Songyosk/ML4SMILES

Automatic Prediction of Molecular Properties Using Substructure Vector Embeddings within a Feature Selection Workflow

27
/ 100
Experimental

This project helps chemists and materials scientists automatically predict molecular properties. You input chemical structures described by SMILES notation, and it outputs a highly accurate prediction of a target molecular property. It's designed for researchers needing to efficiently screen and evaluate new molecules.

No commits in the last 6 months.

Use this if you need to build predictive models for molecular properties based on chemical structure, and you want to automate the complex feature engineering and selection process.

Not ideal if you are looking for a pre-trained model or a simple online calculator for basic molecular properties, as this tool is for building custom predictive pipelines.

computational-chemistry materials-science drug-discovery molecular-design cheminformatics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

Sep 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Songyosk/ML4SMILES"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.