h1

% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@PHDTHESIS{Li:850942,
      author       = {Li, Zhijian},
      othercontributors = {Berlage, Thomas and Filho, Ivan Gesteira Costa and Schaub,
                          Michael Thomas},
      title        = {{C}omputational method for single cell {ATAC}-seq
                      imputation and dimensionality reduction},
      school       = {RWTH Aachen University},
      type         = {Dissertation},
      address      = {Aachen},
      publisher    = {RWTH Aachen University},
      reportid     = {RWTH-2022-07834},
      pages        = {1 Online-Ressource : Illustrationen, Diagramme},
      year         = {2022},
      note         = {Englische und deutsche Zusammenfassung. - Veröffentlicht
                      auf dem Publikationsserver der RWTH Aachen University;
                      Dissertation, RWTH Aachen University, 2022},
      abstract     = {Chromatin accessibility, or the physical access to
                      chromatinized DNA, plays an essential role in controlling
                      the temporal and spatial expression of genes in eukaryotic
                      cells. Assay for transposase- accessible chromatin followed
                      by high throughput sequencing (ATAC-seq) is a sensitive and
                      straight- forward protocol for profiling chromatin
                      accessibility in a genome-wide manner. Moreover, combined
                      with single-cell sequencing technology, the single-cell
                      ATAC-seq (scATAC-seq) is able to map reg- ulatory variation
                      from hundreds to thousands of cells at single-cell
                      resolution, further expanding its applications. However, a
                      major drawback of scATAC-seq data is its inherent sparsity.
                      In other words, many open chromatin regions are not detected
                      due to low input or loss of DNA material in the scATAC-seq
                      experiment, leaving a large number of missing values in the
                      derived count matrix. Such a phenomenon is known as
                      “drop-outs” and is also observed in other single-cell
                      sequencing data, such as scRNA- seq. Although many
                      computational methods have been proposed to address this
                      issue for scRNA-seq based on data imputation or denoising,
                      there is a substantial lack of efforts to assess the
                      usability of these methods on scATAC-seq data. Moreover, the
                      development of specific algorithms for imputing or denoising
                      scATAC-seq is still poorly explored yet.Another critical
                      issue when dealing with the scATAC-seq matrix is the high
                      dimensionality. Be- cause a gene is often regulated by
                      multiple cis-regulatory elements (CREs), the number of
                      features in scATAC-seq (i.e., peaks) is usually one order
                      magnitude higher compared with the number of features in
                      scRNA-seq (i.e., genes). This high dimensionality poses a
                      challenge for the analysis of scATAC-seq, such as clustering
                      and visualization. Therefore, it is a common option to first
                      perform dimensionality reduction prior to interpreting the
                      data. However, the standard computational meth- ods for
                      scRNA-seq data are potentially unsuitable for this task due
                      to the low-count information of scATAC-seq data, i.e., a
                      maximum of 2 digestion events is expected for an individual
                      cell in a specific open chromatin region.In this thesis, we
                      propose scOpen, a computation approach for simultaneous
                      quantification of single-cell open chromatin status and
                      reduction of the dimensionality, to address the
                      aforementioned issues for scATAC-seq data analysis. More
                      formally, scOpen performs imputation and denoising of a
                      scATAC-seq matrix via regularized non-negative matrix
                      factorization (NMF) based on term frequency-inverse document
                      frequency (TF-IDF) transformation. We show that scOpen is
                      able to improve several crucial downstream analysis steps of
                      scATAC-seq data, such as clustering, visualization,
                      cis-regulatory DNA interactions and delineation of
                      regulatory features. Moreover, we also demonstrate its power
                      to dissect chromatin accessibility dynamics on large-scale
                      scATAC-seq data from intact mouse kidney tissue. Finally, we
                      perform additional analyses to investigate the regulatory
                      programs that drive the development of kidney fibrosis. Our
                      analyses shed novel light on mechanisms of myofibroblasts
                      differentiation driving kidney fibrosis and chronic kidney
                      disease (CKD). Altogether, these results demonstrate that
                      scOpen is a useful computational approach in biological
                      studies involving single-cell open chromatin data
                      processing.},
      cin          = {122620 / 120000},
      ddc          = {004},
      cid          = {$I:(DE-82)122620_20140620$ / $I:(DE-82)120000_20140620$},
      typ          = {PUB:(DE-HGF)11},
      doi          = {10.18154/RWTH-2022-07834},
      url          = {https://publications.rwth-aachen.de/record/850942},
}