The Multi-omics Network Analytics group at DTU Health Tech offers courses that give students and researchers hands-on skills in data science, machine learning and AI for biology, from multi-omics data analysis to graph machine learning and protein language models, together with the tools we have developed.
We are strong advocates of open science, and as part of that commitment, we make sure to share all the course materials on our GitHub repository. This means that you will have access to comprehensive resources that aim to enhance the learning experience.
Our courses are designed typically following a short-training format, ranging from single lectures to a few days of intensive, hands-on instruction. Explore our course offerings and contribute or provide feedback!
The omics revolution produces data faster than it produces understanding. Turning a mass spectrometer's output into a biological claim takes a chain of decisions — how to process, filter, normalise, test, annotate and integrate — and each link in that chain can change the answer.
This three-day intensive course offers practical, up-to-date training in data science applied to omics data, with a focus on mass-spectrometry proteomics and metabolomics and on multi-omics integration.
The graph machine learning module of the DTU course 27666 AI-guided Protein Science. It introduces graph biology and how to turn biological data into graphs, graph machine learning tasks and shallow embeddings (Node2Vec, DeepWalk) with PyTorch Geometric, and graph neural networks for node- and graph-level prediction. Every session comes with a hands-on Google Colab notebook.
Objectives
An up-to-date course at the intersection of language models and the complex world of proteins. It provides an overview of the current state of the art of protein language models, which are changing research, discovery and innovation in molecular biology.
Objectives
The goal of the course is to provide an introduction to the use of networks in microbiology. The students will receive an overview of the field of computational microbiology with special emphasis on data standardization* and data sources, and how to use graph structures to solve biological questions. Further, the students will get a hands on introduction to Python programming language and its scientific libraries. At the end of the course the students will be able to: - Use multiple data sources for studying microbes in different biological contexts - Build networks, visualize and analyse them using different tools - Use Python to extract, transform and analyse different data structures
Objectives
Some of the course content is in Spanish, but we are working on an English version.
This course is designed to introduce students to the essential skills required to fully utilize available resources. Further, this course provides an overview of how networks can be used to integrate and analyse these data.
Objectives
An introduction to the fascinating world of Knowledge Graphs and their vital role in the field of biology. This course explores fundamental concepts, practical applications, and significance of Knowledge Graphs in understanding complex biological systems. Whether you’re a biologist, data enthusiast, or simply curious about the intersection of knowledge representation and biology, this course is your gateway to how to leverage interconnected biological data.
Objectives
The Data Science platform has strong commitment to advancing the education of our researcher fellows in Data Science topics. To that end, we are organizing courses about different data-types handled and produced at DTU - Biosustain (during May), and about data science aspects in general (during November). Furthermore, we are also co-organizing with DTU - Bioengineering the Data Science Club on monthly basis.
An overview of the technical trainings offered by the Data Science Platform can be found at biosustain.github.io/dsp_notes/trainings.