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 journalArticle

18 Citations (Scopus)

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

Fingerprint

Quantitative Structure-Activity Relationship
Solubility
solubility
Water
train
Monte Carlo Method
water
Molecular Structure
Molecular structure
Calibration
Monte Carlo methods
Software
calibration
software
attribute

Keywords

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

ASJC Scopus subject areas

  • Environmental Chemistry
  • Chemistry(all)

Cite this

Toropov, A. A., Toropova, A. P., Benfenati, E., Gini, G., Leszczynska, D., & Leszczynski, J. (2013). CORAL: QSPR model of water solubility based on local and global SMILES attributes. Chemosphere, 90(2), 877-880. https://doi.org/10.1016/j.chemosphere.2012.07.035

CORAL : QSPR model of water solubility based on local and global SMILES attributes. / Toropov, Andrey A.; Toropova, Alla P.; Benfenati, Emilio; Gini, Giuseppina; Leszczynska, Danuta; Leszczynski, Jerzy.

In: Chemosphere, Vol. 90, No. 2, 01.2013, p. 877-880.

Research output: Contribution to journalArticle

Toropov, AA, Toropova, AP, Benfenati, E, Gini, G, Leszczynska, D & Leszczynski, J 2013, 'CORAL: QSPR model of water solubility based on local and global SMILES attributes', Chemosphere, vol. 90, no. 2, pp. 877-880. https://doi.org/10.1016/j.chemosphere.2012.07.035
Toropov, Andrey A. ; Toropova, Alla P. ; Benfenati, Emilio ; Gini, Giuseppina ; Leszczynska, Danuta ; Leszczynski, Jerzy. / CORAL : QSPR model of water solubility based on local and global SMILES attributes. In: Chemosphere. 2013 ; Vol. 90, No. 2. pp. 877-880.
@article{813b5df333144362ba67712a37172d2e,
title = "CORAL: QSPR model of water solubility based on local and global SMILES attributes",
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.",
keywords = "CORAL software, Monte Carlo technique, QSPR, Water solubility",
author = "Toropov, {Andrey A.} and Toropova, {Alla P.} and Emilio Benfenati and Giuseppina Gini and Danuta Leszczynska and Jerzy Leszczynski",
year = "2013",
month = "1",
doi = "10.1016/j.chemosphere.2012.07.035",
language = "English",
volume = "90",
pages = "877--880",
journal = "Chemosphere",
issn = "0045-6535",
publisher = "Elsevier Limited",
number = "2",

}

TY - JOUR

T1 - CORAL

T2 - QSPR model of water solubility based on local and global SMILES attributes

AU - Toropov, Andrey A.

AU - Toropova, Alla P.

AU - Benfenati, Emilio

AU - Gini, Giuseppina

AU - Leszczynska, Danuta

AU - Leszczynski, Jerzy

PY - 2013/1

Y1 - 2013/1

N2 - 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.

AB - 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.

KW - CORAL software

KW - Monte Carlo technique

KW - QSPR

KW - Water solubility

UR - http://www.scopus.com/inward/record.url?scp=84869885324&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869885324&partnerID=8YFLogxK

U2 - 10.1016/j.chemosphere.2012.07.035

DO - 10.1016/j.chemosphere.2012.07.035

M3 - Article

VL - 90

SP - 877

EP - 880

JO - Chemosphere

JF - Chemosphere

SN - 0045-6535

IS - 2

ER -