- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper introduces Chemistry-Informed Reaction–Catalyst Embeddings (CIRCE), a dual encoder framework for bidirectional enzyme–reaction retrieval. The enzyme encoder combines global protein representations, functional residue priors, and learned residue views, while the reaction encoder integrates pretrained molecular representations and explicit chemical descriptors. Training combines an anchor-balanced, multi-positive contrastive objective with residual refinement over known enzyme–reaction associations. Experiments on EnzymeMap and ReactZyme demonstrate improved screening and retrieval performance against reported baselines. Additional analyses examine functional organization, inference sensitivity, and catalytic site conservation. However, experimental validation, stronger component attribution, and clearer evaluation protocols are needed to substantiate claims about enzyme discovery and generalization.
Critical strengths
- This paper integrates function-aware protein pooling with chemically enriched reaction representations, providing a biologically motivated approach to connecting enzyme sequences with reaction compatibility.
- This paper accommodates many-to-many enzyme–reaction associations through an anchor-balanced multi-positive objective, avoiding competition between recorded positive partners during initial alignment.
- This paper reports substantial benchmark improvements, including increasing EnzymeMap BEDROC85 from 44.69 to 53.05, and supplements retrieval results with functional-neighborhood analyses and controlled residue-view ablations.
Critical weaknesses
- This paper leaves evaluation reliability insufficiently resolved: Appendix D acknowledges test-set inspection during development, inference coefficients are inconsistently specified as two or three, and Appendix G.4 reports a differently budgeted Horizyn refit outperforming CIRCE on all six ReactZyme MRR settings. These issues require reconciliation before accepting broad state-of-the-art claims.
- This paper does not sufficiently isolate its central contributions. The matched retraining ablation primarily removes learned residue views, without systematically separating functional-site priors, chemical feature sources, and the proposed alignment objective; the additional parameter capacity also confounds attribution.
- This paper provides limited evidence for discovering new catalytic activities or promiscuity. EC3 agreement and active-site conservation indicate functional similarity but cannot establish substrate specificity or catalytic activity, while the case study lacks prospective biochemical validation.
Questions for authors
NA
5 comments
Reply 1/4
This paper leaves evaluation reliability insufficiently resolved: Appendix D acknowledges test-set inspection during development, inference coefficients are inconsistently specified as two or three, and Appendix G.4 reports a differently budgeted Horizyn refit outperforming CIRCE on all six ReactZyme MRR settings. These issues require reconciliation before accepting broad state-of-the-art claims.
Appendix D acknowledges test-set inspection during development; inference coefficients are inconsistently specified as two or three.
Data preparation and test-set inspection. We acknowledge that in Appendix D we refer to a test set inspection, but we also refer to Appendix B, which clarifies that “test set inspection” refers to the analysis of the datasets. Appendix B documents the construction of the released benchmark splits and the overlap audit.
Exact enzyme–reaction association pairs do not overlap between training, validation, and test sets, although individual enzyme sequences or reactions can recur in different pairs; these entity overlaps are explicitly reported and are characteristic of the predetermined dataset splits. The chemistry preprocessing statistics and vocabulary are trained on training data and then frozen for validation and test, whose split is defined according to the released benchmarks.
We clarify that, during development, there was no hyperparameter tuning on the test set and no test-set exploitation: we constructed internal validation from the released training associations, while the test partition was not used for development. By the word “inspection”, we meant “inspecting possible overlaps" for extra fairness. Appendix D refers to this screening procedure when it mentions the test set inspection. We will make this clearer by rephrasing it.
Inference coefficient. We thank the reviewer for identifying the inconsistent description. The correct protein fusion multiplier is , as specified at the start of the main scoring subsection and in the saved inference manifests. The references to in Appendix D are typographical errors; we will consistently report .
Reply 2/4
Appendix G.4 reports a differently budgeted Horizyn refit outperforming CIRCE on all six ReactZyme MRR setting
Horizyn comparison.
