東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Advancing Process Analytical Tools U...

Thite, Nidhi Girish,

Linked to FindBook

Google Book

Amazon

博客來

Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development // Nidhi Girish Thite.
Author:	Thite, Nidhi Girish,
Description:	1 electronic resource (259 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 86-11, Section: A.
Contained By:	Dissertations Abstracts International86-11A.
Subject:	Chemical engineering. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31938693
ISBN:	9798315701880

Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development /
Thite, Nidhi Girish,

Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development /Nidhi Girish Thite. - 1 electronic resource (259 pages)

Source: Dissertations Abstracts International, Volume: 86-11, Section: A.

Manufacturing of biologics and cell and gene therapy (CGT) presents challenges such as limited process understanding, inadequate analytical tools, and quality control issues. These barriers hinder the development and accessibility of life-saving medicines for patients. A critical aspect of ensuring product quality is the detection and characterization of subvisible particles, which can arise from various stresses during manufacturing. The first part of this thesis focuses on mechanistic insights into subvisible particle formation, investigating the interplay between interfacial and hydrodynamic stresses encountered during fill-finish operations and interaction with primary container closures. Flow Imaging Microscopy (FIM) combined with supervised machine learning (ML) was employed to analyze particle morphology and identify dominant degradation pathways. We then shift focus to CGTs where manufacturing is variable and complex, making real-time process monitoring particularly challenging. We apply unsupervised ML (Variational Autoencoders, VAEs) to extract morphological information from FIM images of unstained cells without predefined labels. We track morphological changes in cells during cryopreservation, providing a data-driven approach for assessing cell health and injury mechanisms. We present results from a study on chimeric antigen receptor (CAR)-T cell production using T cells from healthy donors, demonstrating how unsupervised ML enables real-time monitoring of process variability and transduction efficiency.

English

ISBN: 9798315701880Subjects--Topical Terms:

560457
Chemical engineering.
Subjects--Index Terms:

Machine learning

Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development /
LDR:03182nmm a22004453i 4500 001 2435675
005 20251009122908.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798315701880
035 $a (MiAaPQD)AAI31938693
035 $a AAI31938693
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Thite, Nidhi Girish, $e author. $0 (orcid)0009-0006-7224-6271 $3 3826056
245 1 0 $a Advancing Process Analytical Tools Using Machine Learning and Microscopy Images for Biopharmaceutical Process Monitoring and Development / $c Nidhi Girish Thite.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (259 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 86-11, Section: A.
500 $a Advisors: Randolph, Theodore W.; Calderon, Christopher P. Committee members: Schwartz, Daniel K.; Sprenger, Kayla G.; Mallela, Krishna.
502 $b Ph.D. $c University of Colorado at Boulder $d 2025.
520 $a Manufacturing of biologics and cell and gene therapy (CGT) presents challenges such as limited process understanding, inadequate analytical tools, and quality control issues. These barriers hinder the development and accessibility of life-saving medicines for patients. A critical aspect of ensuring product quality is the detection and characterization of subvisible particles, which can arise from various stresses during manufacturing. The first part of this thesis focuses on mechanistic insights into subvisible particle formation, investigating the interplay between interfacial and hydrodynamic stresses encountered during fill-finish operations and interaction with primary container closures. Flow Imaging Microscopy (FIM) combined with supervised machine learning (ML) was employed to analyze particle morphology and identify dominant degradation pathways. We then shift focus to CGTs where manufacturing is variable and complex, making real-time process monitoring particularly challenging. We apply unsupervised ML (Variational Autoencoders, VAEs) to extract morphological information from FIM images of unstained cells without predefined labels. We track morphological changes in cells during cryopreservation, providing a data-driven approach for assessing cell health and injury mechanisms. We present results from a study on chimeric antigen receptor (CAR)-T cell production using T cells from healthy donors, demonstrating how unsupervised ML enables real-time monitoring of process variability and transduction efficiency.
546 $a English
590 $a School code: 0051
650 4 $a Chemical engineering. $3 560457
650 4 $a Cellular biology. $3 3172791
650 4 $a Therapy. $3 3343697
653 $a Machine learning
653 $a Process analytical technology
653 $a Process monitoring
653 $a Protein aggregation
653 $a Gene therapy
690 $a 0542
690 $a 0379
690 $a 0212
710 2 $a University of Colorado at Boulder. $b Chemical and Biological Engineering. $e degree granting institution. $3 3816516
720 1 $a Randolph, Theodore W. $e degree supervisor.
720 1 $a Calderon, Christopher P. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 86-11A.
790 $a 0051
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31938693