MolGen-Lead
MolGen-Lead is a SYNTHETIC/DEMO drug discovery model for de novo lead-like molecule generation. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.
Sequence
Insilico BioFoundry
License: CC-BY-4.0
v2.1.4
RTG 4.2
DL 7,084
Metrics
| Metric | Value | Split |
|---|---|---|
| Validity | 0.87 | Synthetic hold-out |
| Calibration (ECE) | 0.025 | Synthetic |
| Inputs | Outputs |
|---|---|
| Target profile | Candidate SMILES set |
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-014-molgen-lead/predict",
headers={"Authorization": "Bearer <API_KEY>"},
json={"input": "<target profile>"})
print(r.json()) # -> synthetic demo prediction
See the API reference · JSON: /api/models/bf-014-molgen-lead
Version history
| Version | Status | Notes |
|---|---|---|
| v2.1.0 | Archived | Synthetic release note 0 |
| v2.1.1 | Archived | Synthetic release note 1 |
| v2.1.2 | Archived | Synthetic release note 2 |
| v2.1.3 | Archived | Synthetic release note 3 |
| v2.1.4 | Current | Synthetic release note 4 |
Community contributions: 17 synthetic contributors have submitted evaluations and fine-tunes.