<mods:mods xmlns:mods="http://www.loc.gov/mods/v3" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.loc.gov/mods/v3 http://www.loc.gov/standards/mods/v3/mods-3-7.xsd"><mods:titleInfo><mods:title>Interrogating Cellular Heterogeneity with Traditional Machine Learning and Single-Cell Foundation Models</mods:title></mods:titleInfo><mods:typeOfResource authority="primo">dissertations</mods:typeOfResource><mods:name type="personal"><mods:namePart>Denadel, Alan</mods:namePart><mods:role><mods:roleTerm type="text">creator</mods:roleTerm></mods:role></mods:name><mods:name type="personal"><mods:namePart>Singh, Ritambhara</mods:namePart><mods:role><mods:roleTerm type="text">Reader</mods:roleTerm></mods:role></mods:name><mods:name type="personal"><mods:namePart>De Vito, Roberta</mods:namePart><mods:role><mods:roleTerm type="text">Reader</mods:roleTerm></mods:role></mods:name><mods:name type="personal"><mods:namePart>Crawford, Lorin</mods:namePart><mods:role><mods:roleTerm type="text">Advisor</mods:roleTerm></mods:role></mods:name><mods:name type="corporate"><mods:namePart>Brown University. Center for Computational Molecular Biology</mods:namePart><mods:role><mods:roleTerm type="text">sponsor</mods:roleTerm></mods:role></mods:name><mods:originInfo><mods:copyrightDate>2025</mods:copyrightDate></mods:originInfo><mods:physicalDescription><mods:extent>21, 210 p.</mods:extent><mods:digitalOrigin>born digital</mods:digitalOrigin></mods:physicalDescription><mods:note type="thesis">Thesis (Ph. D.)--Brown University, 2025</mods:note><mods:genre authority="aat">theses</mods:genre><mods:abstract>Over the last decade, there have been dramatic improvements in assays that can&#13;
measure RNA in single cells, collectively known as scRNA-seq. These methods have&#13;
revealed unexpected heterogeneity in populations of cells that were previously thought&#13;
to be homogeneous and have enabled researchers to study how genes are co-expressed in&#13;
various cell types and cell states, across both healthy and diseased cells. Understanding the&#13;
complex dynamics of how cells of various types are impacted by disease has the potential&#13;
to allow us to develop targeted therapies, but there are methodological challenges to doing&#13;
so accurately. It is important for computational tools to guide researchers down useful&#13;
research paths, rather than dead ends. There are now thousands of computational tools for&#13;
analyzing scRNA-seq data and so-called single-cell foundation models have been recently&#13;
developed that aim to pre-train on prior studies with the goal of improved performance&#13;
when fine-tuned on multiple downstream tasks. The statistical analysis of scRNA-seq&#13;
data often involves generating and testing hypotheses using the same data, known as&#13;
“double-dipping”, which produces highly inflated P -values and can lead to false discoveries.&#13;
This dissertation presents three contributions to the fast-moving field of scRNA-seq that&#13;
demonstrate its utility in biological discovery, solve a key computational step in the&#13;
analysis of scRNA-seq data, and evaluates the recently developed single-cell foundation&#13;
models. To be specific, this dissertation (1) shows the importance of measuring cell&#13;
state in pancreatic ductal adenocarcinoma and identifies cell states that modulate drug&#13;
resistance, (2) develops an algorithm for detecting distinct cell types and cell states in an&#13;
unsupervised fashion (while preventing over-clustering) by controlling for the phenomenon&#13;
of data “double-dipping”, and (3) evaluates the role of pre-training dataset size and&#13;
diversity on single-cell foundation model performance.analysis of scRNA-seq data,&#13;
and evaluates the recently developed single-cell foundation models. To be specific, this&#13;
dissertation (1) shows the importance of measuring cell state in pancreatic ductal&#13;
adenocarcinoma and identifies cell states that modulate drug resistance, (2) develops &#13;
an algorithm for detecting distinct cell types and cell states in an unsupervised fashion &#13;
(while preventing over-clustering) by controlling for the phenomenon of data “double-dipping”, &#13;
and (3) evaluates the role of pre-training dataset size and diversity on single-cell foundation&#13;
model performance.</mods:abstract><mods:subject><mods:topic>RNA sequencing</mods:topic></mods:subject><mods:subject><mods:topic>unsupervised clustering</mods:topic></mods:subject><mods:subject><mods:topic>pancreatic cancer</mods:topic></mods:subject><mods:subject><mods:topic>knockoffs</mods:topic></mods:subject><mods:language><mods:languageTerm authority="iso639-2b">English</mods:languageTerm></mods:language><mods:recordInfo><mods:recordContentSource authority="marcorg">RPB</mods:recordContentSource><mods:recordCreationDate encoding="iso8601">20250707</mods:recordCreationDate></mods:recordInfo></mods:mods>