{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:48:25Z","timestamp":1777873705000,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":111,"publisher":"ACM","funder":[{"name":"National Key R&D Program of China","award":["2023YFF0725001"],"award-info":[{"award-number":["2023YFF0725001"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92370204"],"award-info":[{"award-number":["92370204"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2023B1515120057"],"award-info":[{"award-number":["2023B1515120057"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737138","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"3216-3227","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1590-601X","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-447X","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2166-4386","authenticated-orcid":false,"given":"Liyi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6595-9849","authenticated-orcid":false,"given":"Mingze","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8020-9979","authenticated-orcid":false,"given":"Yiheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2305-1017","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6016-6465","authenticated-orcid":false,"given":"Hui","family":"Xiong","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong SAR, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4271-6206","authenticated-orcid":false,"given":"Zheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Cloud Computing, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.28948"},{"key":"e_1_3_2_2_2_1","unstructured":"Josh Abramson Jonas Adler Jack Dunger Richard Evans Tim Green Alexander Pritzel Olaf Ronneberger Lindsay Willmore Andrew J Ballard Joshua Bambrick et al. 2024. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature(2024) 1-3."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Ethan C Alley Grigory Khimulya Surojit Biswas Mohammed AlQuraishi and George M Church. 2019. Unified rational protein engineering with sequence-based deep representation learning. Nature methods(2019) 1315-1322.","DOI":"10.1038\/s41592-019-0598-1"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Christian B Anfinsen and Edgar Haber. 1961. Studies on the reduction and re-formation of protein disulfide bonds. Journal of Biological Chemistry(1961) 1361-1363.","DOI":"10.1016\/S0021-9258(18)64177-8"},{"key":"e_1_3_2_2_6_1","unstructured":"Anthropic. 2024. Claude 3 Haiku: our fastest model yet. https:\/\/www.anthropic.com\/news\/claude-3-haiku"},{"key":"e_1_3_2_2_7_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"crossref","unstructured":"Amos Bairoch and Rolf Apweiler. 1997. The SWISS-PROT protein sequence data bank and its supplement TrEMBL. Nucleic acids research(1997) 31-36.","DOI":"10.1093\/nar\/25.1.31"},{"key":"e_1_3_2_2_9_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65-72."},{"key":"e_1_3_2_2_10_1","volume-title":"Bourne","author":"Berman Helen M.","year":"2000","unstructured":"Helen M. Berman, John Westbrook, Zukang Feng, Gary Gilliland, T. N. Bhat, Helge Weissig, Ilya N. Shindyalov, and Philip E. Bourne. 2000. The Protein Data Bank. Nucleic Acids Research(2000), 235-242."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"Nadav Brandes Dan Ofer Yam Peleg Nadav Rappoport and Michal Linial. 2022. ProteinBERT: a universal deep-learning model of protein sequence and function. Bioinformatics(2022) 2102-2110.","DOI":"10.1093\/bioinformatics\/btac020"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3794"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1189"},{"key":"e_1_3_2_2_14_1","volume-title":"Proc. of ICLR.","author":"Clark Kevin","year":"2020","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V Le, and Christopher D Manning. 