A roadmap to AI-driven in silico process development: bioprocessing 4.0 in practice

Stosch, Moritz von; Portela, Rui M C; Varsakelis, Christos

doi:10.1016/j.coche.2021.100692

Cited by 20 publications

(15 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

Section: Digitalisierung In Der Bioprozesstechnik/biotechnologieunclassified

“…Es bleibt jedoch ein erhebliches Potenzial und eine riesige Datenmenge mit wertvollen Informationen ungenutzt, sollte die biochemische Industrie mit der sich schnell entwickelnden digitalen Infrastruktur nicht Schritt halten. [23,54,74] In der Literatur sind schon einige Ideen, Konzepte und erste Umsetzungen von Digitalisierungen fu ¨r verschiedene Bioprozesse vorhanden, auch wenn diese bislang noch nicht immer auf einer einheitlichen oder allgemeingu ¨ltigen Lo ¨sung basieren. So wurde ein DZ fu ¨r die kontinuierliche mRNA-Produktion [75] sowie zumindest erste Modelle und Voraussetzungen fu ¨r die Nutzung eines DZ in der Antiko ¨rperproduktion [76][77][78][79][80][81][82] entwickelt.…”

Section: Einfu ¨Hrungunclassified

See 1 more Smart Citation

Digitale Zwillinge in der Bioprozesstechnik – Chancen und Möglichkeiten

Richter

Lange

Scheper

et al. 2022

Chemie Ingenieur Technik

View full text Add to dashboard Cite

Herrn Prof. Dr. Christian Wandrey zum 80. Geburtstag gewidmet Die Digitalisierung von Prozessen ist eines der aktuell dominierenden Themen und Missionen sowohl in der industriellen Produktion als auch der wissenschaftlichen Forschung. In der Biotechnologie haben diese Bemu ¨hungen ein enormes Potenzial, um existierende Bioprozesse zu optimieren oder neue Bioprozesse fu ¨r zuku ¨nftige Herausforderungen zu entwickeln. In diesem U ¨bersichtsbeitrag wird der aktuelle Stand der Digitalisierung in der Bioprozesstechnik beleuchtet, die Begriffe digitaler Zwilling und digitaler Schatten charakterisiert sowie ein Ausblick auf zuku ¨nftige Lab 4.0-Konzepte gegeben.

show abstract

Section: Digitalisierung In Der Bioprozesstechnik/biotechnologieunclassified

Section: Einfu ¨Hrungunclassified

Digitale Zwillinge in der Bioprozesstechnik – Chancen und Möglichkeiten

Richter

Lange

Scheper

et al. 2022

Chemie Ingenieur Technik

View full text Add to dashboard Cite

show abstract

“…Indeed, based on 5-years actual performance data, a modeling tool 6 developed to estimate the value of earlier approval and launch for pharmaceutical products suggests that a reduction of 3 months in the timeline to market entry for a product with (i) "average" market uptake, (ii) peak sales of $500 million in approximately 6 years and (iii) an eight-year patent life, would increase the product's net present value (NPV) by about 5%, equivalent to roughly $74 million. 5,6 For a product with the most "rapid" market uptake, a reduction of 6 months is equivalent to circa $178 million in NPV improvement. 6 Given the forecasted average sales for the top 10 selling mAb drugs in 2021 was circa $7.4 billion and with total global sales of mAbs projected to reach more than $200 billion in 2024, 7 the commercial benefit from expedited development in this field is substantial.…”

Section: Introductionmentioning

confidence: 99%

Accelerated CMC workflows to enable speed to clinic in the COVID‐19 era: A multi‐company view from the biopharmaceutical industry

