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
Metrics
| Metric | Value | Split |
|---|---|---|
| GDT-TS | 0.821 | Synthetic hold-out |
| Calibration (ECE) | 0.031 | Synthetic |
| Inputs | Outputs |
|---|---|
| Amino-acid sequence | 3D 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
| Version | Status | Notes |
|---|---|---|
| v2.5.0 | Archived | Synthetic release note 0 |
| v2.5.1 | Archived | Synthetic release note 1 |
| v2.5.2 | Archived | Synthetic release note 2 |
| v2.5.3 | Current | Synthetic release note 3 |
Community contributions: 118 synthetic contributors have submitted evaluations and fine-tunes.