# Pseudodata-guided Invariant Representation Learning Boosts the Out-of-Distribution Generalization in Enzymatic Kinetic Parameter Prediction

arXiv: https://arxiv.org/abs/2601.07261 · HTML: https://mlsanity.com/paper/2601.07261/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 31 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 7 of 7)

- [Evaluating Protein Transfer Learning with TAPE](https://mlsanity.com/paper/1906.08230/) (2019)
- [Geometric Deep Learning on Molecular Representations](https://mlsanity.com/paper/2107.12375/) (2021)
- [SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery](https://mlsanity.com/paper/1911.04738/) (2019)
- [Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data](https://mlsanity.com/paper/2111.06849/) (2021)
- [A quantitative analysis of knowledge-learning preferences in large language models in molecular science](https://mlsanity.com/paper/2402.04119/) (2024)
- [Towards out-of-distribution generalizable predictions of chemical kinetics properties](https://mlsanity.com/paper/2310.03152/) (2023)
- [OmniESI: A unified framework for enzyme-substrate interaction prediction with progressive conditional deep learning](https://mlsanity.com/paper/2506.17963/) (2025)

## Abstract (arXiv)

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 O2DENet, a lightweight, plug-and-play module that enhances OOD generalization via biologically and chemically informed perturbation augmentation and invariant representation learning.O2DENet 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, O2DENet consistently improves predictive performance for both kcat and Km 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, O2DENet provides a general and effective strategy to enhance the stability and deployability of data-driven enzyme kinetics predictors for real-world enzyme engineering applications.