Drug Discovery

RepurposeNet

RepurposeNet is a SYNTHETIC/DEMO drug discovery model for drug repurposing from knowledge graph. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified multi-modal data.

Multi-modal Helix Diagnostics License: BSD-3-Clause v2.1.3 RTG 4.3 DL 180,912
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
MRR0.87Synthetic hold-out
Calibration (ECE)0.073Synthetic
InputsOutputs
Disease + drug graphRanked repurposing candidates

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-018-repurposenet/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<disease + drug graph>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-018-repurposenet

Version history

VersionStatusNotes
v2.1.0ArchivedSynthetic release note 0
v2.1.1ArchivedSynthetic release note 1
v2.1.2ArchivedSynthetic release note 2
v2.1.3CurrentSynthetic release note 3

Community contributions: 25 synthetic contributors have submitted evaluations and fine-tunes.