Dataset
GNoME: materials discovery data and code
External resource. Not made or verified by Public Protocol.
Google DeepMind's release accompanying Merchant et al., Scaling deep learning for materials discovery, Nature, 2023. Its repository states 381,000 novel stable materials, expanded in August 2024 to over 520,000 materials within 1 meV/atom of the convex hull. These are computed predictions, not tested engineering materials.
https://github.com/google-deepmind/materials_discovery
- Maintainer
- Google DeepMind
- Licence, as stated at its source
- Code: Apache License, Version 2.0. Data: Creative Commons Attribution Noncommercial 4.0 International
- Open or commercial
- Open
- Maturity
- WorkingOur reading, 16 November 2026
- Safety
- S0
- Review
- Listed 16 November 2026by Public Protocol editors
- Checked
- 16 November 2026
- Next check due
- 16 May 2027
- Steward
- Public Protocol editors
Where it sits in the blueprint
- Stages
Learn, Design
- Elements it supports
- Context
Climate, setting, scale, cost and skill: not stated in this entry. Check the source against your own place and numbers.
Verification
No verification is recorded on Public Platform for this entry. Records are added when someone reads it for accuracy, reviews it with a stated qualification, builds it or measures it.
Record
- How it came in
Seed catalogue, 16 November 2026. Listed from Praecise open research. The repository page was opened on the date shown; the Nature article page refused automated access.
- Licence
Code: Apache License, Version 2.0. Data: Creative Commons Attribution Noncommercial 4.0 International. Read at https://github.com/google-deepmind/materials_discovery. How licences are recorded
- Something wrong?