Gibergy computes free energies for small molecules and protein complexes with models that combine physics and machine learning. Every figure below was measured on data the model was not fitted to, and the calculator prints the one that applies beside each answer. Where a model has no measurement for an input, the answer says so instead of quoting a figure.
Accuracy
Table 1. Typical error (RMSE) on held-out data.
| Question | Measured against | Typical error |
|---|---|---|
| log P, octanol/water | SAMPL, never seen | 0.49 log units |
| log P, octanol/water | Lipophilicity, never seen | 0.85 log units |
| Solvation free energy, CPCM-X | CombiSolv, CPCM-X alone | 2.31 kcal/mol in water, 1.38 in other solvents, rising with size; with one or two O-H, a fitted term and 1.35 in water on unseen solutes |
| Solvation free energy, SMD blend, ORCA | CombiSolv, solute class held out | 1.02 kcal/mol, 1.19 in water; answers only while the ORCA machine is online |
| Solvation free energy, blend, new solutes | FlexiSol, never seen, pre-registered | 2.67 kcal/mol on 213 rows, against 3.20 for SMD with the trees |
| Protein-protein binding | SKEMPI and PDBbind, family held out | 2.28 kcal/mol, r 0.48; 1.90 to 3.02 by type |
| Mutation ddG | SKEMPI, family held out | 1.45 kcal/mol, r 0.56, single-point mutations |
Table 2. Mutation ΔΔG on SKEMPI, held out by sequence family. The last column is the error of always predicting the average change.
| Mutations | Rows | Complexes | RMSE | r | Predicting the mean |
|---|---|---|---|---|---|
| Single-point mutations | 4143 | 320 | 1.45 | 0.56 | 1.75 |
| Two or more mutations | 1715 | 149 | 2.24 | 0.54 | 2.65 |
| All | 5858 | 344 | 1.72 | 0.57 | 2.09 |
Examples
Table 3. Answers from the calculator for three inputs.
| Input | Calculation | Method | Answer |
|---|---|---|---|
| Paracetamol | log P, octanol/water | fitted transfer model | 0.44 log units |
| Paracetamol | absolute G in water | xtb (GFN2), eight conformers | -20508.33 kcal/mol |
| Barnase and barstar, 1BRS | binding affinity | measured in a lab (SKEMPI 2.0), shown in place of a prediction, with the model's own beside it | -19.09 kcal/mol |
Data and licences
The solvation model is fitted on CombiSolv-Exp (Vermeire et al., CC-BY-4.0) and FreeSolv, the log P model on ChEMBL (CC-BY-SA) with every benchmark molecule removed first, and the protein models on SKEMPI and PDBbind under their own terms. MNSol is used only to measure accuracy and is not redistributed. CheMeleon ships under its own licence. The quantum chemistry uses xtb from the Grimme group at the University of Bonn (LGPL-3.0). The tables and figures on this page are read from the model files in the code when the site is built.