Scientific Credibility
Validation Hub
Internal and external validation, kept strictly separate, with R² (hERG's regression metric) never combined with the six classification endpoints' AUC in the same chart.
1. Internal Validation — Scaffold Split
Primary methodology: scaffold-split GroupKFold (k=5), Murcko generic scaffolds — the harder, more realistic estimate (see §2 below for why it matters).
Classification Endpoints (AUC)
hERG is a pIC50 regression model — R², not AUC, and never plotted alongside the classification endpoints above. Scaffold-split R² = 0.38.
Integrated Risk Score
The aggregated score itself has its own reported validation: AUC = 0.81 on a withdrawn/safe compound set.
2. Why Scaffold Split, Not Random Split
Random splits let a model exploit scaffold-level similarity between train and test, inflating performance. These are the two endpoints where the backend documents both numbers.
3. External Validation
Per the model card's TRIPOD-AI checklist (item T14): partial. Reported as status, not invented results.
| Dataset | Purpose | Status |
|---|---|---|
| ClinTox | External classification benchmark (FDA-approved vs. withdrawn-for-toxicity) | In progress |
| Tox21 | External multi-assay toxicity benchmark | In progress |
| Temporal split | Time-split validation (train on older compounds, test on newer) | Methodology implemented |
| Train/test overlap check | Scaffold & exact-structure leakage audit between splits | Implemented |
4. Case Studies
Live predictions on 6 real, well-characterized drugs — not cached screenshots.
Explore case studies