A dual graph neural network for drug–drug interactions prediction based on molecular structure and interactions

Abstract

Expressive molecular representation plays critical roles in researching drug design, while effective methods are beneficial to learning molecular representations and solving related problems in drug discovery, especially for drug-drug interactions (DDIs) prediction. Recently, a lot of work has been put forward using graph neural networks (GNNs) to forecast DDIs and learn molecular representations. However, under the current GNNs structure, the majority of approaches learn drug molecular representation from one-dimensional string or two-dimensional molecular graph structure, while the interaction information between chemical substructure remains rarely explored, and it is neglected to identify key substructures that contribute significantly to the DDIs prediction. Therefore, we proposed a dual graph neural network named DGNN-DDI to learn drug molecular features by using molecular structure and interactions. Specifically, we first designed a directed message passing neural network with substructure attention mechanism (SA-DMPNN) to adaptively extract substructures. Second, in order to improve the final features, we separated the drug-drug interactions into pairwise interactions between each drug’s unique substructures. Then, the features are adopted to predict interaction probability of a DDI tuple. We evaluated DGNN–DDI on real-world dataset. Compared to state-of-the-art methods, the model improved DDIs prediction performance. We also conducted case study on existing drugs aiming to predict drug combinations that may be effective for the novel coronavirus disease 2019 (COVID-19). Moreover, the visual interpretation results proved that the DGNN-DDI was sensitive to the structure information of drugs and able to detect the key substructures for DDIs. These advantages demonstrated that the proposed method enhanced the performance and interpretation capability of DDI prediction modeling.

SSF-DDI: a deep learning method utilizing drug sequence and substructure features for drug–drug interaction prediction

“…Table 2 summarises the corresponding parameters of the model components used in extracting the graph structure information of individual drugs and the transformation of the feature dimensions. Message-passing neural network (MPNN) [ 30 ] is a generalized GNN suitable for feature extraction of graph-structured data, and many recent studies have used MPNN for molecular property prediction and drug feature extraction [ 20 , 29 ]. SSF-DDI uses an MPNN variant called a directed message-passing neural network (D-MPNN) [ 31 ].…”

“…A drug can also be divided into several functional groups or chemical substructures, leading to certain pharmacological properties [ 18 ]. Some studies have predicted DDI based on information about drug molecule substructures, such as GMPNN-CS [ 19 ], DGNN-DDI [ 20 ], DDI-SSL[ 21 ] and SSI-DDI [ 22 ]. DDI is a complex reaction process encompassing knowledge from multiple domains, including biology and chemistry.…”

Attention is all you need: utilizing attention in AI-enabled drug discovery

“…Additionally, Ma et al. [ 47 ] and Yang et al. [ 48 ] employed the substructure attention mechanism to automatically extract drug substructures for DDI prediction.…”

“…This adaptable approach captures evolving substructures and enhances the understanding of complex relationships driving DDIs. Another innovative approach, DGNN-DDI , leverages dual GNNs and substructure attention [ 47 ]. These networks collaboratively extract molecular substructure features and determine the significance of various substructure features in predicting drug pair interactions.…”

An Improved Graph Isomorphism Network for Accurate Prediction of Drug–Drug Interactions

“…Recently, there has been a growing fascination with the utilization of graph neural networks (GNN) [25][26][27][28] in DDI prediction. To effectively aggregate the neighboring information, different aggregation strategies have been designed to develop GNN variants.…”