ENBIS Spring Meeting 2025

Session

Session

29 May 2025, 10:00

Conveners

Session: Quality by Design I

• Sonja Kuhnt (Dortmund University of Applied Sciences and Arts)

Session: Quality by Design II

• Jacqueline Asscher (Kinneret College, Technion)

Session: Hybrid Modelling I

• Pierantonio Facco (University of Padova)

Session: Hybrid Modelling II

• Dongda Zhang (University of Manchester)

Session: xAI

• Sonja Kuhnt (Dortmund University of Applied Sciences and Arts)

Session: Active Learning

• Alberto J. Ferrer-Riquelme (Universidad Politecnica de Valencia)

Session: PAT & Chemometrics

• Raffaele Vitale (Université de Lille)

Session: Data Science

• Alberto J. Ferrer-Riquelme (Universidad Politecnica de Valencia)

3. Defining process operating space under uncertainty: Bayesian Design Space for complex kinetic reactions

Frederico Montes (Hovione)

29/05/2025, 10:00

Spring Meeting

Design of experiments for process scale-up can be described as a double-edged sword for the pharmaceutical industry: intensification of experiments expands the knowledge of the process (uncertainty reduction) but increases resource expenditure. On the other hand, moving forward without enough process understanding is the first stone in a path of deviations, lack of quality, and even safety...

20. Capability by Design: A novel paradigm for selecting raw material suppliers aligned with Quality by Design

Joan Borràs-Ferrís (Kensight)

29/05/2025, 10:20

Spring Meeting

Capability indexes can be used to estimate how likely a given supplier of raw materials is to meet customer's requirements for these raw materials. It is therefore usually used by a customer operating a process as a criterion for selecting raw material suppliers. However, both univariate and multivariate capability indexes provided so far in the literature assume that the specifications are...

38. Optimal Experimental Designs for Process Robustness Studies

Peter Goos (KU Leuven)

29/05/2025, 10:40

Spring Meeting

In process robustness studies, experimenters are interested in comparing the responses at different locations within the normal operating ranges of the process parameters to the response at the target operating condition. Small differences in the responses imply that the manufacturing process is not affected by the expected fluctuations in the process parameters, indicating its robustness. In...

39. Quality by Design (QbD) and Analytical Quality by Design (AQbD): A Holistic Approach to Pharmaceutical Quality

Carla Vitorino (Faculty of Pharmacy, University of Coimbra)

29/05/2025, 11:30

Spring Meeting

The Quality by Design (QbD) approach has been widely adopted in the development of both novel and generic pharmaceutical formulations1. Extending these principles to the analytical domain, Analytical Quality by Design (AQbD) has emerged as a structured framework for optimizing analytical methodologies2. The aim of the present work was to outline a comprehensive framework for development of a...

33. "Connecting The Dots Looking Backward": Enhancing Pharma Manufacturing through a Retrospective Quality By Design Case Study

Helena Bigares Grangeia ((1) University of Coimbra, Faculty of Pharmacy, Drug Development and Technologies Laboratory, 3000-548 Coimbra, Portugal / (2) CERES – Chemical Engineering and Renewable Resources for Sustainability, Department of Chemical Engineering, University of Coimbra, 3030-790 Coimbra, Portugal / (3) Bluepharma Industry, SA, 3045-016 Coimbra, Portugal)

29/05/2025, 11:50

Spring Meeting

Introduction: As Steve Jobs famously stated, "You can't connect the dots looking forward; you can only connect them looking backward." This reflective insight resonates perfectly in this work. Adopt a Retrospective Quality by Design (rQbD) perspective and connect the dots of past manufacturing experiences to drive continuous improvement and innovation in legacy drug products and their...

9. Multiscale interval PLS for spectral data modeling

Tiago Rato (University of Coimbra)

29/05/2025, 12:10

Spring Meeting

Process analytic technologies (PAT) are routinely used to rapidly assess quality properties in many industrial sectors. The performance of PAT-based models is, however, highly related to their ability to pre-process the spectra and select key wavebands. Amongst the modeling methodologies for PAT, partial least squares (PLS) (Wold, Sjöström and Eriksson, 2001) and interval partial least squares...

31. Predicting drug solubility through digital models: towards pharmaceutical industry 5.0

Prof. Pierantonio Facco (University of Padova)

29/05/2025, 14:00

Spring Meeting

In the pharmaceutical industry, drug solubility is a critical quality attribute. For example, drug solubility in organic solvents mixtures is usually screened in drug development to select the best solvent system for crystallization in such a way as to design the manufacturing process. Solubility is also important in the final product because it has a direct impact on the way the drug is...

