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

In silico process development constitutes a viable option for accelerating CMC development timelines and can be achieved through either a hybrid-modeling-driven or an Artificial Intelligence (AI)-driven avenue. Each pathway has its own pros and cons but the biggest difference is that the former can be developed in-house whereas the latter requires inter-corporation collaboration. Motivated by the precedence of inter-corporation data ecosystems targeting drug discovery, in this paper we bring forward the case of the AI-driven approach to in silico process development in terms of both technical feasibility and scientific soundness. Our analysis asserts that methodologically, AI is now mature to be employed for the task at hand, provided that the overall exercise is driven by multi-disciplinary experts. Further, in silico process development should be understood as a collection of models, with each process unit being endowed with its own model.

[1]  Kit-Kay Mak,et al.  Artificial intelligence in drug development: present status and future prospects. , 2019, Drug discovery today.

[2]  Hamidreza Mehdizadeh,et al.  Generic Raman‐based calibration models enabling real‐time monitoring of cell culture bioreactors , 2015, Biotechnology progress.

[3]  Eric A. Stahlberg,et al.  Accelerating Therapeutics for Opportunities in Medicine: A Paradigm Shift in Drug Discovery , 2020, Frontiers in Pharmacology.

[4]  Qassim Nasir,et al.  A systematic literature review on hardware implementation of artificial intelligence algorithms , 2020, The Journal of Supercomputing.

[5]  Pierantonio Facco,et al.  Using data analytics to accelerate biopharmaceutical process scale-up , 2020 .

[6]  Rui Oliveira,et al.  Hybrid semiparametric systems for quantitative sequence-activity modeling of synthetic biological parts , 2018, Synthetic biology.

[7]  Sebastian Schwarz,et al.  Bringing IoT to the Lab: SiLA2 and Open-Source-Powered Gateway Module for Integrating Legacy Devices into the Digital Laboratory , 2020, HardwareX.

[8]  Nilay Shah,et al.  Rapid development and deployment of high‐volume vaccines for pandemic response , 2020, Journal of advanced manufacturing and processing.

[9]  Jarka Glassey,et al.  Toward biotherapeutic product real-time quality monitoring , 2019, Critical reviews in biotechnology.

[10]  Pierantonio Facco,et al.  Data analytics on raw material properties to accelerate pharmaceutical drug development , 2019, International journal of pharmaceutics.

[11]  Dnyaneshwar Kalyane,et al.  Artificial intelligence in drug discovery and development , 2020, Drug Discovery Today.

[12]  Julian Morris,et al.  Calibration of multiplexed fiber-optic spectroscopy. , 2011, Analytical chemistry.

[13]  Gareth John Macdonald.  Biomanufacturing Makes Sense of the Industry 4.0 Concept: The digital transformation of biomanufacturing poses short-term difficulties but promises long-term benefits through real-time monitoring and dynamic process optimization , 2020 .

[14]  Thomas Blaschke,et al.  The rise of deep learning in drug discovery. , 2018, Drug discovery today.

[15]  Jarka Glassey,et al.  Exploiting mAb structure characteristics for a directed QbD implementation in early process development , 2018, Critical reviews in biotechnology.

[16]  Rui M. C. Portela,et al.  Towards in silico Process Modeling for Vaccines. , 2021, Trends in biotechnology.

[17]  Bin Li,et al.  Applications of machine learning in drug discovery and development , 2019, Nature Reviews Drug Discovery.

[18]  Cenk Undey,et al.  A machine‐learning approach to calibrate generic Raman models for real‐time monitoring of cell culture processes , 2019, Biotechnology and bioengineering.

[19]  Ali Ebrahim,et al.  Multi-omic data integration enables discovery of hidden biological regularities , 2016, Nature Communications.

[20]  Brandon Berry,et al.  Cross‐scale predictive modeling of CHO cell culture growth and metabolites using Raman spectroscopy and multivariate analysis , 2015, Biotechnology progress.

[21]  James K. Drennen,et al.  Calibration Transfer of a Quantitative Transmission Raman PLS Model: Direct Transfer vs. Global Modeling , 2017, Journal of Pharmaceutical Innovation.

[22]  Nic Fleming,et al.  How artificial intelligence is changing drug discovery , 2018, Nature.

[23]  J. Smiatek,et al.  Towards a Digital Bioprocess Replica: Computational Approaches in Biopharmaceutical Development and Manufacturing. , 2020, Trends in biotechnology.

[24]  Massimo Morbidelli,et al.  Bioprocessing in the Digital Age: The Role of Process Models , 2019, Biotechnology journal.

[25]  Sebastião Feyo de Azevedo,et al.  Hybrid semi-parametric modeling in process systems engineering: Past, present and future , 2014, Comput. Chem. Eng..

[26]  Why Drugs Fail in Late Stages of Development: Case Study Analyses from the Last Decade and Recommendations , 2018, The AAPS Journal.

[27]  Kurt Brorson,et al.  Innovation in biomanufacturing: the only way forward , 2013 .

[28]  Rui Oliveira,et al.  Modeling of the burst release from PLGA micro- and nanoparticles as function of physicochemical parameters and formulation characteristics. , 2017, International journal of pharmaceutics.

[29]  Shu Yang,et al.  Hybrid Modeling in the Era of Smart Manufacturing , 2020, Comput. Chem. Eng..

[30]  Pierantonio Facco,et al.  A hybrid framework for process monitoring: Enhancing data-driven methodologies with state and parameter estimation , 2020 .

[31]  Kim Bure,et al.  Open Access Could Transform Drug Discovery: A Case Study of JQ1 , 2016, Expert opinion on drug discovery.

[32]  Marianthi G. Ierapetritou,et al.  Challenges and opportunities in modeling pharmaceutical manufacturing processes , 2015, Comput. Chem. Eng..

[33]  A. Rathore,et al.  Quality by design for biopharmaceuticals , 2009, Nature Biotechnology.