Cancer Detection

LiquidBiopsy-ctDNA

LiquidBiopsy-ctDNA is a SYNTHETIC/DEMO cancer detection model for circulating tumor dna variant calling. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.

Sequence Stanford BioML License: BioFoundry Research v1.1.8 RTG 4.2 DL 28,101
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
Sensitivity0.84Synthetic hold-out
Calibration (ECE)0.072Synthetic
InputsOutputs
cfDNA sequencing readsVariant calls + tumor fraction

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-008-liquidbiopsy-ctdna/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<cfdna sequencing reads>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-008-liquidbiopsy-ctdna

Version history

VersionStatusNotes
v1.1.0ArchivedSynthetic release note 0
v1.1.1ArchivedSynthetic release note 1
v1.1.2ArchivedSynthetic release note 2
v1.1.3ArchivedSynthetic release note 3
v1.1.4ArchivedSynthetic release note 4
v1.1.5ArchivedSynthetic release note 5
v1.1.6ArchivedSynthetic release note 6
v1.1.7ArchivedSynthetic release note 7
v1.1.8CurrentSynthetic release note 8

Community contributions: 104 synthetic contributors have submitted evaluations and fine-tunes.