AlphaProtein Novo

Researchers can use it to generate candidate enzyme structures and sequences conditioned on a catalytic motif and ligand context.

Availability

Package and pretrained generator weights are downloadable.

Pricing model

Not established

Deployment

Run locally using the provided Python scripts.

Privacy

Not established

Licence

Weights are subject to AP Novo Parameters Terms of Use.

• The diffusion model co-generates protein structures and sequences conditioned on a catalytic motif and ligand context. ^[1]

  and sequences conditioned on a catalytic motif and ligand context.

• The pipeline can combine generation with optional LigandMPNN sequence redesign, AlphaFold 3 structure prediction, and evaluation metrics. ^[1]
• The source package includes scripts and a quickstart for running the pipeline. ^[1]

  See the [Quickstart](#quickstart) section for a basic launch command and

• Pretrained generator weights must be downloaded separately from Google Cloud Storage. ^[1]

  be downloaded from Google Cloud Storage (see

• The documented setup uses local Python environments and command-line scripts.
• Use of the pretrained weights is subject to the AP Novo Parameters Terms of Use. ^[1]

  [AP Novo Parameters Terms of Use](WEIGHTS_TERMS_OF_USE.md); or configure a

• Two local models can classify, route, or score text and images Daily brief 2026-10-10