본문

서브메뉴

Biologically Motivated Artificial Intelligence for Explainable Gene Regulatory Dynamics
Biologically Motivated Artificial Intelligence for Explainable Gene Regulatory Dynamics
Biologically Motivated Artificial Intelligence for Explainable Gene Regulatory Dynamics

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20250211151455
ISBN  
9798382785189
DDC  
574
저자명  
Hossain, Intekhab.
서명/저자  
Biologically Motivated Artificial Intelligence for Explainable Gene Regulatory Dynamics
발행사항  
[Sl] : Harvard University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
205 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
주기사항  
Advisor: Quackenbush, John.
학위논문주기  
Thesis (Ph.D.)--Harvard University, 2024.
초록/해제  
요약Models that are formulated as ordinary differential equations (ODEs) can accurately explain temporal gene expression patterns and promise to yield new insights into important cellular processes, disease progression, and intervention design. Learning such ODEs is challenging, since we want to predict the evolution of gene expression in a way that accurately encodes the causal gene-regulatory network (GRN) governing the dynamics and the nonlinear functional relationships between genes. Most widely used ODE estimation methods either impose too many parametric restrictions or are not guided by meaningful biological insights, both of which impedes scalability and/or explainability. To overcome these limitations, we developed PHOENIX, a modeling framework based on neural ordinary differential equations (NeuralODEs) and Hill-Langmuir kinetics, that can flexibly incorporate prior domain knowledge and biological constraints to promote sparse, biologically interpretable representations of ODEs. We test accuracy of PHOENIX in a series of in silico experiments benchmarking it against several currently used tools for ODE estimation. We also demonstrate PHOENIX's flexibility by studying oscillating expression data from synchronized yeast cells and assess its scalability by modelling genome-scale breast cancer expression for samples ordered in pseudotime. Finally, we show how the combination of user-defined prior knowledge and functional forms from systems biology allows PHOENIX to encode key properties of the underlying GRN, and subsequently predict expression patterns in a biologically explainable way. Having developed and validated PHOENIX, we next attempt to obtain very sparse representations of the PHOENIX model in order to aid interpretability. To this end, we explore the field of neural network sparsification and the Lottery Ticket Hypothesis (LTH). We argue how the goal of sparsity needs to be conceptualized conjunctively with the goal of biological meaning, and how traditional approaches of sparsification, such as iterative magnitude pruning, fail to bridge these two objectives. We conjecture that biologically meaningful representations can be obtained by leveraging domain knowledge in the sparsification process. This motivates the formulation of DASH, a domain-aware neural network pruning strategy. We use DASH to engineer an algorithm for pruning PHOENIX and demonstrate how this leads to biologically anchored sparsification in silico. We benchmark DASH against other sparsification strategies on both simulated and real world data. Finally, we apply PHOENIX and DASH to three different case studies in order to demonstrate how our tools can be used to understand gene regulation in the context of lung adenocarcinoma, hematopoietic stem cell differentiation, and Rituximab-treated in B cells.
일반주제명  
Biostatistics
일반주제명  
Biophysics
일반주제명  
Computer science
일반주제명  
Biology
일반주제명  
Genetics
키워드  
Gene expression
키워드  
Ordinary differential equations
키워드  
B cells
키워드  
Neural network
키워드  
Breast cancer
기타저자  
Harvard University Biostatistics
기본자료저록  
Dissertations Abstracts International. 85-12B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161863
■00520250211151455
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382785189
■035    ▼a(MiAaPQ)AAI31297033
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a574
■1001  ▼aHossain,  Intekhab.▼0(orcid)0000-0003-0895-8128
■24510▼aBiologically  Motivated  Artificial  Intelligence  for  Explainable  Gene  Regulatory  Dynamics
■260    ▼a[Sl]▼bHarvard  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a205  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-12,  Section:  B.
