• Genome Data Science

    We develop methods and tools to work with tens of thousands of genomes and analyze and integrate the corresponding data.

    Model of DNA double helix in front of a student.
    © Universität Bielefeld

392160 Graph Neural Networks in Biology

392160 Schönhuth / Pianesi Summer 2025 Tue 16-18 in V2-105/115 (S) and Thu 10-12 in V10-118 (Ü)

Content

The recent surge of Machine Learning (ML) has opened up various opportunities when analysing biological datasets. Graph Neural Networks (GNNs) are a fairly new deep learning model capable of handling biological data in the best way overall. The seminar will start with a few (around 4 or 5) introductory lectures on Graph Representation Learning basics and Graph Neural Networks. The earliest and most recent approaches will be discussed, together with their use cases and drawbacks. The initial set of lectures will be followed by two lectures in which it will be presented how to write technical reports and how to prepare a good presentation. Then seminar presentations will take place, and they will need to be presented in small groups of 1-2 students. The course will be seminar+tutorial style, thus students will: 1. present a chosen paper; 2. deliver a final report of around 10 pages; 3. weekly deliver a summary of the presentation that took place during that week (around 500 words long).

The course will is entirely held in English.

Contact

Papers

If there is any problem with accessing a paper, write an email to Luna Pianesi.


Please, see on Moodle

Authors Title Year Source
Gilmer et al. Neural message passing for quantum chemistry 2017 https://arxiv.org/abs/1704.01212
Zitnik et al. Modelling polypharmacy side effects with graph convolutional networks 2018 https://academic.oup.com/bioinformatics/article/34/13/i457/5045770

Time table seminar sessions

Date Topic
15.04.2025 Prof. Schönhuth: Organization (slides), How to present, How to write reports
22.04.2025 Introduction (slides), Glossary (slides), How to write summaries
29.04.2025 Prof. Schönhuth: Lecture 1
06.05.2025 Prof. Schönhuth: Lecture 2
13.05.2025 Prof. Schönhuth: Lecture 3
20.05.2025 Prof. Schönhuth: Lecture 4
27.05.2025 Prof. Schönhuth: Lecture 5, and deadline for choosing paper
03.06.2025 Q&A if needed
10.06.2025 Q&A if needed
17.06.2025 Q&A if needed
24.06.2025 Block presentations: 4 people
01.07.2025 Block presentations: 4 people
08.07.2025 Block presentations: 4 people
15.07.2025 Block presentations: 4 people
18.07.2025 End of lectures
26.08.2025 Deadline for report and paper journal
30.09.2025 End of semester