본문

서브메뉴

Contextual Learning on Graphs for Precision Medicine
Contextual Learning on Graphs for Precision Medicine
Contextual Learning on Graphs for Precision Medicine

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152827
ISBN  
9798346567400
DDC  
574
저자명  
Li, Michelle M.
서명/저자  
Contextual Learning on Graphs for Precision Medicine
발행사항  
[Sl] : Harvard University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
371 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-05, Section: B.
주기사항  
Advisor: Zitnik, Marinka.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2024.
초록/해제  
요약Precision medicine requires reasoning over interconnected data across multiple modalities to tailor medical decisions based on the context of individual patients. Graphs---or networks---are universal descriptors for systems of interacting elements, and deep learning on biomedical graphs has facilitated advancements in medicine, including accelerated disease gene prioritization and drug target identification. However, existing graph-based models are context-free: unable to adjust their outputs based on the contexts in which they operate. This PhD dissertation innovates two fundamental contextual learning algorithms, SHEPHERD and PINNACLE, to tackle medical questions for which patient and cell type contexts, respectively, are important. SHEPHERD addresses the challenge of low sample sizes among rare diseases by infusing patient data with external biomedical knowledge. It considers individual patients as unique subgraphs in a rare disease knowledge graph to learn patient-specific contexts derived from relationships such as genotype-phenotype and disease-gene associations, phenotype ontology, and genetic pathways. SHEPHERD's contextualized patient representations are optimized for multi-faceted rare disease diagnosis: performing causal gene discovery, retrieving "patients-like-me" with the same causal gene or disease, and providing interpretable characterizations of novel disease presentations. PINNACLE leverages cell-type-specific gene expression as well as cellular and tissue organization to resolve the role of a protein depending on the cell type context. It generates unique protein representations for every cell type context using cell-type-specific protein interaction networks constructed from single-cell transcriptomic atlases, and enforces the global organization of these representations with a metagraph of cell type communication and tissue hierarchy. PINNACLE's context-aware protein representations enable the analysis of drug effects across cell type contexts and the prediction of therapeutic targets in a cell-type-specific manner. Overall, this PhD dissertation pioneers the development of contextualized models to empower precision medicine, from rare disease diagnosis to drug discovery.
일반주제명  
Bioinformatics
일반주제명  
Computer science
일반주제명  
Health sciences
키워드  
Contextual learning
키워드  
Drug discovery
키워드  
Graph machine learning
키워드  
Precision medicine
키워드  
Rare disease diagnosis
키워드  
Single-cell transcriptomics
기타저자  
Harvard University Medical Sciences
기본자료저록  
Dissertations Abstracts International. 86-05B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017164061
■00520250211152827
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798346567400
■035    ▼a(MiAaPQ)AAI31560251
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a574
■1001  ▼aLi,  Michelle  M.▼0(orcid)0000-0003-0223-7485
■24510▼aContextual  Learning  on  Graphs  for  Precision  Medicine
■260    ▼a[Sl]▼bHarvard  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a371  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-05,  Section:  B.
■500    ▼aAdvisor:  Zitnik,  Marinka.
■5021  ▼aThesis  (Ph.D.)--Harvard  University,  2024.
■520    ▼aPrecision  medicine  requires  reasoning  over  interconnected  data  across  multiple  modalities  to  tailor  medical  decisions  based  on  the  context  of  individual  patients.  Graphs---or  networks---are  universal  descriptors  for  systems  of  interacting  elements,  and  deep  learning  on  biomedical  graphs  has  facilitated  advancements  in  medicine,  including  accelerated  disease  gene  prioritization  and  drug  target  identification.  However,  existing  graph-based  models  are  context-free:  unable  to  adjust  their  outputs  based  on  the  contexts  in  which  they  operate.  This  PhD  dissertation  innovates  two  fundamental  contextual  learning  algorithms,  SHEPHERD  and  PINNACLE,  to  tackle  medical  questions  for  which  patient  and  cell  type  contexts,  respectively,  are  important.  SHEPHERD  addresses  the  challenge  of  low  sample  sizes  among  rare  diseases  by  infusing  patient  data  with  external  biomedical  knowledge.  It  considers  individual  patients  as  unique  subgraphs  in  a  rare  disease  knowledge  graph  to  learn  patient-specific  contexts  derived  from  relationships  such  as  genotype-phenotype  and  disease-gene  associations,  phenotype  ontology,  and  genetic  pathways.  SHEPHERD's  contextualized  patient  representations  are  optimized  for  multi-faceted  rare  disease  diagnosis:  performing  causal  gene  discovery,  retrieving  "patients-like-me"  with  the  same  causal  gene  or  disease,  and  providing  interpretable  characterizations  of  novel  disease  presentations.  PINNACLE  leverages  cell-type-specific  gene  expression  as  well  as  cellular  and  tissue  organization  to  resolve  the  role  of  a  protein  depending  on  the  cell  type  context.  It  generates  unique  protein  representations  for  every  cell  type  context  using  cell-type-specific  protein  interaction  networks  constructed  from  single-cell  transcriptomic  atlases,  and  enforces  the  global  organization  of  these  representations  with  a  metagraph  of  cell  type  communication  and  tissue  hierarchy.  PINNACLE's  context-aware  protein  representations  enable  the  analysis  of  drug  effects  across  cell  type  contexts  and  the  prediction  of  therapeutic  targets  in  a  cell-type-specific  manner.  Overall,  this  PhD  dissertation  pioneers  the  development  of  contextualized  models  to  empower  precision  medicine,  from  rare  disease  diagnosis  to  drug  discovery.
■590    ▼aSchool  code:  0084.
■650  4▼aBioinformatics
■650  4▼aComputer  science
■650  4▼aHealth  sciences
■653    ▼aContextual  learning
■653    ▼aDrug  discovery
■653    ▼aGraph  machine  learning
■653    ▼aPrecision  medicine
■653    ▼aRare  disease  diagnosis
■653    ▼aSingle-cell  transcriptomics
■690    ▼a0715
■690    ▼a0984
■690    ▼a0566
■71020▼aHarvard  University▼bMedical  Sciences.
■7730  ▼tDissertations  Abstracts  International▼g86-05B.
■790    ▼a0084
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17164061▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF10378 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.