phd_thesis/tex/thesis.tex

% \documentclass[twocolumn]{article}
\documentclass{report}
% TODO I want to keep figures in each subsection, which this doesn't do
\usepackage[section]{placeins}
\usepackage[top=1in,left=1.5in,right=1in,bottom=1in]{geometry}
\usepackage{siunitx}
\usepackage{multicol}
\setlength{\columnsep}{1cm}
\usepackage[acronym]{glossaries}
\usepackage[T1]{fontenc}
\usepackage{enumitem}
\usepackage{titlesec}
\usepackage{titlecaps}
\usepackage{upgreek}
\usepackage{graphicx}
\usepackage{subcaption}
\usepackage{nth}
\usepackage[capitalize]{cleveref}
\usepackage[version=4]{mhchem}
\usepackage{pgfgantt}
\usepackage{setspace}

% TODO glossary can't apparently be used in section header (even thought it
% would be nice)

\doublespacing{}

\titleformat{\chapter}[block]{\filcenter\bfseries\large}
{\MakeUppercase{\chaptertitlename} \thechapter: }{0pt}{\uppercase}
% \titleformat{\chapter}[block]{\filcenter\bfseries\large}{}{0pt}{\uppercase}
\titleformat{\section}[block]{\bfseries\large}{}{0pt}{\titlecap}
\titleformat{\subsection}[block]{\itshape\large}{}{0pt}{\titlecap}
\titleformat{\subsubsection}[runin]{\bfseries\itshape\/}{}{0pt}{\titlecap}

\setlist[description]{font=$\bullet$~\textbf\normalfont}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% acronyms for the lazy

\renewcommand{\glossarysection}[2][]{} % remove glossary title
\makeglossaries
\newacronym{act}{ACT}{adoptive cell therapies}
\newacronym{qc}{QC}{quality control}
\newacronym{tcm}{T\textsubscript{cm}}{central memory T cell}
\newacronym{tscm}{T\textsubscript{scm}}{stem-memory T cell}
\newacronym{car}{CAR}{chimeric antigen receptor}
\newacronym[longplural={monoclonal antibodies}]{mab}{mAb}{monoclonal antibody}
\newacronym{ecm}{ECM}{extracellular matrix}
\newacronym{cqa}{CQA}{critical quality attribute}
\newacronym{cpp}{CPP}{critical process parameter}
\newacronym{dms}{DMS}{degradable microscaffold}
\newacronym{doe}{DOE}{design of experiments}
\newacronym{adoe}{ADOE}{adaptive design of experiments}
\newacronym{gmp}{GMP}{Good Manufacturing Practices}
\newacronym{cho}{CHO}{Chinese hamster ovary}
\newacronym{all}{ALL}{acute lymphoblastic leukemia}
\newacronym{pdms}{PDMS}{polydimethylsiloxane}
\newacronym{dc}{DC}{dendritic cell}
\newacronym{il2}{IL2}{interleukin 2}
\newacronym{il15}{IL15}{interleukin 15}
\newacronym{il15r}{IL15R}{interleukin 15 receptor}
\newacronym{rhil2}{rhIL2}{recombinant human interleukin 2}
\newacronym{apc}{APC}{antigen presenting cell}
\newacronym{mhc}{MHC}{major histocompatibility complex}
\newacronym{elisa}{ELISA}{enzyme-linked immunosorbent assay}
\newacronym{nmr}{NMR}{nuclear magnetic resonance}
\newacronym{haba}{HABA}{4-hydroxyazobenene-2-carboxylic-acid}
\newacronym{pbs}{PBS}{phosphate buffered saline}
\newacronym{bca}{BCA}{bicinchoninic acid assay}
\newacronym{bsa}{BSA}{bovine serum albumin}
\newacronym{hsa}{HSA}{human serum albumin}
\newacronym{stp}{STP}{streptavidin}
\newacronym{stppe}{STP-PE}{streptavidin-phycoerythrin}
\newacronym{snb}{SNB}{sulfo-nhs-biotin}
\newacronym{cug}{CuG}{Cultispher G}
\newacronym{cus}{CuS}{Cultispher S}
\newacronym{pbmc}{PBMC}{peripheral blood mononuclear cells}
\newacronym{macs}{MACS}{magnetic activated cell sorting}
\newacronym{aopi}{AO/PI}{acridine orange/propidium iodide}
\newacronym{igg}{IgG}{immunoglobulin G}
\newacronym{pe}{PE}{phycoerythrin}
\newacronym{fitc}{FITC}{Fluorescein}
\newacronym{fitcbt}{FITC-BT}{Fluorescein-biotin}
\newacronym{ptnl}{PTN-L}{Protein L}
\newacronym{af647}{AF647}{Alexa Fluor 647}
\newacronym{anova}{ANOVA}{analysis of variance}
\newacronym{crispr}{CRISPR}{clustered regularly interspaced short
  palindromic repeats}
\newacronym{mtt}{MTT}{3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide}
\newacronym{bmi}{BMI}{body mass index}
\newacronym{a2b1}{A2B1}{integrin $\upalpha$1$\upbeta$1}
\newacronym{a2b2}{A2B2}{integrin $\upalpha$1$\upbeta$2}
\newacronym{til}{TIL}{tumor infiltrating lymphocytes}
\newacronym{nsg}{NSG}{NOD scid gamma}
\newacronym{colb}{COL-B}{collagenase B}
\newacronym{cold}{COL-D}{collagenase D}
\newacronym{tsne}{tSNE}{t-stochastic neighbor embedding}
\newacronym{anv}{AXV}{Annexin-V}
\newacronym{pi}{PI}{propidium iodide}
\newacronym{rt}{RT}{room temperature}
\newacronym{cas37}{Cas3/7}{Caspase-3/7}
\newacronym{bcl2}{BCL-2}{B cell lymphoma 2}
\newacronym{tmb}{TMB}{3,3',5,5'-Tetramethylbenzidine}
\newacronym{gvhd}{GVHD}{graft-vs-host disease}
\newacronym{bcma}{BCMA}{B-cell maturation antigen}
\newacronym{di}{DI}{deionized}
\newacronym{moi}{MOI}{multiplicity of infection}
\newacronym{ifng}{IFN$\upgamma$}{interferon-$\upgamma$}
\newacronym{tnfa}{TNF$\upalpha$}{tumor necrosis factor-$\upalpha$}
\newacronym{sql}{SQL}{structured query language}
\newacronym{fcs}{FCS}{flow cytometry standard}
\newacronym{ivis}{ivis}{in vivo imaging system}
\newacronym{iacuc}{IACUC}{institutional animal care and use committee}
\newacronym{hbss}{HBSS}{Hank's buffered saline solution}
\newacronym{leaf}{LEAF}{low endotoxin, azide-free}
\newacronym{cytof}{CyTOF}{cytometry time-of-flight}
\newacronym{spade}{SPADE}{spanning-tree progression analysis of
  density-normalized events}
\newacronym{ml}{ML}{machine learning}
\newacronym{rf}{RF}{random forest}
\newacronym{sr}{SR}{symbolic regression}
\newacronym{gbm}{GBM}{gradient boosted trees}
\newacronym{cif}{CIF}{conditional inference forests}
\newacronym{lasso}{LASSO}{least absolute shrinkage and selection operator}
\newacronym{svm}{SVM}{support vector machines}
\newacronym{plsr}{PLSR}{partial least squares regression}
\newacronym{mse}{MSE}{mean squared error}
\newacronym{loocv}{LOO-CV}{leave-one-out cross validation}
\newacronym{hsqc}{HSQC}{heteronuclear single quantum coherence}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% SI units for uber nerds

