AI & Data Science

Mission: Bringing better treatments to the right patients

The research of the "AI & Data Science" team focuses on the development and application of AI/ML algorithms along a value chain, which largely aligns with the needs of pharma and biotech industry as well as the public health sector:

  • Target prioritization (better targets):
    • Rational selection of molecular target structures for future therapies
  • Precision medicine (the right drug for the right patient):
    • Prediction of disease risk, molecular subtype, disease progression, or treatment response at the individual patient level
  • Clinical trials (better trials):
    • Simulation of (counterfactual) synthetic disease trajectories
    • Estimating intervention effects using real-world data

To address the highly complex issues that emerge in our applications, a broad range of AI/ML techniques is needed (covering state-of-the-art artificial neural network architectures as well as classical ML techniques). At the same time, off-the-shelf solutions often do not provide satisfactory results. Hence, a significant proportion of our work goes into the adaptation, development, and design of AI/ML approaches that are tailored to solve a particular application problem. During the last years, our work has specifically covered

  • Hybrid AI/knowledge infusion
  • Generative AI and time series modeling
  • Multi-modal data integration
  • Causal machine learning

We have a long-standing experience with a wide spectrum of relevant data types in biomedicine:

  • Longitudinal clinical studies
  • Real-world data:
    • Electronic health records (EHRs) and claims data
    • Digital markers: data derived from digital device technologies (e.g. gait sensors) and smartphone applications
  • -omics

Expert support: Efficient solutions for customer needs

SCAI's services cover the entire value chain in translational biomedical research within the biotech and pharmaceutical industry. Companies are offered tailor-made AI and data mining solutions, for example, through contract research. This way, different customer needs can be addressed while providing temporary resources and expertise to support internal projects.

Precision medicine, Artificial Intellligence, Cancer, Biomarkers, Systems biology, Statistics, Neurology, Genetics, Network biology, Epidemiology, Mathematical modeling, Signal processing, Computational biology, Graph theory, Chemoinformatics, Signal processing, Data semantics

Selected publications

  • de Jong, J., Emon, M. A., Wu, P., Karki, R., Sood, M., Godard, P., ... & Fröhlich, H. (2019). Deep learning for clustering of multivariate clinical patient trajectories with missing values. Giga Science, 8(11), giz134.
    https://doi.org/10.1093/gigascience/giz134
  • Khanna, S., Domingo-Fernández, D., Iyappan, A., Emon, M. A., Hofmann-Apitius, M., & Fröhlich, H. (2018). Using multi-scale genetic, Neuoimaging and clinical data for predicting Alzheimer’s disease and reconstruction of relevant biological mechanisms. Scientific reports, 8(1),11173.
    https://www.nature.com/articles/s41598-018-29433-3
  • Philipp Wendland, Colin Birkenbihl, Marc Gomez-Freixa, Meemansa Sood, Maik Kschischo, Holger Fröhlich (2022). Generation of realistic synthetic data using Multimodal Neural Ordinary Differential Equations. npj Digital Medicine volume 5, Article number: 122.
    https://www.nature.com/articles/s41746-022-00666-x
  • Johann de Jong, Ioana Cutcutache, Matthew Page, Sami Elmoufti, Cynthia Dilley, Holger Fröhlich, Martin Armstrong (2021). Towards realizing the vision of precision medicine: AI based prediction of clinical drug response. Brain, Volume 144, Issue 6.
    https://academic.oup.com/brain/article/144/6/1738/6178276
  • Birkenbihl, C., Salimi, Y., Fröhlich, H. (2021). Unraveling the heterogeneity in Alzheimer's disease progression across multiple cohorts and the implications for data-driven disease modeling. Alzheimer's & Dementia 2022; 18: 251– 261. 
    https://doi.org/10.1002/alz.12387

Overview about our research projects

  • ADIS (EU Joint Programme Neurodegenerative Disease Research)
    Coordinator, AI methods for biological system modeling and disease diagnosis
  • AIPD (EU)
    Coordinator, Trustworth AI; AI for precision medicine and digital health in Parkinson's Disease
  • CePPH
    AI/ML models for precision medicine
  • CERTAINTY (HORIZON Europe)
    Development of (generative) AI models for the prediction and simulation of therapy response and therapy side effects
  • COMMUTE (EU)
    Causal AI/ML models for predicting the risk of neurodegenerative diseases in dependency of a COVID-19 infection
  • NFDI4Health (DFG)
    AI methods for synthetic patient data
  • PREDICTOM (Innovative Health Initiative / EU)
    AI-screening-platform for identifying dementia risk
  • PsychSTRATA (HORIZON Europe)
    AI/ML models for precision psychiatry
  • Real4Reg (HORIZON Europe)
    AI models for real-world data
  • SYNTHIA (Innovative Health Initiative)
    Development and evaluation of generative AI methods for clinical trial data

  • Graph Machine Learning
    Development of a modern Graph Neural Network approach to support drug target selection.
  • IDERHA
    AI based risk models using real-world data
  • PREDICTOM
    AI-screening-platform for identifying dementia risk
  • Scientific Machine Learning
    Development of hybrid machine learning approaches, which combine mechanistic differential equation models with neural networks.
  • SYNTHIA
    Development and evaluation of generative AI methods for clinical trial data

Collaboration

Videos


Scientific publications

References to scientific publications prior to 2020

Examples

Examples of current research work in the group "AI & Data Science"

Team