Prev. Article Next Article Table of Contents

Article

Virtual Screening of Molecular Databases Using a Support Vector Machine

Supporting Info

Robert N. Jorissen and Michael K. Gilson*

Center for Advanced Research in Biotechnology, University of Maryland Biotechnology Institute, 9600 Gudelsky Drive, Rockville, Maryland 20850

J. Chem. Inf. Model., 2005, 45 (3), pp 549–561

DOI: 10.1021/ci049641u

Publication Date (Web): April 16, 2005

Corresponding author e-mail: gilson@umbi.edu.edu.

Abstract

The Support Vector Machine (SVM) is an algorithm that derives a model used for the classification of data into two categories and which has good generalization properties. This study applies the SVM algorithm to the problem of virtual screening for molecules with a desired activity. In contrast to typical applications of the SVM, we emphasize not classification but enrichment of actives by using a modified version of the standard SVM function to rank molecules. The method employs a simple and novel criterion for picking molecular descriptors and uses cross-validation to select SVM parameters. The resulting method is more effective at enriching for active compounds with novel chemistries than binary fingerprint-based methods such as binary kernel discrimination.

View: Full Text HTML | Hi-Res PDF

Tools

SciFinder Links

History

Published In Issue May 23, 2005
Received November 30, 2004

Recommend & Share

Related Content

Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug ClassificationJournal of Chemical Information and Computer Sciences
- Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification
  Evgeny Byvatov, Uli Fechner, Jens Sadowski, and Gisbert Schneider
  Journal of Chemical Information and Computer Sciences 2003 43 (6), pp 1882–1889
  Abstract: Support vector machine (SVM) and artificial neural network (ANN) systems were applied to a drug/nondrug classification problem as an example of binary decision problems in early-phase virtual compound filtering and screening. The results indicate that ...
  Abstract | Full Text HTML | Hi-Res PDF
Evaluation of Virtual Screening Performance of Support Vector Machines Trained by Sparsely Distributed Active CompoundsJournal of Chemical Information and Modeling
- Evaluation of Virtual Screening Performance of Support Vector Machines Trained by Sparsely Distributed Active Compounds
  X. H. Ma, R. Wang, S. Y. Yang, Z. R. Li, Y. Xue, Y. C. Wei, B. C. Low and Y. Z. Chen
  Journal of Chemical Information and Modeling 2008 48 (6), pp 1227–1237
  Abstract: Virtual screening performance of support vector machines (SVM) depends on the diversity of training active and inactive compounds. While diverse inactive compounds can be routinely generated, the number and diversity of known actives are typically low. We ...
  Abstract | Full Text HTML | PDF w/ Links | Hi-Res PDF
Support-Vector-Machine-Based Ranking Significantly Improves the Effectiveness of Similarity Searching Using 2D Fingerprints and Multiple Reference CompoundsJournal of Chemical Information and Modeling
- Support-Vector-Machine-Based Ranking Significantly Improves the Effectiveness of Similarity Searching Using 2D Fingerprints and Multiple Reference Compounds
  Hanna Geppert, Tamás Horváth, Thomas Gärtner, Stefan Wrobel and Jürgen Bajorath
  Journal of Chemical Information and Modeling 2008 48 (4), pp 742–746
  Abstract: Similarity searching using molecular fingerprints is computationally efficient and a surprisingly effective virtual screening tool. In this study, we have compared ranking methods for similarity searching using multiple active reference molecules. ...
  Abstract | Full Text HTML | PDF w/ Links | Hi-Res PDF

Article

Virtual Screening of Molecular Databases Using a Support Vector Machine

Abstract

Tools

SciFinder Links

History

Recommend & Share

Related Content

Comparison of Support Vector Machine and Artificial Neural Network Systems for Drug/Nondrug Classification

Evaluation of Virtual Screening Performance of Support Vector Machines Trained by Sparsely Distributed Active Compounds

Support-Vector-Machine-Based Ranking Significantly Improves the Effectiveness of Similarity Searching Using 2D Fingerprints and Multiple Reference Compounds

Other ACS content by these authors:

JOURNALS

BOOKS

MAGAZINE

COMMUNITIES

DIRECTORIES & DATABASES