Predicting drug-protein interactions from heterogeneous biological data sources is a key step for in silico drug discovery. The difficulty of this prediction task lies in the rarity of known drug-protein interactions and myriad unknown interactions to be predicted. To meet this challenge, a manifold regularization semi-supervised learning method is presented to tackle this issue by using labeled and unlabeled information which often generates better results than using the labeled data alone. Furthermore, our semi-supervised learning method integrates known drug-protein interaction network information as well as chemical structure and genomic sequence data. Using the proposed method, we predicted certain drug-protein interactions on the enzyme, ion channel, GPCRs, and nuclear receptor data sets. Some of them are confirmed by the latest publicly available drug targets databases such as KEGG. We report encouraging results of using our method for drug-protein interaction network reconstruction which may shed light on the molecular interaction inference and new uses of marketed drugs.