baldassarreFe/graph-network-explainability
Explainability techniques for Graph Networks, applied to a synthetic dataset and an organic chemistry task. Code for the workshop paper "Explainability Techniques for Graph Convolutional Networks" (ICML19)
This project helps organic chemists and material scientists understand why a molecule exhibits certain properties. By inputting a molecule's structure, it provides a breakdown of which atoms and bonds contribute most to a predicted property like solubility. This allows researchers to pinpoint key structural features influencing a molecule's behavior.
127 stars. No commits in the last 6 months.
Use this if you need to explain the specific atomic and bond-level contributions to a predicted molecular property, rather than just getting a prediction.
Not ideal if you are looking for a general-purpose molecular property prediction tool without the need for detailed explanations.
Stars
127
Forks
16
Language
Jupyter Notebook
License
—
Last pushed
Nov 12, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/baldassarreFe/graph-network-explainability"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...