* Leave-one-out cross-validation (LOO CV) procedure is performed using the whole PASS training set for validation of prediction quality. The prediction result is compared with known experimental data for the studied compound. The procedure is repeated for all compounds from the PASS training set; then the average Invariant Accuracy of Prediction (IAP=1-IEP) values are calculated for each biological activity and for all biological activites.
IAP equals numerically to ROC AUC

* Leave-one-out cross-validation (LOO CV) procedure is performed using the whole PASS training set for validation of prediction quality. The prediction result is compared with known experimental data for the studied compound. The procedure is repeated for all compounds from the PASS training set; then the average Invariant Accuracy of Prediction (IAP=1-IEP) values are calculated for each biological activity and for all biological activites.
IAP equals numerically to ROC AUC

Training sets were created on the basis of the data on the drug metabolism. They include the structures of single electroneutral organic molecules with molecular weight of 50 - 1250 Da and the data on the drug metabolism.

Substrate training set consists of 3411 compounds and allows predicting substrate specificity for 18 enzyme. The average accuracy calculated by leave-one-out cross-validation procedure (ROC AUC) is 0.934. Click to Substrate data to see the information about the accuracy of prediction for each enzyme of substrate-based training set.

Metabolite-based training set consists of 2104 compounds and allows predicting if compound could be the metabolite for 18 enzyme. The average accuracy calculated by leave-one-out cross-validation procedure (ROC AUC) is 0.835. Click to Metabolite data to see the information about the accuracy of prediction for each enzyme of Metabolite-based training set.