MolBasis
How the lab works

Fit, don't train

Every kernel is a closed-form equation solved from quantum chemistry — no learnable weights, no gradient descent, no empirical correction tables. Here's the full method and the rigor gate every claim passes through.

Closed-form, not trained

Every kernel is ŷ = β₀ + Σⱼ βⱼ · z(fⱼ^pⱼ) solved by a single Cholesky solve (ridge λ=1e-3). No SGD, no learnable weights, no hyperparameter tuning. We say 'fit' and 'solve', never 'train'.

Quantum-chemical inputs only

The 9-dimensional feature vector comes entirely from one SCF per molecule (wB97M-V / def2-SVP / C-PCM, ε=80). No empirical group contributions, no fitted correction tables.

Quarter-integer exponents

Optimal exponents fall on the ¼-integer grid {…,−0.5,−0.25,0,0.25,0.5,0.75,1.0,…}. Finer grids add <0.002 r; continuous optimisation lands within 0.06 of the nearest ¼-integer with no gain.

Scaffold-blind is the real metric

In-sample r is a sanity check. The number that matters — and that we quote as commercial-grade — is the 25% Bemis–Murcko scaffold-blind held-out lift.

the kernel form
ŷ = β₀ + Σⱼ βⱼ · z(fⱼ^pⱼ)
  • fⱼ — quantum-chemical descriptor from one SCF (wB97M-V / def2-SVP / C-PCM, ε=80)
  • pⱼ — exponent on the ¼-integer grid {−2.25 … +2.25}
  • z() — z-scoring of the transformed feature
  • βⱼ — solved by a single Cholesky solve, ridge λ = 1e-3

The 2-term search is a vmap’d best-of-17,766 over ordered (feature, exponent) pairs, with per-fold independent selection inside nested CV. No SGD, no hyperparameter tuning.

The 8-step rigor gate

Every kernel claim passes this gate before it ships. It was hardened across 12 audit rounds; several steps exist specifically because an earlier version of a kernel failed them.

1

Grouped-LOO by InChI-Key-14

Same molecule under different conditions never straddles train/test — catches cross-condition leakage that anchor-level LOO misses.

2

Bootstrap 95% CI on r & MAE

Exposes small-n volatility. For an A-grade ship the CI lower bound on r must sit at or above 0.50.

3

Permutation sanity floor

Shuffle the target, run the identical search, record the noise p95. A real winner must beat noise by ≥ +0.30 r.

4

Nested cross-validation

The exponent/pair search happens on the TRAINING fold only, scored on held-out chemistry. This is the decisive killer of winner's curse.

5

Pair-stability & plateau width

If ≥3 exponent pairs sit within ±0.01 r of the top, ship the FAMILY — not a single 'magic' pair (this is exactly why Bradley_Tm is a family kernel).

6

Calibration diagnostic

Fit y = α + β·ŷ on grouped-LOO predictions. If the slope ≈ 1 there is no compression to 'recover' — the low-lift verdict is honest signal, not an artefact.

7

Feature-addition gate

A new feature must: raise nested-CV r with a Δr CI excluding 0, enter the winning pair in ≥50% of folds, AND pass a held-out negative control. 'r went up' alone is not success.

8

25% scaffold-blind held-out

A Bemis–Murcko scaffold split (seed 2026) set aside up front, never seen by the fitter. Re-fit β on the 75%, predict the blind 25%. This is the commercial out-of-distribution estimate.

The Quarter-Integer Law

Across every kernel, the optimal exponents fall on the ¼-integer grid. Finer grids (⅛, 1/16) add <0.002 r; coarser grids (½) lose ~0.010 r; continuous optimisation lands within 0.06 of the nearest ¼-integer with no gain. The exponents appear to reflect integer-rational dimensional couplings in continuum solvation theory (Born, Onsager, scaled-particle).

Propertyg_polar exponentPhysical regime
Melting point (Tm)0.25Weak polar coupling to the lattice (¼ of solvation)
Hydration ΔG0.75Full solvation (Born + scaled-particle combined)
Surface tension (γ)1.50Interfacial cooperative regime (3/2)
Enthalpy of vaporisation (ΔH_vap)0.50Cohesion, cavity-dominated (the 'T₄ prophecy' was falsified)

Full derivation in the internal PAPER_DRAFT_quarter_integer_law. All 21 published exponents sit on the ¼-integer grid.