coleygroup/shepherd

Training and inference code for ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design [ICLR 2025 oral]

48
/ 100
Emerging

Shepherd helps drug discovery scientists design new molecules with specific desired 3D characteristics. You provide a target 3D interaction profile, and it generates novel molecular structures in their 3D conformations that match those profiles. This tool is for medicinal chemists and computational chemists working on bioisosteric drug design.

Use this if you need to generate new molecular structures that exhibit specific 3D interaction profiles for drug design.

Not ideal if you are looking for a tool to analyze existing molecules or score their 3D similarity rather than generate new ones.

drug-discovery medicinal-chemistry molecular-design bioisosteric-replacement pharmacophore-modeling
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

91

Forks

11

Language

Python

License

MIT

Last pushed

Jan 29, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/coleygroup/shepherd"

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