ESOL · logS
Aqueous solubility logS · log mol/L
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
Aqueous solubility from cavity (desolvation cost) plus acceptor (hydration reward). Unique-pair winner under nested CV — but the 2-term form overfits on 25% scaffold-blind held-out.
The physics
Dissolving costs cavity formation and pays back H-bond hydration; the two compete. The physics is sound; the sample is just small for a 2-term fit.
Published nested-CV r=0.844 is a full-data UPPER bound. Blind lift is only +21.6% (below the +30% gate). Report the 1-term fallback as the commercial floor. Engineering note logged for v0.92.1.
Diagnostic v2 (2026-06-06): the system is well-conditioned (cond#=1.3) — this is GENUINE statistical overfitting, not numerical instability. 0 of the top-50 LOO-ranked pairs survive r_cv≥0.5. The 1-term cavity fallback is the honest lower bound (blind r≈0.66).
How the methods compare
Watch the hidden cost. The General Solubility Equation is a one-line formula — but it needs the experimental melting point, a lab measurement. The most accurate method (D-MPNN) needs a large labelled corpus. This kernel needs neither: no measured melting point, no training set, just one σ-profile.
Reported error
Each method's own reported error in log units — lower is better. Different datasets and splits, so this is an orientation, not a controlled benchmark.
Lower error isn’t the whole story — read it against input cost and requirements below.
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 |
|---|---|---|---|---|---|---|
| ESOL · logS · this kernel | – | – | – | – | 1 | |
| General Solubility Equation (GSE) | – | – | – | – | 1 | |
| ESOL (MLR) | – | – | – | – | 1 | |
| D-MPNN (Chemprop) | – | – | – | – | 1 | |
| COSMO-RS | – | – | 3 |
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 |
|---|---|---|---|---|
| ESOL · logSthis kernel | closed-form | Pearson r 0.844 (nested-CV) · 0.646 scaffold-blind · MAE 0.94 log mol/L | one DFT SCF σ-profile · no training set · no MD | MF-FQSL (this lab) |
| General Solubility Equation (GSE) | empirical | ≈0.9 log units — but requires the measured melting point | experimental melting point + logP | Jain & Yalkowsky, J. Pharm. Sci. 2001 |
| ESOL (MLR) | group-contribution | RMSE 1.01, avg abs err 0.75 log (n=2874); blind AAE 0.83 | 4 2-D descriptors (clogP, MW, aromatic fraction, rotatable bonds) | Delaney, J. Chem. Inf. Comput. Sci. 2004 |
| D-MPNN (Chemprop) | ML / GNN | RMSE ≈ 0.58 log on ESOL (graph NN) | 2D molecular graph + a labelled training set | Yang et al., J. Chem. Inf. Model. 2019 |
| COSMO-RS | physics | ≈0.5–0.7 log units (needs a fusion term for solids) | DFT σ-profile + a melting/fusion term for crystals | Klamt; COSMO-RS solubility |
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
- 2026-05-29v0.91.1 ship
⭐ Unique-pair winner under nested CV, r=0.844.
- 2026-06-06Overfit diagnostic v2
Well-conditioned; genuine 2-term overfitting on 75% subsample. r_cv collapses to ~0.02. 1-term fallback is the honest floor.