Virtual screening based on one-class classification

DOI10.1134/S0012500811040082MaRDI QIDQ2900848zbMATH OpenOpenAlexWikidataFDO

Authors P. V. Karpov, I. I. Baskin, V. A. Palyulin, N. S. Zefirov

Publication date 26 July 2012

Published in Doklady Akademii Nauk (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1134/s0012500811040082

zbMATH Keywords

ligandsLOOCV methodQSAR/QSPR methodTanimoto index

Mathematics Subject Classification ID

Chemistry (92E99)

Review text

This paper is devoted to the virtual screening of a data base of ligands structure. The method of one-class classification is used. For ligands' parameters presented in the DUD (Directory of Useful Decoys) there are calculated fragmentary descriptors and then by the ``leave-one-out cross validation method and by the SVM (Support Vector Machines) method the one-class model is constructed. The Gauss function is applied to nonlinear transform tool.

Recommendations

• Fuzzy one-class support vector machines
• A neuro-fuzzy approach to virtual screening in molecular bioinformatics
• Milp-hyperbox classification for structure-based drug design in the discovery of small molecule inhibitors of SIRTUIN6
• One-class classification methods via automatic counter-example generation
• The virtual screening of the drug protein with a few crystal structures based on the adaboost-SVM

Cited in

(2)

• Milp-hyperbox classification for structure-based drug design in the discovery of small molecule inhibitors of SIRTUIN6
• The virtual screening of the drug protein with a few crystal structures based on the adaboost-SVM

This page was built for publication: Virtual screening based on one-class classification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2900848)