Predicting Biological Functions of Compounds Based on Chemical-Chemical Interactions

Hu, Le-Le; Chen, Chen; Huang, Tao; Cai, Yu-Dong; Chou, Kuo-Chen

Listed in Table 2 are the accuracies by each of the 11 prediction orders for the 3,137 compounds about their involvement in the 11 metabolic pathway classes using the 5-fold crossvalidation test. The highest accuracy achieved by the 1 st -order prediction was 80.96% for the 1 st metabolic pathway class (''Carbohydrate Metabolism''). And the results obtained by the 1 st and 2 nd prediction orders have covered 89.00% of the true metabolic pathway classes. The second highest accuracy by the 1 storder prediction was 78.77% for the 11 th metabolic pathway class (Xenobiotics Biodegradation and Metabolism), while the results obtained by the 1 st and 2 nd prediction orders have covered 87.00% of the true metabolic pathway classes. Both the two 1 st -order accuracies are higher than the overall 1 st -order prediction accuracy of 77.97%, and each of their combinations with the 2 nd -order predictions is also higher than the overall likelihood of 80.00%. As for the metabolic pathway classes with less compounds, such as ''Glycan Biosynthesis and Metabolism'' class that contains only 68 compounds in Group-I and 43 in Group-II (cf . Table 1) , the predicted accuracies were relatively not as good as the others. It is anticipated that with more experimental data are available in future for the compounds in these classes, the corresponding prediction success rates will be improved. Overall speaking, the aforementioned results are quite encouraging, indicating that our approach may become a useful tool to deal with this kind of very complicated systems.