• 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

Graph Neural Networks in Biology

392160 Schönhuth / Pianesi Summer 2024 Tue 16-18 in X-B2-101 (S)

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 war overall. The seminar will start with an introductory lecture. The earliest and most recent approaches will be discussed, together with their use cases and drawbacks. The mini lecture 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 will be seminar presentations, to be presented in small groups of 1-2 students. The course will be held entirely in English.

Papers

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


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
Gasteiger et al. Directional message passing for molecular graphs 2020 https://arxiv.org/abs/2003.03123
Withnall et al. Building attention and edge message passing neural networks for bioactivity and physico-chemical property prediction 2020 https://jcheminf.biomedcentral.com/articles/10.1186/s13321-019-0407-y
Guo et al. Few-shot graph learning for molecular property prediction 2021 https://arxiv.org/abs/2102.07916
Li et al. Graph representation learning in biomedicine and healthcare 2022 https://www.nature.com/articles/s41551-022-00942-x
Vrcek et al. Learning to untangle genome assembly with graph convolutional networks 2022 https://arxiv.org/abs/2206.00668
Stärk et al. EquiBind: geometric deep learning for drug binding structure prediction 2022 https://arxiv.org/abs/2202.05146
Garcia Satorras et al. E(n)-equivariant graph neural networks 2022 https://arxiv.org/abs/2102.09844
Liu et al. Generating 3D molecules for target protein binding 2022 https://arxiv.org/abs/2204.09410
Alsentzer et al. Deep learning for diagnosing patients with rare genetic diseases 2022 https://www.medrxiv.org/content/10.1101/2022.12.07.22283238v1
Roohani et al. Predicting transcriptional outcomes of novel multigene perturbations with GEARS 2023 https://www.nature.com/articles/s41587-023-01905-6
Huang et al. Zero-shot drug repurposing with geometric deep learning and clinician centered design 2023 https://www.medrxiv.org/content/10.1101/2023.03.19.23287458v2
Deng et al. CHGNet: pretrained universal neural network potential for charge-informed atomistic modelling 2023 https://arxiv.org/abs/2302.14231
Klein et al. Timewarp: transferable acceleration of molecular dynamics by learning time-coarsened dynamics 2023 https://arxiv.org/abs/2302.01170
Cao et al. Learning large graph property prediction via graph segment training 2023 https://arxiv.org/abs/2305.12322
Gao et al. Double equivariance for inductive link prediction for both new nodes and new relation types 2023 https://arxiv.org/abs/2302.01313
Lee et al. A principal odour map unifies diverse tasks in olfactory perception 2023 https://www.science.org/doi/10.1126/science.ade4401
Viñas et al. Hypergraph factorization for multi-tissue gene expression imputation 2023 https://www.nature.com/articles/s42256-023-00684-8
DeZoort et al. Graph neural networks at the Large Hadron Collider 2023 https://www.nature.com/articles/s42254-023-00569-0
Joshi et al. gRNAde: geometric deep learning for 3D RNA inverse design 2024 https://arxiv.org/abs/2305.14749
Bose et al. SE(3)-stochastic flow matching for protein backbone generation 2024 https://arxiv.org/abs/2310.02391
Li et al. Contextualizing protein representations using deep learning on protein networks and single-cell data 2024 https://www.biorxiv.org/content/10.1101/2023.07.18.549602v2
Riebesell et al. Matbench discovery: a framework to evaluate machine learning crystal stability predictions 2024 https://arxiv.org/abs/2308.14920
Wong et al. Discovery of a structural class of antibiotics with explainable deep learning 2024 https://www.nature.com/articles/s41586-023-06887-8

Time table lecture

Date Topic
09.04.2024 Organization (slides), Introduction (slides), Glossary (slides)
16.04.2024 No lecture
23.04.2024 How to present (slides)
30.04.2024 GNN applications
07.05.2024 How to write reports
14.05.2024 1st presentation: 4pm “Modelling polypharmacy side effects with graph convolutional networks”
21.05.2024 2nd presentation: 4pm “Generating 3D molecules for target protein binding”
28.05.2024 3rd presentation: 4pm “E(n)-equivariant graph neural networks” CANCELLED
28.05.2024 3rd presentation: 5pm “Deep learning for diagnosing patients with rare genetic diseases”
04.06.2024 4th presentation: 5pm “Neural message passing for quantum chemistry” CANCELLED
11.06.2024 no seminar session
18.06.2024 no seminar session
25.06.2024 5th presentation: 4pm “Learning large graph property prediction via graph segment training”
25.06.2024 6th presentation: 5pm “Graph neural networks at the Large Hadron Collider”
02.07.2024 7th presentation: 4pm “Graph representation learning in biomedicine and healthcare”
02.07.2024 8th presentation: 5pm “Few-shot graph learning for molecular property prediction”