DrugRepPT: a deep pre-training and fine-tuning framework for drug repositioning based on drug's expression perturbation and treatment effectiveness.

Motivation: Drug repositioning, identifying novel indications for approved drugs, is a cost-effective strategy in drug discovery. Despite numerous proposed drug repositioning models, integrating network-based features, differential gene expression, and chemical structures for high-performance drug repositioning remains challenging.

Results: We propose a comprehensive deep pre-training and fine-tuning framework for drug repositioning, termed DrugRepPT. Initially, we design a graph pre-training module employing model-augmented contrastive learning on a vast drug-disease heterogeneous graph to capture nuanced interactions and expression perturbations after intervention. Subsequently, we introduce a fine-tuning module leveraging a graph residual-like convolution network to elucidate intricate interactions between diseases and drugs. Moreover, a Bayesian multi-loss approach is introduced to balance the existence and effectiveness of drug treatment effectively. Extensive experiments showcase the efficacy of our framework, with DrugRepPT exhibiting remarkable performance improvements compared to SOTA baseline methods (Improvement 106.13% on Hit@1 and 54.45% on mean reciprocal rank). The reliability of predicted results is further validated through two case studies, ie, gastritis and fatty liver, via literature validation, network medicine analysis, and docking screening.

Availability and implementation: The code and results are available at https://github.com/2020MEAI/DrugRepPT.

Supplementary information: Supplementary data are available at Bioinformatics online.