Many therapies are effective in treating multiple diseases. We present an approach that leverages methods developed in natural language processing and real-world data to prioritize potential, new indications for a mechanism of action (MoA). We specifically use representation learning to generate embeddings of indications and prioritize them based on their proximity to the indications with the strongest available evidence for the MoA. We demonstrate the successful deployment of our approach for anti-IL-17A using embeddings generated with SPPMI and present an evaluation framework to determine the quality of indication finding results and the derived embeddings.
@article{arxiv.2410.19174,
title = {Indication Finding: a novel use case for representation learning},
author = {Maren Eckhoff and Valmir Selimi and Alexander Aranovitch and Ian Lyons and Emily Briggs and Jennifer Hou and Alex Devereson and Matej Macak and David Champagne and Chris Anagnostopoulos},
journal= {arXiv preprint arXiv:2410.19174},
year = {2024}
}