Loading...

An Optimized Graph-Based Structure for Single-Cell RNA-Seq Cell-Type Classification Based on Nonlinear Dimension Reduction

Laghaee, Pouria | 2023

59 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56533 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Koohi, Somayyeh
  7. Abstract:
  8. As sequencing technologies have advanced in the field of single cells, it has become possible to investigate complex and rare cell populations and discover regulatory relationships between genes. The detection of rare cells has been greatly facilitated by this technology. However, due to the large volume of data and the complex and uncertain distribution of data, as well as the high rate of technical zeros, the analysis of single cell data clusters remains a computational and statistical challenge. Dimensionality reduction is a significant component of big data analysis. Machine learning methods provide the possibility of better analysis by reducing the non-linear dimensions of data. A graph neural network, one of the most popular methods in artificial intelligence, is useful for discovering intercellular relationships and increasing clustering accuracy. In the proposed method section, a model for single-cell data analysis based on non-linear dimensionality reduction methods and graph attention is presented. Using two consecutive units, an encoder based on MLP and a graph attention auto-encoder, to obtain cell embedding and gene embedding, the model can simultaneously achieve cell low-dimensional representation and clustering. Performing various examinations to obtain the optimal value for each parameter, the presented result is in its most optimal form. To evaluate the performance of the model, we performed it on several real scRNA-seq datasets for clustering and visualization analysis. The experimental results show that the model generally outperforms numerous popular single-cell analysis methods. As a result of using all available datasets, our model, in average, improves clustering accuracy by 4.4% in ARI Parameters over the well-known method scGAC. Also, the accuracy improvement of 11.65% is achieved by our model, compared to the Seurat model
  9. Keywords:
  10. Sequencing ; Nonlinear Dimension Reduction ; Clustering ; Graph Attention Networks ; Data Complex and Uncertain Distribution ; Single Cell RNA Sequencing (scRNA-seq)

 Digital Object List

 Bookmark

No TOC