Structrank: A new approach for ligand-based virtual Screening

Fabian Rathke, Katja Hansen, Ulf Brefeld, Klaus Muller

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure-Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.

Original languageEnglish
Pages (from-to)83-92
Number of pages10
JournalJournal of Chemical Information and Modeling
Volume51
Issue number1
DOIs
Publication statusPublished - 2011 Jan 24
Externally publishedYes

Fingerprint

ranking
Screening
Ligands
Chemical compounds
Support vector machines
Enzymes
activity structure
Molecules
regression
drug
Drug Discovery

ASJC Scopus subject areas

  • Chemistry(all)
  • Chemical Engineering(all)
  • Computer Science Applications
  • Library and Information Sciences

Cite this

Structrank : A new approach for ligand-based virtual Screening. / Rathke, Fabian; Hansen, Katja; Brefeld, Ulf; Muller, Klaus.

In: Journal of Chemical Information and Modeling, Vol. 51, No. 1, 24.01.2011, p. 83-92.

Research output: Contribution to journalArticle

Rathke, Fabian ; Hansen, Katja ; Brefeld, Ulf ; Muller, Klaus. / Structrank : A new approach for ligand-based virtual Screening. In: Journal of Chemical Information and Modeling. 2011 ; Vol. 51, No. 1. pp. 83-92.
@article{d6f489828d1c4671b45c0f60a0cb5232,
title = "Structrank: A new approach for ligand-based virtual Screening",
abstract = "Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure-Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.",
author = "Fabian Rathke and Katja Hansen and Ulf Brefeld and Klaus Muller",
year = "2011",
month = "1",
day = "24",
doi = "10.1021/ci100308f",
language = "English",
volume = "51",
pages = "83--92",
journal = "Journal of Chemical Information and Computer Sciences",
issn = "0095-2338",
publisher = "American Chemical Society",
number = "1",

}

TY - JOUR

T1 - Structrank

T2 - A new approach for ligand-based virtual Screening

AU - Rathke, Fabian

AU - Hansen, Katja

AU - Brefeld, Ulf

AU - Muller, Klaus

PY - 2011/1/24

Y1 - 2011/1/24

N2 - Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure-Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.

AB - Screening large libraries of chemical compounds against a biological target, typically a receptor or an enzyme, is a crucial step in the process of drug discovery. Virtual screening (VS) can be seen as a ranking problem which prefers as many actives as possible at the top of the ranking. As a standard, current Quantitative Structure-Activity Relationship (QSAR) models apply regression methods to predict the level of activity for each molecule and then sort them to establish the ranking. In this paper, we propose a top-k ranking algorithm (StructRank) based on Support Vector Machines to solve the early recognition problem directly. Empirically, we show that our ranking approach outperforms not only regression methods but another ranking approach recently proposed for QSAR ranking, RankSVM, in terms of actives found.

UR - http://www.scopus.com/inward/record.url?scp=79952593481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79952593481&partnerID=8YFLogxK

U2 - 10.1021/ci100308f

DO - 10.1021/ci100308f

M3 - Article

C2 - 21166393

AN - SCOPUS:79952593481

VL - 51

SP - 83

EP - 92

JO - Journal of Chemical Information and Computer Sciences

JF - Journal of Chemical Information and Computer Sciences

SN - 0095-2338

IS - 1

ER -