A novel approach based on deep residual learning to predict drug’s anatomical therapeutic chemical code

Correctly identifying the potential Anatomical Therapeutic Chemical (ATC) codes for drugs can accelerate drug development and reduce the cost of experiments. However, most of the existing methods only analyze the first-level ATC code of drugs and lack of the ability to learn basic features from sparsely known drug-ATC code associations. In this paper, we propose a novel method based on deep residual network framework, named RNPredATC, to predict potential drug-ATC code associations by integrating drug structure similarity, ATC sematic similarity, and known drug-ATC code associations. RNPredATC can extract dense feature vectors from sparsely known drug-ATC code associations and reduce the impact from degradation problem, such as gradient vanishing or gradient explosion of deep network. The experimental results show that RNPredATC achieves better performances.