Protein Folding

MutStab-ddG

MutStab-ddG is a SYNTHETIC/DEMO protein folding model for mutation stability (ddg) prediction. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.

Sequence Helix Diagnostics License: CC-BY-4.0 v3.5.9 RTG 5.0 DL 197,574
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
RMSE1.5Synthetic hold-out
Calibration (ECE)0.046Synthetic
InputsOutputs
Sequence + mutationddG kcal/mol

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-021-mutstab-ddg/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<sequence + mutation>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-021-mutstab-ddg

Version history

VersionStatusNotes
v3.5.0ArchivedSynthetic release note 0
v3.5.1ArchivedSynthetic release note 1
v3.5.2ArchivedSynthetic release note 2
v3.5.3ArchivedSynthetic release note 3
v3.5.4ArchivedSynthetic release note 4
v3.5.5ArchivedSynthetic release note 5
v3.5.6ArchivedSynthetic release note 6
v3.5.7ArchivedSynthetic release note 7
v3.5.8ArchivedSynthetic release note 8
v3.5.9CurrentSynthetic release note 9

Community contributions: 140 synthetic contributors have submitted evaluations and fine-tunes.