QSAR models for anti-androgenic effect - a preliminary study

Research output: Contribution to journalJournal article – Annual report year: 2011Researchpeer-review

Standard

QSAR models for anti-androgenic effect - a preliminary study. / Jensen, Gunde Egeskov; Nikolov, Nikolai Georgiev; Wedebye, Eva Bay; Ringsted, Tine; Niemelä, Jay Russell.

In: S A R and Q S A R in Environmental Research, Vol. 22, No. 1-2, Sp. Iss. SI, 2011, p. 35-49.

Research output: Contribution to journalJournal article – Annual report year: 2011Researchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{19dade49be0446e9a190ec8000ffc9ea,
title = "QSAR models for anti-androgenic effect - a preliminary study",
abstract = "Three modelling systems (MultiCase (R), LeadScope (R) and MDL (R) QSAR) were used for construction of androgenic receptor antagonist models. There were 923-942 chemicals in the training sets. The models were cross-validated (leave-groups-out) with concordances of 77-81{\%}, specificity of 78-91{\%} and sensitivity of 51-76{\%}. The specificity was highest in the MultiCase (R) model and the sensitivity was highest in the MDL (R) QSAR model. A complementary use of the models may be a valuable tool when optimizing the prediction of chemicals for androgenic receptor antagonism. When evaluating the fitness of the model for a particular application, balance of training sets, domain definition, and cut-offs for prediction interpretation should also be taken into account. Different descriptors in the modelling systems are illustrated with hydroxyflutamide and dexamethasone as examples (a non-steroid and a steroid anti-androgen, respectively). More research concerning the mechanism of anti-androgens would increase the possibility for further optimization of the QSAR models. Further expansion of the basis for the models is in progress, including the addition of more drugs.",
keywords = "LeadScope, MultiCase, MDL, QSAR, Anti-androgen",
author = "Jensen, {Gunde Egeskov} and Nikolov, {Nikolai Georgiev} and Wedebye, {Eva Bay} and Tine Ringsted and Niemel{\"a}, {Jay Russell}",
year = "2011",
doi = "10.1080/1062936X.2010.528981",
language = "English",
volume = "22",
pages = "35--49",
journal = "S A R and Q S A R in Environmental Research",
issn = "1062-936X",
publisher = "CRC Press/Balkema",
number = "1-2, Sp. Iss. SI",

}

RIS

TY - JOUR

T1 - QSAR models for anti-androgenic effect - a preliminary study

AU - Jensen, Gunde Egeskov

AU - Nikolov, Nikolai Georgiev

AU - Wedebye, Eva Bay

AU - Ringsted, Tine

AU - Niemelä, Jay Russell

PY - 2011

Y1 - 2011

N2 - Three modelling systems (MultiCase (R), LeadScope (R) and MDL (R) QSAR) were used for construction of androgenic receptor antagonist models. There were 923-942 chemicals in the training sets. The models were cross-validated (leave-groups-out) with concordances of 77-81%, specificity of 78-91% and sensitivity of 51-76%. The specificity was highest in the MultiCase (R) model and the sensitivity was highest in the MDL (R) QSAR model. A complementary use of the models may be a valuable tool when optimizing the prediction of chemicals for androgenic receptor antagonism. When evaluating the fitness of the model for a particular application, balance of training sets, domain definition, and cut-offs for prediction interpretation should also be taken into account. Different descriptors in the modelling systems are illustrated with hydroxyflutamide and dexamethasone as examples (a non-steroid and a steroid anti-androgen, respectively). More research concerning the mechanism of anti-androgens would increase the possibility for further optimization of the QSAR models. Further expansion of the basis for the models is in progress, including the addition of more drugs.

AB - Three modelling systems (MultiCase (R), LeadScope (R) and MDL (R) QSAR) were used for construction of androgenic receptor antagonist models. There were 923-942 chemicals in the training sets. The models were cross-validated (leave-groups-out) with concordances of 77-81%, specificity of 78-91% and sensitivity of 51-76%. The specificity was highest in the MultiCase (R) model and the sensitivity was highest in the MDL (R) QSAR model. A complementary use of the models may be a valuable tool when optimizing the prediction of chemicals for androgenic receptor antagonism. When evaluating the fitness of the model for a particular application, balance of training sets, domain definition, and cut-offs for prediction interpretation should also be taken into account. Different descriptors in the modelling systems are illustrated with hydroxyflutamide and dexamethasone as examples (a non-steroid and a steroid anti-androgen, respectively). More research concerning the mechanism of anti-androgens would increase the possibility for further optimization of the QSAR models. Further expansion of the basis for the models is in progress, including the addition of more drugs.

KW - LeadScope

KW - MultiCase

KW - MDL

KW - QSAR

KW - Anti-androgen

U2 - 10.1080/1062936X.2010.528981

DO - 10.1080/1062936X.2010.528981

M3 - Journal article

VL - 22

SP - 35

EP - 49

JO - S A R and Q S A R in Environmental Research

JF - S A R and Q S A R in Environmental Research

SN - 1062-936X

IS - 1-2, Sp. Iss. SI

ER -