{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T15:20:33Z","timestamp":1773415233420,"version":"3.50.1"},"posted":{"date-parts":[[2026,3,11]]},"group-title":"Bioinformatics","reference-count":21,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T00:00:00Z","timestamp":1773187200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Allergy and Infectious Diseases (NIAID), NIH, Department of Health and Human Services","award":["75N93022C00036"],"award-info":[{"award-number":["75N93022C00036"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Recent advances in Large Language Models (LLMs) present new opportunities for automating critical bottlenecks in scientific workflows such as literature reviews or protocol design. One such bottleneck is the purification of recombinant proteins, a vital aspect of biomedical research that frequently fails. To improve success rates, researchers must manually define optimal large-scale purification conditions and establish robust rescue protocols for proteins with low stability or solubility \u2013 a time-intensive process.<\/jats:p>\n                <jats:p>To address this gap, we introduce a multi-agent LLM system that automates the creation and optimization of protein purification protocols to facilitate the production of high-concentration, high-purity protein samples. Our application streamlines the labor-intensive manual process of sequence similarity searches, literature reviews, and protocol comparison. Operating in a tool-like constrained workflow, the system identifies analogous proteins, leverages specialized LLM agents to extract successful purification methodologies from primary source literature, and cross-references them against failed protocols to generate optimization recommendations.<\/jats:p>\n                <jats:p>Evaluation on a select number of targets demonstrated high accuracy in protocol extraction and the generation of scientifically sound, expert-validated optimization recommendations. While this system reduces complex analysis time from hours to minutes, we identify the lack of programmatic open access to literature, specifically primary citations in the Protein Data Bank, as a fundamental limitation to LLM agent-based scientific workflows. Ultimately, this system demonstrates the feasibility of using LLM agents to streamline wet-lab workflows while preserving methodological transparency and reproducibility.<\/jats:p>","DOI":"10.64898\/2026.03.03.709341","type":"posted-content","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:35:22Z","timestamp":1773250522000},"source":"Crossref","is-referenced-by-count":0,"title":["Automated extraction and optimization of protein purification protocols using multi-agent large language models"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7660-7493","authenticated-orcid":false,"given":"Jeffery","family":"Ye","sequence":"first","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1205-7920","authenticated-orcid":false,"given":"Amy","family":"DeRocher","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3819-9003","authenticated-orcid":false,"given":"Monique","family":"Khim","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5853-7498","authenticated-orcid":false,"given":"Sandhya","family":"Subramanian","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisabeth","family":"Cron","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0056-0513","authenticated-orcid":false,"given":"Peter J.","family":"Myler","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Department of Global Health, University of Washington, 1410 North East Campus Parkway, Seattle, WA 98195 USA"},{"name":"Department of Pediatrics, University of Washington, 1410 North East Campus Parkway, Seattle, WA 98195 USA"},{"name":"Department