Naslov
Carcinogenicity modelling of diverse chemicals based on substructure grouping and support vector machines

Autori
Tanabe, Kazutoshi ; Lučić, Bono ; Amić, Dragan ; Suzuki, Takahiro

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Journal of Pharmacy and Pharmacology, 2009, Volume 61, Supplement 1, Meeting Abstract 88 / Jones, D - London : Delhi : John Wiley & Sons, 2009, A65-A66

Skup
The British Pharmaceutical Conference 2009

Mjesto i datum
Manchester, Ujedinjeno Kraljevstvo, 06.09.2009. - 09.09.2009

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
carcinogenicity ; QSAR ; support vector machines (SVM)

Sažetak
The prediction of carcinogenicity has become a subject of great significance for regulatory perspectives and ecotoxicity assessments. Several quantitative structure–activity relationship (QSAR) systems for predicting carcinogenicity were submitted to the Predictive Toxicology Challenge 2000–2001 Workshop ; however, the exercise revealed that performances of all proposed models were not sufficient in predicting carcinogenicities of test chemicals. In this study, an attempt was performed to construct a reliable QSAR model for predicting carcinogenicity of non- congeneric chemicals with a satisfactory performance. The support vector machines (SVM) approach was applied to develop QSAR models.

Izvorni jezik
Engleski

Znanstvena područja
Kemija

POVEZANOST RADA