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 language | English |
|---|---|
| Pages (from-to) | 1218-1223 |
| Number of pages | 6 |
| Journal | Journal of Computational Chemistry |
| Volume | 33 |
| Issue number | 12 |
| DOIs | |
| Publication status | Published - May 5 2012 |
Fingerprint
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 journal › Article
}
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 -