Drug repurposing study for amyotrophic lateral sclerosis (ALS) using artificial intelligence

In this study, a knowledge graph placement model for drug repurposing for treating Amyotrophic Lateral Sclerosis (ALS) is developed and analyzed, and the results are presented. The knowledge graph embedding model was trained by updating and optimizing a comprehensive biological knowledge graph called Drug Repurposing Knowledge Graph (DRKG). The DRKG is organized as a comprehensive biological knowledge network including genes, compounds, diseases, biological processes, side effects, and symptoms, and was used as an important source for extracting ALS-related information in this study. The resulting knowledge graph from the training resulted in more precise and reliable drug recommendations for ALS. Drug repurposing studies for ALS have been carried out mainly in the framework of two methods based on disease-drug and gene-drug interactions. In this context, links between disease and drug entities associated with ALS were predicted, and potential drug candidates were identified. The results were compared with the list of clinical trial drugs in the DrugBank database and revealed significant findings. In addition, in the gene-drug interactions analysis, the relationships between ALS related genes and potential drugs associated with these genes were evaluated in detail. The results of the study show that the trained knowledge graph placement model is a powerful method for identifying drugs with potential therapeutic effects in the treatment of ALS. The results suggest that the drug repurposing approach has the potential to offer innovative and effective treatment options for ALS.