---
title: "TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval"
description: "The authors argue that protein language models capture structural and evolutionary signals but encode little about chemistry. 37 references."
authors: ["Yuhang Zhang", "Keyan Ding", "Peilin Chen", "Han Liu", "Can Lin", "Ruixi Chen", "Shiqi Wang", "Qi Song"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1643/"
doi: "10.18653/v1/2026.acl-long.1643"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-tiger-text-informed-generalized-enzyme/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-tiger-text-informed-generalized-enzyme/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/) / TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval

# TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval

**Authors:** Yuhang Zhang, [Keyan Ding](https://md.research.elamur.ai/free/en/authors/keyan-ding/), Peilin Chen, [Han Liu](https://md.research.elamur.ai/free/en/authors/han-liu/), Can Lin, Ruixi Chen, [Shiqi Wang](https://md.research.elamur.ai/free/en/authors/shiqi-wang/) and Qi Song · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.1643/) · [PDF](https://aclanthology.org/2026.acl-long.1643.pdf) · [DOI 10.18653/v1/2026.acl-long.1643](https://doi.org/10.18653/v1/2026.acl-long.1643) · [OpenAlex](https://openalex.org/W7166873321)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
TIGER addresses enzyme–reaction retrieval, a two-way matching task: given an enzyme, find the reactions it catalyzes, and given a reaction, find enzymes that could perform it. Earlier contrastive systems, such as CLIPZyme and the baselines in the ReactZyme benchmark, perform unevenly across the two directions and depend heavily on how the data are partitioned. The authors argue that protein language models capture structural and evolutionary signals but encode little about chemistry. To fill that gap, they add natural-language descriptions of each enzyme, produced automatically by protein-to-text generation models.

Generated text can be noisy or hallucinated, so a Dynamic Gating Network learns how much weight the text deserves relative to ESM2 sequence features. Reactions are encoded from substrates and products with a 3D molecular encoder. A Structure-Shared Feature Projector maps enzymes and reactions into a common space, and training uses a bidirectional contrastive loss.

On ReactZyme, TIGER beats prior methods under all three split types. This suggests that adaptively filtered machine-generated text can make cross-modal biochemical retrieval more robust.

## Key points
- Evaluation uses ReactZyme, described as the largest enzyme–reaction dataset, with time-based, enzyme similarity-based and reaction similarity-based splits. Baselines include CLIPZyme-style models and UniMol-3D combined with ESM or SaProt.
- Relative Hit@1 gains over state-of-the-art baselines range from about 14% to more than 200%, depending on the split.
- In the ablation of the Dynamic Gating Network, the gating raised E→R MRR on the reaction similarity split from 0.504 to 0.632.
- The Structure-Shared Feature Projector reached E→R Hit@1 of 0.581 on the time split and 0.931 on the enzyme similarity split, and R→E Hit@1 of 0.430 on the reaction similarity split. It outperformed both removing the projector and using a plain 2-layer MLP in most settings.