of Biomedical Informatics and Medical Education, University of Washington, 1410 North East Campus Parkway, Seattle, WA 98195 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6873-3401","authenticated-orcid":false,"given":"Isabelle Q.","family":"Phan","sequence":"additional","affiliation":[{"name":"Seattle Structural Genomics Center for Infectious Disease, 1916 Boren Avenue, Seattle, WA 98101 USA"},{"name":"Center for Global Infectious Disease Research, Seattle Children\u2019s Research Institute, 1916 Boren Avenue, Seattle, WA 98101 USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2026031304400831000_2026.03.03.709341v1.1","doi-asserted-by":"crossref","unstructured":"Bender, E. M. , Gebru, T. , McMillan-Major, A. , & Shmitchell, S. (2021). On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? . Association for Computing Machinery.","DOI":"10.1145\/3442188.3445922"},{"key":"2026031304400831000_2026.03.03.709341v1.2","doi-asserted-by":"crossref","unstructured":"Bianchini, S. , M\u00fcller, M. , & Pelletier, P. (2025). Drivers and barriers of AI adoption and use in scientific research. Technological Forecasting and Social Change.","DOI":"10.1016\/j.techfore.2025.124303"},{"key":"2026031304400831000_2026.03.03.709341v1.3","doi-asserted-by":"crossref","unstructured":"Bryan, C. M. , Bhandari, J. , Napuli, A. J. , Leibly, D. J. , Choi, R. , Kelley, A. , \u2026 Stewart, L. J. (2011). High-throughput protein production and purification at the Seattle Structural Genomics Center for Infectious Disease. Acta crystallographica.","DOI":"10.1107\/S1744309111018367"},{"key":"2026031304400831000_2026.03.03.709341v1.4","doi-asserted-by":"crossref","unstructured":"Camacho, C. , Coulouris, G. , Avagyan, V. , & Ma, N. (2009). BLAST+: architecture and applications. BMC Bioinformatics.","DOI":"10.1186\/1471-2105-10-421"},{"key":"2026031304400831000_2026.03.03.709341v1.5","unstructured":"Comanici, G. , Bieber, E. , Schaekermann, M. , Pasupat, I. , Sachdeva, N. , Dhillon, I. , \u2026 I. (2025). Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. arXiv (Preprint)."},{"key":"2026031304400831000_2026.03.03.709341v1.6","doi-asserted-by":"crossref","unstructured":"Giesriegl, F. , Mrazek, C. , & Cadamuro, J. (2025). How laboratory medicine will change in the near future: integrating artificial intelligence, automation, and human expertise in the era of Industry 5.0. Journal of Laboratory and Precision Medicine.","DOI":"10.21037\/jlpm-25-6"},{"key":"2026031304400831000_2026.03.03.709341v1.7","doi-asserted-by":"crossref","unstructured":"Gileadi, O. , Knapp, S. , Lee, W. H. , Marsden, B. D. , M\u00fcller, S. , Niesen, F. H. , \u2026 Sundstr\u00f6m, M. (2007). The scientific impact of the Structural Genomics Consortium: a protein family and ligand-centered approach to medically-relevant human proteins. Journal of Structural and Functional Genomics.","DOI":"10.1007\/s10969-007-9027-2"},{"key":"2026031304400831000_2026.03.03.709341v1.8","doi-asserted-by":"crossref","unstructured":"Huang, K. , Zhang, S. , Wang, H. , Qu, Y. , Lu, Y. , Roohani, Y. , \u2026 Mi. (2025). Biomni: A General-Purpose Biomedical AI Agent. Bioarxiv (Preprint).","DOI":"10.1101\/2025.05.30.656746"},{"key":"2026031304400831000_2026.03.03.709341v1.9","doi-asserted-by":"crossref","unstructured":"Jumper, J. , Evans, R. , Pritzel, A. , Green, T. , Figurnov, M. , Ronneberger, O. , \u2026 Bernardino. (2021). Highly accurate protein structure prediction with AlphaFold. Nature .","DOI":"10.1038\/s41586-021-03819-2"},{"key":"2026031304400831000_2026.03.03.709341v1.10","doi-asserted-by":"crossref","unstructured":"Kang, Y.