fairchem-core

FAIR Chemistry's library of machine learning methods for chemistry

https://github.com/facebookresearch/fairchem

Science Score: 77.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 3 DOI reference(s) in README
✓
Academic publication links
Links to: zenodo.org
✓
Committers with academic emails
6 of 55 committers (10.9%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (19.1%) to scientific vocabulary

Keywords from Contributors

materials-informatics materials-science optimizer materials mesh transformer interpretability interactive profiles distribution

Last synced: 6 months ago · JSON representation ·

Repository

FAIR Chemistry's library of machine learning methods for chemistry

Basic Info

Host: GitHub
Owner: facebookresearch
License: other
Language: Python
Default Branch: main
Homepage: https://fair-chem.github.io/
Size: 46.2 MB

Statistics

Stars: 1,689
Watchers: 37
Forks: 377
Open Issues: 37
Releases: 37

Created over 6 years ago · Last pushed 6 months ago

Metadata Files

Readme Contributing License Code of conduct Citation

![tests](https://github.com/facebookresearch/fairchem/actions/workflows/test.yml/badge.svg?branch=main&event=push) ![PyPI - Version](https://img.shields.io/pypi/v/fairchem-core) ![Static Badge](https://img.shields.io/badge/python-3.10%2B-blue) [![codecov](https://codecov.io/gh/facebookresearch/fairchem/graph/badge.svg)](https://codecov.io/gh/facebookresearch/fairchem) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15587498.svg)](https://doi.org/10.5281/zenodo.15587498) [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://github.com/codespaces/new/facebookresearch/fairchem?quickstart=1)

`fairchem` by the FAIR Chemistry team

fairchem is the FAIR Chemistry's centralized repository of all its data, models, demos, and application efforts for materials science and quantum chemistry.

:warning: FAIRChem version 2 is a breaking change from version 1 and is not compatible with our previous pretrained models and code. If you want to use an older model or code from version 1 you will need to install version 1, as detailed here.

:warning: Some of the docs and new features in FAIRChem version 2 are still being updated so you may see some changes over the next few weeks. Check back here for the latest instructions. Thank you for your patience!

Read our latest release post!

Read about the UMA model and OMol25 dataset release.

Try the demo!

If you want to explore model capabilities check out our educational demo

Installation

Although not required, we highly recommend installing using a package manager and virtualenv such as uv, it is much faster and better at resolving dependencies than standalone pip.

Install fairchem-core using pip bash pip install fairchem-core

If you want to contribute or make modifications to the code, clone the repo and install in edit mode ```bash git clone git@github.com:facebookresearch/fairchem.git

pip install -e fairchem/packages/fairchem-core[dev] ```

Quick Start

The easiest way to use pretrained models is via the ASE FAIRChemCalculator. A single uma model can be used for a wide range of applications in chemistry and materials science by picking the appropriate task name for domain specific prediction.

Instantiate a calculator from a pretrained model

Make sure you have a Hugging Face account, have already applied for model access to the UMA model repository, and have logged in to Hugging Face using an access token. You can use the following to save an auth token, bash huggingface-cli login

Models are referenced by their name, below are the currently supported models:

| Model Name | Description | |---|---| | uma-s-1p1 | Latest version of the UMA small model, fastest of the UMA models while still SOTA on most benchmarks (6.6M/150M active/total params) | | uma-m-1p1 | Best in class UMA model across all metrics, but slower and more memory intensive than uma-s (50M/1.4B active/total params) |

Set the task for your application and calculate

oc20: use this for catalysis
omat: use this for inorganic materials
omol: use this for molecules
odac: use this for MOFs
omc: use this for molecular crystals

Relax an adsorbate on a catalytic surface,

```python from ase.build import fcc100, addadsorbate, molecule from ase.optimize import LBFGS from fairchem.core import pretrainedmlip, FAIRChemCalculator

predictor = pretrainedmlip.getpredictunit("uma-s-1p1", device="cuda") calc = FAIRChemCalculator(predictor, taskname="oc20")

Set up your system as an ASE atoms object

slab = fcc100("Cu", (3, 3, 3), vacuum=8, periodic=True) adsorbate = molecule("CO") add_adsorbate(slab, adsorbate, 2.0, "bridge")

slab.calc = calc

Set up LBFGS dynamics object

opt = LBFGS(slab) opt.run(0.05, 100) ```

Relax an inorganic crystal,

