Accurate identification of potential drug–target interactions (DTIs) is a crucial task in drug development and repositioning. Despite the remarkable progress achieved in recent years, improving the performance of DTI prediction still presents significant challenges. In this study, we propose a novel end-to-end deep learning model called AMMVF-DTI (attention mechanism and multi-view fusion), which leverages a multi-head self-attention mechanism to explore varying degrees of interaction between drugs and target proteins. More importantly, AMMVF-DTI extracts interactive features between drugs and proteins from both node-level and graph-level embeddings, enabling a more effective modeling of DTIs. This advantage is generally lacking in existing DTI prediction models. Consequently, when compared to many of the start-of-the-art methods, AMMVF-DTI demonstrated excellent performance on the human, C. elegans, and DrugBank baseline datasets, which can be attributed to its ability to incorporate interactive information and mine features from both local and global structures. The results from additional ablation experiments also confirmed the importance of each module in our AMMVF-DTI model. Finally, a case study is presented utilizing our model for COVID-19-related DTI prediction. We believe the AMMVF-DTI model can not only achieve reasonable accuracy in DTI prediction, but also provide insights into the understanding of potential interactions between drugs and targets.

Targeted drug delivery into cells has been of tremendous scientific interest, and carbon nanotubes (CNTs) can be deemed as a promising material for the loading and unloading of drugs. One of the major challenges is the release of drugs from CNTs, which have a great potential well to trap molecules. By performing molecular dynamics simulations, this work attempts to study the releasing process of encapsulated protein/peptide molecules from CNTs in the presence of uniform electric fields. Zadaxin serves as a model for protein/peptide drugs. External electric fields can assist the peptide in overcoming the potential well during its release. It is found that successful release of the peptide depends on the pore width, the pore length, and the net charges on the peptide. The peptide is less likely to be released either from CNTs with a smaller pore diameter due to a deeper potential well of the tubes or from CNTs with a longer pore length due to a broader and deeper potential well. Peptides with more net charges are ideal for the releasing process driven by electric fields. This work can provide insights into the design of an optimal tube size for effective release of a given protein/peptide.