{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T03:47:41Z","timestamp":1779162461868,"version":"3.51.4"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,3]]},"DOI":"10.1109\/bibm62325.2024.10822695","type":"proceedings-article","created":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T20:12:45Z","timestamp":1736539965000},"page":"2382-2389","source":"Crossref","is-referenced-by-count":6,"title":["TourSynbio: A Multi-Modal Large Model and Agent Framework to Bridge Text and Protein Sequences for Protein Engineering"],"prefix":"10.1109","author":[{"given":"Yiqing","family":"Shen","sequence":"first","affiliation":[{"name":"Toursun Synbio,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zan","family":"Chen","sequence":"additional","affiliation":[{"name":"Toursun Synbio,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michail","family":"Mamalakis","sequence":"additional","affiliation":[{"name":"University of Cambridge,Department of Computer Science and Technology,Cambridge,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yungeng","family":"Liu","sequence":"additional","affiliation":[{"name":"Toursun Synbio,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianbin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanzhou","family":"Su","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjun","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pietro","family":"Li\u00f2","sequence":"additional","affiliation":[{"name":"University of Cambridge,Department of Computer Science and Technology,Cambridge,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu Guang","family":"Wang","sequence":"additional","affiliation":[{"name":"Toursun Synbio,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s00253-007-0964-2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41580-024-00718-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/ijms222111741"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.add2187"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-24760-x"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/28.1.45"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-019-3220-8"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1101\/622803","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume-title":"PNAS","author":"Rives","year":"2019"},{"key":"ref9","article-title":"GPT-4 Technical Report","year":"2024","journal-title":"arxiv preprint arXiv:2303.08774"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa977"},{"key":"ref11","article-title":"Prollama: A protein large language model for multi-task protein language processing","author":"Lv","year":"2024"},{"key":"ref12","article-title":"Protchatgpt: Towards understanding proteins with large language models","author":"Wang","year":"2024"},{"key":"ref13","first-page":"38749","article-title":"ProtST: Multi-modality learning of protein sequences and biomedical texts","volume-title":"ICML","volume":"202","author":"Xu","year":"2023"},{"key":"ref14","article-title":"Protein representation learning via knowledge enhanced primary structure reasoning","volume-title":"ICLR","author":"Zhou","year":"2023"},{"key":"ref15","article-title":"Internlm2 technical report","author":"Cai","year":"2024"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1109\/BIBM62325.2024.10821894","article-title":"A fine-tuning dataset and benchmark for large language models for protein understanding","author":"Shen","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1038"},{"key":"ref18","article-title":"Holistic Evaluation of Language Models","volume-title":"Transactions on Machine Learning Research","author":"Liang","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26202"},{"key":"ref20","article-title":"Measuring massive multitask language understanding","volume-title":"ICLR","author":"Hendrycks","year":"2021"},{"key":"ref21","article-title":"Ai agents that matter","author":"Kapoor","year":"2024"},{"key":"ref22","article-title":"Language models of protein sequences at the scale of evolution enable accurate structure prediction","volume-title":"bioRxiv","author":"Lin","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.08.011"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1101\/2023.10.01.560349","article-title":"Saprot: Protein language modeling with structure-aware vocabulary","volume-title":"bioRxiv","author":"Su","year":"2023"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1101\/2021.07.09.450648","article-title":"Language models enable zero-shot prediction of the effects of mutations on protein function","volume-title":"bioRxiv","author":"Meier","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s00249-021-01530-8"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00791-0"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-66538-7_37","article-title":"Proteinengine: Empower llm with domain knowledge for protein engineering","author":"Shen","year":"2024"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1101\/2022.04.10.487779","article-title":"Learning inverse folding from millions of predicted structures","volume-title":"bioRxiv","author":"Hsu","year":"2022"},{"key":"ref30","article-title":"Graph denoising diffusion for inverse protein folding","volume":"36","author":"Yi","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Antifold: Improved antibody structure-based design using inverse folding","author":"H\u00f8ie","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06728-8"},{"key":"ref33","first-page":"2023","article-title":"Atomic context-conditioned protein sequence design using ligandmpnn","author":"Dauparas","year":"2023","journal-title":"Biorxiv"},{"key":"ref34","article-title":"Lagent: InternLM a lightweight open-source framework that allows users to efficiently build large language model(llm)-based agents","year":"2023"},{"key":"ref35","article-title":"The Falcon Series of Open Language Models","author":"Almazrouei","year":"2023"},{"key":"ref36","article-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"ref37","article-title":"Moonshot: Towards controllable video generation and editing with multimodal conditions","author":"Zhang","year":"2024"},{"key":"ref38","article-title":"Mistral 7B","author":"Jiang","year":"2023"},{"key":"ref39","article-title":"Baichuan 2: Open large-scale language models","year":"2023"},{"key":"ref40","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref42","article-title":"Yi: Open Foundation Models by 01.AI","author":"AI","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3390\/plants12091748"},{"issue":"8","key":"ref44","first-page":"3191","article-title":"Fusing catalase to an alkane-producing enzyme maintains enzymatic activity by converting the inhibitory byproduct h2o2 to the cosubstrate o2","volume-title":"Proceedings of the National Academy of Sciences","volume":"110","author":"Andre"}],"event":{"name":"2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","location":"Lisbon, Portugal","start":{"date-parts":[[2024,12,3]]},"end":{"date-parts":[[2024,12,6]]}},"container-title":["2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10821710\/10821711\/10822695.pdf?arnumber=10822695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T09:49:03Z","timestamp":1736588943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10822695\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/bibm62325.2024.10822695","relation":{},"subject":[],"published":{"date-parts":[[2024,12,3]]}}}