```python from ase.build import bulk from ase.optimize import FIRE from ase.filters import FrechetCellFilter from fairchem.core import pretrained_mlip, FAIRChemCalculator

predictor = pretrainedmlip.getpredictunit("uma-s-1p1", device="cuda") calc = FAIRChemCalculator(predictor, taskname="omat")

atoms = bulk("Fe") atoms.calc = calc

opt = LBFGS(FrechetCellFilter(atoms)) opt.run(0.05, 100) ```

Run molecular MD,

```python from ase import units from ase.io import Trajectory from ase.md.langevin import Langevin from ase.build import molecule from fairchem.core import pretrained_mlip, FAIRChemCalculator

predictor = pretrainedmlip.getpredictunit("uma-s-1p1", device="cuda") calc = FAIRChemCalculator(predictor, taskname="omol")

atoms = molecule("H2O") atoms.calc = calc

dyn = Langevin( atoms, timestep=0.1 * units.fs, temperatureK=400, friction=0.001 / units.fs, ) trajectory = Trajectory("mymd.traj", "w", atoms) dyn.attach(trajectory.write, interval=1) dyn.run(steps=1000) ```

Calculate a spin gap,

```python from ase.build import molecule from fairchem.core import pretrained_mlip, FAIRChemCalculator

predictor = pretrainedmlip.getpredict_unit("uma-s-1p1", device="cuda")

singlet CH2

singlet = molecule("CH2s1A1d") singlet.info.update({"spin": 1, "charge": 0}) singlet.calc = FAIRChemCalculator(predictor, taskname="omol")

triplet CH2

triplet = molecule("CH2s3B1d") triplet.info.update({"spin": 3, "charge": 0}) triplet.calc = FAIRChemCalculator(predictor, taskname="omol")

triplet.getpotentialenergy() - singlet.getpotentialenergy() ```

LICENSE

fairchem is available under a MIT License. Models/checkpoint licenses vary by application area.

Owner

Name: Meta Research
Login: facebookresearch
Kind: organization
Location: Menlo Park, California

Website: https://opensource.fb.com
Repositories: 1,060
Profile: https://github.com/facebookresearch

Citation (CITATION.cff)

cff-version: 1.2.0
title: "FAIRChem"
version: 2.2.0
message: "If you use this software, please cite it as below."
doi: 10.5281/zenodo.15587498
url: "https://github.com/facebookresearch/fairchem"
license:
- MIT
authors:
- affiliation: FAIR, Meta
  family-names: Muhammed Shuaibi
- affiliation: FAIR, Meta AI
  family-names: Abhishek Das
- affiliation: FAIR, Meta
  family-names: Anuroop Sriram
- family-names: Misko
- affiliation: FAIR, Meta AI
  family-names: Luis Barroso-Luque
- family-names: Ray Gao
- family-names: Siddharth Goyal
- affiliation: FAIR, Meta AI
  family-names: Zachary Ulissi
- affiliation: FAIR, Meta
  family-names: Brandon Wood
- affiliation: Microsoft
  family-names: Tian Xie
- affiliation: Carnegie Mellon University
  family-names: Junwoong Yoon
- family-names: Brook Wander
- affiliation: Radical AI
  family-names: Adeesh Kolluru
- family-names: Richard Barnes
- affiliation: Carnegie Mellon University
  family-names: Ethan Sunshine
- affiliation: Toyota Research Institute
  family-names: Kevin Tran
- family-names: Xiang
- affiliation: FAIR, Meta AI
  family-names: Daniel Levine
- family-names: Nima Shoghi
- family-names: Ilias Chair
- affiliation: FAIR, Meta AI
- family-names: Janice Lan
- affiliation: Georgia Institute of Technology
  family-names: Kaylee Tian
- affiliation: Carnegie Mellon University
  family-names: Joseph Musielewicz
- family-names: clz55
- family-names: Weihua Hu
- affiliation: FAIR, Meta AI
- family-names: Kyle Michel
- family-names: willis
- family-names: vbttchr
message: If you use this software, please cite it using the metadata from this file.
repository-code: https://github.com/facebookresearch/fairchem
type: software

GitHub Events

Total

Create event: 157
Release event: 10
Issues event: 180
Watch event: 501
Delete event: 126
Member event: 1
Issue comment event: 312
Push event: 605
Pull request review comment event: 133
Pull request review event: 229
Pull request event: 245
Fork event: 79

Last Year

Create event: 157
Release event: 10
Issues event: 180
Watch event: 501
Delete event: 126
Member event: 1
Issue comment event: 312
Push event: 605
Pull request review comment event: 133
Pull request review event: 229
Pull request event: 245
Fork event: 79