2020. ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators. In Proc. of ICLR."},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of NeurIPS(2024)","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2024. Instructblip: Towards general-purpose vision-language models with instruction tuning. Proc. of NeurIPS(2024)."},{"key":"e_1_3_2_2_16_1","first-page":"2978","article-title":"Transformer-XL: Attentive Language Models beyond a Fixed-Length Context","author":"Dai Zihang","year":"2019","unstructured":"Zihang Dai, Zhilin Yang, Yiming Yang, Jaime G Carbonell, Quoc Le, and Ruslan Salakhutdinov. 2019. Transformer-XL: Attentive Language Models beyond a Fixed-Length Context. In Proc. of ACL. 2978-2988.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_2_17_1","unstructured":"DeepSeek-AI Aixin Liu Bei Feng Bing Xue et al. 2025. DeepSeek-V3 Technical Report. arXiv:2412.19437 [cs.CL] https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"e_1_3_2_2_18_1","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proc. of NAACL. 4171-4186.","journal-title":"Proc. of NAACL."},{"key":"e_1_3_2_2_19_1","first-page":"8469","article-title":"PaLM-E: an embodied multimodal language model","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al., 2023. PaLM-E: an embodied multimodal language model. In Proc. of ICML. 8469-8488.","journal-title":"Proc. of ICML."},{"key":"e_1_3_2_2_20_1","volume-title":"ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning","author":"Elnaggar Ahmed","year":"2022","unstructured":"Ahmed Elnaggar, Michael Heinzinger, Christian Dallago, Ghalia Rehawi, Yu Wang, Llion Jones, Tom Gibbs, Tamas Feher, Christoph Angerer, Martin Steinegger, Debsindhu Bhowmik, and Burkhard Rost. 2022. ProtTrans: Toward Understanding the Language of Life Through Self-Supervised Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence(2022), 7112-7127."},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. of ICLR.","author":"Fan Hehe","year":"2023","unstructured":"Hehe Fan, Zhangyang Wang, Yi Yang, and Mohan Kankanhalli. 2023. Continuous-Discrete Convolution for Geometry-Sequence Modeling in Proteins. In Proc. of ICLR."},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of ICLR.","author":"Fang Yin","year":"2024","unstructured":"Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, and Huajun Chen. 2024. Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models. In Proc. of ICLR."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"crossref","unstructured":"Limin Fu Beifang Niu Zhengwei Zhu Sitao Wu and Weizhong Li. 2012. CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics(2012) 3150-3152.","DOI":"10.1093\/bioinformatics\/bts565"},{"key":"e_1_3_2_2_24_1","first-page":"1970","volume-title":"Proc. of NeurIPS(2020)","author":"Fuchs Fabian","year":"2020","unstructured":"Fabian Fuchs, Daniel Worrall, Volker Fischer, and Max Welling. 2020. Se (3)-transformers: 3d roto-translation equivariant attention networks. Proc. of NeurIPS(2020), 1970-1981."},{"key":"e_1_3_2_2_25_1","unstructured":"Xinyang Geng and Hao Liu. 2023. OpenLLaMA: An Open Reproduction of LLaMA. https:\/\/github.com\/openlm-research\/open_llama"},{"key":"e_1_3_2_2_26_1","volume-title":"Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C Taylor, Ian M Fisk, Hera Vlamakis, et al.","author":"Gligorijevi\u0107 Vladimir","year":"2021","unstructured":"Vladimir Gligorijevi\u0107, P Douglas Renfrew, Tomasz Kosciolek, Julia Koehler Leman, Daniel Berenberg, Tommi Vatanen, Chris Chandler, Bryn C Taylor, Ian M Fisk, Hera Vlamakis, et al., 2021. Structure-based protein function prediction using graph convolutional networks. Nature communications(2021), 3168."