Categorical QSAR models for skin sensitization based on local lymph node assay measures and both ground and excited state 4D-fingerprint descriptors
- 155 Downloads
In previous studies we have developed categorical QSAR models for predicting skin-sensitization potency based on 4D-fingerprint (4D-FP) descriptors and in vivo murine local lymph node assay (LLNA) measures. Only 4D-FP derived from the ground state (GMAX) structures of the molecules were used to build the QSAR models. In this study we have generated 4D-FP descriptors from the first excited state (EMAX) structures of the molecules. The GMAX, EMAX and the combined ground and excited state 4D-FP descriptors (GEMAX) were employed in building categorical QSAR models. Logistic regression (LR) and partial least square coupled logistic regression (PLS-CLR), found to be effective model building for the LLNA skin-sensitization measures in our previous studies, were used again in this study. This also permitted comparison of the prior ground state models to those involving first excited state 4D-FP descriptors. Three types of categorical QSAR models were constructed for each of the GMAX, EMAX and GEMAX datasets: a binary model (2-state), an ordinal model (3-state) and a binary-binary model (two-2-state). No significant differences exist among the LR 2-state model constructed for each of the three datasets. However, the PLS-CLR 3-state and 2-state models based on the EMAX and GEMAX datasets have higher predictivity than those constructed using only the GMAX dataset. These EMAX and GMAX categorical models are also more significant and predictive than corresponding models built in our previous QSAR studies of LLNA skin-sensitization measures.
KeywordsSkin sensitization Categorical QSAR models Excited state structures
This work was funded by the National Institutes of Health through the NIH Roadmap for Medical Research, Grant 1 R21 GM075775-01. Information on Novel Preclinical Tools for Predictive ADME-Toxicology can be found at http://grants.nih.gov/grants/guide/rfa-files/RFA-RM-04-023.html. Links to nine initiatives are found at http://nihroadmap.nih.gov/initiatives.asp. This work was also supported in part by The Procter & Gamble Company. Resources of the Laboratory of Molecular Modeling and Design at UIC and The Chem21 Group, Inc. were used in performing these studies.
- 2.Song PS, Chin CA, Yamazaki I, Baba H (1975) Int J Quantum Chem 1Google Scholar
- 5.Ou C-N, Tsai C-H, Song P-S (1977) In: Castellani A (ed) Research in photobiology. Plenum Press, New York, pp 257–265Google Scholar
- 16.Gerberick GF, Ryan CA, Kern PS, Schlatter H, Dearman RJ, Kimber I, Patlewicz GY, Basketter DA (2005) Dermatitis 16:157Google Scholar
- 18.Contact Sensitisation: Classification According to Potency., European Centre for Ecotoxicology and Toxicology of Chemicals (ECETOC) (2003) Brussels, BelgiumGoogle Scholar
- 19.HyperChem Program Release 7.05 for Windows (2005) In: Hypercube, Inc.Google Scholar
- 22.Pearlstein RA (1998) CHEMLAB-II users guide. CHEMLAB Inc., Lake Forest, ILGoogle Scholar
- 27.Daganzo CF (1999) Logistics systems analysis. SpringerGoogle Scholar
- 28.Hosmer DW, Lemeshow S (2000) Applied logistic regression. John Wiley & Sons, Inc., New YorkGoogle Scholar
- 29.Institute, S., SAS/STAT User’s Guide, SAS Institute Inc., Cary, NC, 1999Google Scholar