Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Bioinformatics Année : 2022

Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder

Résumé

Motivation: Single cell RNA sequencing (scRNA-seq) data makes studying the development of cells possible at unparalleled resolution. Given that many cellular differentiation processes are hierarchical, their scRNA-seq data is expected to be approximately tree-shaped in gene expression space. Inference and representation of this tree-structure in two dimensions is highly desirable for biological interpretation and exploratory analysis. Results: Our two contributions are an approach for identifying a meaningful tree structure from high-dimensional scRNA-seq data, and a visualization method respecting the tree-structure. We extract the tree structure by means of a density based minimum spanning tree on a vector quantization of the data and show that it captures biological information well. We then introduce DTAE, a tree-biased autoencoder that emphasizes the tree structure of the data in low dimensional space. We compare to other dimension reduction methods and demonstrate the success of our method both qualitatively and quantitatively on real and toy data. Availability: Our implementation relying on PyTorch and Higra is available at https://github.com/hci-unihd/DTAE.
Fichier principal
Vignette du fichier
main.pdf (2.87 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03136103 , version 1 (10-02-2021)
hal-03136103 , version 2 (03-02-2022)
hal-03136103 , version 3 (19-04-2022)

Identifiants

Citer

Quentin Garrido, Sebastian Damrich, Alexander Jäger, Dario Cerletti, Manfred Claassen, et al.. Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder. Bioinformatics, 2022, Issue Supplement_1, 38, pp.i316--i324. ⟨10.1093/bioinformatics/btac249⟩. ⟨hal-03136103v3⟩
271 Consultations
252 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More