1
|
Behdani AM, Zhao Y, Yao G, Wasalathanthri D, Hodgman E, Borys M, Li G, Khetan A, Wijesinghe D, Leone A. Rapid total sialic acid monitoring during cell culture process using a machine learning model based soft sensor. Biotechnol Prog 2024:e3493. [PMID: 38953182 DOI: 10.1002/btpr.3493] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2024] [Revised: 06/07/2024] [Accepted: 06/24/2024] [Indexed: 07/03/2024]
Abstract
Total sialic acid content (TSA) in biotherapeutic proteins is often a critical quality attribute as it impacts the drug efficacy. Traditional wet chemical assays to quantify TSA in biotherapeutic proteins during cell culture typically takes several hours or longer due to the complexity of the assay which involves isolation of sialic acid from the protein of interest, followed by sample preparation and chromatographic based separation for analysis. Here, we developed a machine learning model-based technology to rapidly predict TSA during cell culture by using typically measured process parameters. The technology features a user interface, where the users only have to upload cell culture process parameters as input variables and TSA values are instantly displayed on a dashboard platform based on the model predictions. In this study, multiple machine learning algorithms were assessed on our dataset, with the Random Forest model being identified as the most promising model. Feature importance analysis from the Random Forest model revealed that attributes like viable cell density (VCD), glutamate, ammonium, phosphate, and basal medium type are critical for predictions. Notably, while the model demonstrated strong predictability by Day 14 of observation, challenges remain in forecasting TSA values at the edges of the calibration range. This research not only emphasizes the transformative power of machine learning and soft sensors in bioprocessing but also introduces a rapid and efficient tool for sialic acid prediction, signaling significant advancements in bioprocessing. Future endeavors may focus on data augmentation to further enhance model precision and exploration of process control capabilities.
Collapse
Affiliation(s)
- Amir M Behdani
- School of Pharmacy, Virginia Commonwealth University, Richmond, Virginia, USA
| | - Yuxiang Zhao
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Grace Yao
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Dhanuka Wasalathanthri
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Eric Hodgman
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Michael Borys
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Gloria Li
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Anurag Khetan
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| | - Dayanjan Wijesinghe
- School of Pharmacy, Virginia Commonwealth University, Richmond, Virginia, USA
| | - Anthony Leone
- Global Product Development and Supply, Bristol-Myers Squibb Company, Devens, Massachusetts, USA
| |
Collapse
|
2
|
Thakur G, Hebbi V, Parida S, Rathore AS. Automation of Dead End Filtration: An Enabler for Continuous Processing of Biotherapeutics. Front Bioeng Biotechnol 2020; 8:758. [PMID: 32719791 PMCID: PMC7350908 DOI: 10.3389/fbioe.2020.00758] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2020] [Accepted: 06/15/2020] [Indexed: 12/17/2022] Open
Abstract
Dead end filtration is a critical unit operation that is used for primary and secondary clarification during manufacturing of both microbial and mammalian cell based biotherapeutics. Dead end filtration is conventionally done in batch mode and requires filter pre-sizing using extensive scouting studies, along with filter over-sizing before deployment to handle potential variability. However, continuous manufacturing processes require consistent use of dead-end filtration over weeks or months, with potential unpredictable variations in feed stream attributes, which is a challenge currently facing the industry. In this work, a dead-end filtration skid is designed for continuous depth filtration, incorporating multiple small-sized filters along with turbidity, and pressure sensors with immediate switching to a fresh filter whenever turbidity or pressure breakthrough above a pre-determined cut-off is detected in real time. The skid has been successfully tested for manufacturing of granulocyte colony stimulating factor from Escherichia coli, human serum albumin from Pichia pastoris, and a monoclonal antibody therapeutic from CHO cells. The proposed skid can be directly applied for any dead-end filtration application with minimal prior scouting studies or sizing calculations for scale-up. It is a useful solution for continuous processing trains where the nature of the feed, such as its turbidity or host cell proteins content, may change over long continuous campaigns, rendering previous sizing calculations inaccurate. The skid also allows significant cost savings by eliminating the sizing safety factor of 1.5-2x which is generally added before filter deployment at manufacturing scale.
