MDL-QSAR

The FDA [51] has used the MDL QSAR software [19] to develop QSARs for the carcinogenic potential of pharmaceuticals and organic chemicals. These were validated using a test set of 108 compounds, with 72% correct prediction of carcinogens and 72% correct prediction of noncarcinogens. 

MDL QSAR MDL Information Systems, Inc. www.mdl.com/products/predictive/qsar/index.jsp Molecular property descriptors, total topological descriptors, E-state indices... 

TABLE 11.3. Summary of in silica predictive toxicological evaluations of onchidal by Derek for Windows and MDL-QSAR... 

MDL-QSAR Classified as low potential for rodent mutation in vivo Classified as high potential for rodent carcinogenicity High probability 0.8677 Low probability 0.1322... 

FIGURE 11.4. The MDL-QSAR version 2.2.2.0.7 prediction for mutagenic potential of onchidal in Salmonella typhimurium. 

Contrera, J.F., Matthews, E.J., Kruhlak, N.L., Benz, R.D. (2005). In silico screening of chemicals for bacterial mutagenicity using electrotopological E-state indices and MDL-QSAR software. Regul. Toxicol. Pharmacol. 43 313-23. 

For a constituent of an additive with equivocal (mixed positive and negative) battery of genetic toxicity tests and a EDI of < 150 pg/p/d, SAR analysis for SAs and predictive software such as MDL QSAR (Contrera et al, 2005) and MultiCASE s MC4PC (Rosenkranz and Klopman, 1988 Matthews and Contrera, 1998) may be used as part of the weight of evidence approach in assessing the safety of the compound. If a constituent were of potential concern, a quantitative SAR analysis might be feasible to characterize the expected risk. 

Contrera JF, Matthews EJ, Kruhlak NL, Benz RD. In silico screening of chemicals for genetic toxicity using MDL-QSAR, nonparametric discriminant analysis, E-state, connectivity, and molecular property descriptors. Toxicol Mech Methods. 2008 f8(2-3) 207-2f6. 

Matthews EJ, Kruhlak NL, Benz RD et al (2008) Combined use of MC4PC, MDL-QSAR, BioEpisteme, Leadscope PDM, and Derek for Windows Software to Achieve High-performance, high-confidence, mode of action-based predictions of chemical carcinogenesis in rodents. Toxicol Mech Methods 18 189-206. doi 10.1080/15376510701857379... 

---