enzyme subclass by functional domain composition and pseudo amino acid composition
Cai, YD
Chou, KC
[J]. JOURNAL OF PROTEOME RESEARCH, 2005, 4 (03) : 967 - 971
[3] Prediction of Saccharomyces cerevisiae protein functional class from functional domain composition
Cai, YD
Doig, AJ
[J]. BIOINFORMATICS, 2004, 20 (08) : 1292 - 1300
[4] Predicting protein localization in budding yeast
Chou, KC
Cai, YD
[J]. BIOINFORMATICS, 2005, 21 (07) : 944 - 950
[5] Prediction of subcellular protein localization based on functional domain composition
Jia, Peilin
Qian, Ziliang
Zeng, ZhenBin
Cai, Yudong
Li, Yixue
[J]. BIOCHEMICAL AND BIOPHYSICAL RESEARCH COMMUNICATIONS, 2007, 357 (02) : 366 - 370
[6] From genomics to chemical genomics: new developments in KEGG
Kanehisa, Minoru
Goto, Susumu
Hattori, Masahiro
Aoki-Kinoshita, Kiyoko F.
Itoh, Masumi
Kawashima, Shuichi
Katayama, Toshiaki
Araki, Michihiro
Hirakawa, Mika
[J]. NUCLEIC ACIDS RESEARCH, 2006, 34 : D354 - D357
[7] ECS: An automatic enzyme classifier based on functional domain composition
Lu, Lingyi
Qian, Ziliang
Cai, Yu-Dong
Li, Yixue
[J]. COMPUTATIONAL BIOLOGY AND CHEMISTRY, 2007, 31 (03) : 226 - 232
[8] New approach to pharmacophore mapping and QSAR analysis using inductive logic programming.: Application to thermolysin inhibitors and glycogen phosphorylase b inhibitors
Marchand-Geneste, N
Watson, KA
Alsberg, BK
Kings, RD
[J]. JOURNAL OF MEDICINAL CHEMISTRY, 2002, 45 (02) : 399 - 409
[9] MCKEE JRM, 1999, BIOCH INTRO
[10] Pseudo amino acid composition and multi-class support vector machines approach for conotoxin superfamily classification
Mondal, Sukanta
Bhavna, Rajasekaran
Babu, Rajasekaran Mohan
Ramakumar, Suryanarayanarao
[J]. JOURNAL OF THEORETICAL BIOLOGY, 2006, 243 (02) : 252 - 260

← 1 2 →