Multisource Attention-Mechanism-Based Encoder–Decoder Model for Predicting Drug–Drug Interaction Events

Abstract

Many computational methods have been proposed to predict drug−drug interactions (DDIs), which can occur when combining drugs to treat various diseases, but most mainly utilize single-source features of drugs, which is inadequate for drug representation. To fill this gap, we propose two attention-mechanism-based encoder−decoder models that incorporate multisource information: one is MAEDDI, which can predict DDIs, and the other is MAEDDIE, which can make further DDI-associated event predictions for drug pairs with DDIs. To better express the drug feature, we used three encoding methods to encode the drugs, integrating the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multisource feature fusion network. Experiments showed that both MAEDDI and MAEDDIE performed better than some state-of-the-art methods in various validation attempts at different experimental tasks. The visualization analysis showed that the semantic features of drug pairs learned from our models had a good drug representation. In practice, MAEDDIE successfully screened 43 DDI events on favipiravir, an influenza antiviral drug, with a success rate of nearly 50%. Our model achieved competitive results, mainly owing to the design of sequence-based, structural, biochemical, and statistical multisource features. Moreover, different encoders constructed based on different features learn the interrelationship information between drug pairs, and the different representations of these drug pairs are incorporated to predict the target problem. All of these encoders were designed to better characterize the complex DDI relationships, allowing us to achieve high generalization in DDI and DDI-associated event predations.

MecDDI: Clarified Drug–Drug Interaction Mechanism Facilitating Rational Drug Use and Potential Drug–Drug Interaction Prediction

“…The mechanisms underlying DDIs were found to be extremely diverse. − Therefore, it was highly demanded to have a systematic classification of the existing interaction mechanisms. In MecDDI, a well-established classification system based on PK and PD was adopted. , For each of the well-established classifications, further classifications (subclasses) were systematically constructed for all DDI mechanisms in the study.…”

Advances in the Development of Representation Learning and Its Innovations against COVID-19

“…This method also fully utilizes the features extracted from drug molecular structure graphs and biomedical knowledge graphs and can be applied to different types of DDI prediction tasks. Pan et al [149] integrated the self-attention mechanism, cross-attention mechanism, and graph attention network to construct a multi-source feature fusion network, which enables the model to better capture drug-drug interaction information and further predict drug-drug interactionrelated events. Li et al [150] proposed a novel multi-view substructure learning method that fuses multiple views, such as chemical structures, pharmacophores, and targets, to learn key substructure information for drug-drug interaction.…”