aksub99/molecular-vae

Pytorch implementation of the paper "Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules"

43
/ 100
Emerging

This tool helps computational chemists and materials scientists rapidly design new chemical compounds with desired properties. You input a dataset of known molecules, and it outputs novel molecular structures that could potentially have improved characteristics for various applications. It's ideal for researchers in drug discovery or materials science looking to explore chemical space more efficiently.

No commits in the last 6 months.

Use this if you need to generate new molecular structures that are optimized for specific properties, beyond what's already known or easily synthesizable.

Not ideal if you're looking for a simple simulator for existing molecules or a tool to analyze chemical reactions.

drug-discovery materials-science computational-chemistry molecular-design novel-compound-generation
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

71

Forks

15

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 31, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aksub99/molecular-vae"

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