- The direction-balancing weight γ performs best in the range 0.3–0.7, and 0.5 is the default. Setting γ = 1.0 cuts R→E Hit@1 to 0.289. Stated limitations are coarse-grained text and the lack of an explicit measure of text reliability.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Science and Technology of China](https://md.research.elamur.ai/free/en/universities/university-of-science-and-technology-of-china/) — University, Hefei, China · 145 works · 114,409 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations
- [City University of Hong Kong](https://md.research.elamur.ai/free/en/universities/city-university-of-hong-kong/) — University, Hong Kong, China · 59 works · 3,480 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works · [🧬 Biochemistry, Genetics and Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/) · 263 works · [🧬 Molecular Biology](https://md.research.elamur.ai/free/en/shelves/biochemistry-genetics-and-molecular-biology/molecular-biology/) · 260 works

🧭 Topics (1): [🔍 Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · 552 works

## Cite

Cite as: Yuhang Zhang, Keyan Ding, Peilin Chen, Han Liu, Can Lin, Ruixi Chen, Shiqi Wang and Qi Song. 2026. TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026tiger,
  title = {{TIGER: Text-Informed Generalized Enzyme-Reaction Retrieval}},
  author = {Yuhang Zhang, Keyan Ding, Peilin Chen, Han Liu, Can Lin, Ruixi Chen, Shiqi Wang and Qi Song},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1643},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1643}
}
```

- [← previous TiC-MuFormer: Time-Aware Caption-Integrated Multimodal Transformers for User-Level Mental Health Modeling](https://md.research.elamur.ai/free/en/papers/tsoumplekas-2026-tic-muformer-time-aware-caption/)
- [next → Tigrinya Number Verbalization: Rules, Algorithm, and Implementation](https://md.research.elamur.ai/free/en/papers/gaim-2026-tigrinya-number-verbalization-rules-algorithm/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/)

## References

37 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Hadi Abdine, Michail Chatzianastasis, Costas Bouyioukos, and Michalis Vazirgiannis. 2024. Prot2Text: Multimodal protein’s function generation with GNNs and Transformers. Proceedings of the AAAI Conference on Artificial Intelligence, 38(10):10757–10765. [find](https://scholar.google.com/scholar?q=Hadi+Abdine%2C+Michail+Chatzianastasis%2C+Costas+Bouyioukos%2C+and+Michalis+Vazirgiannis%2E+2024%2E+Prot2Text%3A+Multimodal+protein%E2%80%99s+function+generation+with+GNNs+and+Transformers%2E+Proceedings+of+the+AAAI+Confer)
2. Amos Bairoch and Rolf Apweiler. 2000. The SWISS-PROT protein sequence database and its supplement TrEMBL in 2000. Nucleic Acids Research, 28(1):45– 48. [find](https://scholar.google.com/scholar?q=Amos+Bairoch+and+Rolf+Apweiler%2E+2000%2E+The+SWISS%2DPROT+protein+sequence+database+and+its+supplement+TrEMBL+in+2000%2E+Nucleic+Acids+Research%2C+28%281%29%3A45%E2%80%93+48%2E)
3. Ana I Benítez-Mateos, David Roura Padrosa, and Francesca Paradisi. 2022. Multistep enzyme cascades as a route towards green and sustainable pharmaceutical syntheses. Nature Chemistry, 14(5):489– 499. [find](https://scholar.google.com/scholar?q=Ana+I+Ben%C3%ADtez%2DMateos%2C+David+Roura+Padrosa%2C+and+Francesca+Paradisi%2E+2022%2E+Multistep+enzyme+cascades+as+a+route+towards+green+and+sustainable+pharmaceutical+syntheses%2E+Nature+Chemistry%2C+14%285%29%3A489%E2%80%93+499%2E)
4. R Buller, S Lutz, R J Kazlauskas, R Snajdrova, J C Moore, and U T Bornscheuer. 2023. From nature to industry: Harnessing enzymes for biocatalysis. Science, 382(6673):eadh8615. [find](https://scholar.google.com/scholar?q=R+Buller%2C+S+Lutz%2C+R+J+Kazlauskas%2C+R+Snajdrova%2C+J+C+Moore%2C+and+U+T+Bornscheuer%2E+2023%2E+From+nature+to+industry%3A+Harnessing+enzymes+for+biocatalysis%2E+Science%2C+382%286673%29%3Aeadh8615%2E)