12. Physics-Informed Neural Network for Bioprocess digitalization

Monesh kumar Thirugnanasambandam (NOVA School of Science and Technology, Universidade NOVA de Lisboa)

29/05/2025, 14:20

Spring Meeting

Keywords: Bioreactor modeling, Feed forward neural network, Hybrid semiparametric model, Physics-informed neural network, Fed-batch reactor
Abstract
Bioreactors are fundamental to bioprocess technology, yet the complexity of bioreactor systems continues to challenge effective digitalization and optimization. The intricate, dynamic nature of cell...

13. Deep hybrid modelling and control of microbiome evolution

José Pinto (NOVA - SST)

29/05/2025, 14:40

Spring Meeting

Keywords: Biopharma 4.0, Deep learning, Physics Informed Neural Networks, Bioreactors, Digital Twin

Abstract
Hybrid modeling combining First-Principles with Machine Learning (ML) is becoming a pivotal methodology for Industry 4.0 enactment. The combination of ML with prior knowledge generally improves the model predictive power and transparency while reducing the amount of data for process...

14. Hybrid Semiparametric Modelling of the Supercritical Carbon Dioxide Extraction Process

Mrs Roshanak Agharafeie (UCIBIO, NOVA-SST, NOVA University Lisbon- NOVA IMS, NOVA University Lisbon)

29/05/2025, 15:00

Spring Meeting

Keywords: Digital Twin, Hybrid Modeling, Machine Learning, Supercritical Carbon Dioxide Extraction, Process Optimization

Abstract
Supercritical carbon dioxide (ScCO2) extraction is a separation process that presents several advantages over traditional extraction methods of nonpolar solutes, eliminating the need for harmful organic solvents and costly post-processing steps required to...

1. Enhancing Pharmaceutical Manufacturing Efficiency with End-to-End Models and Physics-Informed AI

Ignasi Bofarull-Manzano (RWTH Aachen)

29/05/2025, 16:20

Spring Meeting

End-to-End (E2E) models and Digital Twins in the pharmaceutical industry enhance efficiency, improve decision-making, allow for real-time monitoring, optimization, predictive analytics, and ultimately strengthen quality control and reduce costs. A key component of E2E models is the use of Monte Carlo simulations to capture uncertainties and variability within complex processes.

Typically,...

15. Encoding of neural networks of different architectures to SBML format

Ekaterina Moskovkina (NOVA School of Science and Technology, Universidade NOVA de Lisboa)

29/05/2025, 16:40

Spring Meeting

Despite advancements in Systems Biology, developing purely ODE-based mechanistic models remains challenging due to incomplete knowledge of parameters or computational inefficiencies. In such cases, hybrid and data-driven approaches provide viable alternatives. To facilitate seamless simulation and analysis alongside classical ODE-based models, it is advantageous to encode data-driven models in...

37. 3D-bioprinting by design: A Dynamic Model of the Blood-Brain Barrier and Glioblastoma

Francisco Branco (FFUC)

29/05/2025, 17:00

Spring Meeting

Introduction: The blood-brain barrier (BBB) severely restricts the passage of drugs into the brain, posing a significant challenge in treating central nervous system disorders such as glioblastoma (GBM). Therefore, there is an urgent need for advanced in vitro models that accurately characterize both BBB permeability and GBM behavior [1]. The evolution from two-dimensional (2D) to...

7. An explainability study (XAI) of Deep CNN for near-infrared spectroscopy : IPA under the light

Florent HAFFNER (IFP Energies Nouvelles)

30/05/2025, 09:45

Spring Meeting

Inception for Petroleum Analysis (IPA) [1] is a deep convolutional network inspired from state-of-the-art computer vision architectures. IPA showed improved performance, compared to PLS, without depending on complex pre-processing operations thanks to its several computational blocks. The network begins with three stacked convolutions, followed by a multi-branch module consisting of four...

22. Green LIME: Improving AI Explainability through Design of Experiments

Werner G. Mueller (Johannes Kepler University)

30/05/2025, 10:05

Spring Meeting

In artificial intelligence (AI), the complexity of many models and processes often surpasses human interpretability, making it challenging to understand why a specific prediction is made. This lack of transparency is particularly problematic in critical fields like healthcare, where trust in a model's predictions is paramount. As a result, the explainability of machine learning (ML) and other...

17. Exploring CNN architectures for NIR based chemometric tasks - the Deep Tutti-Frutti application.

Dário Passos (University of Algarve)

30/05/2025, 10:25

Spring Meeting

Convolutional Neural Networks (CNNs) have been increasingly used to build NIR based chemometric models with applications ranging from chemical sample analysis to food quality control. In the latter, NIR spectroscopy combined with CNNs enable rapid, non-destructive SOTA predictions of important quality parameters such as dry matter content in fruit [1].
The lack of a standard CNN architecture...

