DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Chun, Hyonho | - |
dc.contributor.advisor | 전현호 | - |
dc.contributor.author | Jee, Dong Jun | - |
dc.date.accessioned | 2023-06-23T19:31:56Z | - |
dc.date.available | 2023-06-23T19:31:56Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008300&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308922 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 수리과학과, 2022.8,[iii, 22 p. :] | - |
dc.description.abstract | Single-cell RNA sequencing is used to analyze the gene expression data of individual cells, thereby adding to existing knowledge of biological phenomena. Accordingly, this technology is widely used in numerous biomedical studies. Recently, the variational autoencoder has emerged and has been adopted for the analysis of single-cell data owing to its high capacity to manage large-scale data. Many different variants of the variational autoencoder have been applied, and have yielded superior results. However, because it is nonlinear, the model does not provide parameters that can be used to explain the underlying biological patterns. In this thesis, we propose an interpretable nonnegative matrix factorization method that decomposes parameters into those shared across cells and those that are cell-specific. Effective nonlinear dimension reduction was achieved via a variational autoencoder applied to the cell-specific parameters. In addition to achieving nonlinear dimension reduction, our model could estimate the cell-type-specific gene expression. To improve the estimation accuracy, we introduced log-regularization, which reflects the single-cell property. Overall, our approach displayed excellent performance in a simulation study and in real data analyses, while maintaining good biological interpretability. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep neural networks▼aNonlinear dimension reduction▼aNonnegative matrix factorization▼aVariational autoencoder▼aClustering▼aSingle-cell RNA sequencing data | - |
dc.subject | 심층신경망▼a비선형 차원 축소▼a비음수 행렬 분해▼a변분 오토인코더▼a군집화▼a단일 세포 리보핵산 시퀀싱 데이터 | - |
dc.title | Deep nonnegative matrix factorization using a variational autoencoder with application to single-cell RNA sequencing data | - |
dc.title.alternative | 단일 세포 리보핵산 시퀀싱 데이터에 적용되는 변분 오토인코더를 사용한 심층 비음수 행렬 분해 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :수리과학과, | - |
dc.contributor.alternativeauthor | 지동준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.