Collaborative Matrix Factorization with Soft Regularization for Drug-Target Interaction Prediction

Identifying the potential drug-target interactions (DTI) is critical in drug discovery. The drug-target interaction prediction methods based on collaborative filtering have demonstrated attractive prediction performance. However, many corresponding models cannot accurately express the relationship between similarity features and DTI features. In order to rationally represent the correlation, we propose a novel matrix factorization method, so-called collaborative matrix factorization with soft regularization (SRCMF). SRCMF improves the prediction performance by combining the drug and the target similarity information with matrix factorization. In contrast to general collaborative matrix factorization, the fundamental idea of SRCMF is to make the similarity features and the potential features of DTI approximate, not identical. Specifically, SRCMF obtains low-rank feature representations of drug similarity and target similarity, and then uses a soft regularization term to constrain the approximation between drug (target) similarity features and drug (target) potential features of DTI. To comprehensively evaluate the prediction performance of SRCMF, we conduct cross-validation experiments under three different settings. In terms of the area under the precision-recall curve (AUPR), SRCMF achieves better prediction results than six state-of-the-art methods. Besides, under different noise levels of similarity data, the prediction performance of SRCMF is much better than that of collaborative matrix factorization. In conclusion, SRCMF is robust leading to performance improvement in drug-target interaction prediction.

Automated summary

In this study, a novel matrix factorization method called collaborative matrix factorization with soft regularization (SRCMF) is proposed to improve prediction performance of drug-target interactions by combining drug and target similarity information with matrix factorization. SRCMF aims to approximate similarity features and potential features of DTI, rather than making them identical. Experimental results show that SRCMF achieves better prediction results in terms of AUPR compared to six state-of-the-art methods, and outperforms collaborative matrix factorization under different noise levels of similarity data.