36. "Classic" DoE vs. Bayesian Optimization / Active learning:

Dr Stefanie Feiler (FHNW School of Life Sciences)

30/05/2025, 11:15

Spring Meeting

Design of experiments is one of the main Quality by Design (QbD) tools within the process industry.
However, "classic" DoE is increasingly challenged by modern techniques such as Bayesian Optimization and Active Learning.
These innovative methods are promoted as faster and more intuitive, offering greater flexibility in experimentation.
In this talk, I will provide a direct comparison of...

32. Traditional or Adaptive Experimental Design? A Comparison of Statistical Design of Experiments and Bayesian Optimization for a Chemical Synthesis Problem

João Coutinho (Department of Chemical Engineering, University of Coimbra)

30/05/2025, 11:35

Spring Meeting

Bayesian Optimization (BO) has been recently shown as an efficient method for data-driven optimization of expensive and unknown functions. BO relies on a probabilistic surrogate model, commonly a Gaussian Process (GP), and an auxiliary acquisition function that balances exploration and exploitation for a goal-oriented experimental design, with the aim of finding the global optimum under a...

16. A Comparison of DOE and BO in the In Silico Optimization of Lipid Nanoparticles (LNPs)

Daniel Alexandre Vidinha Batista (University of Coimbra)

30/05/2025, 11:55

Spring Meeting

Carefully designing experiments is crucial for gaining a deeper understanding of process behaviour. Design of Experiments (DOE) is a well-established active learning methodology with an extensive track record of solid contributions to research and industry in various areas, including screening, modelling, optimisation, specification matching, and robust design. Based on a reduced set of...

11. Predicting the coagulation potential of waste lubricant oils (WLO) using multiblock machine learning of NIR and MIR spectra

Ruben Gariso (University of coimbra)

30/05/2025, 14:00

Spring Meeting

Waste lubricant oil (WLO) is a hazardous residue that requires proper management. Among the options available, regeneration is the preferred approach to promote a sustainable circular economy. However, WLO regeneration is only viable if the WLO does not coagulate during processing as it can cause operational problems and possibly lead to a premature shutdown of the process for cleaning and...

19. Implementation of in-line PLS model and sensor fusion for real-time reaction monitoring

Jose Granjo (Hovione Farmaciência SA)

30/05/2025, 14:20

Spring Meeting

Real-time monitoring of chemical processes is key for optimizing yield, preventing out of specification product, and improving overall process efficiency. Process analytical technology (PAT) tools, such as near-infrared and infrared (IR) spectroscopies, provide a real-time window into chemical processes, enabling non-destructive monitoring of analyte concentrations, and reducing dependance on...

8. Optimising PAT for Continuous Direct Compression using Feed Frame Simulator and SentroPAT FO NIR Spectrometer

Eleonora De Giorgi (AstraZeneca, University of Birmingham)

30/05/2025, 14:40

Spring Meeting

Monitoring formulation quality during Continuous Direct Compression (CDC) and therefore remaining within product specifications is complex and cannot easily be inferred from process measurements. Process Analytical Technology (PAT) sensors allow in-line process monitoring and control of Critical Quality Attributes (CQAs), reducing the time and effort required for both sampling and off-line...

10. ONLINE MONITORING AND OPTIMIZATION OF REACTIVE EXTRUSION PROCESSES

Dr Manis Gheghiani (Axel'One)

30/05/2025, 15:05

Spring Meeting

Online analysis has been widely developed to monitor the chemistry or the physics on batch or continuous processes. One of the major issues concerns the sampling part to integrate the analytical solution into the process. Optical spectroscopy is one of the most used technologies as it can be implemented directly inline and does not necessary required a sampling loop to adapt the process to the...

18. Industrial Text Data Analysis: From Word Counting to GenAI Applications

Dr Eugeniu Strelet (The Dow Chemical Company)

30/05/2025, 15:25

Spring Meeting

In the Chemical Manufacturing Industry, a diverse array of sensor technologies and data collection methods provide valuable insights into monitoring physical and chemical phenomena, equipment status, process conditions, raw material attributes, product quality, emissions, and logistics. Despite the extensive use of sensors, critical process information such as leaks, corrosion, and insulation...

35. Knowledge transfer for biopharmaceutical production: data analysis of different process development campaigns

Nuno Francisco Bragança (Universidade Nova de Lisboa)

30/05/2025, 15:45

Spring Meeting

Background
Monoclonal antibodies (mAbs) are highly specific proteins used in personalized therapeutics, with applications ranging from cancer treatment to autoimmune disease management. In this study, we focus on the production of 86 monoclonal antibody (mAb) molecules, each potentially having unique production characteristics.
Due to the confidential nature of proprietary data in the...