Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model
Abstract
Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function. We formulate this problem as learning an enzymatic reaction space linking reactants, products, and Enzyme Commission (EC) annotations. To characterize this space, we introduce VenusRX-Bench, a unified benchmark for forward reaction prediction, single-step retrosynthesis, and EC-number prediction. VenusRX-Bench integrates reactions from multiple biochemical databases with standardized curation, leakage- controlled splits, and consistent evaluation. Benchmarking representative chemical and enzymatic models reveals a clear chemical-to-enzymatic domain gap, driven by limited domain data, catalytic-context dependency, and the difficulty of modeling large biomolecular structures. To bridge this gap, we develop VenusRX, a unified T5-style sequence-to-sequence model for enzymatic reactions. VenusRX jointly learns forward prediction, ret- rosynthesis, and reaction reconstruction, with two-stage training on millions of template-expanded reactions followed by real biochemical reactions. In addition, optional EC conditioning incorporates catalytic context, while Molecule Library- Constrained Decoding improves the generation of complex biomolecules. Across benchmark tasks and challenging generalization splits, VenusRX achieves the best or competitive performance on most evaluated settings over representative chem- ical and enzymatic baselines. Moreover, EC information consistently improves reaction prediction, while learned reaction representations support accurate EC prediction, revealing a bidirectional relationship between reaction structure and catalytic function. Together, VenusRX-Bench and VenusRX provide a unified framework for elucidating and modeling enzymatic reaction space
Related
- Denoising broadband CARS hyperspectral images on variance-stabilized data: a unified benchmark
- Benchmark validity in graph neural network scoring of metabolic reaction activity on Recon3D: detecting label leakage, memorized noise and input-invariant models
- Pretrained gene representations transfer mean expression more broadly than spatial patterns in virtual spatial transcriptomics
- Automated screening of autism via a pretrained vision-language model in naturalistic caregiver-child interactions.
- Elucidating the Functional Role of Arabidopsis Fimbrins in Actin Cytoskeleton Rearrangements in Root‐Knot Nematode Feeding Sites
BibTeX
@misc{hu2026elucidating,
title = {{Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model}},
author = {Yutong Hu and Tianming Huang and Yanbo Zhao and Qiongyu Zhang and Shixiang Tang and Lei Bai and Ziyi Zhou and Liang Hong and Pan Tan},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.11694},
eprint = {2610.11694},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.11694},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Elucidating the Space of Enzymatic Reaction: A Unified Benchmark and Pretrained Model
AU - Yutong Hu
AU - Tianming Huang
AU - Yanbo Zhao
AU - Qiongyu Zhang
AU - Shixiang Tang
AU - Lei Bai
AU - Ziyi Zhou
AU - Liang Hong
AU - Pan Tan
PY - 2026
DA - 2026/10/08
PB - arXiv
DO - 10.48550/arxiv.2610.11694
UR - https://arxiv.org/abs/2610.11694
AB - Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic function. We formulate this problem as learning an enzymatic reaction space linking reactants, products, and Enzyme Commission (EC) annotations. To characterize this space, we introduce VenusRX-Bench, a unified benchmark for forward reaction prediction, single-step retrosynthesis, and EC-number prediction. VenusRX-Bench integrates reactions from multiple biochemical databases with standardized curation, leakage- controlled splits, and consistent evaluation. Benchmarking representative chemical and enzymatic models reveals a clear chemical-to-enzymatic domain gap, driven by limited domain data, catalytic-context dependency, and the difficulty of modeling large biomolecular structures. To bridge this gap, we develop VenusRX, a unified T5-style sequence-to-sequence model for enzymatic reactions. VenusRX jointly learns forward prediction, ret- rosynthesis, and reaction reconstruction, with two-stage training on millions of template-expanded reactions followed by real biochemical reactions. In addition, optional EC conditioning incorporates catalytic context, while Molecule Library- Constrained Decoding improves the generation of complex biomolecules. Across benchmark tasks and challenging generalization splits, VenusRX achieves the best or competitive performance on most evaluated settings over representative chem- ical and enzymatic baselines. Moreover, EC information consistently improves reaction prediction, while learned reaction representations support accurate EC prediction, revealing a bidirectional relationship between reaction structure and catalytic function. Together, VenusRX-Bench and VenusRX provide a unified framework for elucidating and modeling enzymatic reaction space
ER -