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

Abstract

This report describes a coordinated use of four quantitative structure-activity relationship (QSAR) programs and an expert knowledge base system to predict the occurrence and the mode of action of chemical carcinogenesis in rodents. QSAR models were based upon a weight-of-evidence paradigm of carcinogenic activity that was linked to chemical structures (n = 1,572). Identical training data sets were configured for four QSAR programs (MC4PC, MDL-QSAR, BioEpisteme, and Leadscope PDM), and QSAR models were constructed for the male rat, female rat, composite rat, male mouse, female mouse, composite mouse, and rodent composite endpoints. Model predictions were adjusted to favor high specificity (>80%). Performance was shown to be affected by the method used to score carcinogenicity study findings and the ratio of the number of active to inactive chemicals in the QSAR training data set. Results demonstrated that the four QSAR programs were complementary, each detecting different profiles of carcinogens. Accepting any positive prediction from two programs showed better overall performance than either of the single programs alone; specificity, sensitivity, and Chi-square values were 72.9%, 65.9%, and 223, respectively, compared to 84.5%, 45.8%, and 151. Accepting only consensus-positive predictions using any two programs had the best overall performance and higher confidence; specificity, sensitivity, and Chi-square values were 85.3%, 57.5%, and 287, respectively. Specific examples are provided to demonstrate that consensus-positive predictions of carcinogenicity by two QSAR programs identified both genotoxic and nongenotoxic carcinogens and that they detected 98.7% of the carcinogens linked in this study to Derek for Windows defined modes of action.

Genetic Toxicity:In VitroApproaches for Medicinal Chemists

“…The first branch is based on mathematical algorithms, which generate a statistical assessment of risk by the definition of quantitative structure-activity relationships (QSAR), based on correlations between molecular structure and genotoxicity endpoints. Examples of these are MC4PC (MultiCASE), MDL-QSAR (MDL), BioEpisteme (Prous Science), and Predictive Data Miner (LeadScope) [17,18]. In general, these methods have high specificity and low sensitivity.…”

Using In Silico Tools in a Weight of Evidence Approach to Aid Toxicological Assessment

“…In consensus QSAR, many models have been built using approaches such as genetic algorithms to derive a number of QSAR models based on the same data. [22] In addition, Matthews et al [24] have demonstrated how structural alert models can be incorporated into a consensus model to add mechanistic understanding. Consensus modelling differs from a WoE approach as only the predictions of toxicity are used to reach the final conclusion in a consensus approach.…”

3,5-Dibenzyloxy-4'-hydroxystilbene induces early caspase-9 activation during apoptosis in human K562 chronic myelogenous leukemia cells

“…Statistics are calculated to determine whether there is a significant association between the chemical family and the biological response (Roberts et al, 2000). The software has been used and validated by many organizations, including the US FDA, to analyze the relationships between chemical structural features and toxicity data (Matthews et al, 2008).…”