Digital craftsman of the biodata revolution.
Project Rephetio & systematic prediction of antiepileptic drugs
Presented on January 30, 2017 to Blackfynn by
- Daniel Himmelstein
- Pouya Khankhanian
Slides online at slides.com/dhimmel/blackfynn
- Hetnet of biology designed for drug repurposing
- ~50 thousand nodes
11 types (labels)
- ~2.25 million relationships
- integrates 29 public resources
knowledge from millions of studies
- the hardest part:
licensing of publicly available data
Visualizing Hetionet v1.0
Future: all biomedical knowledge in a single network
- Teach computers how to read the literature and extract knowledge.
- Continuously and automatically refine and grow the hetnet.
- Free from any legal restrictions on reuse.
Project Rephetio: drug repurposing predictions
Hetionet v1.0 contains:
- 1,538 connected compounds
- 136 connected diseases
- 209,168 compound–disease pairs
- 755 treatments
- 1,206 compound–disease metapaths with length ≤ 4
- machine learning classifier
- predict the probability of treatment for all 209,168 compound–disease pairs (het.io/repurpose)
- Project online at thinklab.com/p/rephetio
Systematic integration of biomedical knowledge prioritizes drugs for repurposing
Daniel S Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, Sergio E Baranzini
bioRxiv. 2016. DOI: 10.1101/087619
Does bupropion treat nicotine dependence?
- Bupropion was first approved for depression in 1985
In 1997, bupropion was approved for smoking cessation
- Can we predict this repurposing from Hetionet? The prediction was:
- 99.5th percentile for nicotine dependence
- probability 2.50-fold greater than null
(browse all predictions at het.io/repurpose)
Discuss at thinklab.com/d/224
Evaluating the top 100 epilepsy predictions
Discuss at thinklab.com/d/224#5
Which target genes supported the top epilepsy predictions?
Online at thinklab.com/d/230#11
To Blackfynn: predicting antiepileptic drugs in Project Rephetio
By Daniel Himmelstein