},{"key":"e_1_3_2_2_27_1","volume-title":"Proc. of ICLR.","author":"Godwin Jonathan","year":"2022","unstructured":"Jonathan Godwin, Michael Schaarschmidt, Alexander L Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veli\u010dkovi\u0107, James Kirkpatrick, and Peter Battaglia. 2022. Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond. In Proc. of ICLR."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"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. ACM Transactions on Computing for Healthcare (HEALTH)(2021) 1-23.","DOI":"10.1145\/3458754"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Han Guo Mingjia Huo and Pengtao Xie. 2023. ProteinChat: Towards Enabling ChatGPT-Like Capabilities on Protein 3D Structures. (2023).","DOI":"10.36227\/techrxiv.23120606"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Harold Hartley. 1951. Origin of the word 'protein'. Nature(1951) 244-244.","DOI":"10.1038\/168244a0"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Thomas Hayes Roshan Rao Halil Akin Nicholas J Sofroniew Deniz Oktay Zeming Lin Robert Verkuil Vincent Q Tran Jonathan Deaton Marius Wiggert et al. 2025. Simulating 500 million years of evolution with a language model. Science(2025) eads0018.","DOI":"10.1101\/2024.07.01.600583"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"crossref","unstructured":"Michael Heinzinger Ahmed Elnaggar Yu Wang Christian Dallago Dmitrii Nechaev Florian Matthes and Burkhard Rost. 2019. Modeling aspects of the language of life through transfer-learning protein sequences. BMC bioinformatics(2019) 1-17.","DOI":"10.1186\/s12859-019-3220-8"},{"key":"e_1_3_2_2_33_1","volume-title":"Proc. of ICLR.","author":"Hermosilla Pedro","year":"2021","unstructured":"Pedro Hermosilla, Marco Sch\u00e4fer, Matej Lang, Gloria Fackelmann, Pere-Pau V\u00e1zquez, Barbora Kozlikova, Michael Krone, Tobias Ritschel, and Timo Ropinski. 2021. Intrinsic-Extrinsic Convolution and Pooling for Learning on 3D Protein Structures. In Proc. of ICLR."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"crossref","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation(1997) 1735-1780.","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Chloe Hsu Robert Verkuil Jason Liu Zeming Lin Brian Hie Tom Sercu Adam Lerer and Alexander Rives. 2022. Learning inverse folding from millions of predicted structures. ICML(2022).","DOI":"10.1101\/2022.04.10.487779"},{"key":"e_1_3_2_2_36_1","volume-title":"Li","author":"Hu Bozhen","year":"2022","unstructured":"Bozhen Hu, Jun Xia, Jiangbin Zheng, Cheng Tan, Yufei Huang, Yongjie Xu, and Stan Z. Li. 2022. Protein Language Models and Structure Prediction: Connection and Progression. arXiv:2211.16742 [q-bio.QM] https:\/\/arxiv.org\/abs\/2211.16742"},{"key":"e_1_3_2_2_37_1","unstructured":"Zhiheng Huang Wei Xu and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. arXiv:1508.01991 [cs.CL] https:\/\/arxiv.org\/abs\/1508.01991"},{"key":"e_1_3_2_2_38_1","volume-title":"Hinton","author":"Jacobs Robert A.","year":"1991","unstructured":"Robert A. Jacobs, Michael I. Jordan, Steven J. Nowlan, and Geoffrey E. Hinton. 1991. Adaptive Mixtures of Local Experts. Neural Computation(1991), 79-87."},{"key":"e_1_3_2_2_39_1","volume-title":"Proc. of ICLR.","author":"Jing Bowen","year":"2021","unstructured":"Bowen Jing, Stephan Eismann, Patricia Suriana, Raphael John Lamarre Townshend, and Ron Dror. 2021. Learning from Protein Structure with Geometric Vector Perceptrons. In Proc. of ICLR."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"crossref","unstructured":"John Jumper Richard Evans Alexander Pritzel Tim Green Michael Figurnov Olaf Ronneberger Kathryn Tunyasuvunakool Russ Bates Augustin \u017d\u00eddek Anna Potapenko et al. 2021. Highly accurate protein structure prediction with AlphaFold. Nature(2021) 583-589.","DOI":"10.1038\/s41586-021-03819-2"},{"key":"e_1_3_2_2_41_1","unstructured":"Jared Kaplan Sam McCandlish Tom Henighan Tom B. Brown Benjamin Chess Rewon Child Scott Gray Alec Radford Jeffrey Wu and Dario Amodei. 