Committers

Last synced: 7 months ago

All Time

Total Commits: 1,011
Total Committers: 55
Avg Commits per committer: 18.382
Development Distribution Score (DDS): 0.771

Past Year

Commits: 261
Committers: 25
Avg Commits per committer: 10.44
Development Distribution Score (DDS): 0.774

Top Committers

Name	Email	Commits
Abhishek Das	d**k@g**m	232
Muhammed Shuaibi	4****i	228
anuroopsriram	a**s@f**m	83
Misko	m**o@m**m	72
rayg1234	7****4	70
Luis Barroso-Luque	l****e	69
zulissimeta	1****a	36
Siddharth Goyal	s**l@f**m	28
Brandon Wood	b**d@b**u	19
dependabot[bot]	4****]	18
Tian Xie	t**e@g**m	13
Brook Wander	7****r	12
Adeesh Kolluru	4****u	12
junwoony	j**n@g**m	11
Richard Barnes	r**s@u**u	10
Nima Shoghi	n**i@f**m	10
Ethan Sunshine	9****e	8
Kevin Tran	k**1@g**m	7
Daniel Levine	l**s@m**m	7
Johannes Klicpera	j**a@m**g	6
Kyle Michel	5****l	6
Xiang	3****x	5
Nima Shoghi	n**i@g**m	4
Ilias Chair	8****r	3
Janice Lan	j**n@f**m	3
Vahe Gharakhanyan	v**g@m**m	3
Artur Toshev	4****v	2
Facebook Community Bot	f****t	2
Weihua Hu	w**6@g**m	2
clz55	5****5	2
and 25 more...

Committer Domains (Top 20 + Academic)

meta.com: 4 fb.com: 4 mailbox.org: 2 berkeley.edu: 2 gatech.edu: 1 umich.edu: 1 hitachi.com: 1 qq.com: 1 devfair0331.h2.fair: 1 mail.mcgill.ca: 1 umn.edu: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 135
Total pull requests: 296
Average time to close issues: 19 days
Average time to close pull requests: 6 days
Total issue authors: 93
Total pull request authors: 30
Average comments per issue: 1.6
Average comments per pull request: 0.39
Merged pull requests: 161
Bot issues: 0
Bot pull requests: 38

Past Year

Issues: 133
Pull requests: 296
Average time to close issues: 9 days
Average time to close pull requests: 6 days
Issue authors: 91
Pull request authors: 30
Average comments per issue: 1.56
Average comments per pull request: 0.39
Merged pull requests: 161
Bot issues: 0
Bot pull requests: 38

View more stats

Top Authors

Issue Authors

2506363862 (5)
anyangml (5)
XYxiyang (4)
brunosamp4 (4)
ericyuan00000 (4)
nevinngyt (3)
zulissimeta (3)
Zhangzhiwei39 (3)
yang-lin430 (2)
caolz (2)
kaijiz (2)
1716757342 (2)
runtian97 (2)
GuideBariri (2)
leifjacobson (2)

Pull Request Authors

lbluque (52)
rayg1234 (42)
dependabot[bot] (38)
zulissimeta (35)
misko (33)
mshuaibii (22)
levineds (8)
kjmichel (7)
wood-b (6)
arturtoshev (5)
gvahe (5)
EricZQu (4)
santi921 (4)
ericyuan00000 (4)
anuroopsriram (4)

Top Labels

Issue Labels

bug (30) stale (8) enhancement (2) documentation (1) dont-close (1) question (1)

Pull Request Labels

cla signed (235) patch (92) minor (81) enhancement (79) no-op (58) documentation (55) dependencies (50) bug (39) python (34) github_actions (17) test (12) major (6) stale (5) refactor (4) do not merge (4)

Packages

Total packages: 3
Total downloads:
- pypi 11,961 last-month

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 0
(may contain duplicates)
Total versions: 30
Total maintainers: 1

pypi.org: fairchem-data-omol

Code for generating OMOL input configurations

Documentation: https://fairchem-data-omol.readthedocs.io/
License: MIT License
Latest release: 0.1.0
published 6 months ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 157 Last month

Rankings

Stargazers count: 2.5%

Forks count: 3.6%

Dependent packages count: 8.7%

Average: 15.9%

Dependent repos count: 48.7%

Maintainers (1)

lbluque

Last synced: 6 months ago

pypi.org: fairchem-data-oc

Code for generating adsorbate-catalyst input configurations

Documentation: https://fairchem-data-oc.readthedocs.io/
License: MIT License
Latest release: 1.0.2
published 6 months ago

Versions: 7
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 1,332 Last month

