Drug-Target Interaction Prediction via Dual Laplacian Graph Regularized Logistic Matrix Factorization.

摘要: Drug-target interactions provide useful information for biomedical drug discovery as well development. However, it is costly and time consuming to find drug-target by experimental methods. As a result, developing computational approaches this task necessary has practical significance. In study, we establish novel dual Laplacian graph regularized logistic matrix factorization model interaction prediction, referred DLGrLMF briefly. Specifically, regards the of prediction weighted problem, in which experimentally validated are allocated with larger weights. Meanwhile, considering that drugs similar chemical structure should have targets genomic sequence similarity turn drugs, pairwise similarities target fully exploited serve problem using regularization term. addition, design gradient descent algorithm solve resultant optimization problem. Finally, efficacy on various benchmark datasets results demonstrate performs better than other state-of-the-art Case studies also conducted validate can successfully predict most interactions.