PuSH - Publikationsserver des Helmholtz Zentrums München

Zhang, Y.* ; Mezrag, L.* ; Sun, X.* ; Xu, C.* ; MacDonald, K.* ; Bhaskar, D.* ; Krishnaswamy, S.* ; Wolf, G. ; Rieck, B.

Principal curvatures estimation with applications to single cell data.

In: (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, 6-11 April 2025, Hyderabad). 2025. DOI: 10.1109/ICASSP49660.2025.10888433 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings)
Postprint DOI
The rapidly growing field of single-cell transcriptomic sequencing (scRNAseq) presents challenges for data analysis due to its massive datasets. A common method in manifold learning consists in hypothesizing that datasets lie on a lower dimensional manifold. This allows to study the geometry of point clouds by extracting meaningful descriptors like curvature. In this work, we will present Adaptive Local PCA (AdaL-PCA), a data-driven method for accurately estimating various notions of intrinsic curvature on data manifolds, in particular principal curvatures for surfaces. The model relies on local PCA to estimate the tangent spaces. The evaluation of AdaL-PCA on sampled surfaces shows state-of-the-art results. Combined with a PHATE embedding, the model applied to single-cell RNA sequencing data allows us to identify key variations in the cellular differentiation.
Altmetric
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Korrespondenzautor
Schlagwörter Gaussian Curvature ; Principal Curvature ; Principal Directions ; Single-cell
ISSN (print) / ISBN 1520-6149
Konferenztitel ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Konferzenzdatum 6-11 April 2025
Konferenzort Hyderabad
Nichtpatentliteratur Publikationen
Institut(e) Institute of AI for Health (AIH)