Go to the newsletter page and sign up to receive course dates, call for applications and other related programme news.
Data Science
Learn to analyse large data sets and train machine learning methods
This course is a part of
Increasing amounts of data are being collected in the healthcare system from high throughput genomics, wearable devices, and electronic patient records. This course will provide you with the necessary data science skills required to analyse such large datasets.
We will cover the various data analysis steps from loading and transforming data to visualization, statistical analysis, and machine learning (both supervised and unsupervised learning).
You will learn about tools that can help make clear and reproducible analyses such as software for version control and workflow management and be introduced to the use of High-Performance Computing (HPC) and parallelization.
The course will be hands-on where you will analyse relevant data sets combined with a systematic review of the various methods and tools, including sources of error, variation, and uncertainty.
The data analysis will be done using R (tidyverse) and experience with the use of R is an advantage. Experience with R can possibly be gained by self-study in connection with the course.
Teaching form
Combined on campus and online sessions, project work and report writing. The course concludes with interdisciplinary group work based on a case.
Course directors on Data Science
Jakob Skou Pedersen
Professor
Søren Besenbacher
Associate Professor
Course details for Data Science
Dates and examination
Place
Aarhus University
Course dates
Spring 2026. The course dates are yet to be announced.
The course is available every other Spring.
30 seats.
Examination
Please find the exam dates in the exam plan.
You can find relevant information about the exam in the course curriculum.
See an overview of all courses (in Danish) on Master of Personalised Medicine.
Learning outcomes
Upon completion of the course, you will be able to:
Understand the principles behind tidyverse’s data handling, visualization, modeling, and analysis. In addition, you will have knowledge of different machine learning methods (both supervised and unsupervised learning) and when they can be used. Finally, you will have knowledge of using high performance computing (HPC) for analysis of large data sets.
Use Tidyverse to perform a complete data analysis, starting from the acquisition and formatting of raw data, over visualization, to modeling and inference.
Follow and be critical of scientific analyses of large data sets. You will be able to evaluate the possibilities and limitations of different machine learning methods in relation to various uses and the amount of data available.
Admission criteria
You must meet the following criteria to be admitted to this course:
- Hold a relevant master degree or equivalent
- Have a minimum 2 years of professional experience within personal medicine in a clinical, research or academic field
- Be proficient in English
Find detailed information in the admission criteria on Master of Personalised Medicine (in Danish).
Priority is given to enrolled students
This course is offered as an elective course on the Master of Personalised Medicine programme (website in Danish). Priority is given to students already enrolled on Master of Personalised Medicine. Once the enrolled students have been admitted to the course, the remaining seats are distributed on a first-come, first-served basis.
Tuition fees
EU/EEA citizens: 11.500 DKK
Non EU/EAA Citizens: 15.500 DKK
Terms of Payment (in Danish)
Contact
Janni Stubkjær Rasmussen
Studiekoordinator
Tlf.: +45 35 32 12 79
Place
Aarhus University, Aarhus, Denmark
Jakob Skou Pedersen
Professor
Jakob Skou Pedersen is a Professor of Bioinformatics at the Department of Molecular Medicine and the Bioinformatics Research Centre, Aarhus University, Denmark.
His field of research is computational genomics, and he is interested in statistical method development and large-scale data analysis. His past contributions have spanned diverse areas, including comparative genomics, RNA structure prediction, RNA biology, ancient DNA, and cancer genomics.
His current research uses Generative AI and Bayesian modeling for computational genomics, focusing on applications within circulating tumor DNA (ctDNA) and single-cell data analysis.
Søren Besenbacher
Associate Professor
Søren Besenbacher er lektor i bioinformatik på Molekylær Medicinsk Afdeling (MOMA), Aarhus Universitet. I hans forskning bruger han statistiske og datalogiske metoder til at løse problemer inden for menskelig genomforskning. En af hans primære forskningsinteresser er at studere og modelere de mutationsprocesser der skaber nye mutation i mennesker.
Derudover arbejder hans forskningsgruppe på at lave nye metoder til at identificere om et individ har kræft udfra sekvensdata fra celle frit-DNA i blodet.