% NOTE the \SI macro is depreciated but the arch repo (!!!) hasn't been updated
% with the latest package yet (texlive-science)

\sisetup{per-mode=symbol,list-units=single}
\DeclareSIUnit\IU{IU}
\DeclareSIUnit\rpm{RPM}
\DeclareSIUnit\carrier{carrier}
\DeclareSIUnit\dms{DMS}
\DeclareSIUnit\cell{cells}
\DeclareSIUnit\ab{mAb}
\DeclareSIUnit\normal{N}
\DeclareSIUnit\molar{M}
\DeclareSIUnit\mM{\milli\molar}
\DeclareSIUnit\uM{\micro\molar}
\DeclareSIUnit\gforce{\times{} g}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% commands for lazy farts like me

\newcommand{\mytitle}{
  \Large{
    \textbf{
      Optimizing T Cell Manufacturing and Quality Using Functionalized
      Degradable Microscaffolds
    }
  }
}

\newcommand{\mycommitteemember}[3]{
  \begin{flushleft}
    \noindent
    #1 \\
    #2 \\
    \textit{#3}
  \end{flushleft}
}

% a BME's best friend
\newcommand{\invivo}{\textit{in vivo}}
\newcommand{\invitro}{\textit{in vitro}}
\newcommand{\exvivo}{\textit{ex vivo}}

% various CD-whatever crap
\newcommand{\cd}[1]{CD{#1}}
\newcommand{\anti}[1]{anti-{#1}}
\newcommand{\antih}[1]{anti-human {#1}}
\newcommand{\antim}[1]{anti-mouse {#1}}
\newcommand{\acd}[1]{\anti{\cd{#1}}}
\newcommand{\ahcd}[1]{\antih{\cd{#1}}}
\newcommand{\amcd}[1]{\antim{\cd{#1}}}
\newcommand{\pos}[1]{#1+}
\newcommand{\cdp}[1]{\pos{\cd{#1}}}
\newcommand{\cdn}[1]{\cd{#1}-}
\newcommand{\ptmem}{\cdp{62L}\pos{CCR7}}
\newcommand{\ptmemp}{\ptmem{}~\si{\percent}}
\newcommand{\pth}{\cdp{4}}
\newcommand{\pthp}{\pth{}~\si{\percent}}
\newcommand{\ptk}{\cdp{8}}
\newcommand{\ptmemh}{\pth\ptmem}
\newcommand{\ptmemk}{\ptk\ptmem}
\newcommand{\dpthp}{$\Updelta$\pthp{}}
\newcommand{\ptcar}{\gls{car}+}
\newcommand{\ptcarp}{\ptcar~\si{\percent}}

% DOE responses I don't feel like typing ad-nauseam
\newcommand{\pilII}{\gls{il2} concentration}
\newcommand{\pdms}{\gls{dms} concentration}
\newcommand{\pmab}{functional \gls{mab} surface density}