2020. Scaling Laws for Neural Language Models. arXiv:2001.08361 [cs.LG] https:\/\/arxiv.org\/abs\/2001.08361"},{"key":"e_1_3_2_2_42_1","volume-title":"Proc. of ICLR.","author":"Komatsuzaki Aran","year":"2023","unstructured":"Aran Komatsuzaki, Joan Puigcerver, James Lee-Thorp, Carlos Riquelme Ruiz, Basil Mustafa, Joshua Ainslie, Yi Tay, Mostafa Dehghani, and Neil Houlsby. 2023. Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints. In Proc. of ICLR."},{"key":"e_1_3_2_2_43_1","unstructured":"Ben Krause Liang Lu Iain Murray and Steve Renals. 2017. Multiplicative LSTM for sequence modelling. arXiv:1609.07959 [cs.NE] https:\/\/arxiv.org\/abs\/1609.07959"},{"key":"e_1_3_2_2_44_1","volume-title":"Proc. of ICLR.","author":"Lan Zhenzhong","year":"2020","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A Lite BERT for Self-supervised Learning of Language Representations. In Proc. of ICLR."},{"key":"e_1_3_2_2_45_1","volume-title":"Proc. of ICLR.","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2020. GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding. In Proc. of ICLR."},{"key":"e_1_3_2_2_46_1","volume-title":"Proc. of ICML. 19730-19742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In Proc. of ICML. 19730-19742."},{"key":"e_1_3_2_2_47_1","first-page":"9694","volume-title":"Proc. of NeurIPS(2021)","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath Selvaraju, Akhilesh Gotmare, Shafiq Joty, Caiming Xiong, and Steven Chu Hong Hoi. 2021. Align before fuse: Vision and language representation learning with momentum distillation. Proc. of NeurIPS(2021), 9694-9705."},{"key":"e_1_3_2_2_48_1","volume-title":"Proc. of ICLR.","author":"Liao Yi-Lun","year":"2022","unstructured":"Yi-Lun Liao and Tess Smidt. 2022. Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs. In Proc. of ICLR."},{"key":"e_1_3_2_2_49_1","volume-title":"Proc. of ICLR.","author":"Liao Yi-Lun","year":"2024","unstructured":"Yi-Lun Liao, Brandon Wood, Abhishek Das*, and Tess Smidt*. 2024. EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations. In Proc. of ICLR."},{"key":"e_1_3_2_2_50_1","unstructured":"Bin Lin Zhenyu Tang Yang Ye Jinfa Huang Junwu Zhang Yatian Pang Peng Jin Munan Ning Jiebo Luo and Li Yuan. 2024. MoE-LLaVA: Mixture of Experts for Large Vision-Language Models. arXiv:2401.15947 [cs.CV] https:\/\/arxiv.org\/abs\/2401.15947"},{"key":"e_1_3_2_2_51_1","first-page":"74","article-title":"ROUGE","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out. 74-81.","journal-title":"A Package for Automatic Evaluation of Summaries. In Text Summarization Branches Out."},{"key":"e_1_3_2_2_52_1","volume-title":"Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, et al.","author":"Lin Zeming","year":"2022","unstructured":"Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Sal Candido, et al., 2022. Language models of protein sequences at the scale of evolution enable accurate structure prediction. bioRxiv(2022)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"Zeming Lin Halil Akin Roshan Rao Brian Hie Zhongkai Zhu Wenting Lu Nikita Smetanin Robert Verkuil Ori Kabeli Yaniv Shmueli et al. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science(2023) 1123-1130.","DOI":"10.1126\/science.ade2574"},{"key":"e_1_3_2_2_54_1","volume-title":"Proc. of NeurIPS(2024)","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024a. Visual instruction tuning. Proc. of NeurIPS(2024)."},{"key":"e_1_3_2_2_55_1","unstructured":"Shengchao Liu Yanjing Li Zhuoxinran Li Anthony Gitter Yutao Zhu Jiarui Lu Zhao Xu Weili Nie Arvind Ramanathan Chaowei Xiao et al. 2025. A text-guided protein design framework. Nature Machine Intelligence(2025) 1-12."