Selected Topics in Bioinformatics

This course teaches advanced computational tools across spatial transcriptomics, knowledge graphs, graph representation learning, network-based integrative approaches, and machine learning applications in drug discovery.

Course abbreviation: MODS

Instructor: Bishoy Wadie, Hamza Ibrahim & Mohamed Hamed

EMBL Heidelberg, Germany; Saarland University, Germany; Rostock University, Germany

Workload: 12 lectures, 3 hours each. Total workload: 48 hours: 36 hours of lectures and tutorials and 12 hours of self studies.

Entrance requirements: DAV-R and MODA.

Used media: PowerPoint presentation

Objectives

• Learn advanced computational tools in selected bioinformatics topics
• Explore spatial transcriptomics, knowledge graphs, graph representation learning, and network-based integration
• Apply machine learning to drug discovery problems

Competences to be Developed

• Knowledge graph and network embeddings
• Exploration of spatial single-cell data
• Graph representation learning
• Compass tool for studying metabolic heterogeneity using scRNA-seq
• Machine learning applications in drug discovery
• Whole methylome analysis
• Network-based integrative approaches and TFmiR

Assessment

• Finalize a research project applying learned methods and skills
• Compile project outcomes into a high-quality scientific presentation that could lead to an article
• Present, discuss, and scientifically review projects in the last lecture