CORAL: The prediction of biodegradation of organic compounds with optimal SMILES-based descriptors

Andrey A. Toropov, Alla P. Toropova, Anna Lombardo, Alessandra Roncaglioni, Nicoletta De Brita, Giovanni Stella, Emilio Benfenati

Research output: Contribution to journalArticle

Abstract

CORAL software (http:/www.insilico.eu/coral) has been used to build up quantitative structure-biodegradation relationships (QSPR). The normalized degradation percentage has been used as the measure of biodegradation (for diverse organic compounds, n=445). Six random splits into sub-training, calibration, and test sets were examined. For each split the QSPR one-variable linear regression model based on the SMILES-based optimal descriptors has been built up. The average values of numbers of compounds and the correlation coefficients (r 2) between experimental and calculated biodegradability values of these six models for the test sets are n=88.2±11.7 and r 2=0.728±0.05. These six models were further tested against a set of chemicals (n=285) for which only categorical values (biodegradable or not) were available. Thus we also evaluated the use of the model as a classifier. The average values of the sensitivity, specificity, and accuracy were 0.811±0.019, 0.795±0.024, and 0.803±0.008, respectively.

Original languageEnglish
Pages (from-to)1042-1048
Number of pages7
JournalCentral European Journal of Chemistry
Volume10
Issue number4
DOIs
Publication statusPublished - Aug 2012

Fingerprint

Biodegradation
Organic compounds
Biodegradability
Linear regression
Classifiers
Calibration
Degradation

Keywords

  • Biodegradability
  • CORAL software
  • QSPR
  • SMILES

ASJC Scopus subject areas

  • Chemistry(all)
  • Materials Chemistry

Cite this

CORAL : The prediction of biodegradation of organic compounds with optimal SMILES-based descriptors. / Toropov, Andrey A.; Toropova, Alla P.; Lombardo, Anna; Roncaglioni, Alessandra; De Brita, Nicoletta; Stella, Giovanni; Benfenati, Emilio.

In: Central European Journal of Chemistry, Vol. 10, No. 4, 08.2012, p. 1042-1048.

Research output: Contribution to journalArticle

@article{8a83e8d2523f403a8804e28aba5a1f0e,
title = "CORAL: The prediction of biodegradation of organic compounds with optimal SMILES-based descriptors",
abstract = "CORAL software (http:/www.insilico.eu/coral) has been used to build up quantitative structure-biodegradation relationships (QSPR). The normalized degradation percentage has been used as the measure of biodegradation (for diverse organic compounds, n=445). Six random splits into sub-training, calibration, and test sets were examined. For each split the QSPR one-variable linear regression model based on the SMILES-based optimal descriptors has been built up. The average values of numbers of compounds and the correlation coefficients (r 2) between experimental and calculated biodegradability values of these six models for the test sets are n=88.2±11.7 and r 2=0.728±0.05. These six models were further tested against a set of chemicals (n=285) for which only categorical values (biodegradable or not) were available. Thus we also evaluated the use of the model as a classifier. The average values of the sensitivity, specificity, and accuracy were 0.811±0.019, 0.795±0.024, and 0.803±0.008, respectively.",
keywords = "Biodegradability, CORAL software, QSPR, SMILES",
author = "Toropov, {Andrey A.} and Toropova, {Alla P.} and Anna Lombardo and Alessandra Roncaglioni and {De Brita}, Nicoletta and Giovanni Stella and Emilio Benfenati",
year = "2012",
month = "8",
doi = "10.2478/s11532-012-0031-4",
language = "English",
volume = "10",
pages = "1042--1048",
journal = "Central European Journal of Chemistry",
issn = "1895-1066",
publisher = "Central European Science Journals",
number = "4",

}

TY - JOUR

T1 - CORAL

T2 - The prediction of biodegradation of organic compounds with optimal SMILES-based descriptors

AU - Toropov, Andrey A.

AU - Toropova, Alla P.

AU - Lombardo, Anna

AU - Roncaglioni, Alessandra

AU - De Brita, Nicoletta

AU - Stella, Giovanni

AU - Benfenati, Emilio

PY - 2012/8

Y1 - 2012/8

N2 - CORAL software (http:/www.insilico.eu/coral) has been used to build up quantitative structure-biodegradation relationships (QSPR). The normalized degradation percentage has been used as the measure of biodegradation (for diverse organic compounds, n=445). Six random splits into sub-training, calibration, and test sets were examined. For each split the QSPR one-variable linear regression model based on the SMILES-based optimal descriptors has been built up. The average values of numbers of compounds and the correlation coefficients (r 2) between experimental and calculated biodegradability values of these six models for the test sets are n=88.2±11.7 and r 2=0.728±0.05. These six models were further tested against a set of chemicals (n=285) for which only categorical values (biodegradable or not) were available. Thus we also evaluated the use of the model as a classifier. The average values of the sensitivity, specificity, and accuracy were 0.811±0.019, 0.795±0.024, and 0.803±0.008, respectively.

AB - CORAL software (http:/www.insilico.eu/coral) has been used to build up quantitative structure-biodegradation relationships (QSPR). The normalized degradation percentage has been used as the measure of biodegradation (for diverse organic compounds, n=445). Six random splits into sub-training, calibration, and test sets were examined. For each split the QSPR one-variable linear regression model based on the SMILES-based optimal descriptors has been built up. The average values of numbers of compounds and the correlation coefficients (r 2) between experimental and calculated biodegradability values of these six models for the test sets are n=88.2±11.7 and r 2=0.728±0.05. These six models were further tested against a set of chemicals (n=285) for which only categorical values (biodegradable or not) were available. Thus we also evaluated the use of the model as a classifier. The average values of the sensitivity, specificity, and accuracy were 0.811±0.019, 0.795±0.024, and 0.803±0.008, respectively.

KW - Biodegradability

KW - CORAL software

KW - QSPR

KW - SMILES

UR - http://www.scopus.com/inward/record.url?scp=84867100893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867100893&partnerID=8YFLogxK

U2 - 10.2478/s11532-012-0031-4

DO - 10.2478/s11532-012-0031-4

M3 - Article

AN - SCOPUS:84867100893

VL - 10

SP - 1042

EP - 1048

JO - Central European Journal of Chemistry

JF - Central European Journal of Chemistry

SN - 1895-1066

IS - 4

ER -