},{"key":"e_1_3_2_2_56_1","first-page":"5949","article-title":"ProtT3","author":"Liu Zhiyuan","year":"2024","unstructured":"Zhiyuan Liu, An Zhang, Hao Fei, Enzhi Zhang, Xiang Wang, Kenji Kawaguchi, and Tat-Seng Chua. 2024b. ProtT3: Protein-to-Text Generation for Text-based Protein Understanding. In Proc. of ACL. 5949-5966.","journal-title":"Protein-to-Text Generation for Text-based Protein Understanding. In Proc. of ACL."},{"key":"e_1_3_2_2_57_1","volume-title":"Proc. of ICLR.","author":"Luo Shengjie","year":"2023","unstructured":"Shengjie Luo, Tianlang Chen, Yixian Xu, Shuxin Zheng, Tie-Yan Liu, Liwei Wang, and Di He. 2023a. One Transformer Can Understand Both 2D & 3D Molecular Data. In Proc. of ICLR."},{"key":"e_1_3_2_2_58_1","unstructured":"Yizhen Luo Jiahuan Zhang Siqi Fan Kai Yang Yushuai Wu Mu Qiao and Zaiqing Nie. 2023b. BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine. arXiv:2308.09442 [cs.CE] https:\/\/arxiv.org\/abs\/2308.09442"},{"key":"e_1_3_2_2_59_1","volume-title":"Li Yuan, and Yonghong Tian.","author":"Lv Liuzhenghao","year":"2024","unstructured":"Liuzhenghao Lv, Zongying Lin, Hao Li, Yuyang Liu, Jiaxi Cui, Calvin Yu-Chian Chen, Li Yuan, and Yonghong Tian. 2024. ProLLaMA: A Protein Language Model for Multi-Task Protein Language Processing. arXiv:2402.16445 [cs.CE] https:\/\/arxiv.org\/abs\/2402.16445"},{"key":"e_1_3_2_2_60_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia Leoni Aleman et al. 2024. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_2_61_1","first-page":"27730","volume-title":"Proc. of NeurIPS(2022)","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al., 2022. Training language models to follow instructions with human feedback. Proc. of NeurIPS(2022), 27730-27744."},{"key":"e_1_3_2_2_62_1","first-page":"1216","article-title":"BioT5","author":"Pei Qizhi","year":"2024","unstructured":"Qizhi Pei, Lijun Wu, Kaiyuan Gao, Xiaozhuan Liang, Yin Fang, Jinhua Zhu, Shufang Xie, Tao Qin, and Rui Yan. 2024a. BioT5: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning. In Proc. of ACL Findings. 1216-1240.","journal-title":"In Proc. of ACL Findings."},{"key":"e_1_3_2_2_63_1","unstructured":"Qizhi Pei Lijun Wu Kaiyuan Gao Jinhua Zhu Yue Wang Zun Wang Tao Qin and Rui Yan. 2024b. Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey. arXiv preprint arXiv:2403.01528(2024). arXiv:2403.01528 [cs.CL] https:\/\/arxiv.org\/abs\/2403.01528"},{"key":"e_1_3_2_2_64_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021a. Learning transferable visual models from natural language supervision. In Proc. of ICML. 8748-8763.","journal-title":"Proc. of ICML."},{"key":"e_1_3_2_2_65_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021b. Learning transferable visual models from natural language supervision. In Proc. of ICML. 8748-8763.","journal-title":"Proc. of ICML."},{"key":"e_1_3_2_2_66_1","volume-title":"Alexandra M Schnoes, Tobias Wittkop, Artem Sokolov, Kiley Graim, Christopher Funk, Karin Verspoor, Asa Ben-Hur, et al.","author":"Radivojac Predrag","year":"2013","unstructured":"Predrag Radivojac, Wyatt T Clark, Tal Ronnen Oron, Alexandra M Schnoes, Tobias Wittkop, Artem Sokolov, Kiley Graim, Christopher Funk, Karin Verspoor, Asa Ben-Hur, et al., 2013. A large-scale evaluation of computational protein function prediction. Nature methods(2013), 221-227."},{"key":"e_1_3_2_2_67_1","unstructured":"Colin Raffel Noam Shazeer Adam Roberts Katherine Lee Sharan Narang Michael Matena Yanqi Zhou Wei Li and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research(2020) 1-67."