Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug–drug interactions prediction

Abstract

Multi-drug combinations for the treatment of complex diseases are gradually becoming an important treatment, and this type of treatment can take advantage of the synergistic effects among drugs. However, drug–drug interactions (DDIs) are not just all beneficial. Accurate and rapid identifications of the DDIs are essential to enhance the effectiveness of combination therapy and avoid unintended side effects. Traditional DDIs prediction methods use only drug sequence information or drug graph information, which ignores information about the position of atoms and edges in the spatial structure. In this paper, we propose Molormer, a method based on a lightweight attention mechanism for DDIs prediction. Molormer takes the two-dimension (2D) structures of drugs as input and encodes the molecular graph with spatial information. Besides, Molormer uses lightweight-based attention mechanism and self-attention distilling to process spatially the encoded molecular graph, which not only retains the multi-headed attention mechanism but also reduces the computational and storage costs. Finally, we use the Siamese network architecture to serve as the architecture of Molormer, which can make full use of the limited data to train the model for better performance and also limit the differences to some extent between networks dealing with drug features. Experiments show that our proposed method outperforms state-of-the-art methods in Accuracy, Precision, Recall and F1 on multi-label DDIs dataset. In the case study section, we used Molormer to make predictions of new interactions for the drugs Aliskiren, Selexipag and Vorapaxar and validated parts of the predictions. Code and models are available at https://github.com/IsXudongZhang/Molormer.

Deep learning for drug‐drug interaction prediction: A comprehensive review

“…To address the problem that traditional DDI prediction methods ignore information about the positions of atoms and edges in the spatial structure, Wang et al. [19] proposed a lightweight method based on self‐attention for drug‐drug interaction prediction using CNN with a ProbSparse self‐attention mechanism. The Molormer model takes the 2D structure of drugs as input and encodes the molecular graph using four features related to spatial information.…”

“…CNN-based methods MGP-DR Transformer encoder (BERT). [16] CNN-DDI Multi-type feature fusion and convolution neural network [17] META-DDIE Few-shot learning, sequential pattern mining algorithm (SPM), autoencoder, and CNN [18] Molormer Siamese network, lightweight self-attention and CNN [19] DDI REVIEW OF DEEP LEARNING -33…”

PETrans: De Novo Drug Design with Protein-Specific Encoding Based on Transfer Learning

“…There are increasing efforts to develop deep learning algorithms that can automatically generate chemically valid molecular structures [ 19 ]. Similar to natural language processing and social networks, molecules are represented as texts and graphs [ 20 , 21 , 22 ]. Therefore, models for de novo molecular design are naturally applicable to drug discovery.…”

MDDI-SCL: predicting multi-type drug-drug interactions via supervised contrastive learning

“…To facilitate the understanding of the causal mechanisms of DDIs, recent studies have developed multi-type DDIs prediction methods to elaborate sufficient details beyond the chance of DDI occurrence [ 16 ]. The pioneering study by Ryu et al constructed the gold standard DDI dataset from DrugBank [ 17 ], which covers 192,284 DDIs associated with 86 DDI types (changes in pharmacological effects and/or the risk of ADEs as a result of DDI) from 191,878 drug pairs [ 18 ].…”