MOTIVATION: Drug repositioning, identifying new therapeutic applications for existing drugs, can significantly reduce the time and cost involved in drug development. Recent studies have explored the use of Anatomical Therapeutic Chemical (ATC) codes in drug repositioning, offering a systematic framework to predict ATC codes for a drug. The ATC classification system organizes drugs according to their chemical properties, pharmacological actions, and therapeutic effects. However, its complex hierarchical structure and the limited scalability at higher levels present significant challenges for achieving accurate ATC code prediction. RESULTS: We propose a novel approach to predict ATC codes of drugs, named Feature Aggregation and Convolution with Transformer models (FACT). This method computes three types of drug similarities, incorporating ATC code similarity with hierarchical weights and masked drug-ATC code associations. These features are then aggregated for each target drug-ATC code pair and processed through a convolution-transformer encoder to generate three embeddings. The embeddings are finally used to estimate the probability of an association between the target pair. The experimental results demonstrate that the proposed method achieves an area under the receiver operating characteristic curve (AUROC) of 0.9805 and an area under the precision-recall curve of 0.9770 at level 4 of the ATC codes, outperforming the previous methods by 15.05% and 18.42%, respectively. This study highlights the effectiveness of integrating diverse drug features and the potential of transformer-based models in ATC code prediction. AVAILABILITY AND IMPLEMENTATION: Source code of FACT is freely available at https://github.com/knhc1234/FACT.

Identifying drug-target interactions is a crucial step in drug discovery and drug repurposing. To efficiently predict these interactions, various computational tools have been developed. Recently, machine learning, especially deep learning, has gained significant attention for predicting drug-target interactions. Deep learning models extract features of both drugs and targets, capturing hidden relationships between them through deep neural networks. In this study, we evaluate the performance of several attention-based models in predicting interactions using four publicly available benchmark datasets. Their performance is assessed with three metrics: the area under the receiver operating characteristic curve, the area under the precision-recall curve, and the F1-score. Experimental results demonstrate that attention-based methods generally exhibit high predictive performance and possess distinct advantages under various conditions.