{"title":"使用第一个工业智能实验室框架,通过深度学习驱动的机器人实验创新细胞培养过程开发。","authors":"Shuting Xu, Yanting Huang, Xin Shen, Rongjia Mao, Yiming Song, Wanying Ye, Lijun Wang, Xiaoxiao Tong, Yun Cao, Ruiqiang Sun, Hang Zhou, Weichang Zhou","doi":"10.1002/btpr.70051","DOIUrl":null,"url":null,"abstract":"<p><p>Traditional biologics process development, including antibody and recombinant protein production, typically relies on labor-intensive, iterative cell culture optimization to determine optimal process parameters. To address this inefficiency, we introduced the Industrial Smart Lab Framework for Cell Culture (ISLFCC), an autonomous laboratory that combines deep learning and robotic experimentation to enhance cell culture processes. In this system, robotic arms sample various bioreactors for analysis, and the IoT system transmits these analysis results to decoder-only transformer deep learning models. Based on these analysis results, these models predict future cell states and recommend optimal actions, which are then executed by automation devices through the IoT system, such as adjusting nutrient feeds and temperature shifts. In a comparative case study, our AI-driven process development for three different cell clones resulted in an average titer increase of 26.8% and maintained lactate levels below 1 g/L without rebound in the late phase within just a single batch, surpassing traditional three-stage empirical process development methods. Moreover, our approach has greatly automated cell culture to ensure enhanced reproducibility, data accuracy, adaptability to various cell lines, and seamless scalability across production scales, marking the first implementation of high-throughput automated cell culture in 3 and 15 L bioreactors. By merging AI with robotic execution, ISLFCC provides a transformative framework that accelerates biologics development, representing a paradigm shift towards autonomous, data-driven biomanufacturing.</p>","PeriodicalId":8856,"journal":{"name":"Biotechnology Progress","volume":" ","pages":"e70051"},"PeriodicalIF":2.5000,"publicationDate":"2025-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Innovating cell culture process development with deep learning-powered robotic experimentation using the first Industrial Smart Lab Framework.\",\"authors\":\"Shuting Xu, Yanting Huang, Xin Shen, Rongjia Mao, Yiming Song, Wanying Ye, Lijun Wang, Xiaoxiao Tong, Yun Cao, Ruiqiang Sun, Hang Zhou, Weichang Zhou\",\"doi\":\"10.1002/btpr.70051\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Traditional biologics process development, including antibody and recombinant protein production, typically relies on labor-intensive, iterative cell culture optimization to determine optimal process parameters. To address this inefficiency, we introduced the Industrial Smart Lab Framework for Cell Culture (ISLFCC), an autonomous laboratory that combines deep learning and robotic experimentation to enhance cell culture processes. In this system, robotic arms sample various bioreactors for analysis, and the IoT system transmits these analysis results to decoder-only transformer deep learning models. Based on these analysis results, these models predict future cell states and recommend optimal actions, which are then executed by automation devices through the IoT system, such as adjusting nutrient feeds and temperature shifts. In a comparative case study, our AI-driven process development for three different cell clones resulted in an average titer increase of 26.8% and maintained lactate levels below 1 g/L without rebound in the late phase within just a single batch, surpassing traditional three-stage empirical process development methods. Moreover, our approach has greatly automated cell culture to ensure enhanced reproducibility, data accuracy, adaptability to various cell lines, and seamless scalability across production scales, marking the first implementation of high-throughput automated cell culture in 3 and 15 L bioreactors. By merging AI with robotic execution, ISLFCC provides a transformative framework that accelerates biologics development, representing a paradigm shift towards autonomous, data-driven biomanufacturing.</p>\",\"PeriodicalId\":8856,\"journal\":{\"name\":\"Biotechnology Progress\",\"volume\":\" \",\"pages\":\"e70051\"},\"PeriodicalIF\":2.5000,\"publicationDate\":\"2025-06-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biotechnology Progress\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1002/btpr.70051\",\"RegionNum\":3,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biotechnology Progress","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1002/btpr.70051","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
Innovating cell culture process development with deep learning-powered robotic experimentation using the first Industrial Smart Lab Framework.
Traditional biologics process development, including antibody and recombinant protein production, typically relies on labor-intensive, iterative cell culture optimization to determine optimal process parameters. To address this inefficiency, we introduced the Industrial Smart Lab Framework for Cell Culture (ISLFCC), an autonomous laboratory that combines deep learning and robotic experimentation to enhance cell culture processes. In this system, robotic arms sample various bioreactors for analysis, and the IoT system transmits these analysis results to decoder-only transformer deep learning models. Based on these analysis results, these models predict future cell states and recommend optimal actions, which are then executed by automation devices through the IoT system, such as adjusting nutrient feeds and temperature shifts. In a comparative case study, our AI-driven process development for three different cell clones resulted in an average titer increase of 26.8% and maintained lactate levels below 1 g/L without rebound in the late phase within just a single batch, surpassing traditional three-stage empirical process development methods. Moreover, our approach has greatly automated cell culture to ensure enhanced reproducibility, data accuracy, adaptability to various cell lines, and seamless scalability across production scales, marking the first implementation of high-throughput automated cell culture in 3 and 15 L bioreactors. By merging AI with robotic execution, ISLFCC provides a transformative framework that accelerates biologics development, representing a paradigm shift towards autonomous, data-driven biomanufacturing.
期刊介绍:
Biotechnology Progress , an official, bimonthly publication of the American Institute of Chemical Engineers and its technological community, the Society for Biological Engineering, features peer-reviewed research articles, reviews, and descriptions of emerging techniques for the development and design of new processes, products, and devices for the biotechnology, biopharmaceutical and bioprocess industries.
Widespread interest includes application of biological and engineering principles in fields such as applied cellular physiology and metabolic engineering, biocatalysis and bioreactor design, bioseparations and downstream processing, cell culture and tissue engineering, biosensors and process control, bioinformatics and systems biology, biomaterials and artificial organs, stem cell biology and genetics, and plant biology and food science. Manuscripts concerning the design of related processes, products, or devices are also encouraged. Four types of manuscripts are printed in the Journal: Research Papers, Topical or Review Papers, Letters to the Editor, and R & D Notes.