HSP · δ_d
Hansen dispersion parameter · MPa^½
In-sample → out-of-distribution
How the correlation holds when moving to unseen scaffolds.
Vertical marker = the +30% production gate.
Blind calibration slope
Slope of measured vs predicted on the blind set. 1.0 = no magnitude compression.
What it is
The hardest HSP component. r=0.473 (below the 0.50 floor) and blind lift −1.1% — the kernel orders molecules but does not predict absolute dispersion values. Honestly the weakest ship.
The physics
Dispersion cohesion needs polarizability. A dedicated test added explicit isotropic α (GFN2-CPSCF via dxtb): a {donor+α} 2-term reaches r=0.586 (MAE-vs-NULL 23.7%) — real and dispersion-specific, but still below the 30% gate, so α was NOT productionised.
B.UNDERFIT. Needs crystal-lattice / polarizability physics beyond single-geometry σ-profiles.
How the methods compare
Hansen parameters are dominated by group-contribution tables (Stefanis–Panayiotou / HSPiP). This kernel derives δ_h directly from hydrogen-bond acceptor surface area — a physical quantity — instead of counting functional groups. δ_p and δ_d remain honestly under-fit on current physics.
Input cost
Per-molecule compute/data burden to predict a new molecule — shorter is cheaper.
What each method needs
External dependencies each method carries. An amber dot means the method requires it — fewer dots means fewer things to procure or that can go wrong.
| Method | 3D geometry | MD / sampling | training corpus | a measured value | proprietary params | deps |
|---|---|---|---|---|---|---|
| HSP · δ_d · this kernel | – | – | – | – | 1 | |
| Stefanis–Panayiotou (group contribution) | – | – | – | – | 1 | |
| Van Krevelen / Hansen–Beerbower | – | – | – | – | – | 0 |
| ML (XGBoost / CatBoost on HSPiP) | – | – | – | – | 1 | |
| COSMO-RS σ-moment mapping | – | – | – | 2 |
This kernel needs only a 3D geometry for its one SCF — no MD, no training corpus, no measured value, no proprietary software.
Competing methods
How this property is predicted elsewhere — with the input each method needs (a key differentiator) and the literature reference. Numbers are each method’s own reported figure on its own benchmark, so they are indicative, not a head-to-head on an identical split.
| Method | Class | Reported performance | Input needed | Reference |
|---|---|---|---|---|
| HSP · δ_dthis kernel | closed-form | Pearson r 0.473 (nested-CV) · 0.710 scaffold-blind | one DFT SCF σ-profile · no training set · no MD | MF-FQSL (this lab) |
| Stefanis–Panayiotou (group contribution) | group-contribution | The standard GC route; 1st + 2nd-order groups, implemented in HSPiP | 2D functional-group counts (UNIFAC + conjugation groups) | Stefanis & Panayiotou, Int. J. Thermophys. 2008 |
| Van Krevelen / Hansen–Beerbower | group-contribution | Classic additive GC; component-dependent accuracy | 2D functional-group counts | Van Krevelen; Hansen, HSP Handbook 2007 |
| ML (XGBoost / CatBoost on HSPiP) | ML / GNN | Recent gradient-boosted models on the extended HSPiP corpus | molecular descriptors + the HSPiP training set | recent HSP ML studies (2023–2024) |
| COSMO-RS σ-moment mapping | physics | HSP from σ-profile moments; parametrisation-dependent | DFT σ-profile | Klamt; σ-moment → HSP correlations |
Metrics are as published by each method on its own dataset (different splits, different cohorts) — treat them as an orientation of the landscape, not a controlled benchmark. The differentiator for this kernel is the input column: a single closed-form solve from one σ-profile, with no training corpus, no MD, and no measured melting point.
Descriptors used
Version history
- 2026-05-31v0.91.1 B.UNDERFIT
r=0.473, blind lift −1.1%. Orders but doesn't predict.
- 2026-06-01Program 0 (α test)
Explicit polarizability α complementary to donor (r 0.586) but sub-gate → not productionised.