Fig 3. Performance measures for all of the independent datasets of the PubChem dataset.

We measured various performances such as sensitivity (Sen.), specificity (Spe.), precision (Pre.), accuracy (Acc.), and F1 score (F1) from the prediction results given by descriptors (A-D). (A) All queried PubChem datasets. (B) PubChem dataset whose compounds are not in the training dataset. (C) PubChem dataset whose targets are not in the training dataset. (D) PubChem dataset whose compounds and targets are not in the training dataset. Our convolution model shows better performances for all datasets in terms of accuracy and F1 score.