RXNRECer Enables Fine-grained Enzymatic Function Annotation through Active Learning and Protein Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915858739101696 |
|---|---|
| author | Shi, Zhenkun Zhu, Jun Wang, Dehang Chen, BoYu Yuan, Qianqian Mao, Zhitao Wei, Fan Wu, Weining Liao, Xiaoping Ma, Hongwu |
| author_facet | Shi, Zhenkun Zhu, Jun Wang, Dehang Chen, BoYu Yuan, Qianqian Mao, Zhitao Wei, Fan Wu, Weining Liao, Xiaoping Ma, Hongwu |
| contents | A key challenge in enzyme annotation is identifying the biochemical reactions catalyzed by proteins. Most existing methods rely on Enzyme Commission (EC) numbers as intermediaries: they first predict an EC number and then retrieve the associated reactions. This indirect strategy introduces ambiguity due to the complex many-to-many mappings among proteins, EC numbers, and reactions, and is further complicated by frequent updates to EC numbers and inconsistencies across databases. To address these challenges, we present RXNRECer, a transformer-based ensemble framework that directly predicts enzyme-catalyzed reactions without relying on EC numbers. It integrates protein language modeling and active learning to capture both high-level sequence semantics and fine-grained transformation patterns. Evaluations on curated cross-validation and temporal test sets demonstrate consistent improvements over six EC-based baselines, with gains of 16.54% in F1 score and 15.43% in accuracy. Beyond accuracy gains, the framework offers clear advantages for downstream applications, including scalable proteome-wide reaction annotation, enhanced specificity in refining generic reaction schemas, systematic annotation of previously uncurated proteins, and reliable identification of enzyme promiscuity. By incorporating large language models, it also provides interpretable rationales for predictions. These capabilities make RXNRECer a robust and versatile solution for EC-free, fine-grained enzyme function prediction, with potential applications across multiple areas of enzyme research and industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_12694 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RXNRECer Enables Fine-grained Enzymatic Function Annotation through Active Learning and Protein Language Models Shi, Zhenkun Zhu, Jun Wang, Dehang Chen, BoYu Yuan, Qianqian Mao, Zhitao Wei, Fan Wu, Weining Liao, Xiaoping Ma, Hongwu Machine Learning Quantitative Methods I.2.6 A key challenge in enzyme annotation is identifying the biochemical reactions catalyzed by proteins. Most existing methods rely on Enzyme Commission (EC) numbers as intermediaries: they first predict an EC number and then retrieve the associated reactions. This indirect strategy introduces ambiguity due to the complex many-to-many mappings among proteins, EC numbers, and reactions, and is further complicated by frequent updates to EC numbers and inconsistencies across databases. To address these challenges, we present RXNRECer, a transformer-based ensemble framework that directly predicts enzyme-catalyzed reactions without relying on EC numbers. It integrates protein language modeling and active learning to capture both high-level sequence semantics and fine-grained transformation patterns. Evaluations on curated cross-validation and temporal test sets demonstrate consistent improvements over six EC-based baselines, with gains of 16.54% in F1 score and 15.43% in accuracy. Beyond accuracy gains, the framework offers clear advantages for downstream applications, including scalable proteome-wide reaction annotation, enhanced specificity in refining generic reaction schemas, systematic annotation of previously uncurated proteins, and reliable identification of enzyme promiscuity. By incorporating large language models, it also provides interpretable rationales for predictions. These capabilities make RXNRECer a robust and versatile solution for EC-free, fine-grained enzyme function prediction, with potential applications across multiple areas of enzyme research and industrial applications. |
| title | RXNRECer Enables Fine-grained Enzymatic Function Annotation through Active Learning and Protein Language Models |
| topic | Machine Learning Quantitative Methods I.2.6 |
| url | https://arxiv.org/abs/2603.12694 |