Collapse
Affiliation(s)
| | | | | | - Anurag S. Rathore
- Department of Chemical Engineering, Indian Institute of Technology Delhi, New Delhi, India
| |
Collapse
|
3
|
Chopda VR, Holzberg T, Ge X, Folio B, Wong L, Tolosa M, Kostov Y, Tolosa L, Rao G. Real-time dissolved carbon dioxide monitoring II: Surface aeration intensification for efficient CO 2 removal in shake flasks and mini-bioreactors leads to superior growth and recombinant protein yields. Biotechnol Bioeng 2020; 117:992-998. [PMID: 31840800 PMCID: PMC7078866 DOI: 10.1002/bit.27252] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2019] [Revised: 12/10/2019] [Accepted: 12/13/2019] [Indexed: 01/07/2023]
Abstract
Mass transfer is known to play a critical role in bioprocess performance and henceforth monitoring dissolved O2 (DO) and dissolved CO2 (dCO2 ) is of paramount importance. At bioreactor level these parameters can be monitored online and can be controlled by sparging air/oxygen or stirrer speed. However, traditional small-scale systems such as shake flasks lack real time monitoring and also employ only surface aeration with additional diffusion limitations imposed by the culture plug. Here we present implementation of intensifying surface aeration by sparging air in the headspace of the reaction vessel and real-time monitoring of DO and dCO2 in the bioprocesses to evaluate the impact of intensified surface aeration. We observed that sparging air in the headspace allowed us to keep dCO2 at low level, which significantly improved not only biomass growth but also protein yield. We expect that implementing such controlled smart shake flasks can minimize the process development gap which currently exists in shake flask level and bioreactor level results.
Collapse
Affiliation(s)
- Viki R. Chopda
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Timothy Holzberg
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Xudong Ge
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Brandon Folio
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Lynn Wong
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Michael Tolosa
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Yordan Kostov
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Leah Tolosa
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| | - Govind Rao
- Department of Chemical, Biochemical and Environmental EngineeringCenter for Advanced Sensor Technology, University of MarylandBaltimoreMaryland
| |
Collapse
|
4
|
Chopda VR, Holzberg T, Ge X, Folio B, Tolosa M, Kostov Y, Tolosa L, Rao G. Real-time dissolved carbon dioxide monitoring I: Application of a novel in situ sensor for CO 2 monitoring and control. Biotechnol Bioeng 2020; 117:981-991. [PMID: 31840812 PMCID: PMC7079146 DOI: 10.1002/bit.27253] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2019] [Revised: 12/10/2019] [Accepted: 12/13/2019] [Indexed: 12/21/2022]
Abstract
Dissolved carbon dioxide (dCO2 ) is a well-known critical parameter in bioprocesses due to its significant impact on cell metabolism and on product quality attributes. Processes run at small-scale faces many challenges due to limited options for modular sensors for online monitoring and control. Traditional sensors are bulky, costly, and invasive in nature and do not fit in small-scale systems. In this study, we present the implementation of a novel, rate-based technique for real-time monitoring of dCO2 in bioprocesses. A silicone sampling probe that allows the diffusion of CO2 through its wall was inserted inside a shake flask/bioreactor and then flushed with air to remove the CO2 that had diffused into the probe from the culture broth (sensor was calibrated using air as zero-point calibration). The gas inside the probe was then allowed to recirculate through gas-impermeable tubing to a CO2 monitor. We have shown that by measuring the initial diffusion rate of CO2 into the sampling probe we were able to determine the partial pressure of the dCO2 in the culture. This technique can be readily automated, and measurements can be made in minutes. Demonstration experiments conducted with baker's yeast and Yarrowia lipolytica yeast cells in both shake flasks and mini bioreactors showed that it can monitor dCO2 in real-time. Using the proposed sensor, we successfully implemented a dCO2 -based control scheme, which resulted in significant improvement in process performance.
Collapse
Affiliation(s)
- Viki R. Chopda
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Timothy Holzberg
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Xudong Ge
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Brandon Folio
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Michael Tolosa
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Yordan Kostov
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Leah Tolosa
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| | - Govind Rao
- Department of Chemical, Biochemical and Environmental Engineering, Center for Advanced Sensor TechnologyUniversity of MarylandBaltimoreMaryland
| |
Collapse
|
5
|
Pais DAM, Portela RMC, Carrondo MJT, Isidro IA, Alves PM. Enabling PAT in insect cell bioprocesses:
In situ
monitoring of recombinant adeno‐associated virus production by fluorescence spectroscopy. Biotechnol Bioeng 2019; 116:2803-2814. [DOI: 10.1002/bit.27117] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2018] [Revised: 04/22/2019] [Accepted: 07/09/2019] [Indexed: 12/25/2022]
Affiliation(s)
- Daniel A. M. Pais
- iBET, Instituto de Biologia Experimental e Tecnológica Oeiras Portugal
- Instituto de Tecnologia Química e Biológica António XavierUniversidade Nova de Lisboa Oeiras Portugal
| | - Rui M. C. Portela
- iBET, Instituto de Biologia Experimental e Tecnológica Oeiras Portugal
| | | | - Inês A. Isidro
- iBET, Instituto de Biologia Experimental e Tecnológica Oeiras Portugal
- Instituto de Tecnologia Química e Biológica António XavierUniversidade Nova de Lisboa Oeiras Portugal
| | - Paula M. Alves
- iBET, Instituto de Biologia Experimental e Tecnológica Oeiras Portugal
- Instituto de Tecnologia Química e Biológica António XavierUniversidade Nova de Lisboa Oeiras Portugal
| |
Collapse
|