CRISPR-Guide
CRISPR-Guide is a SYNTHETIC/DEMO genomics model for grna on/off-target efficiency. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.
Sequence
NeuroScan Labs
License: Apache-2.0
v1.3.2
RTG 4.9
DL 456,666
Metrics
| Metric | Value | Split |
|---|---|---|
| Spearman | 0.849 | Synthetic hold-out |
| Calibration (ECE) | 0.057 | Synthetic |
| Inputs | Outputs |
|---|---|
| Target locus + gRNA | Efficiency + off-target risk |
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-030-crispr-guide/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<target locus + grna>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-030-crispr-guide
Version history
| Version | Status | Notes |
|---|---|---|
| v1.3.0 | Archived | Synthetic release note 0 |
| v1.3.1 | Archived | Synthetic release note 1 |
| v1.3.2 | Current | Synthetic release note 2 |
Community contributions: 137 synthetic contributors have submitted evaluations and fine-tunes.