},{"key":"e_1_3_2_2_68_1","first-page":"8844","article-title":"MSA Transformer","author":"Rao Roshan M","year":"2021","unstructured":"Roshan M Rao, Jason Liu, Robert Verkuil, Joshua Meier, John Canny, Pieter Abbeel, Tom Sercu, and Alexander Rives. 2021. MSA Transformer. In Proc. of ICML. 8844-8856.","journal-title":"Proc. of ICML."},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.880083"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"crossref","unstructured":"B. Scholkopf Kah-Kay Sung C.J.C. Burges F. Girosi P. Niyogi T. Poggio and V. Vapnik. 1997. Comparing support vector machines with Gaussian kernels to radial basis function classifiers. IEEE Transactions on Signal Processing(1997) 2758-2765.","DOI":"10.1109\/78.650102"},{"key":"e_1_3_2_2_72_1","unstructured":"Yu Shi Shuxin Zheng Guolin Ke Yifei Shen Jiacheng You Jiyan He Shengjie Luo Chang Liu Di He and Tie-Yan Liu. 2023. Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets. arXiv:2203.04810 [cs.LG] https:\/\/arxiv.org\/abs\/2203.04810"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"crossref","unstructured":"Martin Steinegger Milot Mirdita and Johannes S\u00f6ding. 2019. Protein-level assembly increases protein sequence recovery from metagenomic samples manyfold. Nature methods(2019) 603-606.","DOI":"10.1038\/s41592-019-0437-4"},{"key":"e_1_3_2_2_74_1","doi-asserted-by":"crossref","unstructured":"Martin Steinegger and Johannes S\u00f6ding. 2018. Clustering huge protein sequence sets in linear time. Nature communications(2018) 2542.","DOI":"10.1101\/104034"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"crossref","unstructured":"Nils Strodthoff Patrick Wagner Markus Wenzel and Wojciech Samek. 2020. UDSMProt: universal deep sequence models for protein classification. Bioinformatics(2020) 2401-2409.","DOI":"10.1093\/bioinformatics\/btaa003"},{"key":"e_1_3_2_2_76_1","volume-title":"Proc. of ICLR.","author":"Su Jin","year":"2024","unstructured":"Jin Su, Chenchen Han, Yuyang Zhou, Junjie Shan, Xibin Zhou, and Fajie Yuan. 2024. SaProt: Protein Language Modeling with Structure-aware Vocabulary. In Proc. of ICLR."},{"key":"e_1_3_2_2_77_1","volume-title":"Proc. of NeurIPS(2014)","author":"Sutskever Ilya","year":"2014","unstructured":"Ilya Sutskever, Oriol Vinyals, and Quoc V Le. 2014. Sequence to sequence learning with neural networks. Proc. of NeurIPS(2014)."},{"key":"e_1_3_2_2_78_1","doi-asserted-by":"crossref","unstructured":"Baris E Suzek Yuqi Wang Hongzhan Huang Peter B McGarvey Cathy H Wu and UniProt Consortium. 2015. UniRef clusters: a comprehensive and scalable alternative for improving sequence similarity searches. Bioinformatics(2015) 926-932.","DOI":"10.1093\/bioinformatics\/btu739"},{"key":"e_1_3_2_2_79_1","volume-title":"Galactica: A Large Language Model for Science. arXiv:2211.09085 [cs.CL] https:\/\/arxiv.org\/abs\/2211.09085","author":"Taylor Ross","year":"2022","unstructured":"Ross Taylor, Marcin Kardas, Guillem Cucurull, Thomas Scialom, Anthony Hartshorn, Elvis Saravia, Andrew Poulton, Viktor Kerkez, and Robert Stojnic. 2022. Galactica: A Large Language Model for Science. arXiv:2211.09085 [cs.CL] https:\/\/arxiv.org\/abs\/2211.09085"},{"key":"e_1_3_2_2_80_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2025. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805(2025). arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_2_2_81_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv:2307.09288 [cs.CL] https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_2_2_82_1","doi-asserted-by":"crossref","unstructured":"Mihaly Varadi Stephen Anyango Mandar Deshpande Sreenath Nair Cindy Natassia Galabina Yordanova David Yuan Oana Stroe Gemma Wood Agata Laydon et al. 2022. AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models. Nucleic acids research(2022) D439-D444.","DOI":"10.1093\/nar\/gkab1061"},{"key":"e_1_3_2_2_83_1","volume-title":"Proc. of NeurIPS(2017)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Proc. of NeurIPS(2017)."