dorsal/arxiv
View SchemaPseudodata-guided Invariant Representation Learning Boosts the Out-of-Distribution Generalization in Enzymatic Kinetic Parameter Prediction
| Authors | Haomin Wu, Zhiwei Nie, Hongyu Zhang, Zhixiang Ren |
|---|---|
| Categories | |
| ArXiv ID | 2601.07261vv1 |
| URL | https://arxiv.org/abs/2601.07261 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
Accurate prediction of enzyme kinetic parameters is essential for understanding catalytic mechanisms and guiding enzyme engineering.However, existing deep learning-based enzyme-substrate interaction (ESI) predictors often exhibit performance degradation on sequence-divergent, out-of-distribution (OOD) cases, limiting robustness under biologically relevant perturbations.We propose O$^2$DENet, a lightweight, plug-and-play module that enhances OOD generalization via biologically and chemically informed perturbation augmentation and invariant representation learning.O$^2$DENet introduces enzyme-substrate perturbations and enforces consistency between original and augmented enzyme-substrate-pair representations to encourage invariance to distributional shifts.When integrated with representative ESI models, O$^2$DENet consistently improves predictive performance for both $k_{cat}$ and $K_m$ across stringent sequence-identity-based OOD benchmarks, achieving state-of-the-art results among the evaluated methods in terms of accuracy and robustness metrics.Overall, O$^2$DENet provides a general and effective strategy to enhance the stability and deployability of data-driven enzyme kinetics predictors for real-world enzyme engineering applications.
{
"annotation_id": "a87dd64d-c4d9-4450-a41c-2a8e1c4d8312",
"date_created": "2026-02-17T05:53:11.334000Z",
"date_modified": "2026-02-17T05:53:11.334000Z",
"file_hash": "e470cd6f5905cf6801a6fec3905a75aa3392b76091d922677949d4e0daaf3624",
"private": false,
"record": {
"abstract": "Accurate prediction of enzyme kinetic parameters is essential for understanding catalytic mechanisms and guiding enzyme engineering.However, existing deep learning-based enzyme-substrate interaction (ESI) predictors often exhibit performance degradation on sequence-divergent, out-of-distribution (OOD) cases, limiting robustness under biologically relevant perturbations.We propose O$^2$DENet, a lightweight, plug-and-play module that enhances OOD generalization via biologically and chemically informed perturbation augmentation and invariant representation learning.O$^2$DENet introduces enzyme-substrate perturbations and enforces consistency between original and augmented enzyme-substrate-pair representations to encourage invariance to distributional shifts.When integrated with representative ESI models, O$^2$DENet consistently improves predictive performance for both $k_{cat}$ and $K_m$ across stringent sequence-identity-based OOD benchmarks, achieving state-of-the-art results among the evaluated methods in terms of accuracy and robustness metrics.Overall, O$^2$DENet provides a general and effective strategy to enhance the stability and deployability of data-driven enzyme kinetics predictors for real-world enzyme engineering applications.",
"arxiv_id": "2601.07261",
"authors": [
"Haomin Wu",
"Zhiwei Nie",
"Hongyu Zhang",
"Zhixiang Ren"
],
"categories": [
"cs.LG",
"cs.AI",
"q-bio.QM"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "Pseudodata-guided Invariant Representation Learning Boosts the Out-of-Distribution Generalization in Enzymatic Kinetic Parameter Prediction",
"url": "https://arxiv.org/abs/2601.07261",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "81b0259e-2ec2-4cff-acce-b7ec77e54bc9",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}