Molecules 2013, 18(1), 735-756; doi:10.3390/molecules18010735
Article

Benchmarking Ligand-Based Virtual High-Throughput Screening with the PubChem Database

Mariusz Butkiewicz, Edward W. Lowe Jr., Ralf Mueller, Jeffrey L. Mendenhall, Pedro L. Teixeira, C. David Weaver and Jens Meiler* email
Department of Chemistry, Pharmacology, and Biomedical Informatics, Center for Structural Biology, Institute of Chemical Biology, Vanderbilt University, Nashville, TN 37232, USA
* Author to whom correspondence should be addressed.
Received: 26 September 2012; in revised form: 11 October 2012 / Accepted: 17 December 2012 / Published: 8 January 2013
(This article belongs to the Special Issue QSAR and Its Applications)
PDF Full-text Download PDF Full-Text [268 KB, uploaded 8 January 2013 09:10 CET]
Abstract: With the rapidly increasing availability of High-Throughput Screening (HTS) data in the public domain, such as the PubChem database, methods for ligand-based computer-aided drug discovery (LB-CADD) have the potential to accelerate and reduce the cost of probe development and drug discovery efforts in academia. We assemble nine data sets from realistic HTS campaigns representing major families of drug target proteins for benchmarking LB-CADD methods. Each data set is public domain through PubChem and carefully collated through confirmation screens validating active compounds. These data sets provide the foundation for benchmarking a new cheminformatics framework BCL::ChemInfo, which is freely available for non-commercial use. Quantitative structure activity relationship (QSAR) models are built using Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), Decision Trees (DTs), and Kohonen networks (KNs). Problem-specific descriptor optimization protocols are assessed including Sequential Feature Forward Selection (SFFS) and various information content measures. Measures of predictive power and confidence are evaluated through cross-validation, and a consensus prediction scheme is tested that combines orthogonal machine learning algorithms into a single predictor. Enrichments ranging from 15 to 101 for a TPR cutoff of 25% are observed.
Keywords: virtual screening; machine learning; quantitative structure-activity relations (QSAR); high-throughput screening (HTS); cheminformatics; PubChem; BCL

Supplementary Files

Article Statistics

Click here to load and display the download statistics.

Cite This Article

MDPI and ACS Style

Butkiewicz, M.; Lowe, E.W., Jr.; Mueller, R.; Mendenhall, J.L.; Teixeira, P.L.; Weaver, C.D.; Meiler, J. Benchmarking Ligand-Based Virtual High-Throughput Screening with the PubChem Database. Molecules 2013, 18, 735-756.

AMA Style

Butkiewicz M, Lowe EW, Jr, Mueller R, Mendenhall JL, Teixeira PL, Weaver CD, Meiler J. Benchmarking Ligand-Based Virtual High-Throughput Screening with the PubChem Database. Molecules. 2013; 18(1):735-756.

Chicago/Turabian Style

Butkiewicz, Mariusz; Lowe, Edward W., Jr.; Mueller, Ralf; Mendenhall, Jeffrey L.; Teixeira, Pedro L.; Weaver, C. D.; Meiler, Jens. 2013. "Benchmarking Ligand-Based Virtual High-Throughput Screening with the PubChem Database." Molecules 18, no. 1: 735-756.

Molecules EISSN 1420-3049 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert