AttentionSiteDTI: an interpretable graph-based model for drug-target interaction prediction using NLP sentence-level relation classification

In this study, we introduce an interpretable graph-based deep learning prediction model, AttentionSiteDTI, which utilizes protein binding sites along with a self-attention mechanism to address the problem of drug-target interaction prediction. Our proposed model is inspired by sentence classification models in the field of Natural Language Processing, where the drug-target complex is treated as a sentence with relational meaning between its biochemical entities a.k.a. protein pockets and drug molecule. AttentionSiteDTI enables interpretability by identifying the protein binding sites that contribute the most toward the drug-target interaction. Results on three benchmark datasets show improved performance compared with the current state-of-the-art models. More significantly, unlike previous studies, our model shows superior performance, when tested on new proteins (i.e. high generalizability). Through multidisciplinary collaboration, we further experimentally evaluate the practical potential of our proposed approach. To achieve this, we first computationally predict the binding interactions between some candidate compounds and a target protein, then experimentally validate the binding interactions for these pairs in the laboratory. The high agreement between the computationally predicted and experimentally observed (measured) drug-target interactions illustrates the potential of our method as an effective pre-screening tool in drug repurposing applications.

Automated summary

In this study, an interpretable graph-based deep learning prediction model called AttentionSiteDTI is introduced to address the problem of drug-target interaction prediction. The model utilizes protein binding sites and a self-attention mechanism to identify the most contributive binding sites. Experimental results show that AttentionSiteDTI outperforms current state-of-the-art models on three benchmark datasets and exhibits high generalizability on new proteins. The agreement between computationally predicted and experimentally observed drug-target interactions demonstrates the potential of the proposed method as an effective pre-screening tool in drug repurposing applications.