Advanced AI for Biological Data A1F
Course, Master's (2nd cycle),
7.5 credits,
BI765A
Application
Choose a course instance to see course syllabus and admission requirements.
Spring 2026, Location: Skövde, Pace of study: 50%
Application
Application is done after nomination.
Course syllabus, with reading list
When? Where? How?
Study period: 30 March 2026 - 7 June 2026
Location: Skövde, Campus, Daytime
Pace of study: 50%
Admission Requirements
Entry requirements higher education not set. The course has the following entry requirements: attended BI763A Introduction to AI in Bioinformatics A1N and attended BI764A Bioinformatics Analysis Pipelines for Large-Scale Sequence Data A1N (or the equivalent).A further requirement is proof of skills in English equivalent of studies at upper secondary level in Sweden, known as the Swedish course English 6 or English level 2. This is normally demonstrated by means of an internationally recognized language test, e.g. IELTS or TOEFL or the equivalent.
Selection
Guaranteed admission.
Language
The courses are conducted in English.
What happens when AI meets biological data? In this course, you will explore how machine learning – from classical methods to deep learning – can be used to understand complex biological patterns. With a focus on both coding and critical thinking, you will learn to build, interpret, and evaluate intelligent models that make a difference in research.
Machine learning plays an increasingly important role in biological research. Advanced algorithms are used to interpret and predict complex biological processes. These methods help us gain a better understanding of genetic mechanisms and protein structures. By applying machine learning techniques to unimodal data, researchers can analyze specific biological systems in detail. The developed methods enable thorough evaluation of the results, leading to more accurate and robust analyses. However, when data from different sources is combined, more sophisticated techniques are required to integrate the information. Researchers critically reflect on how well machine learning methods work for integrating multimodal biological data. One challenge is to ensure that the integrated models are both reliable and transparent. Therefore, explainable AI techniques are used to clearly demonstrate how decisions within the models are made. By combining advanced machine learning with explainable AI, pathways are paved for more insightful and secure biological discoveries.