Transcriptomics-based matching of drugs to diseases with deep learning
This work addresses drug repurposing for diseases by providing a more accurate computational method, though it appears incremental as it builds on existing transcriptomics-based approaches.
The authors tackled the problem of matching drugs to diseases using transcriptomics data, achieving a more than 200% improvement over baseline methods in retrieval metrics.
In this work we present a deep learning approach to conduct hypothesis-free, transcriptomics-based matching of drugs for diseases. Our proposed neural network architecture is trained on approved drug-disease indications, taking as input the relevant disease and drug differential gene expression profiles, and learns to identify novel indications. We assemble an evaluation dataset of disease-drug indications spanning 68 diseases and evaluate in silico our approach against the most widely used transcriptomics-based matching baselines, CMap and the Characteristic Direction. Our results show a more than 200% improvement over both baselines in terms of standard retrieval metrics. We further showcase our model's ability to capture different genes' expressions interactions among drugs and diseases. We provide our trained models, data and code to predict with them at https://github.com/healx/dgem-nn-public.