All model cards
Nephrotoxicity
classification · RandomForest (classification)
Purpose
Predicts nephrotoxicity (drug-induced kidney injury) potential.
Prediction Output
Binary classification (nephrotoxic / non-nephrotoxic) + probability.
Input Requirements
A single valid SMILES string, standardized server-side before featurization.
Training Methodology
Algorithm: RandomForest (classification) · Optuna, TPE sampler, 100 trials, random_state=42
Feature representation: 2,048-bit Morgan ECFP4 (radius=2) + 167 MACCS keys + 25 RDKit physicochemical descriptors → 2,240 raw features → variance threshold (>0.01) → Pearson correlation filter (|r|<0.95) → top 500 features → StandardScaler (fit on the training fold only).
- Sources: FDA DIRIL database + curated literature. N = 302 compounds (as documented in reproducibility.md — the repo's own train/test split figures for this endpoint, 118/31, do not sum to 302; reported here verbatim rather than reconciled).
Validation Methodology
- Scaffold-split GroupKFold (k=5).
Scaffold-split AUC = 0.868. Bootstrap 95% CI ≈ ±0.08 (wide, due to the small dataset).
Known Limitations
- Small dataset (N=302) — confidence intervals on the reported AUC are wide.
- Applicability domain coverage on the training set: 93.5%.
Applicability Domain
Leverage-based applicability domain: h* = 3×(p+1)/n (Williams plot). in_domain=true → confidence 1.0; in_domain=false → confidence 0.0, and the prediction should be treated as exploratory only. Supplementary checks: Tanimoto k-NN distance > 0.6 or descriptor values outside [min−3σ, max+3σ].
Interpretability Support
SHAP (SHapley Additive exPlanations) feature attribution is available via /predict/interpret and /predict/integrated, returning per-feature contribution values and a global/local breakdown by feature category (physicochemical / structural fingerprints / substructure keys).
Research-Use Disclaimer
Research use only. Not validated for regulatory submissions or clinical decision-making. Predictions must not be the sole basis for safety decisions without independent experimental validation.