% vendor and product stuff I don't feel like typing
\newcommand{\catnum}[2]{(#1, #2)}
\newcommand{\product}[3]{#1 \catnum{#2}{#3}}
\newcommand{\thermo}{Thermo Fisher}
\newcommand{\miltenyi}{Miltenyi Biotech}
\newcommand{\bl}{Biolegend}
\newcommand{\bd}{Becton Dickenson}

% the obligatory misc category
\newcommand{\inlinecode}{\texttt}
\newcommand{\subcap}[2]{\subref{#1}) #2}
\newcommand{\sigkey}{Significance test key: *p<0.1; **p < 0.05; ***p<0.01}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% ditto for environments

\newenvironment{mytitlepage}{
  \begin{singlespace}
    \begin{center}
    }
    {
    \end{center}
  \end{singlespace}
}

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% begin document (proceed with caution)

\begin{document}

\begin{titlepage}
  \begin{mytitlepage}
    \mytitle{}

    \vfill

    \Large{
      A Dissertation \\
      Presented to \\
      The Academic Faculty \\

      \vspace{1.5em}

      by

      \vspace{1.5em}

      Nathan John Dwarshuis, B.S. \\

      \vfill

      In Partial Fulfillment \\
      of the Requirements for the Degree \\
      Doctor of Philosophy in Biomedical Engineering in the \\
      Wallace H. Coulter Department of Biomedical Engineering

      \vfill

      Georgia Institute of Technology and Emory University \\
      August 2021

      \vfill

      COPYRIGHT \copyright{} BY NATHAN J. DWARSHUIS
    }
  \end{mytitlepage}
\end{titlepage}

\onecolumn \pagenumbering{roman}
\clearpage
\begin{mytitlepage}
  \mytitle{}
\end{mytitlepage}

\vfill

\large{
  \noindent
  Committee Members

  \begin{multicols}{2}
    \begin{singlespace}

      \mycommitteemember{Dr.\ Krishnendu\ Roy\ (Advisor)}
      {Department of Biomedical Engineering}
      {Georgia Institute of Technology and Emory University}

      \vspace{1.5em}

      \mycommitteemember{Dr.\ Madhav\ Dhodapkar}
      {Department of Hematology and Medical Oncology}
      {Emory University}

      \vspace{1.5em}

      \mycommitteemember{Dr.\ Melissa\ Kemp}
      {Department of Biomedical Engineering}
      {Georgia Institute of Technology and Emory University}

      \columnbreak{}
      \null{}
      \vfill

      \mycommitteemember{Dr.\ Wilbur\ Lam}
      {Department of Biomedical Engineering}
      {Georgia Institute of Technology and Emory University}

      \vspace{1.5em}

      \mycommitteemember{Dr.\ Sakis\ Mantalaris}
      {Department of Biomedical Engineering}
      {Georgia Institute of Technology and Emory University}

    \end{singlespace}
  \end{multicols}

  \vspace{1.5em}

  \hfill Date Approved:
}

\clearpage

\chapter*{acknowledgements}
\addcontentsline{toc}{chapter}{acknowledgements} 

Thank you to Lex Fridman and Devin Townsend for being awesome and inspirational.

\clearpage

\chapter*{summary}
\addcontentsline{toc}{chapter}{summary} 

\Gls{act} using \gls{car} T cells have shown promise in treating cancer, but
manufacturing large numbers of high quality cells remains challenging. Currently
approved T cell expansion technologies involve \anti-cd{3} and \anti-cd{28}
\glspl{mab}, usually mounted on magnetic beads. This method fails to
recapitulate many key signals found \invivo{} and is also heavily licensed by a
few companies, limiting its long-term usefulness to manufactures and clinicians.
Furthermore, we understand that highly potent T cells are generally
less-differentiated subtypes such as central memory and stem memory T cells.
Despite this understanding, little has been done to optimize T cell expansion
for generating these subtypes, including measurement and feedback control
strategies that are necessary for any modern manufacturing process.

The goal of this thesis was to develop a microcarrier-based \gls{dms} T cell
expansion system as well as determine biologically-meaningful \glspl{cqa} and
\glspl{cpp} that could be used to optimize for highly-potent T cells. In Aim 1,
we develop and characterized the \gls{dms} system, including quality control
steps. We also demonstrate the feasiblity of expanding highly-potent memory and
CD4+ T cells, and showing compatibility with existing \gls{car} transduction
methods. In aim 2, we use \gls{doe} methodology to optimize the \gls{dms}
platform, and develop a computational pipeline to identify and model the effect
of measurable \glspl{cqa} and \glspl{cpp} on the final product. In aim 3, we
demonstrate the effectiveness of the \gls{dms} platform \invivo{}. This
thesis lays the groundwork for a novel T cell expansion method which can be used
in a clinical setting, and also provides a path toward optimizing for product
quality in an industrial setting.

