PuSH - Publication Server of Helmholtz Zentrum München

Malagoli, G. ; Hanel, P. ; Danese, A. ; Wolf, G.* ; Colomé-Tatché, M.

Geometry-aware graph attention networks to explain single-cell chromatin states and gene expression with SEAGALL.

Genome Biol. 27:188 (2026)
Publ. Version/Full Text Postprint Research data DOI PMC
Open Access Gold
Creative Commons Lizenzvertrag
High-throughput single-cell sequencing is widely used to study cell identity. We present SEAGALL (Single-cell Explainable Geometry-Aware Graph Attention Learning pipeLine), a deep learning method to quantify the impact of molecular features on cellular phenotype, based on geometry-regularised autoencoders (GRAE) and explainable graph attention networks (X-GAT). The GRAE embeds the data into a latent space to build a reliable cell-cell graph. The GAT is trained to learn the annotations and XAI is used to explain the predictions, unravelling the features driving cell identity. SEAGALL extracts specific and stable signatures from multiple omics experiments, going beyond differential marker genes.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Journal article
Document type Scientific Article
Keywords Induction
ISSN (print) / ISBN 1474-760X
e-ISSN 1465-6906
Journal Genome Biology
Quellenangaben Volume: 27, Issue: 1, Pages: , Article Number: 188 Supplement: ,
Publisher Springer
Publishing Place Campus, 4 Crinan St, London N1 9xw, England
Reviewing status Peer reviewed
Institute(s) Institute of Computational Biology (ICB)
Institute of Stem Cell Research (ISF)
Grants Ludwig-Maximilians-Universitt Mnchen (1024)
Hermann von Helmholtz-Association Deutscher Forschungszentren e.V