Protein Folding

DisorderPred

DisorderPred is a SYNTHETIC/DEMO protein folding model for intrinsically disordered region prediction. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.

Sequence BroadOpen Collective License: MIT v3.9.7 RTG 4.6 DL 83,002
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
AUC0.845Synthetic hold-out
Calibration (ECE)0.024Synthetic
InputsOutputs
Amino-acid sequencePer-residue disorder score

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-022-disorderpred/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-022-disorderpred

Version history

VersionStatusNotes
v3.9.0ArchivedSynthetic release note 0
v3.9.1ArchivedSynthetic release note 1
v3.9.2ArchivedSynthetic release note 2
v3.9.3ArchivedSynthetic release note 3
v3.9.4ArchivedSynthetic release note 4
v3.9.5ArchivedSynthetic release note 5
v3.9.6ArchivedSynthetic release note 6
v3.9.7CurrentSynthetic release note 7

Community contributions: 131 synthetic contributors have submitted evaluations and fine-tunes.