scRNA-Annotate
scRNA-Annotate is a SYNTHETIC/DEMO genomics model for single-cell type annotation. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.
Sequence
Helix Diagnostics
License: Apache-2.0
v1.7.3
RTG 4.5
DL 265,579
Metrics
| Metric | Value | Split |
|---|---|---|
| Accuracy | 0.935 | Synthetic hold-out |
| Calibration (ECE) | 0.062 | Synthetic |
| Inputs | Outputs |
|---|---|
| scRNA-seq matrix | Cell-type labels |
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-028-scrna-annotate/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<scrna-seq matrix>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-028-scrna-annotate
Version history
| Version | Status | Notes |
|---|---|---|
| v1.7.0 | Archived | Synthetic release note 0 |
| v1.7.1 | Archived | Synthetic release note 1 |
| v1.7.2 | Archived | Synthetic release note 2 |
| v1.7.3 | Current | Synthetic release note 3 |
Community contributions: 56 synthetic contributors have submitted evaluations and fine-tunes.