A decade in review: use of data analytics within the biopharmaceutical sector

Banner, Matthew; Alosert, Haneen; Spencer, Chris; Cheeks, Matthew; Farid, Suzanne S.; Thomas, Michael R.; Goldrick, Stephen

doi:10.1016/j.coche.2021.100758

Cited by 28 publications

(10 citation statements)

References 40 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning algorithms were shown to be highly effective in depicting the data landscape they are exposed to. , This ability to translate a data landscape description into an understanding of the relationships between observable and response variables is of utmost importance in protein engineering, where the connection between protein function and product creation is crucial . Therefore, it is imperative to develop an interpretable system that can use the information gathered by these models.…”

Section: Resultsmentioning

confidence: 99%

Machine Learning Integrating Protein Structure, Sequence, and Dynamics to Predict the Enzyme Activity of Bovine Enterokinase Variants

Venanzi,

Basciu,

Vargiu

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Despite recent advances in computational protein science, the dynamic behavior of proteins, which directly governs their biological activity, cannot be gleaned from sequence information alone. To overcome this challenge, we propose a framework that integrates the peptide sequence, protein structure, and protein dynamics descriptors into machine learning algorithms to enhance their predictive capabilities and achieve improved prediction of the protein variant function. The resulting machine learning pipeline integrates traditional sequence and structure information with molecular dynamics simulation data to predict the effects of multiple point mutations on the fold improvement of the activity of bovine enterokinase variants. This study highlights how the combination of structural and dynamic data can provide predictive insights into protein functionality and address protein engineering challenges in industrial contexts.

show abstract

Section: Resultsmentioning

confidence: 99%

Machine Learning Integrating Protein Structure, Sequence, and Dynamics to Predict the Enzyme Activity of Bovine Enterokinase Variants

Venanzi,

Basciu,

Vargiu

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…The surge in the application of these techniques is seen due to significantly improved access to high‐performance machines and wider availability of commercial software, making algorithm testing and validation for big datasets easy. A recent study shows that application of ML algorithms has increased by 250% in journal articles and 357% for patents from 2015 to 2020 (Banner et al, 2021). However, with increasing digitalization and automation, a major emerging challenge is that of data integrity (DI) while performing key operations of data storage, transfer, and processing.…”

Section: Bioreactor Controlmentioning

confidence: 99%

“…A recent study shows that application of ML algorithms has increased by 250% in journal articles and 357% for patents from 2015 to 2020 (Banner et al, 2021). However, with increasing digitalization and automation, a major emerging challenge is that of data integrity (DI) while performing key operations of data storage, transfer, and processing.…”

Section: Advancements In Data Analyticsmentioning

confidence: 99%

Advances in bioreactor control for production of biotherapeutic products

Nikita

Mishra

Gupta

et al. 2023

Biotech & Bioengineering

View full text Add to dashboard Cite

Advanced control strategies are well established in chemical, pharmaceutical, and food processing industries. Over the past decade, the application of these strategies is being explored for control of bioreactors for manufacturing of biotherapeutics.Most of the industrial bioreactor control strategies apply classical control techniques, with the control system designed for the facility at hand. However, with the recent progress in sensors, machinery, and industrial internet of things, and advancements in deeper understanding of the biological processes, coupled with the requirement of flexible production, the need to develop a robust and advanced process control system that can ease process intensification has emerged. This has further fuelled the development of advanced monitoring approaches, modeling techniques, process analytical technologies, and soft sensors. It is seen that proper application of these concepts can significantly improve bioreactor process performance, productivity, and reproducibility. This review is on the recent advancements in bioreactor control and its related aspects along with the associated challenges. This study also offers an insight into the future prospects for development of control strategies that can be designed for industrial-scale production of biotherapeutic products.

show abstract

“…It is an integral part of the Process Analytical Technology (PAT) methodology, which aims to improve the understanding, optimization, monitoring, and control of various processes involved in the manufacturing of pharmaceutical products [ 7 ]. Moreover, MVDA proves to be a powerful tool in the modeling and prediction of end products, being an important asset in granulation techniques [ 8 , 9 , 10 , 11 ], various pharmaceutical applications [ 12 , 13 , 14 , 15 ], and the scale-up process (from the laboratory scale to the pilot scale or the pilot scale to the industrial scale) during production development [ 16 , 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

The Effect of Formulation Variables on the Manufacturability of Clopidogrel Tablets via Fluidized Hot-Melt Granulation—From the Lab Scale to the Pilot Scale

Kovács,

Tőkés,

Kelemen

et al. 2024

Pharmaceutics

View full text Add to dashboard Cite

Solid pharmaceutical formulations with class II active pharmaceutical ingredients (APIs) face dissolution challenges due to limited solubility, affecting in vivo behavior. Robust computational tools, via data mining, offer valuable insights into product performance, complementing traditional methods and aiding in scale-up decisions. This study utilizes the design of experiments (DoE) to understand fluidized hot-melt granulation manufacturing technology. Exploratory data analysis (MVDA) highlights similarities and differences in tablet manufacturability and dissolution profiles at both the lab and pilot scales. The study sought to gain insights into the application of multivariate data analysis by identifying variations among batches produced at different manufacturing scales for this technology. DoE and MVDA findings show that the granulation temperature, time, and Macrogol type significantly impact product performance. These factors, by influencing particle size distribution, become key predictors of product quality attributes such as resistance to crushing, disintegration time, and early-stage API dissolution in the profile. Software-aided data mining, with its multivariate and versatile nature, complements the empirical approach, which is reliant on trial and error during product scale-up.

show abstract

A decade in review: use of data analytics within the biopharmaceutical sector

Cited by 28 publications

References 40 publications

Machine Learning Integrating Protein Structure, Sequence, and Dynamics to Predict the Enzyme Activity of Bovine Enterokinase Variants

Machine Learning Integrating Protein Structure, Sequence, and Dynamics to Predict the Enzyme Activity of Bovine Enterokinase Variants

Advances in bioreactor control for production of biotherapeutic products

The Effect of Formulation Variables on the Manufacturability of Clopidogrel Tablets via Fluidized Hot-Melt Granulation—From the Lab Scale to the Pilot Scale

Contact Info

Product

Resources

About