SBRI19004U Big Data Analytics and Machine Learning I – Computational Biology in Translational Medicine
BRIDGE - Translational Excellence Program
Big data is a crucial resource for translational medicine. Registries contain decades of priceless individual-level information about disease history, medicine use, family relationships etc. The development of high-throughput methods has also led to a drastic increase in big data available. Both data types are already used in the clinic for diagnosis, to predict treatment responses etc. Yet, we are only in the beginning of exploiting the potential of big data in translational medicine. One of the key tool areas for utilizing such data is through bioinformatics analysis.
The focus in bioinformatics is on integrative analysis of large data ranging from molecular-level data on sequences, gene transcription patterns and molecular interactions to clinical data. A major aim is to gain insights into both rare and complex diseases in relation to patient stratification and elucidation of differences in the biological mechanisms that lead to similar phenotypes.
The objectives of the course are to provide knowledge how to get data access to big data of various types and of a range of methods, including machine learning and biological network analysis, for finding, analyzing and integrating heterogeneous data in the context of a specific disease , and to provide students with the necessary foundation to critically evaluate results of such analyzes. The critical assessment is relevant in the context of decision support systems where elements of the learning healthcare system, benchmarking and general insights into evidence-based medicine are important.
On completion of the course, the participants should be able to:
- Identify and describe resources of big data including omics and registry data
- Explain the procedure for applying for data access, capturing data and how data harmonization is necessary for data analysis and integration
- Discuss how heterogeneous data can be integrated and evaluated
- Explain machine learning and provide examples of specific methods and their advantages and disadvantages
- Design studies and explain workflows for integrative analysis of big data for generation of disease knowledge
- Use data analysis programs such as Unix / Linux
- Locate and apply for data access to registries
- Run machine learning algorithms on big data to predict patient mortality, identify disease biomarkers relevant patient outcome or similar
- Apply text mining for extracting information from clinical notes or biomedical literature
- Perform integrative analysis of heterogeneous data such as data and clinical data
- Present heterogeneous data on a biological system for employing biological questions
- Overview of big data types and what such data can be used for in the context of translational medicine with specific focus on precision medicine
- Master a range of methods for analyzing and integrating heterogeneous data in the context of a specific disease including machine learning methods and network analysis
- Benchmark and critically evaluate results of such analyzes
- Understand the central aspects of big data analytics and be able to discuss and communicate to other scientists, clinicians, and the public
To be added
- Theory exercises
Automatic registration upon appointment in the Translational Excellence Program
- 0 ECTS
- Type of assessment
- Continuous assessmentCourse participationAttendance and active participation
- Exam registration requirements
Participants are automatically registered for the Examination upon course registration.
- All aids allowed
- Marking scale
- passed/not passed
- Censorship form
- No external censorship
Criteria for exam assesment
i) an overview theory and application of technologies in epigenetic modification and genomic regulation,
ii) a basic overview of modern human tissue and organ models,
iii) an overview of possibilities of system biology approaches for integrating omics data in translational research,
iv) an understanding of application of technologies in microbiome research in health and disease, and v) knowledge of online omics resources and tools.