},{"key":"e_1_3_2_2_84_1","volume-title":"Proc. of NeurIPS.","author":"Wang Weihan","year":"2024","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Song XiXuan, Jiazheng Xu, Keqin Chen, Bin Xu, Juanzi Li, Yuxiao Dong, Ming Ding, and Jie Tang. 2024b. CogVLM: Visual Expert for Pretrained Language Models. In Proc. of NeurIPS."},{"key":"e_1_3_2_2_85_1","volume-title":"Proc. of NeurIPS(2024)","author":"Wang Yusong","year":"2024","unstructured":"Yusong Wang, Shaoning Li, Tong Wang, Bin Shao, Nanning Zheng, and Tie-Yan Liu. 2024a. Geometric Transformer with Interatomic Positional Encoding. Proc. of NeurIPS(2024)."},{"key":"e_1_3_2_2_86_1","volume-title":"Panpan Xu, George Price, Nataliya Golovach, Emmanuel O Salawu, Colby J Wise, Sri Priya Ponnapalli, et al.","author":"Wang Zichen","year":"2022","unstructured":"Zichen Wang, Steven A Combs, Ryan Brand, Miguel Romero Calvo, Panpan Xu, George Price, Nataliya Golovach, Emmanuel O Salawu, Colby J Wise, Sri Priya Ponnapalli, et al., 2022. Lm-gvp: an extensible sequence and structure informed deep learning framework for protein property prediction. Scientific reports(2022), 6832."},{"key":"e_1_3_2_2_87_1","volume-title":"Proc. of ICLR.","author":"Wang Zirui","year":"2021","unstructured":"Zirui Wang, Jiahui Yu, Adams Wei Yu, Zihang Dai, Yulia Tsvetkov, and Yuan Cao. 2021. SimVLM: Simple Visual Language Model Pretraining with Weak Supervision. In Proc. of ICLR."},{"key":"e_1_3_2_2_88_1","first-page":"1114","article-title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","author":"Wang Zeyuan","year":"2024","unstructured":"Zeyuan Wang, Qiang Zhang, Keyan Ding, Ming Qin, Xiang Zhuang, Xiaotong Li, and Huajun Chen. 2024c. InstructProtein: Aligning Human and Protein Language via Knowledge Instruction. In Proc. of ACL. 1114-1136.","journal-title":"Proc. of ACL."},{"key":"e_1_3_2_2_89_1","volume-title":"Lesk","author":"Whisstock James C.","year":"2003","unstructured":"James C. Whisstock and Arthur M. Lesk. 2003. Prediction of protein function from protein sequence and structure. Quarterly Reviews of Biophysics(2003), 307-340."},{"key":"e_1_3_2_2_90_1","volume-title":"Li","author":"Wu Lirong","year":"2022","unstructured":"Lirong Wu, Yufei Huang, Haitao Lin, and Stan Z. Li. 2022. A Survey on Protein Representation Learning: Retrospect and Prospect. arXiv:2301.00813 [cs.LG] https:\/\/arxiv.org\/abs\/2301.00813"},{"key":"e_1_3_2_2_91_1","doi-asserted-by":"crossref","unstructured":"Wei Wu Zhuoshi Pan Chao Wang Liyi Chen Yunchu Bai Tianfu Wang Kun Fu Zheng Wang and Hui Xiong. 2025. TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection. arXiv:2411.02886 [cs.CL] https:\/\/arxiv.org\/abs\/2411.02886","DOI":"10.18653\/v1\/2025.emnlp-main.1079"},{"key":"e_1_3_2_2_92_1","first-page":"1242","article-title":"AFDGCF","author":"Wu Wei","year":"2024","unstructured":"Wei Wu, Chao Wang, Dazhong Shen, Chuan Qin, Liyi Chen, and Hui Xiong. 2024. AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations. In Proc. of SIGIR. 1242-1252.","journal-title":"Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations. In Proc. of SIGIR."},{"key":"e_1_3_2_2_93_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_2_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599510"},{"key":"e_1_3_2_2_95_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671992"},{"key":"e_1_3_2_2_96_1","first-page":"38749","article-title":"Protst: Multi-modality learning of protein sequences and biomedical texts","author":"Xu Minghao","year":"2023","unstructured":"Minghao Xu, Xinyu Yuan, Santiago Miret, and Jian Tang. 2023. Protst: Multi-modality learning of protein sequences and biomedical texts. In Proc. of ICML. 38749-38767.","journal-title":"Proc. of ICML."