CORAL: QSPR model of water solubility based on local and global SMILES attributes

Andrey A. Toropov, Alla P. Toropova, Emilio Benfenati, Giuseppina Gini, Danuta Leszczynska, Jerzy Leszczynski

Research output: Contribution to journalArticlepeer-review

Abstract

Water solubility is an important characteristic of a chemical in many aspects. However experimental definition of the endpoint for all substances is impossible. In this study quantitative structure-property relationships (QSPRs) for negative logarithm of water solubility-logS (molL-1) are built up for five random splits into the sub-training set (≈55%), the calibration set (≈25%), and the test set (≈20%). Simplified molecular input-line entry system (SMILES) is used as the representation of the molecular structure. Optimal SMILES-based descriptors are calculated by means of the Monte Carlo method using the CORAL software (http://www.insilico.eu/coral). These one-variable models for water solubility are characterized by the following average values of the statistical characteristics: nsub_train=725-763; ncalib=312-343; ntest=231-261; rsub_train2=0.9211±0.0028; rcalib2=0.9555±0.0045; rtest2=0.9365±0.0073; ssub_train=0.561±0.0086; scalib=0.453±0.0209; stest=0.520±0.0205. Thus, the reproducibility of statistical quality of suggested models for water solubility confirmed for five various splits.

Original languageEnglish
Pages (from-to)877-880
Number of pages4
JournalChemosphere
Volume90
Issue number2
DOIs
Publication statusPublished - Jan 2013

Keywords

  • CORAL software
  • Monte Carlo technique
  • QSPR
  • Water solubility

ASJC Scopus subject areas

  • Environmental Chemistry
  • Chemistry(all)

Fingerprint Dive into the research topics of 'CORAL: QSPR model of water solubility based on local and global SMILES attributes'. Together they form a unique fingerprint.

Cite this