5. Yihan Cao, Siyu Li, Yixin Liu, Zhiling Yan, Yutong Dai, Philip Yu, and Lichao Sun. 2025. A survey of AI-generated content (AIGC). ACM Computing Surveys, 57(5):1–38. [find](https://scholar.google.com/scholar?q=Yihan+Cao%2C+Siyu+Li%2C+Yixin+Liu%2C+Zhiling+Yan%2C+Yutong+Dai%2C+Philip+Yu%2C+and+Lichao+Sun%2E+2025%2E+A+survey+of+AI%2Dgenerated+content+%28AIGC%29%2E+ACM+Computing+Surveys%2C+57%285%29%3A1%E2%80%9338%2E)
6. Alperen Dalkiran, Ahmet Sureyya Rifaioglu, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay, and Tunca Doğan. 2018. ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature. BMC Bioinformatics, 19(1):334. [find](https://scholar.google.com/scholar?q=Alperen+Dalkiran%2C+Ahmet+Sureyya+Rifaioglu%2C+Maria+Jesus+Martin%2C+Rengul+Cetin%2DAtalay%2C+Volkan+Atalay%2C+and+Tunca+Dog%CC%86an%2E+2018%2E+ECPred%3A+a+tool+for+the+prediction+of+the+enzymatic+functions+of+protein+seque)
7. Duoduo Feng, Xiangteng He, and Yuxin Peng. 2023. MKVSE: Multimodal knowledge enhanced visual-semantic embedding for image-text retrieval. ACM Transactions on Multimedia Computing, Communications and Applications, 19(5):1–21. [find](https://scholar.google.com/scholar?q=Duoduo+Feng%2C+Xiangteng+He%2C+and+Yuxin+Peng%2E+2023%2E+MKVSE%3A+Multimodal+knowledge+enhanced+visual%2Dsemantic+embedding+for+image%2Dtext+retrieval%2E+ACM+Transactions+on+Multimedia+Computing%2C+Communications+and+A)
8. Sara Johansson Fernstad and Jimmy Johansson. 2011. A task based performance evaluation of visualization approaches for categorical data analysis. In 2011 15th International Conference on Information Visualisation, pages 80–89. IEEE. [find](https://scholar.google.com/scholar?q=Sara+Johansson+Fernstad+and+Jimmy+Johansson%2E+2011%2E+A+task+based+performance+evaluation+of+visualization+approaches+for+categorical+data+analysis%2E+In+2011+15th+International+Conference+on+Information+V)
9. Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jianfeng Gao, and Hoifung Poon. 2021. [Domain-specific language model pretraining for biomedical natural language processing](https://md.research.elamur.ai/free/en/papers/gu-2020-domain-specific-language-model-pretraining/). ACM Transactions on Computing for Healthcare, 3(1):1–23.
10. Joseph I Hoffman, Fraser Simpson, Patrice David, Jo-lianne M Rijks, Thijs Kuiken, Michael AS Thorne, Robert C Lacy, and Kanchon K Dasmahapatra. 2014. High-throughput sequencing reveals inbreeding depression in a natural population. Proceedings of the National Academy of Sciences, 111(10):3775–3780. [find](https://scholar.google.com/scholar?q=Joseph+I+Hoffman%2C+Fraser+Simpson%2C+Patrice+David%2C+Jo%2Dlianne+M+Rijks%2C+Thijs+Kuiken%2C+Michael+AS+Thorne%2C+Robert+C+Lacy%2C+and+Kanchon+K+Dasmahapatra%2E+2014%2E+High%2Dthroughput+sequencing+reveals+inbreeding+depr)
11. Chenqing Hua, Bozitao Zhong, Sitao Luan, Liang Hong, Guy Wolf, Doina Precup, and Shuangjia Zheng. 2024. ReactZyme: A benchmark for enzyme-reaction prediction. Advances in Neural Information Processing Systems, 37:26415–26442. [find](https://scholar.google.com/scholar?q=Chenqing+Hua%2C+Bozitao+Zhong%2C+Sitao+Luan%2C+Liang+Hong%2C+Guy+Wolf%2C+Doina+Precup%2C+and+Shuangjia+Zheng%2E+2024%2E+ReactZyme%3A+A+benchmark+for+enzyme%2Dreaction+prediction%2E+Advances+in+Neural+Information+Processing)
12. Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P Cunningham, and David Blei. 2024. Estimating the hallucination rate of generative AI. Advances in Neural Information Processing Systems, 37:31154– 31201. [find](https://scholar.google.com/scholar?q=Andrew+Jesson%2C+Nicolas+Beltran%2DVelez%2C+Quentin+Chu%2C+Sweta+Karlekar%2C+Jannik+Kossen%2C+Yarin+Gal%2C+John+P+Cunningham%2C+and+David+Blei%2E+2024%2E+Estimating+the+hallucination+rate+of+generative+AI%2E+Advances+in+Ne)
13. John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Michael Figurnov, Olaf Ronneberger, Kathryn Tunyasuvunakool, Russ Bates, Augustin Žídek, Anna Potapenko, and 1 others. 2021. [Highly accurate protein structure prediction with AlphaFold](https://md.research.elamur.ai/free/en/papers/jumper-2021-highly-accurate-protein-structure-prediction/). Nature, 596(7873):583–589.