},{"key":"e_1_3_2_2_97_1","volume-title":"Proc. of NeurIPS(2019)","author":"Yang Zhilin","year":"2019","unstructured":"Zhilin Yang, Zihang Dai, Yiming Yang, Jaime Carbonell, Russ R Salakhutdinov, and Quoc V Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. Proc. of NeurIPS(2019)."},{"key":"e_1_3_2_2_98_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2024. mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality. arXiv preprint arXiv:2304.14178(2024). arXiv:2304.14178 [cs.CL] https:\/\/arxiv.org\/abs\/2304.14178"},{"key":"e_1_3_2_2_99_1","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review(2024) nwae403."},{"key":"e_1_3_2_2_100_1","doi-asserted-by":"crossref","unstructured":"Yong Yu Xiaosheng Si Changhua Hu and Jianxun Zhang. 2019. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation(2019) 1235-1270.","DOI":"10.1162\/neco_a_01199"},{"key":"e_1_3_2_2_101_1","volume-title":"Proc. of ICLR.","author":"Zaidi Sheheryar","year":"2023","unstructured":"Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter Battaglia, Razvan Pascanu, and Jonathan Godwin. 2023. Pre-training via Denoising for Molecular Property Prediction. In Proc. of ICLR."},{"key":"e_1_3_2_2_102_1","volume-title":"Proc. of ICLR.","author":"Zhang Ningyu","year":"2022","unstructured":"Ningyu Zhang, Zhen Bi, Xiaozhuan Liang, Siyuan Cheng, Haosen Hong, Shumin Deng, Qiang Zhang, Jiazhang Lian, and Huajun Chen. 2022. OntoProtein: Protein Pretraining With Gene Ontology Embedding. In Proc. of ICLR."},{"key":"e_1_3_2_2_103_1","unstructured":"Peiyuan Zhang Guangtao Zeng Tianduo Wang and Wei Lu. 2024. TinyLlama: An Open-Source Small Language Model. arXiv:2401.02385 [cs.CL] https:\/\/arxiv.org\/abs\/2401.02385"},{"key":"e_1_3_2_2_104_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714676"},{"key":"e_1_3_2_2_105_1","volume-title":"Proc. of ICLR.","author":"Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In Proc. of ICLR."},{"key":"e_1_3_2_2_106_1","unstructured":"Zuobai Zhang Chuanrui Wang Minghao Xu Vijil Chenthamarakshan Aur\u00e9lie Lozano Payel Das and Jian Tang. 2023a. A Systematic Study of Joint Representation Learning on Protein Sequences and Structures. arXiv:2303.06275 [q-bio.QM] https:\/\/arxiv.org\/abs\/2303.06275"},{"key":"e_1_3_2_2_107_1","volume-title":"Proc. of ICLR.","author":"Zhang Zuobai","year":"2023","unstructured":"Zuobai Zhang, Minghao Xu, Arian Rokkum Jamasb, Vijil Chenthamarakshan, Aurelie Lozano, Payel Das, and Jian Tang. 2023b. Protein Representation Learning by Geometric Structure Pretraining. In Proc. of ICLR."},{"key":"e_1_3_2_2_108_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li et al. 2025. A Survey of Large Language Models. arXiv:2303.18223 [cs.CL] https:\/\/arxiv.org\/abs\/2303.18223"},{"key":"e_1_3_2_2_109_1","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4"},{"key":"e_1_3_2_2_110_1","volume-title":"Proc. of ICLR.","author":"Zhu Deyao","year":"2024","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2024. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. In Proc. of ICLR."},{"key":"e_1_3_2_2_111_1","unstructured":"Barret Zoph Irwan Bello Sameer Kumar Nan Du Yanping Huang Jeff Dean Noam Shazeer and William Fedus. 2022. ST-MoE: Designing Stable and Transferable Sparse Expert Models. arXiv:2202.08906 [cs.CL] https:\/\/arxiv.org\/abs\/2202.08906"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:14:00Z","timestamp":1777572840000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":111,"alternative-id":["10.1145\/3711896.3737138","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737138","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}