Visualizing High-Dimensional Single-Cell RNA-seq Data via Random Projections and Geodesic Distances
Ημερομηνία
2019Γλώσσα
en
Λέξη-κλειδί
Επιτομή
The recent advent in Next Generation Sequencing has created a huge data source which offers a great potential for elucidating complex disease mechanisms and biological processes. A recent technology is the single-cell RNA sequencing, which allows transcriptomics measurements in individual cells, having promising results. However, such studies measure the entire genome for thousands of cells, creating datasets with extremely high dimensionality and complexity. Following this perspective, we propose a dimensionality reduction approach, called RGt-SNE, which visualizes single-cell RNA-seq data in two dimensions. Initially, RGt-SNE defines a cell-cell distance matrix based on Random Projections and Geodesic Distances. The first is used to define the pairwise cells distances in a low dimensional projected space avoiding the difficulties that exist in data with ultra-high dimensionality. The latter is used to better define the large pairwise cells distances. Subsequently, the t-SNE method is applied in the customized distance matrix for two dimensional visualization. RGt-SNE was evaluated in two real experimental single-cell RNA-seq data against three well-known methods, such as t-SNE, Multidimensional scaling, and ISOMAP. Outcomes provide the superiority of RGt-SNE suggesting it as a reliable tool for single-cell RNA-seq data analysis and visualization. © 2019 IEEE.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Recent Dimensionality Reduction Techniques for High-Dimensional COVID-19 Data
Dallas I.L., Vrahatis A.G., Tasoulis S.K., Plagianakos V.P. (2022)We are going through the last years of the COVID-19 pandemic, where almost the entire research community has focused on the challenges that constantly arise. From the computational and mathematical perspective, we have to ... -
Towards the mathematic formalization of parametric generalized cylinders and initial results in modeling 3D image data
Kechriniotis, A. I.; Delibasis, K. K.; Tsonos, C.; Assimakis, N.; Asvestas, P. (2009)Generalized cylinders (GCs) have been proposed in computer vision for object modeling in two dimensional images. However approaches so far have not investigated closed form solutions, based on a formal generic definition ... -
Comparison of 3D ultrasound, 2D ultrasound and 3D Doppler in the diagnosis of endometrial carcinoma in patients with uterine bleeding: A systematic review and meta-analysis
Xydias E.M., Kalantzi S., Tsakos E., Ntanika A., Beis N., Prior M., Daponte A., Ziogas A.C. (2022)Endometrial cancer is a common malignancy affecting women worldwide. Usually, it clinically manifests with uterine bleeding, although identical clinical manifestations occur in benign conditions as well, with several ...