Drug-Drug Interaction Prediction Based on Probability Transfer Multi-modal Feature Representation Learning

In drug discovery and combination therapy, drug-drug interactions can lead to adverse reactions, affecting not only disease treatment but also risking the market withdrawal of new drugs. Traditional experiments in vitro and in vivo are labor-intensive and time-consuming for identifying potential DDIs. Although existing computational methods offer new perspectives for DDIs identification, they still have limitations. This paper innovatively uses the probability transfer matrix combined with Stacked Denoising Autoencoder to propose a model named MultiPT-DDI to calculate the correlation of edge nodes in the adjacency matrix, which effectively learns the multi-level representation of nodes and mitigates the probabilistic bias of the edge nodes in the sparse matrices and the noise of the original data. Specifically, the method first samples multiple bipartite graph networks using random surfing thus obtaining multiple probabilistic transfer matrices. Subsequently, multiple denoising autoencoder modules are employed for layer-wise unsupervised pre-training of the network. Finally, we infer the relationships between drug pairs using the Random Forest algorithm. The experiment obtains the AUC score of 0.9433 and the AUPR score of 0.9372 in the 5-fold cross-validation, significantly outperforming existing models. In the case studies, 26 of the top 30 drug pairs with the highest scores were validated. The empirical evidence indicates that MultiPT-DDI is an effective complementary model for predicting potential DDIs, providing a reliable reference for traditional experimental methods.