\clearpage

\tableofcontents

\clearpage

\listoffigures

\clearpage

\listoftables

\clearpage

% \twocolumn
\chapter*{acronyms}
\addcontentsline{toc}{chapter}{acronyms}

\printglossary[type=\acronymtype]

\clearpage
\pagenumbering{arabic}

\clearpage

\chapter{introduction}

\section*{overview}

% TODO this is basically the same as the first part of the backgound, I guess I
% can just trim it down

T cell-based immunotherapies have received great interest from clinicians and
industry due to their potential to treat, and often cure, cancer and other
diseases\cite{Fesnak2016,Rosenberg2015}. In 2017, Novartis and Kite Pharma
received FDA approval for \textit{Kymriah} and \textit{Yescarta} respectively,
two genetically-modified \gls{car} T cell therapies against B cell malignancies.
Despite these successes, \gls{car} T cell therapies are constrained by an
expensive and difficult-to-scale manufacturing process with little control on
cell quality and phenotype3,4. State-of-the-art T cell manufacturing techniques
focus on \acd{3} and \acd{28} activation and expansion, typically
presented on superparamagnetic, iron-based microbeads (Invitrogen Dynabead,
Miltenyi MACS beads), on nanobeads (Miltenyi TransACT), or in soluble tetramers
(Expamer)\cite{Roddie2019,Dwarshuis2017,Wang2016, Piscopo2017, Bashour2015}.
These strategies overlook many of the signaling components present in the
secondary lymphoid organs where T cells expand \invivo{}. Typically, T cells are
activated under close cell-cell contact, which allows for efficient
autocrine/paracrine signaling via growth-stimulating cytokines such as
\gls{il2}. Additionally, the lymphoid tissues are comprised of \gls{ecm}
components such as collagen, which provide signals to upregulate proliferation,
cytokine production, and pro-survival pathways\cite{Gendron2003, Ohtani2008,
  Boisvert2007, Ben-Horin2004}. We hypothesized that culture conditions that
better mimic these \invivo{} expansion conditions of T cells, can significantly
improve the quality and quantity of manufactured T cells and provide better
control on the resulting T cell phenotype.

% TODO mention the Cloudz stuff that's in my presentation

A variety of solutions have been proposed to make the T cell expansion process
more physiological. One strategy is to use modified feeder cell cultures to
provide activation signals similar to those of \glspl{dc}\cite{Forget2014}.
While this has the theoretical capacity to mimic many components of the lymph
node, it is hard to reproduce on a large scale due to the complexity and
inherent variability of using cell lines in a fully \gls{gmp}-compliant manner.
Others have proposed biomaterials-based solutions to circumvent this problem,
including lipid-coated microrods\cite{Cheung2018}, 3D-scaffolds via either
Matrigel\cite{Rio2018} or 3d-printed lattices\cite{Delalat2017}, ellipsoid
beads\cite{meyer15_immun}, and \gls{mab}-conjugated \gls{pdms}
beads\cite{Lambert2017} that respectively recapitulate the cellular membrane,
large interfacial contact area, 3D-structure, or soft surfaces T cells normally
experience \invivo{}. While these have been shown to provide superior expansion
compared to traditional microbeads, none of these methods has been able to show
preferential expansion of functional naïve/memory and CD4 T cell populations.
Generally, T cells with a lower differentiation state such as naïve and memory
cells have been shown to provide superior anti-tumor potency, presumably due to
their higher potential to replicate, migrate, and engraft, leading to a
long-term, durable response\cite{Xu2014, Fraietta2018, Gattinoni2011,
  Gattinoni2012}. Likewise, CD4 T cells are similarly important to anti-tumor
potency due to their cytokine release properties and ability to resist
exhaustion\cite{Wang2018, Yang2017}. Therefore, methods to increase naïve/memory
and CD4 T cells in the final product are needed, a critical consideration being
ease of translation to industry and ability to interface with scalable systems
such as bioreactors.

% TODO probably need to address some of the modeling stuff here as well

This thesis describes a novel degradable microscaffold-based method derived from
porous microcarriers functionalized with \acd{3} and \acd{28} \glspl{mab}
for use in T cell expansion cultures. Microcarriers have historically been used
throughout the bioprocess industry for adherent cultures such as stem cells and
\gls{cho} cells, but not with suspension cells such as T
cells\cite{Heathman2015, Sart2011}. The microcarriers chosen to make the DMSs in
this study have a microporous structure that allows T cells to grow inside and
along the surface, providing ample cell-cell contact for enhanced autocrine and
paracrine signaling. Furthermore, the carriers are composed of gelatin, which is
a collagen derivative and therefore has adhesion domains that are also present
within the lymph nodes. Finally, the 3D surface of the carriers provides a
larger contact area for T cells to interact with the \glspl{mab} relative to
beads; this may better emulate the large contact surface area that occurs
between T cells and \glspl{dc}. These microcarriers are readily available in
over 30 countries and are used in an FDA fast-track-approved combination retinal
pigment epithelial cell product (Spheramine, Titan Pharmaceuticals) {\#}[Purcell
documentation]. This regulatory history will aid in clinical translation. We
show that compared to traditional microbeads, \gls{dms}-expanded T cells not
only provide superior expansion, but consistently provide a higher frequency of
naïve/memory and CD4 T cells (CCR7+CD62L+) across multiple donors. We also
demonstrate functional cytotoxicity using a CD19 \gls{car} and a superior
performance, even at a lower \gls{car} T cell dose, of \gls{dms}-expanded
\gls{car}-T cells \invivo{} in a mouse xenograft model of human B cell
\gls{all}. Our results indicate that \glspl{dms} provide a robust and scalable
platform for manufacturing therapeutic T cells with higher naïve/memory
phenotype and more balanced CD4+ T cell content.