14. Xun Liang, Hanyu Wang, Yezhaohui Wang, Shichao Song, Jiawei Yang, Simin Niu, Jie Hu, Dan Liu, Shunyu Yao, Feiyu Xiong, and 1 others. 2024. Controllable text generation for [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). arXiv preprint arXiv:2408.12599.
15. Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, and 1 others. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science, 379(6637):1123–1130. [find](https://scholar.google.com/scholar?q=Zeming+Lin%2C+Halil+Akin%2C+Roshan+Rao%2C+Brian+Hie%2C+Zhongkai+Zhu%2C+Wenting+Lu%2C+Nikita+Smetanin%2C+Robert+Verkuil%2C+Ori+Kabeli%2C+Yaniv+Shmueli%2C+and+1+others%2E+2023%2E+Evolutionary%2Dscale+prediction+of+atomic%2Dlevel+p)
16. Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao, and 1 others. 2025. A text-guided protein design framework. Nature Machine Intelligence, pages 1–12. [find](https://scholar.google.com/scholar?q=Shengchao+Liu%2C+Yanjing+Li%2C+Zhuoxinran+Li%2C+Anthony+Gitter%2C+Yutao+Zhu%2C+Jiarui+Lu%2C+Zhao+Xu%2C+Weili+Nie%2C+Arvind+Ramanathan%2C+Chaowei+Xiao%2C+and+1+others%2E+2025%2E+A+text%2Dguided+protein+design+framework%2E+Nature+)
17. Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, and Tat-Seng Chua. 2024. ProtT3: Protein-to-text generation for text-based protein understanding. In ACL. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Zhiyuan+Liu%2C+An+Zhang%2C+Hao+Fei%2C+Enzhi+Zhang%2C+Xiang+Wang%2C+Kenji+Kawaguchi%2C+and+Tat%2DSeng+Chua%2E+2024%2E+ProtT3%3A+Protein%2Dto%2Dtext+generation+for+text%2Dbased+protein+understanding%2E+In+ACL%2E+Association+for+Comp)
18. Łukasz Maziarka, Tomasz Danel, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor, and Stanisław Jastrz˛eb-ski. 2020. Molecule attention transformer. arXiv preprint arXiv:2002.08264. — [arXiv:2002.08264](https://arxiv.org/abs/2002.08264) [find](https://scholar.google.com/scholar?q=%C5%81ukasz+Maziarka%2C+Tomasz+Danel%2C+S%C5%82awomir+Mucha%2C+Krzysztof+Rataj%2C+Jacek+Tabor%2C+and+Stanis%C5%82aw+Jastrz%CB%9Beb%2Dski%2E+2020%2E+Molecule+attention+transformer%2E+arXiv+preprint+arXiv%3A2002%2E08264%2E+%E2%80%94+%5BarXiv%3A2002%2E08264%5D%28ht)
19. Li Mi, Xianjie Dai, Javiera Castillo-Navarro, and Devis Tuia. 2024. Knowledge-aware text-image retrieval for remote sensing images. IEEE Transactions on Geoscience and Remote Sensing. [find](https://scholar.google.com/scholar?q=Li+Mi%2C+Xianjie+Dai%2C+Javiera+Castillo%2DNavarro%2C+and+Devis+Tuia%2E+2024%2E+Knowledge%2Daware+text%2Dimage+retrieval+for+remote+sensing+images%2E+IEEE+Transactions+on+Geoscience+and+Remote+Sensing%2E)