-J. , Lee, H. , Yi, J. P. , Kim, H. , Yoon, C. I. , Baek, J. M. , \u2026 Oh, S. J. (2025). Large Language Model Versus Manual Review for Clinical Data Curation in Breast Cancer: Retrospective Comparative Study. JMIR Med Inform.","DOI":"10.2196\/73605"},{"key":"2026031304400831000_2026.03.03.709341v1.11","doi-asserted-by":"crossref","unstructured":"Klang, E. , Omar, M. , Raut, G. , Agbareia, R. , Timsina, P. , Freeman, R. , \u2026 Nadkarni, G. N. (2025). Orchestrated multi agents sustain accuracy under clinical-scale workloads compared to a single agent. medRxiv (Preprint).","DOI":"10.1101\/2025.08.22.25334049"},{"key":"2026031304400831000_2026.03.03.709341v1.12","doi-asserted-by":"crossref","unstructured":"Li, M. , Sun, J. , & Tan, X. (2024). Evaluating the effectiveness of large language models in abstract screening: a comparative analysis. Springer Nature Link.","DOI":"10.21203\/rs.3.rs-3788921\/v1"},{"key":"2026031304400831000_2026.03.03.709341v1.13","unstructured":"Lin, X. , Ma, S. , Shan, J. , Zhang, X. , Hu, S. X. , Guo, T. , \u2026 Yu, K. (2024). BioKGBench: A Knowledge Graph Checking Benchmark of AI Agent for Biomedical Science. arXiv (Preprint)."},{"key":"2026031304400831000_2026.03.03.709341v1.14","doi-asserted-by":"crossref","unstructured":"Luo, Y. , Shi, L. , Li, Y. , Zhuang, A. , Gong, Y. , Liu, L. , & Lin, C. (2024). From Intention to Implementation: Automating Biomedical Research via LLMs. Science China (Information Sciences).","DOI":"10.1007\/s11432-024-4485-0"},{"key":"2026031304400831000_2026.03.03.709341v1.15","doi-asserted-by":"crossref","unstructured":"Raynal, B. , Lenormand, P. , Baron, B. , Hoos, S. , & England, P. (2014). Quality assessment and optimization of purified protein samples: why and how? Microb Cell Fact.","DOI":"10.1186\/s12934-014-0180-6"},{"key":"2026031304400831000_2026.03.03.709341v1.16","doi-asserted-by":"crossref","unstructured":"Rosano, G. L. , & Ceccarelli, E. A. (2014). Recombinant protein expression in Escherichia coli: advances and challenges. Frontiers in Microbiology.","DOI":"10.3389\/fmicb.2014.00172"},{"key":"2026031304400831000_2026.03.03.709341v1.17","doi-asserted-by":"crossref","unstructured":"Scherbakov, D. , Hubig, N. , Jansari, V. , Bakumenko, A. , & Lenert, L. A. (2025). The emergence of large language models as tools in literature reviews: a large language model-assisted systematic review. Journal of the American Medical Informatics Association.","DOI":"10.1093\/jamia\/ocaf063"},{"key":"2026031304400831000_2026.03.03.709341v1.18","doi-asserted-by":"crossref","unstructured":"Soria, P. S. , McGary, K. L. , & Rokas, A. (2014). Functional Divergence for Every Paralog . Molecular Biology and Evolution.","DOI":"10.1093\/molbev\/msu050"},{"key":"2026031304400831000_2026.03.03.709341v1.19","doi-asserted-by":"crossref","unstructured":"Stacy, R. , Begley, D. W. , Phan, I. , Staker, B. L. , Voorhis, W. C. , Varani, G. , \u2026 Myler, P. J. (2011). Structural genomics of infectious disease drug targets: the SSGCID. Structural Biology Communications.","DOI":"10.1107\/S1744309111029204"},{"key":"2026031304400831000_2026.03.03.709341v1.20","unstructured":"Su, X. , Wang, Y. , Gao, S. , Liu, X. , Giunchiglia, V. , Clevert, D.-A. , & Zitnik, M. (2024). KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA. Arxiv (Preprint)."},{"key":"2026031304400831000_2026.03.03.709341v1.21","unstructured":"The UniProt Consortium . (2024). UniProt: the Universal Protein Knowledgebase in 2025. Nucleic Acids Research."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.03.03.709341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T11:40:18Z","timestamp":1773402018000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.03.03.709341"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,11]]},"references-count":21,"URL":"https:\/\/doi.org\/10.64898\/2026.03.03.709341","relation":{},"subject":[],"published":{"date-parts":[[2026,3,11]]},"subtype":"preprint"}}