English

Learning Interpretable Disease Self-Representations for Drug Repositioning

Machine Learning 2019-10-22 v2 Machine Learning

Abstract

Drug repositioning is an attractive cost-efficient strategy for the development of treatments for human diseases. Here, we propose an interpretable model that learns disease self-representations for drug repositioning. Our self-representation model represents each disease as a linear combination of a few other diseases. We enforce proximity in the learnt representations in a way to preserve the geometric structure of the human phenome network - a domain-specific knowledge that naturally adds relational inductive bias to the disease self-representations. We prove that our method is globally optimal and show results outperforming state-of-the-art drug repositioning approaches. We further show that the disease self-representations are biologically interpretable.

Keywords

Cite

@article{arxiv.1909.06609,
  title  = {Learning Interpretable Disease Self-Representations for Drug Repositioning},
  author = {Fabrizio Frasca and Diego Galeano and Guadalupe Gonzalez and Ivan Laponogov and Kirill Veselkov and Alberto Paccanaro and Michael M. Bronstein},
  journal= {arXiv preprint arXiv:1909.06609},
  year   = {2019}
}

Comments

10 pages, 2 figures, v2 corresponds to the camera ready version accepted at the Graph Representation Learning Workshop, NeurIPS 2019

R2 v1 2026-06-23T11:15:19.879Z