본문

서브메뉴

Developing Differentiable Toolkits for Computational Biology
Developing Differentiable Toolkits for Computational Biology  / Seong Ho Pahng
Developing Differentiable Toolkits for Computational Biology

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260311091529.5
ISBN  
9798280710337
DDC  
001
저자명  
Ho Pahng, Seong
서명/저자  
Developing Differentiable Toolkits for Computational Biology / Seong Ho Pahng
발행사항  
[Sl] : Harvard University, 2025
형태사항  
1 electronic resource (128 pages)
주기사항  
Source: Dissertations Abstracts International, Volume: 86-12, Section: B.
주기사항  
Advisors: Hormoz, Sahand Committee members: Shakhnovich, Eugene; Mason, Jarad.
학위논문주기  
- Ph.D. : Harvard University, 2025.
초록/해제  
요약In any biological experiment, no matter how sophisticated, we capture only a small, noisy glimpse of a complex underlying process. For dry-lab researchers, interpreting these messy data raises a fundamental question: should one strive for a mechanistic understanding of the biological processes involved, or simply focus on data analysis for a specific task? This dissertation presents three computational tools that emerged from our attempt to strike a balance between these two extremes when modeling novel data.Chapter 1 presents two stochastic models that address the major contamination issues in probebased bacterial single-cell sequencing: spurious unique molecular identifier (UMI) counts and the difficulty of distinguishing genuine cellular signals from noise. By modeling two specific steps of the 10x sequencing pipeline, these methods accurately infer true UMI counts and identify real cells, enabling downstream single-cell analyses that revealed heterogeneous toxin expression in isogenic C. perfringens populations.Chapter 2 employs a deep learning technique to predict cellular responses in Perturb-seq experiments. We posit that the intermediate biological adaptations governing these responses are driven by gene regulatory networks composed of directed, nonreciprocal interactions. To model such interactions, we propose a novel directed graph neural network (CoED) along with a new Laplacian (Fuzzy graph Laplacian) that better captures directional effects. We show that learning both the edge directions and the CoED parameters simultaneously improves predictive performance over existing methods.Chapter 3 presents a differentiable in silico morphogenesis framework that learns to transform a spherical arrangement of point clouds into any desired 3D shape. To compare 3D objects in a manner invariant to index permutations, density, and orientation, we design a loss function that operates in the spectral domain. We also propose a neural network-based force model in which individual agents learn to interact so that, collectively, the system forms the target shape.
언어주기  
English
일반주제명  
Biology
일반주제명  
Applied mathematics
일반주제명  
Bioinformatics
키워드  
Computational tools
키워드  
Unique molecular identifier
키워드  
Single-cell sequencing
키워드  
Data analysis
기타저자  
Harvard University Chemistry and Chemical Biology
기본자료저록  
Dissertations Abstracts International. 86-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260311s2025        us                                    eng  d
■001000017357553
■00520260311091529.5
■006m          o    d                
■007cr|nu||||||||
■020    ▼a9798280710337
■040    ▼aMiAaPQD▼beng▼cMiAaPQD▼erda
■082    ▼a001
■1001  ▼aHo  Pahng,  Seong  ▼eauthor.▼0(orcid)0000-0002-9247-7425
■24510▼aDeveloping  Differentiable  Toolkits  for  Computational  Biology  ▼cSeong  Ho  Pahng
■260    ▼a[Sl]▼bHarvard  University▼c2025
■264  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a1  electronic  resource  (128  pages)
■336    ▼atext▼btxt▼2rdacontent
■337    ▼acomputer▼bc▼2rdamedia
■338    ▼aonline  resource▼bcr▼2rdacarrier
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-12,  Section:  B.
■500    ▼aAdvisors:  Hormoz,  Sahand    Committee  members:  Shakhnovich,  Eugene;  Mason,  Jarad.
■5021  ▼bPh.D.▼cHarvard  University▼d2025.
■520    ▼aIn  any  biological  experiment,  no  matter  how  sophisticated,  we  capture  only  a  small,  noisy  glimpse  of  a  complex  underlying  process.  For  dry-lab  researchers,  interpreting  these  messy  data  raises  a  fundamental  question:  should  one  strive  for  a  mechanistic  understanding  of  the  biological  processes  involved,  or  simply  focus  on  data  analysis  for  a  specific  task?  This  dissertation  presents  three  computational  tools  that  emerged  from  our  attempt  to  strike  a  balance  between  these  two  extremes  when  modeling  novel  data.Chapter  1  presents  two  stochastic  models  that  address  the  major  contamination  issues  in  probebased  bacterial  single-cell  sequencing:  spurious  unique  molecular  identifier  (UMI)  counts  and  the  difficulty  of  distinguishing  genuine  cellular  signals  from  noise.  By  modeling  two  specific  steps  of  the  10x  sequencing  pipeline,  these  methods  accurately  infer  true  UMI  counts  and  identify  real  cells,  enabling  downstream  single-cell  analyses  that  revealed  heterogeneous  toxin  expression  in  isogenic  C.  perfringens  populations.Chapter  2  employs  a  deep  learning  technique  to  predict  cellular  responses  in  Perturb-seq  experiments.  We  posit  that  the  intermediate  biological  adaptations  governing  these  responses  are  driven  by  gene  regulatory  networks  composed  of  directed,  nonreciprocal  interactions.  To  model  such  interactions,  we  propose  a  novel  directed  graph  neural  network  (CoED)  along  with  a  new  Laplacian  (Fuzzy  graph  Laplacian)  that  better  captures  directional  effects.  We  show  that  learning  both  the  edge  directions  and  the  CoED  parameters  simultaneously  improves  predictive  performance  over  existing  methods.Chapter  3  presents  a  differentiable  in  silico  morphogenesis  framework  that  learns  to  transform  a  spherical  arrangement  of  point  clouds  into  any  desired  3D  shape.  To  compare  3D  objects  in  a  manner  invariant  to  index  permutations,  density,  and  orientation,  we  design  a  loss  function  that  operates  in  the  spectral  domain.  We  also  propose  a  neural  network-based  force  model  in  which  individual  agents  learn  to  interact  so  that,  collectively,  the  system  forms  the  target  shape.
■546    ▼aEnglish
■590    ▼aSchool  code:  0084
■650  4▼aBiology
■650  4▼aApplied  mathematics
■650  4▼aBioinformatics
■653    ▼aComputational  tools
■653    ▼aUnique  molecular  identifier
■653    ▼aSingle-cell  sequencing
■653    ▼aData  analysis
■7102  ▼aHarvard  University▼bChemistry  and  Chemical  Biology.▼edegree  granting  institution.
■7201  ▼aHormoz,  Sahand▼edegree  supervisor.
■7730  ▼tDissertations  Abstracts  International▼g86-12B.
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357553▼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
    TF18161 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.