LigSeeSVM

Ligand-based virtual Screening using Support Vector Machines and data fusion

Yen Fu Chen, Kai Cheng Hsu, Po Tsun Lin, D. Frank Hsu, Bruce S. Kristal, Jinn Moon Yang

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Ligand-based in silico drug screening is useful for lead discovery, in particular for those targets without structures. Here, we have developed LigSeeSVM, a ligand-based screening tool using data fusion and Support Vector Machines (SVMs). We used Atom Pair (AP) structure descriptors and Physicochemical (PC) descriptors of compounds to generate SVM-AP and SVM-PC models. Sequentially, the two models were combined using rank-based data fusion to create LigSeeSVM model. LigSeeSVM was evaluated on five data sets. Experimental results show that the performance of LigSeeSVM is better than other ligand-based virtual screening approaches. We believe that LigSeeSVM is useful for lead compounds.

Original languageEnglish
Pages (from-to)274-289
Number of pages16
JournalInternational Journal of Computational Biology and Drug Design
Volume4
Issue number3
DOIs
Publication statusPublished - Jul 2011
Externally publishedYes

Fingerprint

Data fusion
Support vector machines
Screening
Ligands
Lead compounds
Atoms
Preclinical Drug Evaluations
Computer Simulation
Support Vector Machine
Lead

Keywords

  • Data fusion
  • Ligand-based virtual screening
  • Oestrogen receptor
  • Rank combination
  • Support Vector Machines
  • Thymidine kinase substrates

ASJC Scopus subject areas

  • Computer Science Applications
  • Drug Discovery

Cite this

LigSeeSVM : Ligand-based virtual Screening using Support Vector Machines and data fusion. / Chen, Yen Fu; Hsu, Kai Cheng; Lin, Po Tsun; Frank Hsu, D.; Kristal, Bruce S.; Yang, Jinn Moon.

In: International Journal of Computational Biology and Drug Design, Vol. 4, No. 3, 07.2011, p. 274-289.

Research output: Contribution to journalArticle

Chen, Yen Fu ; Hsu, Kai Cheng ; Lin, Po Tsun ; Frank Hsu, D. ; Kristal, Bruce S. ; Yang, Jinn Moon. / LigSeeSVM : Ligand-based virtual Screening using Support Vector Machines and data fusion. In: International Journal of Computational Biology and Drug Design. 2011 ; Vol. 4, No. 3. pp. 274-289.
@article{a098e2a31f98429fa190d805212cfb36,
title = "LigSeeSVM: Ligand-based virtual Screening using Support Vector Machines and data fusion",
abstract = "Ligand-based in silico drug screening is useful for lead discovery, in particular for those targets without structures. Here, we have developed LigSeeSVM, a ligand-based screening tool using data fusion and Support Vector Machines (SVMs). We used Atom Pair (AP) structure descriptors and Physicochemical (PC) descriptors of compounds to generate SVM-AP and SVM-PC models. Sequentially, the two models were combined using rank-based data fusion to create LigSeeSVM model. LigSeeSVM was evaluated on five data sets. Experimental results show that the performance of LigSeeSVM is better than other ligand-based virtual screening approaches. We believe that LigSeeSVM is useful for lead compounds.",
keywords = "Data fusion, Ligand-based virtual screening, Oestrogen receptor, Rank combination, Support Vector Machines, Thymidine kinase substrates",
author = "Chen, {Yen Fu} and Hsu, {Kai Cheng} and Lin, {Po Tsun} and {Frank Hsu}, D. and Kristal, {Bruce S.} and Yang, {Jinn Moon}",
year = "2011",
month = "7",
doi = "10.1504/IJCBDD.2011.041415",
language = "English",
volume = "4",
pages = "274--289",
journal = "International Journal of Computational Biology and Drug Design",
issn = "1756-0756",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

TY - JOUR

T1 - LigSeeSVM

T2 - Ligand-based virtual Screening using Support Vector Machines and data fusion

AU - Chen, Yen Fu

AU - Hsu, Kai Cheng

AU - Lin, Po Tsun

AU - Frank Hsu, D.

AU - Kristal, Bruce S.

AU - Yang, Jinn Moon

PY - 2011/7

Y1 - 2011/7

N2 - Ligand-based in silico drug screening is useful for lead discovery, in particular for those targets without structures. Here, we have developed LigSeeSVM, a ligand-based screening tool using data fusion and Support Vector Machines (SVMs). We used Atom Pair (AP) structure descriptors and Physicochemical (PC) descriptors of compounds to generate SVM-AP and SVM-PC models. Sequentially, the two models were combined using rank-based data fusion to create LigSeeSVM model. LigSeeSVM was evaluated on five data sets. Experimental results show that the performance of LigSeeSVM is better than other ligand-based virtual screening approaches. We believe that LigSeeSVM is useful for lead compounds.

AB - Ligand-based in silico drug screening is useful for lead discovery, in particular for those targets without structures. Here, we have developed LigSeeSVM, a ligand-based screening tool using data fusion and Support Vector Machines (SVMs). We used Atom Pair (AP) structure descriptors and Physicochemical (PC) descriptors of compounds to generate SVM-AP and SVM-PC models. Sequentially, the two models were combined using rank-based data fusion to create LigSeeSVM model. LigSeeSVM was evaluated on five data sets. Experimental results show that the performance of LigSeeSVM is better than other ligand-based virtual screening approaches. We believe that LigSeeSVM is useful for lead compounds.

KW - Data fusion

KW - Ligand-based virtual screening

KW - Oestrogen receptor

KW - Rank combination

KW - Support Vector Machines

KW - Thymidine kinase substrates

UR - http://www.scopus.com/inward/record.url?scp=80555149711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80555149711&partnerID=8YFLogxK

U2 - 10.1504/IJCBDD.2011.041415

DO - 10.1504/IJCBDD.2011.041415

M3 - Article

VL - 4

SP - 274

EP - 289

JO - International Journal of Computational Biology and Drug Design

JF - International Journal of Computational Biology and Drug Design

SN - 1756-0756

IS - 3

ER -