Biological and Medical Informatics Program, University of California, San Francisco, San Francisco, United States; Department of Systems Pharmacology and Translational Therapeutics, University of Pennsylvania, Philadelphia, United States
Antoine Lizee
Department of Neurology, University of California, San Francisco, San Francisco, United States; ITUN-CRTI-UMR 1064 Inserm, University of Nantes, Nantes, France
Christine Hessler
Department of Neurology, University of California, San Francisco, San Francisco, United States
Leo Brueggeman
Department of Neurology, University of California, San Francisco, San Francisco, United States; University of Iowa, Iowa City, United States
Sabrina L Chen
Department of Neurology, University of California, San Francisco, San Francisco, United States; Johns Hopkins University, Baltimore, United States
Dexter Hadley
Department of Pediatrics, University of California, San Fransisco, San Fransisco, United States; Institute for Computational Health Sciences, University of California, San Francisco, San Francisco, United States
Ari Green
Department of Neurology, University of California, San Francisco, San Francisco, United States
Pouya Khankhanian
Department of Neurology, University of California, San Francisco, San Francisco, United States; Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, United States
Biological and Medical Informatics Program, University of California, San Francisco, San Francisco, United States; Department of Neurology, University of California, San Francisco, San Francisco, United States
The ability to computationally predict whether a compound treats a disease would improve the economy and success rate of drug approval. This study describes Project Rephetio to systematically model drug efficacy based on 755 existing treatments. First, we constructed Hetionet (neo4j.het.io), an integrative network encoding knowledge from millions of biomedical studies. Hetionet v1.0 consists of 47,031 nodes of 11 types and 2,250,197 relationships of 24 types. Data were integrated from 29 public resources to connect compounds, diseases, genes, anatomies, pathways, biological processes, molecular functions, cellular components, pharmacologic classes, side effects, and symptoms. Next, we identified network patterns that distinguish treatments from non-treatments. Then, we predicted the probability of treatment for 209,168 compound–disease pairs (het.io/repurpose). Our predictions validated on two external sets of treatment and provided pharmacological insights on epilepsy, suggesting they will help prioritize drug repurposing candidates. This study was entirely open and received realtime feedback from 40 community members.