\section*{hypothesis}

The hypothesis of this dissertation was that using \glspl{dms} created from
off-the-shelf microcarriers and coated with activating \glspl{mab} would lead to
higher quantity and quality T cells as compared to state-of-the-art bead-based
expansion. The objective of this dissertation was to develop this platform, test
its effectiveness both \invivo{} and \invivo{}, and develop computational
pipelines that could be used in a manufacturing environment.

\section*{specific aims}

The specific aims of this dissertation are outlined in
\cref{fig:graphical_overview}.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics[width=\textwidth]{../figures/overview.png}

  \endgroup
  \caption[Project Overview]{High-level overview.}
  \label{fig:graphical_overview}
\end{figure*}

\subsection*{aim 1: develop and optimize a novel T cell expansion process that
  mimics key components of the lymph nodes}

% TODO this might be easier to break apart in separate aims

In this first aim, we demonstrated the process for manufacturing \glspl{dms},
including quality control steps that are necessary for translation of this
platform into a scalable manufacturing setting. We also demonstrate that the
\gls{dms} platform leads to higher overall expansion of T cells and higher
overall fractions of potent memory and CD4+ subtypes desired for T cell
therapies. Finally, we demonstrate \invitro{} that the \gls{dms} platform can be
used to generate functional \gls{car} T cells targeted toward CD19.

\subsection*{aim 2: develop methods to control and predict T cell quality}

For this second aim, we investigated methods to identify and control \glspl{cqa}
and glspl{cpp} for manufacturing T cells using the \gls{dms} platform. This was
accomplished through two sub-aims:

\begin{itemize}
  \item[A --] Develop computational methods to control and predict T cell
    expansion and quality
  \item[B --] Perturb \gls{dms} expansion to identify additional mechanistic
    controls for expansion and quality
\end{itemize}

\subsection*{aim 3: confirm potency of T cells from novel T cell expansion
  process using \invivo{} xenograft mouse model}

In this final aim, we demonstrate the effectiveness of \gls{dms}-expanded T
cells compared to state-of-the-art beads using \invivo{} mouse models for
\gls{all}.

\section*{outline}

In Chapter~\ref{background}, we provide additional background on the current
state of T cell manufacturing and how the work in this dissertation moves the
field forward. In Chapters~\ref{aim1},~\ref{aim2a},~\ref{aim2b}, and~\ref{aim3}
we present the work pertaining to Aims 1, 2, and 3 respectively. Finally, we
present our final conclusions in Chapter~\ref{conclusions}.

\chapter{background and significance}\label{background}
\section*{background}

% TODO break this apart into mfg tech and T cell phenotypes/quality
% TODO consider adding a separate section on microcarriers and their use in
% bioprocess
% TODO add stuff about T cell licensing
\subsection*{current T cell manufacturing technologies}

\Gls{car} T cell therapy has received great interest from both academia and
industry due to its potential to treat cancer and other
diseases\cite{Fesnak2016, Rosenberg2015}. In 2017, Novartis and Kite Pharma
acquired FDA approval for \textit{Kymriah} and \textit{Yescarta} respectively,
two \gls{car} T cell therapies against B cell malignancies. Despite these
successes, \gls{car} T cell therapies are constrained by an expensive and
difficult-to-scale manufacturing process\cite{Roddie2019, Dwarshuis2017}.

Of critical concern, state-of-the-art manufacturing techniques focus only on
Signal 1 and Signal 2-based activation via \acd{3} and \acd{28} \glspl{mab},
typically presented on a microbead (Invitrogen Dynabead, Miltenyi MACS beads) or
nanobead (Miltenyi TransACT), but also in soluble forms in the case of antibody
tetramers (Expamer)\cite{Wang2016, Piscopo2017, Roddie2019, Bashour2015}. These
strategies overlook many of the signaling components present in the secondary
lymphoid organs where T cells normally expand. Typically, T cells are activated
under close cell-cell contact via \glspl{apc} such as \glspl{dc}, which present
peptide-\glspl{mhc} to T cells as well as a variety of other costimulatory
signals. These close quarters allow for efficient autocrine/paracrine signaling
among the expanding T cells, which secrete gls{il2} and other cytokines to
assist their own growth. Additionally, the lymphoid tissues are comprised of
\gls{ecm} components such as collagen, which provide signals to upregulate
proliferation, cytokine production, and pro-survival pathways\cite{Gendron2003,
  Ohtani2008, Boisvert2007, Ben-Horin2004}.