■500    ▼aAdvisor:  Quackenbush,  John.
■5021  ▼aThesis  (Ph.D.)--Harvard  University,  2024.
■520    ▼aModels  that  are  formulated  as  ordinary  differential  equations  (ODEs)  can  accurately  explain  temporal  gene  expression  patterns  and  promise  to  yield  new  insights  into  important  cellular  processes,  disease  progression,  and  intervention  design.  Learning  such  ODEs  is  challenging,  since  we  want  to  predict  the  evolution  of  gene  expression  in  a  way  that  accurately  encodes  the  causal  gene-regulatory  network  (GRN)  governing  the  dynamics  and  the  nonlinear  functional  relationships  between  genes.  Most  widely  used  ODE  estimation  methods  either  impose  too  many  parametric  restrictions  or  are  not  guided  by  meaningful  biological  insights,  both  of  which  impedes  scalability  and/or  explainability.  To  overcome  these  limitations,  we  developed  PHOENIX,  a  modeling  framework  based  on  neural  ordinary  differential  equations  (NeuralODEs)  and  Hill-Langmuir  kinetics,  that  can  flexibly  incorporate  prior  domain  knowledge  and  biological  constraints  to  promote  sparse,  biologically  interpretable  representations  of  ODEs.  We  test  accuracy  of  PHOENIX  in  a  series  of  in  silico  experiments  benchmarking  it  against  several  currently  used  tools  for  ODE  estimation.  We  also  demonstrate  PHOENIX's  flexibility  by  studying  oscillating  expression  data  from  synchronized  yeast  cells  and  assess  its  scalability  by  modelling  genome-scale  breast  cancer  expression  for  samples  ordered  in  pseudotime.  Finally,  we  show  how  the  combination  of  user-defined  prior  knowledge  and  functional  forms  from  systems  biology  allows  PHOENIX  to  encode  key  properties  of  the  underlying  GRN,  and  subsequently  predict  expression  patterns  in  a  biologically  explainable  way.  Having  developed  and  validated  PHOENIX,  we  next  attempt  to  obtain  very  sparse  representations  of  the  PHOENIX  model  in  order  to  aid  interpretability.  To  this  end,  we  explore  the  field  of  neural  network  sparsification  and  the  Lottery  Ticket  Hypothesis  (LTH).  We  argue  how  the  goal  of  sparsity  needs  to  be  conceptualized  conjunctively  with  the  goal  of  biological  meaning,  and  how  traditional  approaches  of  sparsification,  such  as  iterative  magnitude  pruning,  fail  to  bridge  these  two  objectives.  We  conjecture  that  biologically  meaningful  representations  can  be  obtained  by  leveraging  domain  knowledge  in  the  sparsification  process.  This  motivates  the  formulation  of  DASH,  a  domain-aware  neural  network  pruning  strategy.  We  use  DASH  to  engineer  an  algorithm  for  pruning  PHOENIX  and  demonstrate  how  this  leads  to  biologically  anchored  sparsification  in  silico.  We  benchmark  DASH  against  other  sparsification  strategies  on  both  simulated  and  real  world  data.  Finally,  we  apply  PHOENIX  and  DASH  to  three  different  case  studies  in  order  to  demonstrate  how  our  tools  can  be  used  to  understand  gene  regulation  in  the  context  of  lung  adenocarcinoma,  hematopoietic  stem  cell  differentiation,  and  Rituximab-treated  in  B  cells.
■590    ▼aSchool  code:  0084.
■650  4▼aBiostatistics
■650  4▼aBiophysics
■650  4▼aComputer  science
■650  4▼aBiology
■650  4▼aGenetics
■653    ▼aGene  expression
■653    ▼aOrdinary  differential  equations
■653    ▼aB  cells
■653    ▼aNeural  network
■653    ▼aBreast  cancer
■690    ▼a0308
■690    ▼a0786
■690    ▼a0984
■690    ▼a0306
■690    ▼a0369
■71020▼aHarvard  University▼bBiostatistics.
■7730  ▼tDissertations  Abstracts  International▼g85-12B.
■790    ▼a0084
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161863▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    Подробнее информация.

    • Бронирование
    • не существует
    • моя папка
    • Первый запрос зрения
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    материал
    Reg No. Количество платежных Местоположение статус Ленд информации
    TF13953 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Бронирование доступны в заимствований книги. Чтобы сделать предварительный заказ, пожалуйста, нажмите кнопку бронирование

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.