Visualizing hierarchies in scRNA-seq data using a density tree-biased autoencoder
Autor: | Quentin Garrido, Sebastian Damrich, Alexander Jäger, Dario Cerletti, Manfred Claassen, Laurent Najman, Fred A Hamprecht |
---|---|
Přispěvatelé: | Laboratoire d'Informatique Gaspard-Monge (LIGM), École des Ponts ParisTech (ENPC)-Centre National de la Recherche Scientifique (CNRS)-Université Gustave Eiffel, Heidelberg Collaboratory for Image Processing (HCI), Universität Heidelberg [Heidelberg], Institute of Microbiology, Department of Biology, ETH Zurich, Institute of Microbiology, Universitätsklinikum Tübingen - University Hospital of Tübingen, Eberhard Karls Universität Tübingen = Eberhard Karls University of Tuebingen |
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
Statistics and Probability
FOS: Computer and information sciences Sequence Analysis RNA Gene Expression Profiling Computer Science - Neural and Evolutionary Computing [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE] Biochemistry Quantitative Biology - Quantitative Methods Computer Science Applications Computational Mathematics Computational Theory and Mathematics FOS: Biological sciences Exome Sequencing Neural and Evolutionary Computing (cs.NE) Single-Cell Analysis [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM] Molecular Biology Software Quantitative Methods (q-bio.QM) |
Zdroj: | Bioinformatics Bioinformatics, Oxford University Press (OUP), In press |
ISSN: | 1367-4803 1367-4811 |
Popis: | Motivation Single-cell RNA sequencing (scRNA-seq) allows studying the development of cells in unprecedented detail. Given that many cellular differentiation processes are hierarchical, their scRNA-seq data are 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 maximum spanning tree on a vector quantization of the data and show that it captures biological information well. We then introduce density-tree biased autoencoder (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 and implementation Our implementation relying on PyTorch and Higra is available at github.com/hci-unihd/DTAE. Supplementary information Supplementary data are available at Bioinformatics online. |
Databáze: | OpenAIRE |
Externí odkaz: |