mims-harvard/decagon
Graph convolutional neural network for multirelational link prediction
This project helps pharmacologists and drug safety researchers predict the potential side effects when patients take multiple drugs together. It takes information about protein-protein interactions, drug-protein targeting, and known side effects of drug combinations as input. The output is a prediction of which specific side effects are likely to occur from new drug combinations.
469 stars. No commits in the last 6 months.
Use this if you need to identify previously unknown or unstudied adverse effects of combining medications.
Not ideal if your primary goal is to understand the biological mechanisms of individual drug actions rather than combination effects.
Stars
469
Forks
151
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Nov 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/mims-harvard/decagon"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
eliorc/node2vec
Implementation of the node2vec algorithm.
mims-harvard/nimfa
Nimfa: Nonnegative matrix factorization in Python
ferencberes/online-node2vec
Node Embeddings in Dynamic Graphs
claws-lab/jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in...
mims-harvard/Raindrop
Graph Neural Networks for Irregular Time Series