KineCouple: Substrate-conditioned residual readout for enzyme kinetic prediction
Organizations: School of Artificial Intelligence, Beihang University · OxTium AI Research · Imperial College London
Abstract
Accurate prediction of enzyme kinetic parameters can support enzyme engineering and metabolic modeling by complementing experimental characterization. Existing prediction methods often pool residue-level protein features before combining them with substrate features. Such substrate-independent pooling cannot adapt residue weighting to the substrate during aggregation, potentially diluting information relevant to a specific enzyme-substrate pair. Since the contributions of individual residues to catalysis can depend on the substrate, substrate-conditioned aggregation offers a way to emphasize residue features relevant to the prediction. We introduce KineCouple, which uses substrate queries and residue-level keys and values in cross-attention, allowing the substrate to guide residue selection before aggregation. The model preserves the global protein representation and adds a gated correction defined as the difference between the conditioned readout and a uniform readout. ProtT5 and MolT5 remain frozen, and separate models predict kcat and Km on a logarithmic scale. In pooled out-of-fold predictions on the CataPro benchmarks, KineCouple reduces kcat RMSE from 1.333 to 1.330 and increases PCC from 0.492 to 0.496 relative to reproduced CataPro. For Km, RMSE decreases from 0.998 to 0.997 and PCC increases from 0.633 to 0.634. Spearman correlation also improves for both tasks.
Figures & tables
| Method | RMSE | PCC | SCC | RMSE | PCC | SCC |
|---|---|---|---|---|---|---|
| DLKcat ‡ | 1.426 | 0.368 | 0.349 | 1.052 | 0.578 | 0.578 |
| UniKP ‡ | 1.382 | 0.448 | 0.449 | 1.039 | 0.599 | 0.594 |
| CataPro (reproduced) † | 1.327 | 0.481 | 0.470 | 1.006 | 0.622 | 0.610 |
| CataPro+SaProt ‡ | 1.317 | 0.493 | 0.489 | 0.999 | 0.631 | 0.625 |
| KineCouple † | 1.319 | 0.496 | 0.495 | 0.997 | 0.634 | 0.631 |
| Variant | RMSE | PCC | SCC | RMSE | PCC | SCC |
|---|---|---|---|---|---|---|
| Baseline (A) | 1.3274 | 0.4808 | 0.4699 | 1.0056 | 0.6217 | 0.6103 |
| Continued Training (B) | 1.3238 | 0.4855 | 0.4725 | 1.0039 | 0.6239 | 0.6148 |
| Mean Readout (P) | 1.3204 | 0.4882 | 0.4748 | 1.0032 | 0.6245 | 0.6150 |
| Fixed-Query Attention (Q) | 1.3188 | 0.4899 | 0.4751 | 1.0039 | 0.6238 | 0.6152 |
| KineCouple (F) | 1.3185 | 0.4962 | 0.4948 | 0.9974 | 0.6344 | 0.6309 |
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
| Variable | Definition | Shape |
|---|---|---|
| Frozen ProtT5 residue representations | ||
| Mean over valid residues | ||
| Frozen MolT5 substrate vector | ||
| MACCS fingerprint | ||
| Substrate features supplied to the predictor | ||
| Output of the substrate conditioning network |
| Method | RMSE | PCC | SCC | RMSE | PCC | SCC |
|---|---|---|---|---|---|---|
| DLKcat ‡ | 1.426 | 0.368 | 0.349 | 1.052 | 0.578 | 0.578 |
| UniKP ‡ | 1.382 | 0.448 | 0.449 | 1.039 | 0.599 | 0.594 |
| ESM2_15B ‡ | 1.431 | 0.435 | 0.467 | 1.063 | 0.581 | 0.567 |
| ESM2_RDKitFP ‡ | 1.380 | 0.435 | 0.424 | 1.025 | 0.609 | 0.607 |
| ESM2_Morgan ‡ | 1.370 | 0.446 | 0.436 | 1.017 | 0.617 | 0.616 |
Molecular Property Prediction
Molecular property prediction estimates chemical, physical, and biological properties from molecular structure and context.
See all 226 papers