Instructions to use Delower/liver-extratrees-deployment with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Delower/liver-extratrees-deployment with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Delower/liver-extratrees-deployment", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Liver toxicity (DILI) β ExtraTrees deployment model
Binary classifier for drug-induced liver injury (DILI) concern: the
probability that a compound belongs to the toxic class. This is the
deployment refit of the liver programme's Arch3 LazyPredict-best
model (ExtraTrees), one of the two winners selected on the locked
regulatory benchmark. It is deployed as a pair with the GAT
deployment model (Delower/liver-gat-deployment); a compound
flagged by both models is the highest-concern readout.
Recipe
- Model:
ExtraTreesClassifierwith scikit-learn defaults andrandom_state=42β the arm's own recipe, reused unchanged with no re-tuning. - Features (
fp_desc, 1,404 columns): Morgan fingerprint bits (1024) + MACCS keys (167) + RDKit descriptors prepared by the arm'sDescPrep(fit on the full deployment set; shipped inside the weights bundle). - Flag threshold: probability β₯ 0.5 (the arm's own convention).
Deployment training set
All labeled liver data the programme holds, identity-deduped by InChIKey connectivity of the standardized parent: 1,891 unique compounds (1,003 positive / 888 negative), composed of train_locked.csv (1,769 rows) + train_enriched.csv additions + internal_test.csv + every regulatory benchmark compound (withdrawn, clinical failures, PASS), with benchmark labels governing conflicts. 1,769 duplicate rows dropped; 42 label conflicts (all inside train_locked, the groups the earlier merge had excluded) kept at the first train_locked row's label and logged.
Hard gate (passed before training): every deduped regulatory
benchmark compound was verified compound-by-compound (InChIKey
connectivity) inside the actual training matrix,
post-featurization: withdrawn 71/71, clinical failures 10/10,
PASS 304/304. See gate_verification.json.
Honest benchmark scores β benchmark version only
The deployment refit absorbed the regulatory benchmark and is never scored on it. The frozen claim for this recipe comes from the locked-wave benchmark model (benchmark locked out of training, overlap verified 0; 385 scored compounds):
| Metric | Value |
|---|---|
| Pooled regulatory AUROC | 0.690 |
| Pooled balanced accuracy | 0.623 |
| Withdrawn drugs caught | 65/71 |
| Clinical failures caught | 10/10 |
| PASS compounds correct | 97/304 (0.319) |
Deployment screen results
Applied to the DPP-4 programme's potent leads (flag = prob β₯ 0.5): 1,113/1,113 workbook leads scored, 1,082 flagged (97.5%); 4,898/4,898 of the full potent union scored, 4,722 flagged (96.5%). These flag rates are high β every model in this programme is a high-sensitivity, low-specificity screen, and the pair's discriminative readout is the dual flag (1,003/1,110 leads flagged by both models; only 6 pass both). Treat single-model flags as low-information on their own.
Files
model.joblibβ joblib bundle: the fittedExtraTreesClassifier, the fittedDescPreppreprocessing object, and the feature-block kind. Unpickling requiresdeployment_common.py(shipped here) to be importable.config.jsonβ recipe, training composition, gate counts, benchmark scores.deployment_common.pyβ the programme's shared featurization module (fingerprints, descriptors,DescPrep).infer.pyβ prediction entry point (predict(smiles)).validate.py+examples.jsonβ runnable validation: reproduces this model's probabilities on 8 screened DPP-4 leads (tolerance 1e-6; the model is deterministic). Verified locally before upload: max deviation 0.gate_verification.json,training_manifest.jsonβ hard-gate result and full training manifest.absorbed_compounds.csvβ the 1,891-compound deployment training set (the absorbed data, for audit).
Limitations
Requires scikit-learn, rdkit, joblib, numpy. Probabilities
are screening scores, not calibrated clinical risks.
- Downloads last month
- -