Nidhi G. Thite, Michael Yarnell, Terry J. Fry, Matthew Seefeldt, Christopher P. Calderon, Theodore W. Randolph
{"title":"基于无监督机器学习的过程分析工具,用于CAR-T细胞制造过程中的近实时细胞形态分析。","authors":"Nidhi G. Thite, Michael Yarnell, Terry J. Fry, Matthew Seefeldt, Christopher P. Calderon, Theodore W. Randolph","doi":"10.1002/bit.70005","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>Cell therapies like Chimeric Antigen Receptor (CAR)-T cell therapy deliver living cells to patients as active pharmaceutical ingredients. Manufacturing of these cells is complex, often yielding, heterogeneous products and high failure rates. Quality control (QC) assays used in CAR-T cell production primarily provide end-point product testing. Real-time process monitoring would be ideal to reduce failure rates and ensure final product quality. However, current analytical tools often fall short due to the heterogeneity of CAR-T cell products and their sensitivity to process changes. In this study, we showcase unsupervised image-based machine learning as a process analytical tool (PAT) for near real-time process monitoring during the production of CAR-T cells. Flow imaging microscopy (FIM) images of T cells collected from nine healthy donors were recorded during the activation, lentiviral-based transduction (expressing CD19 CAR protein), and expansion stages of CAR-T cell production. These images were used to train a Variational Autoencoder (VAE), allowing quantitative tracking of changes in cell morphologies during the various stages of production of CAR-T cells from each donor. Findings include observation of a new, transient population in T cells transduced to express CAR protein. This population was absent in T cells that were not transduced. The density of the new population was proportional to the transduction efficiency determined by traditional stain-based flow cytometry assays. Together, this study demonstrates the utility of using VAEs as a PAT tool for monitoring patient-to-patient variability and early detection of process deviations/upsets.</p></div>","PeriodicalId":9168,"journal":{"name":"Biotechnology and Bioengineering","volume":"122 9","pages":"2377-2388"},"PeriodicalIF":3.6000,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Unsupervised Machine Learning-Based Process Analytical Tools for Near Real-Time Cell Morphology Analysis During CAR-T Cell Manufacturing\",\"authors\":\"Nidhi G. Thite, Michael Yarnell, Terry J. Fry, Matthew Seefeldt, Christopher P. Calderon, Theodore W. Randolph\",\"doi\":\"10.1002/bit.70005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div>\\n \\n <p>Cell therapies like Chimeric Antigen Receptor (CAR)-T cell therapy deliver living cells to patients as active pharmaceutical ingredients. Manufacturing of these cells is complex, often yielding, heterogeneous products and high failure rates. Quality control (QC) assays used in CAR-T cell production primarily provide end-point product testing. Real-time process monitoring would be ideal to reduce failure rates and ensure final product quality. However, current analytical tools often fall short due to the heterogeneity of CAR-T cell products and their sensitivity to process changes. In this study, we showcase unsupervised image-based machine learning as a process analytical tool (PAT) for near real-time process monitoring during the production of CAR-T cells. Flow imaging microscopy (FIM) images of T cells collected from nine healthy donors were recorded during the activation, lentiviral-based transduction (expressing CD19 CAR protein), and expansion stages of CAR-T cell production. These images were used to train a Variational Autoencoder (VAE), allowing quantitative tracking of changes in cell morphologies during the various stages of production of CAR-T cells from each donor. Findings include observation of a new, transient population in T cells transduced to express CAR protein. This population was absent in T cells that were not transduced. The density of the new population was proportional to the transduction efficiency determined by traditional stain-based flow cytometry assays. Together, this study demonstrates the utility of using VAEs as a PAT tool for monitoring patient-to-patient variability and early detection of process deviations/upsets.</p></div>\",\"PeriodicalId\":9168,\"journal\":{\"name\":\"Biotechnology and Bioengineering\",\"volume\":\"122 9\",\"pages\":\"2377-2388\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2025-06-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Biotechnology and Bioengineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://analyticalsciencejournals.onlinelibrary.wiley.com/doi/10.1002/bit.70005\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"BIOTECHNOLOGY & APPLIED MICROBIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biotechnology and Bioengineering","FirstCategoryId":"5","ListUrlMain":"https://analyticalsciencejournals.onlinelibrary.wiley.com/doi/10.1002/bit.70005","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
Unsupervised Machine Learning-Based Process Analytical Tools for Near Real-Time Cell Morphology Analysis During CAR-T Cell Manufacturing
Cell therapies like Chimeric Antigen Receptor (CAR)-T cell therapy deliver living cells to patients as active pharmaceutical ingredients. Manufacturing of these cells is complex, often yielding, heterogeneous products and high failure rates. Quality control (QC) assays used in CAR-T cell production primarily provide end-point product testing. Real-time process monitoring would be ideal to reduce failure rates and ensure final product quality. However, current analytical tools often fall short due to the heterogeneity of CAR-T cell products and their sensitivity to process changes. In this study, we showcase unsupervised image-based machine learning as a process analytical tool (PAT) for near real-time process monitoring during the production of CAR-T cells. Flow imaging microscopy (FIM) images of T cells collected from nine healthy donors were recorded during the activation, lentiviral-based transduction (expressing CD19 CAR protein), and expansion stages of CAR-T cell production. These images were used to train a Variational Autoencoder (VAE), allowing quantitative tracking of changes in cell morphologies during the various stages of production of CAR-T cells from each donor. Findings include observation of a new, transient population in T cells transduced to express CAR protein. This population was absent in T cells that were not transduced. The density of the new population was proportional to the transduction efficiency determined by traditional stain-based flow cytometry assays. Together, this study demonstrates the utility of using VAEs as a PAT tool for monitoring patient-to-patient variability and early detection of process deviations/upsets.
期刊介绍:
Biotechnology & Bioengineering publishes Perspectives, Articles, Reviews, Mini-Reviews, and Communications to the Editor that embrace all aspects of biotechnology. These include:
-Enzyme systems and their applications, including enzyme reactors, purification, and applied aspects of protein engineering
-Animal-cell biotechnology, including media development
-Applied aspects of cellular physiology, metabolism, and energetics
-Biocatalysis and applied enzymology, including enzyme reactors, protein engineering, and nanobiotechnology
-Biothermodynamics
-Biofuels, including biomass and renewable resource engineering
-Biomaterials, including delivery systems and materials for tissue engineering
-Bioprocess engineering, including kinetics and modeling of biological systems, transport phenomena in bioreactors, bioreactor design, monitoring, and control
-Biosensors and instrumentation
-Computational and systems biology, including bioinformatics and genomic/proteomic studies
-Environmental biotechnology, including biofilms, algal systems, and bioremediation
-Metabolic and cellular engineering
-Plant-cell biotechnology
-Spectroscopic and other analytical techniques for biotechnological applications
-Synthetic biology
-Tissue engineering, stem-cell bioengineering, regenerative medicine, gene therapy and delivery systems
The editors will consider papers for publication based on novelty, their immediate or future impact on biotechnological processes, and their contribution to the advancement of biochemical engineering science. Submission of papers dealing with routine aspects of bioprocessing, description of established equipment, and routine applications of established methodologies (e.g., control strategies, modeling, experimental methods) is discouraged. Theoretical papers will be judged based on the novelty of the approach and their potential impact, or on their novel capability to predict and elucidate experimental observations.