Higgins

Abu‐Absi

Gontarz

et al. 2023

Biotechnology Progress

View full text Add to dashboard Cite

The COVID‐19 pandemic has placed unprecedented pressure on biopharmaceutical companies to develop efficacious preventative and therapeutic treatments, which is unlikely to abate in the coming years. The importance of fast progress to clinical evaluation for treatments, which tackle unmet medical needs puts strain on traditional product development timelines, which can take years from start to finish. Although previous work has been successful in reducing phase 1 timelines for recombinant antibodies, through utilization of the latest technological advances and acceptance of greater business risk or costs, substantially faster development is likely achievable without increased risk to patients during initial clinical evaluation. To optimize lessons learned from the pandemic and maximize multi‐stakeholder (i.e., patients, clinicians, companies, regulatory agencies) benefit, we conducted an industry wide benchmarking survey in September/October 2021. The aims of this survey were to: (i) benchmark current technical practices of key process and product development activities related to manufacturing of therapeutic proteins, (ii) understand the impact of changes implemented in COVID‐19 accelerated Ab programs, and whether any such changes can be retained as part of sustainable long‐term business practices and (iii) understand whether any accelerative action(s) taken have (negatively) impacted the wider development process. This article provides an in‐depth analysis of this data, ultimately highlighting an industry perspective of how biopharmaceutical companies can sustainably adopt new approaches to therapeutic protein development and production.

show abstract

“…The inability of current models to transfer process knowledge from existing mAbs to new drug candidates has increased interest in machine learning and AI‐based methods for bioprocessing (Hutter et al, 2021; Smiatek et al, 2020; von Stosch et al, 2021; Wang et al, 2017). Quantitative structure–property relationships (QSPR) leverage machine learning algorithms and existing data to predict a target property based on the protein structure.…”

Section: Introductionmentioning

confidence: 99%

“…For CEX chromatography, the stoichiometric displacement model (SDM) allows simulation of protein adsorption and desorption under diluted loading conditions (Boardman & Partridge, 1955;Velayudhan & Horváth, 1988). In light of the Quality by Design (QbD) initiative (Mollerup et al, 2008), regulatory authorities support the use of mechanistic models to increase product quality by understanding the fundamental relationships between process parameters and quality attributes (Mollerup et al, 2008;Rathore & Winkle, 2009) The inability of current models to transfer process knowledge from existing mAbs to new drug candidates has increased interest in machine learning and AI-based methods for bioprocessing (Hutter et al, 2021;Smiatek et al, 2020;von Stosch et al, 2021;Wang et al, 2017). Quantitative structure-property relationships (QSPR) leverage machine learning algorithms and existing data to predict a target property based on the protein structure.…”

Section: Introductionmentioning

confidence: 99%

A multiscale modeling method for therapeutic antibodies in ion exchange chromatography

Saleh

Hess

Ahlers-Hesse

et al. 2022

Biotech & Bioengineering

View full text Add to dashboard Cite

The development of biopharmaceutical downstream processes relies on exhaustive experimental studies. The root cause is the poorly understood relationship between the protein structure of monoclonal antibodies (mAbs) and their macroscopic process behavior. Especially the development of preparative chromatography processes is challenged by the increasing structural complexity of novel antibody formats and accelerated development timelines. This study introduces a multiscale in silico model consisting of homology modeling, quantitative structure–property relationships (QSPR), and mechanistic chromatography modeling leading from the amino acid sequence of a mAb to the digital representation of its cation exchange chromatography (CEX) process. The model leverages the mAbs' structural characteristics and experimental data of a diverse set of 21 therapeutic antibodies to predict elution profiles of two mAbs that were removed from the training data set. QSPR modeling identified mAb‐specific protein descriptors relevant for the prediction of the thermodynamic equilibrium and the stoichiometric coefficient of the adsorption reaction. The consideration of two discrete conformational states of IgG4 mAbs enabled prediction of split‐peak elution profiles. Starting from the sequence, the presented multiscale model allows in silico development of chromatography processes before protein material is available for experimental studies.

show abstract

A roadmap to AI-driven in silico process development: bioprocessing 4.0 in practice

Cited by 20 publications

References 35 publications

Digitale Zwillinge in der Bioprozesstechnik – Chancen und Möglichkeiten

Digitale Zwillinge in der Bioprozesstechnik – Chancen und Möglichkeiten

Accelerated CMC workflows to enable speed to clinic in the COVID‐19 era: A multi‐company view from the biopharmaceutical industry

A multiscale modeling method for therapeutic antibodies in ion exchange chromatography

Contact Info

Product

Resources

About