Drug Discovery

KinaseHit-Screen

KinaseHit-Screen is a SYNTHETIC/DEMO drug discovery model for kinase inhibitor virtual screening. Outputs are deterministic demo values — NOT for clinical use. Trained (synthetically) on de-identified sequence data.

Sequence BroadOpen Collective License: MIT v2.9.7 RTG 4.0 DL 291,314
SYNTHETIC DEMOAll outputs are deterministic demo data — not for clinical use, not real medical inference.

Metrics

MetricValueSplit
Enrichment0.968Synthetic hold-out
Calibration (ECE)0.043Synthetic
InputsOutputs
Compound libraryRanked hits + scores

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-016-kinasehit-screen/predict",
    headers={"Authorization": "Bearer <API_KEY>"},
    json={"input": "<compound library>"})
print(r.json())  # -> synthetic demo prediction

See the API reference · JSON: /api/models/bf-016-kinasehit-screen

Version history

VersionStatusNotes
v2.9.0ArchivedSynthetic release note 0
v2.9.1ArchivedSynthetic release note 1
v2.9.2ArchivedSynthetic release note 2
v2.9.3ArchivedSynthetic release note 3
v2.9.4ArchivedSynthetic release note 4
v2.9.5ArchivedSynthetic release note 5
v2.9.6ArchivedSynthetic release note 6
v2.9.7CurrentSynthetic release note 7

Community contributions: 136 synthetic contributors have submitted evaluations and fine-tunes.