Corollary

Research

  • Papers

Library

  • Catalog

Account

  • Jobs
  • Billing
SettingsResearch demo · not for clinical or commercial use
Corollary
  1. Catalog
  2. Protein Structure
  3. OpenFold

Protein Structure · AlQuraishi Lab / Columbia

OpenFold

A fully retrained, Apache-2.0 reproduction of AlphaFold2.

Commercial use permittedThe Apache-2.0 licence allows use in commercial research and products.Apache-2.0
Availability
Not runnable yet

No backend is configured for this model.

Typical latency
2.0min
Credits per run
~336
Compute tier
B · Standard

30s–5min

Not runnable yet

This model isn't available to run right now.

Run this model

OpenFold

Single-letter amino acid code. Whitespace and FASTA headers are stripped automatically.

Needs protein sequence

About this model

OpenFold matches AlphaFold2 accuracy from a clean-room retraining, released under Apache 2.0. When licensing is the deciding constraint rather than raw accuracy, this is the structure predictor to reach for.

Standardized I/O contract

Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.

Inputs

  • sequencesequence · required

    Protein sequence

Outputs

  • pdbstructure

    All-atom coordinates in PDB format, viewable and downloadable.

  • plddtvector

    pLDDT score per residue (0–100). Above 70 is generally reliable.

Specification

Hardware
1× A100 40GB
GPU memory
40 GB
Version
2.0
Licence
Apache-2.0
Backend
not configured
MCP server
mcp-protein-server

Tasks

structure prediction

Source

  • Repository
foldingapache-2retrained