A variety of solutions have been proposed to make the T cell expansion process
more physiological. One strategy is to use modified feeder cell cultures to
provide activation signals similar to those of \glspl{dc}\cite{Forget2014}.
While this has the theoretical capacity to mimic several key components of the
lymph node, it is hard to reproduce on a large scale due to the complexity and
inherent variability of using cell lines in a fully \gls{gmp}-compliant manner.
Others have proposed biomaterials-based solutions to circumvent this problem,
including lipid-coated microrods\cite{Cheung2018}, 3D-scaffolds via either
Matrigel\cite{Rio2018} or 3d-printed lattices\cite{Delalat2017}, ellipsoid
beads\cite{meyer15_immun}, and \gls{mab}-conjugated \gls{pdms}
beads\cite{Lambert2017} that respectively recapitulate the cellular membrane,
large interfacial contact area, 3D-structure, or soft surfaces T cells normally
experience \textit{in vivo}. While these have been shown to provide superior
expansion compared to traditional microbeads, no method has been able to show
preferential expansion of functional memory and CD4 T cell populations.
Generally, T cells with a lower differentiation state such as memory cells have
been shown to provide superior anti-tumor potency, presumably due to their
higher potential to replicate, migrate, and engraft, leading to a long-term,
durable response\cite{Xu2014, Gattinoni2012, Fraietta2018, Gattinoni2011}.
Likewise, CD4 T cells are similarly important to anti-tumor potency due to their
cytokine release properties and ability to resist exhaustion\cite{Wang2018,
  Yang2017}, and no method exists to preferentially expand the CD4 population
compared to state-of-the-art systems.

Here we propose a method using microcarriers functionalized with \acd{3} and
\acd{28} \glspl{mab} for use in T cell expansion cultures. Microcarriers have
historically been used throughout the bioprocess industry for adherent cultures
such as stem cells and \gls{cho} cells, but not with suspension cells such as T
cells\cite{Heathman2015, Sart2011}. The carriers have a macroporous structure
that allows T cells to grow inside and along the surface, providing ample
cell-cell contact for enhanced autocrine and paracrine signaling. Furthermore,
the carriers are composed of gelatin, which is a collagen derivative and
therefore has adhesion domains that are also present within the lymph nodes.
Finally, the 3D surface of the carriers provides a larger contact area for T
cells to interact with the \glspl{mab} relative to beads; this may better
emulate the large contact surface area that occurs between T cells and
\glspl{dc}.

\subsection*{strategies to optimize cell manufacturing}

The \gls{dms} system has a number of parameters that can be optimized, and a
\gls{doe} is an ideal framework to test multiple parameters simultaneously. The
goal of \gls{doe} is to answer a data-driven question with the least number of
resources. It was developed in many non-biological industries throughout the
\nth{20} century such as the automotive and semiconductor industries where
engineers needed to minimize downtime and resource consumption on full-scale
production lines.

% TODO add a bit more about the math of a DOE here

\Glspl{doe} served three purposes in this dissertation. First, we used them as
screening tools, which allowed us to test many input parameters and filter out
the few that likely have the greatest effect on the response. Second, they were
used to make a robust response surface model to predict optimums using
relatively few resources, especially compared to full factorial or
one-factor-at-a-time approaches. Third, we used \glspl{doe} to discover novel
effects and interactions that generated hypotheses that could influence the
directions for future work.

\subsection*{strategies to characterize cell manufacturing}

A number of multiomics strategies exist which can generate rich datasets for T
cells. We will consider several multiomics strategies within this proposal:

\begin{description}
\item[Luminex:] A multiplexed bead-based \gls{elisa} that can measure
  many bulk (not single cell) cytokine concentrations simultaneously
  in a media sample. Since this only requires media (as opposed to
  destructively measuring cells) we will use this as a longitudinal
  measurement.
\item[Metabolomics:] It is well known that T cells of different
  lineages have different metabolic profiles; for instance memory T
  cells have larger aerobic capacity and fatty acid
  oxidation\cite{Buck2016, van_der_Windt_2012}. We will interrogate
  key metabolic species using \gls{nmr} in collaboration with the
  Edison Lab at the University of Georgia. This will be both a
  longitudinal assay using media samples (since some metabolites may
  be expelled from cells that are indicative of their phenotype) and
  at endpoint where we will lyse the cells and interogate their entire
  metabolome.
\item[Flow and Mass Cytometry:] Flow cytometry using fluorophores has been used
  extensively for immune cell analysis, but has a practical limit of
  approximately 18 colors\cite{Spitzer2016}. Mass cytometry is analogous to
  traditional flow cytometry except that it uses heavy-metal \gls{mab}
  conjugates, which has a practical limit of over 50 markers. This will be
  useful in determining precise subpopulations and phenotypes that may be
  influencing responses, especially when one considers that many cell types can
  be defined by more than one marker combination. We will perform this at
  endpoint. While mass cytometry is less practical than simple flow cytometers
  such as the BD Accuri, we may find that only a few markers are required to
  accurately predict performance, and thus this could easily translate to
  industry using relatively cost-effective equipment.
\end{description}

% TODO add a computational section

% TODO add a section explaining causal inference since this is a big part of
% the end of aim 1

\section{Innovation}

\subsection{Innovation}

Several aspects of this work are novel considering the state-of-the-art
technology for T cell manufacturing:

\begin{itemize}
\item \Glspl{dms} offers a compelling alternative to state-of-the-art magnetic
  bead technologies (e.g. DynaBeads, MACS-Beads), which is noteworthy because
  the licenses for these techniques is controlled by only a few companies
  (Invitrogen and Miltenyi respectively). Because of this, bead-based expansion
  is more expensive to implement and therefore hinders companies from entering
  the rapidly growing T cell manufacturing arena. Providing an alternative as we
  are doing will add more options, increase competition among both raw material
  and T cell manufacturers, and consequently drive down cell therapy market
  prices and increase innovation throughout the industry.
\item This is the first technology for T cell immunotherapies that selectively
  expands memory T cell populations with greater efficiency relative to
  bead-based expansion Others have demonstrated methods that can achieve greater
  expansion of T cells, but not necessarily specific populations that are known
  to be potent.
\item We propose to optimize our systems using \gls{doe} methodology, which is a
  strategy commonly used in other industries and disciplines but has yet to gain
  wide usage in the development of cell therapies. \Glspl{doe} are advantageous
  as they allow the inspection of multiple parameters simultaneously, allowing
  efficient and comprehensive analysis of the system vs a one-factor-at-a-time
  approach. We believe this method is highly relevant to the development of cell
  therapies, not only for process optimization but also hypotheses generation.
  Of further note, most \textit{in vivo} experiments are not done using a
  \gls{doe}-based approach; however, a \gls{doe} is perfectly natural for a
  large mouse study where one naturally desires to use as few animals as
  possible.
\item The \gls{dms} system is be compatible with static bioreactors such as the
  G-Rex which has been adopted throughout the cell therapy industry. Thus this
  technology can be easily incorporated into existing cell therapy process that
  are performed at scale.
\item We analyzed our system using a multiomics approach, which will enable the
  discovery of novel biomarkers to be used as \glspl{cqa}. While this approach
  has been applied to T cells previously, it has not been done in the context of
  a large \gls{doe}-based model. This approach is aware of the whole design
  space, and thus enables greater understanding of process parameters and their
  effect on cell phenotype.
\end{itemize}

\chapter{aim 1}\label{aim1}

\section{introduction}

The first aim was to develop a microcarrier system that mimics several key
aspects of the \invivo{} lymph node microenvironment. We compared compare this
system to state-of-the-art T cell activation technologies for both expansion
potential and memory cell formation. The governing hypothesis was that
microcarriers functionalized with \acd{3} and \acd{28} \glspl{mab} will
provide superior expansion and memory phenotype compared to state-of-the-art
bead-based T cell expansion technology.

% TODO this doesn't flow that well and is repetitive with what comes above

Microcarriers have been used throughout the bioprocess industry for adherent
cell cultures such as \gls{cho} cells and stem cells, as they are able to
achieve much greater surface area per unit volume than traditional 2D
cultures\cite{Heathman2015, Sart2011}. Adding adhesive \glspl{mab} to the
microcarriers will adapt them for suspension cell cultures such as T cells.
Consequently, the large macroporous structure will allow T cells to cluster more
closely, which in turn will enable better autocrine and paracrine signaling.
Specifically, two cytokines that are secreted by T cells, IL-2 and IL-15, are
known to drive expansion and memory phenotype respectively\cite{Buck2016}.
Therefore, the proposed microcarrier system should enable greater expansion and
better retention of memory phenotype compared to current bead-based methods.

\section{methods}

\subsection{dms functionalization}\label{sec:dms_fab}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_flowchart.png}

  \endgroup
  \caption[\gls{dms} Flowchart]{Overview of \gls{dms} manufacturing process.}
  \label{fig:dms_flowchart}
\end{figure*}

Gelatin microcarriers (\gls{cus} or \gls{cug}, GE Healthcare, DG-2001-OO and
DG-0001-OO) were suspended at \SI{20}{\mg\per\ml} in 1X \gls{pbs} and
autoclaved. All subsequent steps were done aseptically, and all reactions were
carried out at \SI{20}{\mg\per\ml} carriers at room temperature and agitated
using an orbital shaker with a \SI{3}{\mm} orbit diameter. After autoclaving,
the microcarriers were washed using sterile \gls{pbs} three times in a 10:1
volume ratio. \product{\Gls{snb}}{\thermo}{21217} was dissolved at
approximately \SI{10}{\uM} in sterile ultrapure water, and the true
concentration was then determined using the \gls{haba} assay (see below).
\SI{5}{\ul\of{\ab}\per\mL} \gls{pbs} was added to carrier suspension and allowed
to react for \SI{60}{\minute} at \SI{700}{\rpm} of agitation. After the
reaction, the amount of biotin remaining in solution was quantified using the
\gls{haba} assay (see below). The carriers were then washed three times, which
entailed adding sterile \gls{pbs} in a 10:1 volumetric ratio, agitating at
\SI{900}{\rpm} for \SI{10}{\minute}, adding up to a 15:1 volumetric ratio
(relative to reaction volume) of sterile \gls{pbs}, centrifuging at
\SI{1000}{\gforce} for \SI{1}{\minute}, and removing all liquid back down to the
reaction volume.

To coat with \gls{stp}, \SI{40}{\ug\per\mL} \product{\gls{stp}}{Jackson
  Immunoresearch}{016-000-114} was added and allowed to react for
\SI{60}{\minute} at \SI{700}{RPM} of agitation. After the reaction, supernatant
was taken for the \product{\gls{bca} assay}{\thermo}{23225}, and the carriers
were washed analogously to the previous wash step to remove the biotin, except
two washes were done and the agitation time was \SI{30}{\minute}. Biotinylated
\glspl{mab} against human CD3 \catnum{\bl}{317320} and CD28 \catnum{\bl}{302904}
were combined in a 1:1 mass ratio and added to the carriers at
\SI{0.2}{\ug\of{\ab}\per\mg\of{\dms}}. Along with the \glspl{mab}, sterile
\product{\gls{bsa}}{Sigma}{A9576} was added to a final concentration of
\SI{2}{\percent} in order to prevent non-specific binding of the antibodies to
the reaction tubes. \glspl{mab} were allowed to bind to the carriers for
\SI{60}{\minute} with \SI{700}{\rpm} agitation. After binding, supernatants were
sampled to quantify remaining \gls{mab} concentration using an
\product{\anti{\gls{igg}} \gls{elisa} kit}{Abcam}{157719}. Fully functionalized
\glspl{dms} were washed in sterile \gls{pbs} analogous to the previous washing
step to remove excess \gls{stp}. They were washed once again in the cell culture
media to be used for the T cell expansion.

