Protein Folding

FoldOpen-Mini

FoldOpen-Mini is a SYNTHETIC/DEMO protein folding model for single-chain structure prediction. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.

Sequence Genoma Institute License: CC-BY-4.0 v2.5.3 RTG 4.5 DL 101,539
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
GDT-TS0.821Synthetic hold-out
Calibration (ECE)0.031Synthetic
InputsOutputs
Amino-acid sequence3D coordinates + pLDDT

Run a synthetic prediction

Returns a deterministic synthetic result — clearly labeled, not for clinical use.

API integration

Call this model from your pipeline (demo — no real key required):

import requests
r = requests.post("https://api.biofoundry.ai/v1/models/bf-019-foldopen-mini/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<amino-acid sequence>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-019-foldopen-mini

Version history

VersionStatusNotes
v2.5.0ArchivedSynthetic release note 0
v2.5.1ArchivedSynthetic release note 1
v2.5.2ArchivedSynthetic release note 2
v2.5.3CurrentSynthetic release note 3

Community contributions: 118 synthetic contributors have submitted evaluations and fine-tunes.