Bioinformatics: Artificial Intelligence and Algorithmic Approaches (Module: 13978)

Molecular biology is a scientific field that has undergone dramatic changes over the last four decades, driven by novel scientific instruments such as sequencing machines, which allow us to study genomes as well as gene activity. This has enabled a much deeper understanding of the molecular mechanisms of life, the evolution of species and, very importantly, a better understanding of human disease.

A large part of this change was fuelled by methods from computer science, most notably algorithms for comparing biological sequences (also known as approximate string matching) and for combining or assembling short sequences into complete genomes. In fact, for large parts of bioinformatics, the required representation of biology is that of a string over the alphabet {A, C, G, T}.  

The course’s focus on sequence analysis allows us to concentrate on state-of-the-art methods in bioinformatics whilst keeping the biological background fairly abstract and thus easily accessible even to students with limited background in the natural sciences or biology. 

The course will provide an introduction to modern bioinformatics and to selected applications from biology and medicine addressed using computational approaches based on classical algorithms and statistical machine learning, as well as modern deep learning approaches. The focus will be on four fundamental problem areas:

• Comparing sequences: Sequence alignment algorithms, genome-scale approaches using index data structures, alignment-free methods
• Analysing gene expression: alignment-based and alignment-free methods for analysing RNA-Seq and single-cell data
• Signals in sequences: identification of motifs, accessibility, and modification of DNA
• Sequence variations and their relation to phenotypes: structural variants in disease, potentially pan-genome approaches

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/section.php?id=157834.

Seminar: Artificial Intelligence for Drug Design (Module: 13979)

Drug design is one of the most exciting fields where artificial intelligence (AI) has a measurable positive impact on human lives by greatly accelerating the complicated and failure-prone process of designing new drugs. 

For this seminar, we plan to focus on oligonucleotides and gene editing, two of the most modern approaches to treating disease.  

Some biological concepts (DNA sequences, genes, gene expression) are necessarily part of the research articles that form the subject of the seminar. We will introduce these in an initial presentation, which will also cover the biological processes targeted by the diseases.

However, machine learning methods often employ simple abstractions, such as representing a DNA sequence as a string over the alphabet {A, C, G, T}. In other words, no in-depth biological background is required. Consequently, the seminar is accessible even to students with limited experience in the natural sciences or biology.

Students will present a topic based on—typically—one original research article chosen from a list of suggestions made available here and prepare a report on the same topic. Attendance at all presentations by other students and participation in discussions is required to pass the course.

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/view.php?id=14656.

Seminar: Computing at Scale in Machine Learning (Module: 14445)

Upon successful completion of the module, students will be familiar with state-of-the-art problems and methodological approaches used in medical bioinformatics. They will be able to familiarise themselves with current research in medical bioinformatics through original research literature, participate in technical discussions within the context of international science, and present scientific content in written and oral form.
Students will learn about specific state-of-the-art problems and methodological approaches used in medical bioinformatics. Applications will range from diagnosing and monitoring patients using sensor, clinical and omics data, to detecting clinically relevant conditions or understanding cellular processes relevant to diagnosis and disease, as well as mechanisms for treating diseases. Methods will include both algorithmic and machine learning approaches. 

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/view.php?id=14661.

Research Module in Artificial Intelligence: Specialisation in Medical Bioinformatics (Module: 14060)

The research module helps students prepare for a Master’s thesis in the fields of medical bioinformatics, particularly with regard to the use of machine learning and AI methods. The format consists of weekly meetings in which students read an original research paper, prepare a project proposal and a project plan for a potential thesis project based on the original research paper following some preliminary analysis. The writing process, the formulation of scientific questions and the design to address them are important initial steps in the Master’s programme.

There will be weekly meetings; the time and day of the week are to be arranged.

About the field:

Molecular biology and biomedicine are scientific fields that have undergone dramatic changes over the last four decades, driven by novel scientific instruments such as sequencing machines, which allow us to study genomes as well as gene activity. This has enabled a much deeper understanding of the molecular mechanisms of life, the evolution of species and, very importantly, a better understanding of human disease.
A large part of this change was driven by methods from computer science, most notably algorithms for comparing biological sequences (also known as approximate string matching) and for combining or assembling short sequences into complete genomes. In fact, for much of bioinformatics, the required representation of biology is that of a string over the alphabet {A, C, G, T}.  

Consequently, by keeping the biological background quite abstract, research on state-of-the-art methods in bioinformatics is easily accessible even to students with limited background in natural sciences or biology. 

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/view.php?id=14658.

Bioinformatics Laboratory (Module: 14441)

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/view.php?id=14662.

Workflows for Machine Learning and Reproducible Science Laboratory (Module: 14449)

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/view.php?id=14663.

Advanced Seminar in Medical Bioinformatics

Detailed information for participants is available at https://www.b-tu.de/elearning/btu/course/section.php?id=157963.