Disease Systems Biology and Health Data Science

Upon completing the course, participants should be able to:

Knowlegde

• Identify and describe key categories of health-related big data, including molecular (genomic, proteomic, metabolomic) and clinical registry and patient record data.
• Explain the role of programming in processing, analyzing and interpreting large biomedical datasets.
• Discuss classical machine learning and deep learning approaches including their main principles, advantages, limitations, and clinical use cases.
• Describe basic principles of genetic sequence analysis for Genome Wide Associations Studies (GWAS) and Polygenetic Risk Scores (PRS) and explain their relevance to precision medicine.
• Describe how complex, interacting biological systems can be represented and analyzed as networks.
• Describe and evaluate methods used for integrating heterogeneous biological and clinical data types.

Skills

• Apply text-mining techniques to extract information from clinical records or biomedical literature.
• Search for and retrieve data from publicly available network biology databases such as STRING and DISEASES.
• Use analytical software, including Cytoscape, Disease Trajectory Browser, and R, to process and visualize biomedical data.
• Perform and critically evaluate biological analyses like variant calling, functional enrichment and protein network construction.
• Present integrated, heterogeneous data to address specific biological and clinical questions.
• Communicate analytical results clearly and effectively in both written and oral formats to interdisciplinary audiences.

Competences

• Critically assess the reliability, limitations, and clinical relevance of big-data analyses in the context of personalized medicine.
• Integrate population-level research findings with patient-specific information to support clinical decision-making.
• Work independently and in teams on complex data-driven research tasks in a biomedical setting.
• Reflect on the ethical and societal implications of collecting, integrating, and applying health-related big data.
• Benchmark and critically evaluate results of machine learning, deep learning and text mining methods used for big data analysis.
• Discuss the potential and limitations of big data in translational medicine and communicate key aspects of data analytics to scientists, clinicians, and the general public.