AlphaFold 2 vs OpenFold

AlphaFold 2: DeepMind's open-source protein structure prediction model (monomer and multimer). OpenFold: Trainable open-source reproduction of AlphaFold2 in PyTorch.

Facts below come from each project's own website, repository and paper. We don't publish benchmark claims here; see the papers for evaluations. Shared tags: structure.

FieldAlphaFold 2OpenFold
TaskStructure predictionStructure prediction (trainable AlphaFold2)
ModalitiesMonomer, multimerMonomer, multimer
MSA requiredYes (genetic databases)Yes (alignment databases; precomputed MSAs released)
Open weights—Yes (Apache 2.0)
GPU needNVIDIA GPUGPU (fastest on Ampere+); low-memory attention for long chains
LicenseApache-2.0Apache-2.0
PricingOpen sourceOpen source
Released2021-07-152021-11-18
PaperLinkLink
GitHubGitHubGitHub
GitHub stars14,8903,439
InterfaceDocker, Colab—

License and commercial use

FieldAlphaFold 2OpenFold
Code licenseApache-2.0Apache-2.0
Weights license—Apache 2.0
Commercial usePermissive (commercial OK)Permissive (commercial OK)
AnswerYes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. DetailsYes. The recorded license is permissive, so closed-source commercial use is allowed if you keep the notices. Details

Add more Protein structure & design tools to this comparison →

More Protein structure & design comparisons

← All Protein structure & design tools