Rankings

Dependent packages count: 9.4%

Average: 35.6%

Dependent repos count: 61.8%

Maintainers (1)

lbluque

Last synced: 6 months ago

pypi.org: fairchem-core

Machine learning models for chemistry and materials science by the FAIR Chemistry team

Documentation: https://fairchem-core.readthedocs.io/
License: MIT License
Latest release: 2.4.0
published 6 months ago

Versions: 22
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 10,472 Last month

Rankings

Dependent packages count: 9.4%

Average: 35.8%

Dependent repos count: 62.1%

Maintainers (1)

lbluque

Last synced: 6 months ago

Dependencies

.github/workflows/test-release.yml actions

actions/download-artifact v4 composite
pypa/gh-action-pypi-publish release/v1 composite

packages/fairchem-applications-cattsunami/pyproject.toml pypi

ase *
fairchem-core *
fairchem-data-oc *
networkx *
numpy >=1.25.0
scipy *
torch >=2.2

.github/workflows/stale.yml actions

actions/stale v8.0.0 composite

.github/workflows/build.yml actions

actions/checkout v4 composite
actions/upload-artifact v4 composite

.github/workflows/lint.yml actions

actions/checkout v4 composite
actions/setup-python v5 composite

.github/workflows/release.yml actions

actions/download-artifact v4 composite
pypa/gh-action-pypi-publish release/v1 composite

.github/workflows/test.yml actions

actions/cache v4 composite
actions/checkout v4 composite
actions/setup-python v5 composite
codecov/codecov-action v4 composite

packages/fairchem-applications-AdsorbML/pyproject.toml pypi

packages/fairchem-core/pyproject.toml pypi

ase *
e3nn >=0.5
lmdb *
numba *
numpy >=1.25.0
orjson *
pymatgen >=2023.10.3
pyyaml *
submitit *
tensorboard *
torch >=2.2
tqdm *
urllib3 *
wandb *

packages/fairchem-data-oc/pyproject.toml pypi

packages/fairchem-data-om/pyproject.toml pypi

ase @git+https://gitlab.com/ase/ase.git@dc86a19a280741aa2b42a08d0fa63a8d0348e225
quacc [sella]>=0.7.6
sella ==2.3.3

packages/fairchem-demo-ocpapi/pyproject.toml pypi

dataclasses-json == 0.6.0
inquirer == 3.1.3
requests == 2.31.0
responses == 0.23.2
tenacity == 8.2.3
tqdm == 4.66.1

packages/requirements-optional.txt pypi

torch_cluster ==1.6.3
torch_geometric ==2.3.0
torch_scatter ==2.1.2
torch_sparse ==0.6.18

packages/requirements.txt pypi

ase ==3.22.1
numpy ==1.23.5
torch ==2.2.0

.github/workflows/build_docs.yml actions

actions/checkout v4 composite
actions/setup-python v5 composite
actions/upload-artifact v4 composite

.github/workflows/deploy_docs.yml actions

actions/download-artifact v4 composite
peaceiris/actions-gh-pages v3 composite
peaceiris/actions-gh-pages v4 composite

.github/workflows/integration-test.yml actions

actions/cache v4 composite
actions/checkout v4 composite
actions/setup-python v5 composite

.github/workflows/label_checker.yml actions

actions/checkout v4 composite

.github/workflows/release-drafter-applications_cattsunami.yml actions

release-drafter/release-drafter v6 composite

.github/workflows/release-drafter-core.yml actions

release-drafter/release-drafter v6 composite

.github/workflows/release-drafter-data_oc.yml actions

release-drafter/release-drafter v6 composite

.github/workflows/release-drafter-demo_ocpapi.yml actions

release-drafter/release-drafter v6 composite

fairchem-core

Science Score: 77.0%

Keywords from Contributors

Repository

Basic Info

Statistics

Metadata Files

README.md

fairchem by the FAIR Chemistry team

Read our latest release post!

Try the demo!

Installation

Quick Start

Instantiate a calculator from a pretrained model

Set the task for your application and calculate

Relax an adsorbate on a catalytic surface,

Set up your system as an ASE atoms object

Set up LBFGS dynamics object

Relax an inorganic crystal,

Run molecular MD,

Calculate a spin gap,

singlet CH2

triplet CH2

LICENSE

Owner

Citation (CITATION.cff)

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

pypi.org: fairchem-data-omol

Rankings

Maintainers (1)

pypi.org: fairchem-data-oc

Rankings

Maintainers (1)

pypi.org: fairchem-core

Rankings

Maintainers (1)

Dependencies

`fairchem` by the FAIR Chemistry team