AI-Driven Digital Twins for Microphysiological Systems in Biomedical Research

The use of in vitro cell cultures derived from human induced pluripotent stem cells (hiPSCs) is rapidly transforming biomedical research. These systems offer a promising alternative to traditional animal models, not only addressing ethical concerns but also overcoming the limitations in translating animal to human biology. In particular, emerging Microphysiological Systems (MPS), including on-chip platforms and advanced imaging techniques such as lens-free imaging (LFI), are poised to replace conventional tools—provided their reliability and scalability can be established.

However, the development and validation of these complex systems come with significant challenges. Experimentation protocols must often be designed from scratch and may require iterative adaptation. Available hardware prototypes are typically limited and may produce results with low generalizability. Data generated from experiments is often heterogeneous, sparsely populated, and lacks standardized structuring, making reproducibility and knowledge sharing difficult. Furthermore, there is a scarcity of reference datasets, benchmarks, and computational tools to support robust analysis and model development. These constraints pose barriers to producing reproducible and scientifically meaningful outcomes, limiting the path toward clinical or industrial translation.

This PhD project proposes a solution based on a hardware/software (HW/SW) co-design strategy, centered around the research and development of AI methods for a digital twin that will support structured experimentation, metadata capture, data annotation, and predictive modeling. By incorporating feedback mechanisms, it will enable hypothesis generation, experimental design optimization, and real-time decision support. Ultimately, the goal is to identify promising methods that can accelerate the validation of MPS technologies across multiple biomedical applications, including:

• Blood-Brain Barrier models
• On-Chip systems such as Brain-on-Chip, Organ-on-Chip (liver, gut, ...)
• Advanced imaging via LFI

Of these MPS's the Brain-on-Chip system is most mature in terms of data availability, and as such would be the primary focus initially.

The methodological focus of this research lies in the application and development of AI techniques across several key areas:

1. Digital Phenotyping and Data Exploration

• Feature engineering and extraction, data selection / pruning
• Exploratory data analysis and visualization
• Dimensionality reduction
• Clustering and pattern discovery
• Defining data expectations and quality metrics

2. Predictive and Generative Modeling

• Outlier detection
• Tabular learning and model interpretability
• Application of foundation models
• Small-data methodologies:
• Data augmentation techniques
• Hybrid learning approaches (e.g., physics-informed ML)
• Recommender systems for experimental design
• Design space exploration and Bayesian optimization
• Integration of computer vision for microscopy and imaging data

This PhD research aims to contribute foundational tools and methodologies to enable scalable, generalizable, and AI-driven insights into complex cell-based systems. The candidate will work at the intersection of biomedical engineering, machine learning, and systems biology, collaborating closely with domain experts across disciplines.

Our ideal candidate for this position has the following qualifications:   

• You have a Master’s degree in Computer Science, Informatics, AI, Engineering, Bioinformatics or a related field.  
• You have experience with machine learning and / or deep learning
• You have strong python skills and familiarity with machine learning libraries such as scikit-learn, and deep learning libraries such as PyTorch 
• Experience with investigative data exploration practices, testing hypotheses and storytelling through effective visual communication is a plus
• Biomedical knowledge is considered a plus 
• Knowledge of multi-modal modelling techniques is considered a plus
• You are able to plan and carry out your tasks in an independent way.  
• You have strong analytical skills and the ability to think critically about research results 
• You are a responsible, communicative and flexible person.  
• You are a team player.  
• You are fluent in English (speaking and writing).