We describe a novel approach of reaction representation as a combination of two mixtures: a mixture of reactants and a mixture of products. In turn, each mixture can be encoded using an earlier reported approach involving simplex descriptors (SiRMS). The feature vector representing these two mixtures results from either concatenated product and reactant descriptors or the difference between descriptors of products and reactants. This reaction representation doesn't need an explicit labeling of a reaction center. The rigorous "product-out" cross-validation (CV) strategy has been suggested. Unlike the naïve "reaction-out" CV approach based on a random selection of items, the proposed one provides with more realistic estimation of prediction accuracy for reactions resulting in novel products. The new methodology has been applied to model rate constants of E2 reactions. It has been demonstrated that the use of the fragment control domain applicability approach significantly increases prediction accuracy of the models. The models obtained with new "mixture" approach performed better than those required either explicit (Condensed Graph of Reaction) or implicit (reaction fingerprints) reaction center labeling.

A 5 Bogatsky Physico Chemical Institute of National Academy of Sciences of Ukraine Odessa Ukraine

A M Butlerov Institute of Chemistry Kazan Federal University Kazan Russia

Department of General and Organic Chemistry Kazan State Medical University Kazan Russia

Institute of Molecular and Translational Medicine Faculty of Medicine and Dentistry Palacky University Olomouc Czech Republic

Laboratory of Chemoinformatics University of Strasbourg Strasbourg France

Zobrazit více v PubMed

J Chem Inf Model. 2012 Sep 24;52(9):2325-38 PubMed

J Chem Inf Comput Sci. 2003 May-Jun;43(3):707-20 PubMed

J Chem Inf Model. 2005 Nov-Dec;45(6):1775-83 PubMed

J Chem Inf Model. 2012 Dec 21;52(12):3116-22 PubMed

J Mol Model. 2005 Nov;11(6):457-67 PubMed

J Chem Inf Model. 2006 Nov-Dec;46(6):2256-66 PubMed

J Chem Inf Model. 2015 Feb 23;55(2):239-50 PubMed

J Comput Aided Mol Des. 2005 Sep-Oct;19(9-10):693-703 PubMed

Bioinformatics. 2008 Jan 15;24(2):225-33 PubMed

ChemMedChem. 2008 May;3(5):821-32 PubMed

J Chem Inf Model. 2010 May 24;50(5):742-54 PubMed

J Chem Inf Model. 2015 Jan 26;55(1):39-53 PubMed

Mol Inform. 2010 Dec 17;29(12):855-68 PubMed

J Comput Aided Mol Des. 2008 Jun-Jul;22(6-7):403-21 PubMed

Mol Inform. 2012 Jul;31(6-7):491-502 PubMed

J Chem Inf Model. 2009 May;49(5):1163-84 PubMed