20. Wenkai Wang, Zhenling Peng, and Jianyi Yang. 2022. Single-sequence protein structure prediction using supervised transformer protein language models. Nature Computational Science, 2(12):804–814. [find](https://scholar.google.com/scholar?q=Wenkai+Wang%2C+Zhenling+Peng%2C+and+Jianyi+Yang%2E+2022%2E+Single%2Dsequence+protein+structure+prediction+using+supervised+transformer+protein+language+models%2E+Nature+Computational+Science%2C+2%2812%29%3A804%E2%80%93814%2E)
21. Peter G Mikhael, Itamar Chinn, and Regina Barzilay. 2024. CLIPzyme: Reaction-conditioned virtual screening of enzymes. arXiv preprint arXiv:2402.06748. [find](https://scholar.google.com/scholar?q=Peter+G+Mikhael%2C+Itamar+Chinn%2C+and+Regina+Barzilay%2E+2024%2E+CLIPzyme%3A+Reaction%2Dconditioned+virtual+screening+of+enzymes%2E+arXiv+preprint+arXiv%3A2402%2E06748%2E)
22. Kevin E Wu, Howard Chang, and James Zou. 2024. ProteinCLIP: Enhancing protein language models with natural language. bioRxiv, pages 2024–05. [find](https://scholar.google.com/scholar?q=Kevin+E+Wu%2C+Howard+Chang%2C+and+James+Zou%2E+2024%2E+ProteinCLIP%3A+Enhancing+protein+language+models+with+natural+language%2E+bioRxiv%2C+pages+2024%E2%80%9305%2E)
23. Song Ouyang, Huiyu Cai, Yong Luo, Kehua Su, Lefei Zhang, and Bo Du. 2024. MMSite: A multi-modal framework for the identification of active sites in proteins. Advances in Neural Information Processing Systems, 37:45819–45849. [find](https://scholar.google.com/scholar?q=Song+Ouyang%2C+Huiyu+Cai%2C+Yong+Luo%2C+Kehua+Su%2C+Lefei+Zhang%2C+and+Bo+Du%2E+2024%2E+MMSite%3A+A+multi%2Dmodal+framework+for+the+identification+of+active+sites+in+proteins%2E+Advances+in+Neural+Information+Processing+)
24. Joy A Pai and Ansuman T Satpathy. 2021. High-throughput and single-cell T cell receptor sequencing technologies. Nature Methods, 18(8):881–892. [find](https://scholar.google.com/scholar?q=Joy+A+Pai+and+Ansuman+T+Satpathy%2E+2021%2E+High%2Dthroughput+and+single%2Dcell+T+cell+receptor+sequencing+technologies%2E+Nature+Methods%2C+18%288%29%3A881%E2%80%93892%2E)
25. Qizhi Pei, Wei Zhang, Jinhua Zhu, Kehan Wu, Kaiyuan Gao, Lijun Wu, Yingce Xia, and Rui Yan. 2023. BioT5: Enriching cross-modal integration in biology with chemical knowledge and natural language associations. arXiv preprint arXiv:2310.07276. [find](https://scholar.google.com/scholar?q=Qizhi+Pei%2C+Wei+Zhang%2C+Jinhua+Zhu%2C+Kehan+Wu%2C+Kaiyuan+Gao%2C+Lijun+Wu%2C+Yingce+Xia%2C+and+Rui+Yan%2E+2023%2E+BioT5%3A+Enriching+cross%2Dmodal+integration+in+biology+with+chemical+knowledge+and+natural+language+assoc)
26. Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023. ProtST: Multi-modality learning of protein sequences and biomedical texts. In International Conference on Machine Learning, pages 38749–38767. PMLR. [find](https://scholar.google.com/scholar?q=Minghao+Xu%2C+Xinyu+Yuan%2C+Santiago+Miret%2C+and+Jian+Tang%2E+2023%2E+ProtST%3A+Multi%2Dmodality+learning+of+protein+sequences+and+biomedical+texts%2E+In+International+Conference+on+Machine+Learning%2C+pages+38749%E2%80%93387)
27. Tianhao Yu, Haiyang Cui, Jianan Canal Li, Yunan Luo, Guangde Jiang, and Huimin Zhao. 2023. Enzyme function prediction using contrastive learning. Science, 379(6639):1358–1363. [find](https://scholar.google.com/scholar?q=Tianhao+Yu%2C+Haiyang+Cui%2C+Jianan+Canal+Li%2C+Yunan+Luo%2C+Guangde+Jiang%2C+and+Huimin+Zhao%2E+2023%2E+Enzyme+function+prediction+using+contrastive+learning%2E+Science%2C+379%286639%29%3A1358%E2%80%931363%2E)
28. Wei Zeng, Xiuqin Li, Yunyun Yang, Jian Min, Jian-Wen Huang, Weidong Liu, Du Niu, Xuechun Yang, Xu Han, Lilan Zhang, and 1 others. 2022. Substrate-binding mode of a thermophilic PET hydrolase and engineering the enzyme to enhance the hydrolytic efficacy. ACS Catalysis, 12(5):3033–3040. [find](https://scholar.google.com/scholar?q=Wei+Zeng%2C+Xiuqin+Li%2C+Yunyun+Yang%2C+Jian+Min%2C+Jian%2DWen+Huang%2C+Weidong+Liu%2C+Du+Niu%2C+Xuechun+Yang%2C+Xu+Han%2C+Lilan+Zhang%2C+and+1+others%2E+2022%2E+Substrate%2Dbinding+mode+of+a+thermophilic+PET+hydrolase+and+engin)
29. Omri Puny, Matan Atzmon, Heli Ben-Hamu, Ishan Misra, Aditya Grover, Edward J Smith, and Yaron Lipman. 2021. Frame averaging for invariant and equivariant network design. arXiv preprint arXiv:2110.03336. — [arXiv:2110.03336](https://arxiv.org/abs/2110.03336) [find](https://scholar.google.com/scholar?q=Omri+Puny%2C+Matan+Atzmon%2C+Heli+Ben%2DHamu%2C+Ishan+Misra%2C+Aditya+Grover%2C+Edward+J+Smith%2C+and+Yaron+Lipman%2E+2021%2E+Frame+averaging+for+invariant+and+equivariant+network+design%2E+arXiv+preprint+arXiv%3A2110%2E0333)
30. Hua Zhang, Xiaoqi Yang, Pengliang Chen, Cheng Yang, Bi Chen, Bo Jiang, and Guogen Shan. 2025. CoSEF-DBP: Convolution scope expanding fusion network for identifying DNA-binding proteins through bilingual representations. Expert Systems with Applications, 263:125763. [find](https://scholar.google.com/scholar?q=Hua+Zhang%2C+Xiaoqi+Yang%2C+Pengliang+Chen%2C+Cheng+Yang%2C+Bi+Chen%2C+Bo+Jiang%2C+and+Guogen+Shan%2E+2025%2E+CoSEF%2DDBP%3A+Convolution+scope+expanding+fusion+network+for+identifying+DNA%2Dbinding+proteins+through+bilingu)
31. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International Conference on Machine Learning, pages 8748–8…
32. Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. 2023. Uni-Mol: A universal 3d molecular representation learning framework. In The Eleventh International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Gengmo+Zhou%2C+Zhifeng+Gao%2C+Qiankun+Ding%2C+Hang+Zheng%2C+Hongteng+Xu%2C+Zhewei+Wei%2C+Linfeng+Zhang%2C+and+Guolin+Ke%2E+2023%2E+Uni%2DMol%3A+A+universal+3d+molecular+representation+learning+framework%2E+In+The+Eleventh+In)
33. Jin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, and Fajie Yuan. 2023. SaProt: Protein language modeling with structure-aware vocabulary. bioRxiv, pages 2023–10. [find](https://scholar.google.com/scholar?q=Jin+Su%2C+Chenchen+Han%2C+Yuyang+Zhou%2C+Junjie+Shan%2C+Xibin+Zhou%2C+and+Fajie+Yuan%2E+2023%2E+SaProt%3A+Protein+language+modeling+with+structure%2Daware+vocabulary%2E+bioRxiv%2C+pages+2023%E2%80%9310%2E)
34. Hanjing Zhou, Mingze Yin, Wei Wu, Mingyang Li, Kun Fu, Jintai Chen, Jian Wu, and Zheng Wang. 2025. ProtCLIP: Function-informed protein multi-modal learning. Proceedings of the AAAI Conference on Artificial Intelligence, 39(21):22937–22945. [find](https://scholar.google.com/scholar?q=Hanjing+Zhou%2C+Mingze+Yin%2C+Wei+Wu%2C+Mingyang+Li%2C+Kun+Fu%2C+Jintai+Chen%2C+Jian+Wu%2C+and+Zheng+Wang%2E+2025%2E+ProtCLIP%3A+Function%2Dinformed+protein+multi%2Dmodal+learning%2E+Proceedings+of+the+AAAI+Conference+on+Artif)
35. Jin Su, Xibin Zhou, Xuting Zhang, and Fajie Yuan. 2024. ProTrek: Navigating the protein universe through tri-modal contrastive learning. bioRxiv, pages 2024–05. [find](https://scholar.google.com/scholar?q=Jin+Su%2C+Xibin+Zhou%2C+Xuting+Zhang%2C+and+Fajie+Yuan%2E+2024%2E+ProTrek%3A+Navigating+the+protein+universe+through+tri%2Dmodal+contrastive+learning%2E+bioRxiv%2C+pages+2024%E2%80%9305%2E)
36. Yucheng Suo, Fan Ma, Linchao Zhu, and Yi Yang. 2024. Knowledge-enhanced dual-stream zero-shot composed image retrieval. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 26951–26962. [find](https://scholar.google.com/scholar?q=Yucheng+Suo%2C+Fan+Ma%2C+Linchao+Zhu%2C+and+Yi+Yang%2E+2024%2E+Knowledge%2Denhanced+dual%2Dstream+zero%2Dshot+composed+image+retrieval%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recogni)
37. Prathiksha Rumale Vishwanath, Simran Tiwari, Tejas Ganesh Naik, Sahil Gupta, Dung Ngoc Thai, Wenlong Zhao, SUNJAE KWON, Victor Ardulov, Karim Tarabishy, Andrew McCallum, and 1 others. 2024. Faithfulness hallucination detection in healthcare ai. In Artificial Intelligence and Data Science for Healthc… [find](https://scholar.google.com/scholar?q=Prathiksha+Rumale+Vishwanath%2C+Simran+Tiwari%2C+Tejas+Ganesh+Naik%2C+Sahil+Gupta%2C+Dung+Ngoc+Thai%2C+Wenlong+Zhao%2C+SUNJAE+KWON%2C+Victor+Ardulov%2C+Karim+Tarabishy%2C+Andrew+McCallum%2C+and+1+others%2E+2024%2E+Faithfulne)

*Updated 2 November 2026*