A Needle in a Haystack: Leveraging Machine Learning for Drug-Mechanism of Action Identification across Existing Therapeutics, with Specific Applications for Drug Repurposing for Rare Diseases

Rare diseases are a prevalent problem within the healthcare sector, primarily due to the multitude of conditions and the limited profiling available for each. Consequently, developing novel therapeutics for rare diseases through traditional pipelines is fraught with risk and cost. The integration of machine learning into bioinformatics has facilitated the growth of in silico drug repurposing, where existing compounds are repositioned based on newly identified molecular targets. This study proposes a multi-class predictive model capable of accurately determining the mechanisms of action for existing compounds. By leveraging even limited rare disease profiles, the model aims to identify candidates for drug repurposing. Four supervised learning algorithms were trained using a combination of Clue and PubChem datasets. The results indicate that the random forest model boasts the best performance with an accuracy of 72.4% – comparable to existing literature. As all the top-performing models in this study were black-box, interpretability features of LIME and OpenAI API were integrated to ensure transparency in the recommendation of drug candidates, preparing the model for clinical integration. This model was then applied to a case study of Infantile Dystonia-Parkinson (IDP), where 105,552 compounds were screened for association with the condition. This study proposes pramipexole, bromocriptine, and ropinirole as candidate compounds for further investigation for IDP treatment. Due to the accuracy of both mechanism prediction and candidate generation, this computational model stands as a suitable approach for rare disease drug repurposing.