PuSH - Publication Server of Helmholtz Zentrum München

Sushko, I. ; Novotarskyi, S. ; Körner, R. ; Pandey, A.K. ; Cherkasov, A.* ; Li, J.* ; Gramatica, P.* ; Hansen, K.* ; Schroeter, T.* ; Müller, K.R.* ; Xi, L.* ; Liu, H.* ; Yao, X.* ; Öberg, T.* ; Hormozdiari, F.* ; Dao, P.* ; Sahinalp, C.* ; Todeschini, R.* ; Polishchuk, P.* ; Artemenko, A.* ; Kuz'min, V.* ; Martin, T.M.* ; Young, D.M.* ; Fourches, D.* ; Muratov, E.* ; Tropsha, A.* ; Baskin, I.* ; Horvath, D.* ; Marcou, G.* ; Müller, C.* ; Varnek, A.* ; Prokopenko, V.V.* ; Tetko, I.V.

Applicability domains for classification problems: Benchmarking of distance to models for ames mutagenicity set.

J. Chem. Inf. Model. 50, 2094-2111 (2010)
DOI PMC
Open Access Green as soon as Postprint is submitted to ZB.
The estimation of accuracy and applicability of QSAR and QSPR models for biological and physicochemical properties represents a critical problem. The developed parameter of "distance to model" (DM) is defined as a metric of similarity between the training and test set compounds that have been subjected to QSAR/QSPR modeling. In our previous work, we demonstrated the utility and optimal performance of DM metrics that have been based on the standard deviation within an ensemble of QSAR models. The current study applies such analysis to 30 QSAR models for the Ames mutagenicity data set that were previously reported within the 2009 QSAR challenge. We demonstrate that the DMs based on an ensemble (consensus) model provide systematically better performance than other DMs. The presented approach identifies 30-60% of compounds having an accuracy of prediction similar to the interlaboratory accuracy of the Ames test, which is estimated to be 90%. Thus, the in silico predictions can be used to halve the cost of experimental measurements by providing a similar prediction accuracy. The developed model has been made publicly available at http://ochem.eu/models/1 .
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Corresponding Author
Keywords artificial neural networks; support vector machines; partial least-squares; e-state indexes; quantitative structure; uncertainty assessment; qspr models; qsar models; selection; accuracy
ISSN (print) / ISBN 0021-9576
e-ISSN 1520-5142
Journal Journal of Chemical Information and Modeling
Quellenangaben Volume: 50, Issue: 12, Pages: 2094-2111 Article Number: , Supplement: ,
Publisher American Chemical Society (ACS)
Non-patent literature Publications
Reviewing status Peer reviewed
Institute(s) Institute of Bioinformatics and Systems Biology (IBIS)