CORAL: QSAR models for acute toxicity in fathead minnow (Pimephales promelas)

A. P. Toropova, A. A. Toropov, A. Lombardo, A. Roncaglioni, E. Benfenati, G. Gini

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

CORrelation And Logic (CORAL) is a software that generates quantitative structure activity relationships (QSAR) for different endpoints. This study is dedicated to the QSAR analysis of acute toxicity in Fathead minnow (Pimephales promelas). Statistical quality for the external test set is a complex function of the split (into training and test subsets), the number of epochs of the Monte Carlo optimization, and the threshold that is a criterion for dividing the correlation weights into two classes rare (blocked) and not rare (active). Computational experiments with three random splits (data on 568 compounds) indicated that this approach can satisfactorily predict the desired endpoint (the negative decimal logarithm of the 50% lethal concentration, in mmol/L, pLC 50). The average correlation coefficients (r 2) are 0.675 ± 0.0053, 0.824 6 0.0242, 0.787 ± 0.0101 for subtraining, calibration, and test set, respectively. The average standard errors of estimation (s) are 0.837 ± 0.021, 0.555 ± 0.047, 0.606 ± 0.049 for subtraining, calibration, and test set, respectively. The CORAL software together with three random splits into subtraining, calibration, and test sets can be downloaded on the Internet (http://www.insilico.eu/coral/).

Original languageEnglish
Pages (from-to)1218-1223
Number of pages6
JournalJournal of Computational Chemistry
Volume33
Issue number12
DOIs
Publication statusPublished - May 5 2012

Fingerprint

Cyprinidae
Quantitative Structure-activity Relationship
Quantitative Structure-Activity Relationship
Test Set
Toxicity
Acute
Calibration
Logic
Software
Anthozoa
Monte Carlo Optimization
Internet
Complex Functions
Standard error
Logarithm
Computational Experiments
Correlation coefficient
Model
Weights and Measures
Predict

Keywords

  • Acute toxicity
  • CORAL software
  • Fathead minnow
  • Optimal descriptor
  • QSAR

ASJC Scopus subject areas

  • Chemistry(all)
  • Computational Mathematics
  • Medicine(all)

Cite this

CORAL : QSAR models for acute toxicity in fathead minnow (Pimephales promelas). / Toropova, A. P.; Toropov, A. A.; Lombardo, A.; Roncaglioni, A.; Benfenati, E.; Gini, G.

In: Journal of Computational Chemistry, Vol. 33, No. 12, 05.05.2012, p. 1218-1223.

Research output: Contribution to journalArticle

@article{6ab4cff69247495993d9701fc59da020,
title = "CORAL: QSAR models for acute toxicity in fathead minnow (Pimephales promelas)",
abstract = "CORrelation And Logic (CORAL) is a software that generates quantitative structure activity relationships (QSAR) for different endpoints. This study is dedicated to the QSAR analysis of acute toxicity in Fathead minnow (Pimephales promelas). Statistical quality for the external test set is a complex function of the split (into training and test subsets), the number of epochs of the Monte Carlo optimization, and the threshold that is a criterion for dividing the correlation weights into two classes rare (blocked) and not rare (active). Computational experiments with three random splits (data on 568 compounds) indicated that this approach can satisfactorily predict the desired endpoint (the negative decimal logarithm of the 50{\%} lethal concentration, in mmol/L, pLC 50). The average correlation coefficients (r 2) are 0.675 ± 0.0053, 0.824 6 0.0242, 0.787 ± 0.0101 for subtraining, calibration, and test set, respectively. The average standard errors of estimation (s) are 0.837 ± 0.021, 0.555 ± 0.047, 0.606 ± 0.049 for subtraining, calibration, and test set, respectively. The CORAL software together with three random splits into subtraining, calibration, and test sets can be downloaded on the Internet (http://www.insilico.eu/coral/).",
keywords = "Acute toxicity, CORAL software, Fathead minnow, Optimal descriptor, QSAR",
author = "Toropova, {A. P.} and Toropov, {A. A.} and A. Lombardo and A. Roncaglioni and E. Benfenati and G. Gini",
year = "2012",
month = "5",
day = "5",
doi = "10.1002/jcc.22953",
language = "English",
volume = "33",
pages = "1218--1223",
journal = "Journal of Computational Chemistry",
issn = "0192-8651",
publisher = "John Wiley and Sons Inc.",
number = "12",

}

TY - JOUR

T1 - CORAL

T2 - QSAR models for acute toxicity in fathead minnow (Pimephales promelas)

AU - Toropova, A. P.

AU - Toropov, A. A.

AU - Lombardo, A.

AU - Roncaglioni, A.

AU - Benfenati, E.

AU - Gini, G.

PY - 2012/5/5

Y1 - 2012/5/5

N2 - CORrelation And Logic (CORAL) is a software that generates quantitative structure activity relationships (QSAR) for different endpoints. This study is dedicated to the QSAR analysis of acute toxicity in Fathead minnow (Pimephales promelas). Statistical quality for the external test set is a complex function of the split (into training and test subsets), the number of epochs of the Monte Carlo optimization, and the threshold that is a criterion for dividing the correlation weights into two classes rare (blocked) and not rare (active). Computational experiments with three random splits (data on 568 compounds) indicated that this approach can satisfactorily predict the desired endpoint (the negative decimal logarithm of the 50% lethal concentration, in mmol/L, pLC 50). The average correlation coefficients (r 2) are 0.675 ± 0.0053, 0.824 6 0.0242, 0.787 ± 0.0101 for subtraining, calibration, and test set, respectively. The average standard errors of estimation (s) are 0.837 ± 0.021, 0.555 ± 0.047, 0.606 ± 0.049 for subtraining, calibration, and test set, respectively. The CORAL software together with three random splits into subtraining, calibration, and test sets can be downloaded on the Internet (http://www.insilico.eu/coral/).

AB - CORrelation And Logic (CORAL) is a software that generates quantitative structure activity relationships (QSAR) for different endpoints. This study is dedicated to the QSAR analysis of acute toxicity in Fathead minnow (Pimephales promelas). Statistical quality for the external test set is a complex function of the split (into training and test subsets), the number of epochs of the Monte Carlo optimization, and the threshold that is a criterion for dividing the correlation weights into two classes rare (blocked) and not rare (active). Computational experiments with three random splits (data on 568 compounds) indicated that this approach can satisfactorily predict the desired endpoint (the negative decimal logarithm of the 50% lethal concentration, in mmol/L, pLC 50). The average correlation coefficients (r 2) are 0.675 ± 0.0053, 0.824 6 0.0242, 0.787 ± 0.0101 for subtraining, calibration, and test set, respectively. The average standard errors of estimation (s) are 0.837 ± 0.021, 0.555 ± 0.047, 0.606 ± 0.049 for subtraining, calibration, and test set, respectively. The CORAL software together with three random splits into subtraining, calibration, and test sets can be downloaded on the Internet (http://www.insilico.eu/coral/).

KW - Acute toxicity

KW - CORAL software

KW - Fathead minnow

KW - Optimal descriptor

KW - QSAR

UR - http://www.scopus.com/inward/record.url?scp=84860836409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860836409&partnerID=8YFLogxK

U2 - 10.1002/jcc.22953

DO - 10.1002/jcc.22953

M3 - Article

C2 - 22371019

AN - SCOPUS:84860836409

VL - 33

SP - 1218

EP - 1223

JO - Journal of Computational Chemistry

JF - Journal of Computational Chemistry

SN - 0192-8651

IS - 12

ER -