| Literature DB >> 20106561 |
Andrey A Toropov1, Alla P Toropova, Ivan Raska, Emilio Benfenati.
Abstract
Three different splits into the subtraining set (n = 22), the set of calibration (n = 21), and the test set (n = 12) of 55 antineoplastic agents have been examined. By the correlation balance of SMILES-based optimal descriptors quite satisfactory models for the octanol/water partition coefficient have been obtained on all three splits. The correlation balance is the optimization of a one-variable model with a target function that provides both the maximal values of the correlation coefficient for the subtraining and calibration set and the minimum of the difference between the above-mentioned correlation coefficients. Thus, the calibration set is a preliminary test set. Copyright (c) 2009 Elsevier Masson SAS. All rights reserved.Entities:
Mesh:
Substances:
Year: 2010 PMID: 20106561 DOI: 10.1016/j.ejmech.2009.12.043
Source DB: PubMed Journal: Eur J Med Chem ISSN: 0223-5234 Impact factor: 6.514