서브메뉴
검색
Machine Learning Approaches to Decode Aging at Spatial and Single-Cell Resolution
Machine Learning Approaches to Decode Aging at Spatial and Single-Cell Resolution
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202103638
- ISBN
- 9798290625119
- DDC
- 591
- 저자명
- Sun, Eric David.
- 서명/저자
- Machine Learning Approaches to Decode Aging at Spatial and Single-Cell Resolution
- 발행사항
- [Sl] : Stanford University, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 347 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-01, Section: B.
- 주기사항
- Advisor: Brunet, Anne;Zou, James.
- 학위논문주기
- Thesis (Ph.D.)--Stanford University, 2025.
- 초록/해제
- 요약Aging is one of the greatest risk factors for disease. However, the biology underlying aging is incredibly complex with a multitude of changes occurring across all cells, tissues, and organs. My work is focused on developing computational and machine learning tools to understand the complex biology of aging, particularly in the context of spatial and single-cell omics. High-dimensional biological readouts such as those obtained from spatial and single-cell omics have become increasingly prevalent in the study of complex biological processes such as brain aging. Here, I will present the development of machine learning models for quantifying aging at spatial and single-cell resolution. These single-cell and spatial ``aging clocks" are developed using spatially resolved single-cell transcriptomics data from the brain and can provide a high-resolution profile of how diverse interventions impact the aging of different cells and brain regions. In particular, spatial aging clocks reveal that some rare cell types, T cells and neural stem cells, can have dramatic effects on the aging of nearby cells, suggesting a potential avenue for modulating brain aging.I will also present a set of computational methods with broad applications in the analysis of high-dimensional biological data. First, I will introduce TISSUE, a method for uncertainty-calibrated prediction of spatially resolved single-cell transcriptomics, and its use in improving the outputs of common downstream analysis tasks. Then, I will present SPRITE, a method that improves the imputation of spatial gene expression by leveraging spatial and gene correlation structure to propagate information across cells and genes. Finally, I will discuss DynamicViz, a meta-algorithm for building more reliable visualizations of high-dimensional data with potential applications in multiple domains of biomedical research.In summary, my work develops new computational and machine learning methods for analyzing high-dimensional datasets to understand complex biology such as that underlying aging.
- 일반주제명
- Neurons
- 일반주제명
- Gene expression
- 일반주제명
- Aging
- 일반주제명
- Lymphocytes
- 일반주제명
- Data processing
- 일반주제명
- Visualization
- 일반주제명
- Reproducibility
- 일반주제명
- Cell cycle
- 기타저자
- Stanford University.
- 기본자료저록
- Dissertations Abstracts International. 87-01B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017358060
■00520260202103638
■006m o d
■007cr#unu||||||||
■020 ▼a9798290625119
■035 ▼a(MiAaPQ)AAI32090134
■035 ▼a(MiAaPQ)Stanfordhh922zv9189
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a591
■1001 ▼aSun, Eric David.
■24510▼aMachine Learning Approaches to Decode Aging at Spatial and Single-Cell Resolution
■260 ▼a[Sl]▼bStanford University▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a347 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-01, Section: B.
■500 ▼aAdvisor: Brunet, Anne;Zou, James.
■5021 ▼aThesis (Ph.D.)--Stanford University, 2025.
■520 ▼aAging is one of the greatest risk factors for disease. However, the biology underlying aging is incredibly complex with a multitude of changes occurring across all cells, tissues, and organs. My work is focused on developing computational and machine learning tools to understand the complex biology of aging, particularly in the context of spatial and single-cell omics. High-dimensional biological readouts such as those obtained from spatial and single-cell omics have become increasingly prevalent in the study of complex biological processes such as brain aging. Here, I will present the development of machine learning models for quantifying aging at spatial and single-cell resolution. These single-cell and spatial ``aging clocks" are developed using spatially resolved single-cell transcriptomics data from the brain and can provide a high-resolution profile of how diverse interventions impact the aging of different cells and brain regions. In particular, spatial aging clocks reveal that some rare cell types, T cells and neural stem cells, can have dramatic effects on the aging of nearby cells, suggesting a potential avenue for modulating brain aging.I will also present a set of computational methods with broad applications in the analysis of high-dimensional biological data. First, I will introduce TISSUE, a method for uncertainty-calibrated prediction of spatially resolved single-cell transcriptomics, and its use in improving the outputs of common downstream analysis tasks. Then, I will present SPRITE, a method that improves the imputation of spatial gene expression by leveraging spatial and gene correlation structure to propagate information across cells and genes. Finally, I will discuss DynamicViz, a meta-algorithm for building more reliable visualizations of high-dimensional data with potential applications in multiple domains of biomedical research.In summary, my work develops new computational and machine learning methods for analyzing high-dimensional datasets to understand complex biology such as that underlying aging.
■590 ▼aSchool code: 0212.
■650 4▼aNeurons
■650 4▼aGene expression
■650 4▼aAging
■650 4▼aLymphocytes
■650 4▼aData processing
■650 4▼aVisualization
■650 4▼aReproducibility
■650 4▼aCell cycle
■690 ▼a0493
■690 ▼a0800
■71020▼aStanford University.
■7730 ▼tDissertations Abstracts International▼g87-01B.
■790 ▼a0212
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17358060▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