We retrained Horizyn on the identical training associations using CIRCE's first-stage schedule: batch size 1,024, 20 epochs, AdamW learning rate , and weight decay . Validation selected epoch 20 on all three splits. This control also exceeds submitted CIRCE in all six settings.
The following are test MRR values.
| Configuration | Time E→R MRR | Time R→E MRR | Enzyme-Sim E→R MRR | Enzyme-Sim R→E MRR | Reaction-Sim E→R MRR | Reaction-Sim R→E MRR |
|---|---|---|---|---|---|---|
| CIRCE | 0.765 | 0.456 | 0.959 | 0.636 | 0.528 | 0.377 |
| Horizyn | 0.835 | 0.589 | 0.977 | 0.698 | 0.531 | 0.449 |
EnzymeMap. CIRCE exceeds all three benchmark-trained Horizyn controls on all eight screening metrics. The table below shows the fixed epoch-15 Horizyn checkpoint, matching CIRCE's encoder endpoint. “Full” contains 261,907 candidate identifiers; “Excluded” contains 252,113 after removing training enzyme IDs. This is identifier exclusion, not homology exclusion. B85/B20 denote BEDROC85/BEDROC20 multiplied by 100; EF5/EF10 are fold enrichment.
| Configuration | Full B85 | Full B20 | Full EF5 | Full EF10 | Excluded B85 | Excluded B20 | Excluded EF5 | Excluded EF10 |
|---|---|---|---|---|---|---|---|---|
| Horizyn | 44.46 | 60.70 | 13.38 | 7.68 | 39.42 | 56.38 | 12.48 | 7.38 |
| CIRCE | 53.05 | 71.32 | 16.03 | 8.62 | 49.64 | 68.70 | 15.48 | 8.45 |
Case study and observed gains.
Under the revised recipe, we decided to inspect the method and to apply changes to the CIRCE framework.
We additionally evaluated an auxiliary reaction fingerprint under a revised training recipe. It concatenates two 512-bit, radius-3, chirality-aware Morgan fingerprints, which are computed separately for reactants and products and then aggregated with a Differential Reaction Fingerprint (DRFP). This is then applied with a gated, , attention to the feature fusion of the reaction modality. We denote this extension as CIRCE*.
We evaluated $g\in{0,0.25,0.5,0.75,1,1.5,2$ for value selection, using as a criterion the mean of the six validation MRR values for ReactZyme and the mean across the four full-bank validation screening metrics for EnzymeMap. The recorded choices are for ReactZyme and for EnzymeMap. While for EnzymeMap the performance of CIRCE* reduces to the CIRCE ones, the ReactZyme test results for the extension are:
| Configuration | Time E→R MRR | Time R→E MRR | Enzyme-Sim E→R MRR | Enzyme-Sim R→E MRR | Reaction-Sim E→R MRR | Reaction-Sim R→E MRR |
|---|---|---|---|---|---|---|
| CIRCE*, | 0.839 | 0.591 | 0.982 | 0.699 | 0.463 | 0.423 |
| Horizyn, 20-epoch budget | 0.835 | 0.589 | 0.977 | 0.698 | 0.531 | 0.449 |
CIRCE* improves five of six settings over submitted CIRCE and four of six over the Horizyn model. Both configurations remain below Horizyn on the two Reaction-Sim directions. We will revise the unrestricted state-of-the-art claim to reflect these benchmark-, split-, and direction-specific comparisons
General comment.
We thank the reviewer for recognizing CIRCE's biological motivation, many-to-many formulation, and screening results. We have audited the configurations underlying the submitted results, completed a Horizyn comparison using CIRCE's first-stage schedule, and conducted additional component ablations.
To enhance clarity while reading the reply, we define two different configurations of the proposed model: CIRCE denotes the submitted model, i.e., the one in the original paper, while CIRCE* denotes the gated fingerprint extension evaluated during the rebuttal.