The concentration of the final \gls{dms} suspension was found by taking a
\SI{50}{\uL} sample, plating in a well, and imaging the entire well. The image
was then manually counted to obtain a concentration. Surface area for
\si{\ab\per\um\squared} was calculated using the properties for \gls{cus} and
\gls{cug} as given by the manufacturer {Table X}.

\subsection{dms quality control assays}

Biotin was quantified using the \product{\gls{haba} assay}{Sigma}{H2153-1VL}. In
the case of quantifying \gls{snb} prior to adding it to the microcarriers, the
sample volume was quenched in a 1:1 volumetric ratio with \SI{1}{\molar} NaOH
and allowed to react for \SI{1}{\minute} in order to prevent the reactive ester
linkages from binding to the avidin proteins in the \gls{haba}/avidin premix.
All quantifications of \gls{haba} were performed on an Eppendorf D30
Spectrophotometer using \product{\SI{70}{\ul} cuvettes}{BrandTech}{759200}. The
extinction coefficient at \SI{500}{\nm} for \gls{haba}/avidin was assumed to be
\SI{34000}{\per\cm\per\molar}.

\gls{stp} binding to the carriers was quantified indirectly using a
\product{\gls{bca} kit}{\thermo}{23227} according to the manufacturer’s
instructions, with the exception that the standard curve was made with known
concentrations of purified \gls{stp} instead of \gls{bsa}. Absorbance at
\SI{592}{\nm} was quantified using a Biotek plate reader.

\Gls{mab} binding to the microcarriers was quantified indirectly using an
\gls{elisa} assay per the manufacturer’s instructions, with the exception that
the same antibodies used to coat the carriers were used as the standard for the
\gls{elisa} standard curve.

Open biotin binding sites on the \glspl{dms} after \gls{stp} coating was
quantified indirectly using \product{\gls{fitcbt}}{\thermo}{B10570}.
Briefly, \SI{400}{\pmol\per\ml} \gls{fitcbt} were added to \gls{stp}-coated
carriers and allowed to react for \SI{20}{\minute} at room temperature under
constant agitation. The supernatant was quantified against a standard curve of
\gls{fitcbt} using a Biotek plate reader.

\Gls{stp} binding was verified after the \gls{stp}-binding step visually by
adding \gls{fitcbt} to the \gls{stp}-coated \glspl{dms}, resuspending in
\SI{1}{\percent} agarose gel, and imaging on a \product{lightsheet
 microscope}{Zeiss}{Z.1}. \Gls{mab} binding was verified visually by first
staining with \product{\anti{\gls{igg}}-\gls{fitc}}{\bl}{406001}, incubating for
\SI{30}{\minute}, washing with \gls{pbs}, and imaging on a confocal microscope.

\subsection{t cell culture}\label{sec:tcellculture}

% TODO verify countess product number
Cryopreserved primary human T cells were either obtained as sorted
\product{\cdp{3} T cells}{Astarte Biotech}{1017} or isolated from
\product{\glspl{pbmc}}{Zenbio}{SER-PBMC} using a negative selection
\product{\cdp{3} \gls{macs} kit}{\miltenyi}{130-096-535}. T cells were activated
using \glspl{dms} or \product{\SI{3.5}{\um} CD3/CD28 magnetic
  beads}{\miltenyi}{130-091-441}. In the case of beads, T cells were activated
at the manufacturer recommended cell:bead ratio of 2:1. In the case of
\glspl{dms}, cells were activated using \SI{2500}{\dms\per\cm\squared} unless
otherwise noted. Initial cell density was \SIrange{2e6}{2.5e6}{\cell\per\ml} to
in a 96 well plate with \SI{300}{\ul} volume. Serum-free media was either
\product{OpTmizer}{\thermo}{A1048501} or
\product{TexMACS}{\miltenyi}{170-076-307} supplemented with
\SIrange{100}{400}{\IU\per\ml} \product{\gls{rhil2}}{Peprotech}{200-02}. Cell
cultures were expanded for \SI{14}{\day} as counted from the time of initial
seeding and activation. Cell counts and viability were assessed using
\product{trypan blue}{\thermo}{T10282} or \product{\gls{aopi}}{Nexcelom
  Bioscience}{CS2-0106-5} and a \product{Countess Automated Cell Counter}{Thermo
  Fisher}{Countess 3 FL}. Media was added to cultures every \SIrange{2}{3}{\day}
depending on media color or a \SI{300}{\mg\per\deci\liter} minimum glucose
threshold. Media glucose was measured using a \product{GlucCell glucose
  meter}{Chemglass}{CLS-1322-02}.

Cells on the \glspl{dms} were visualized by adding \SI{0.5}{\ul}
\product{\gls{stppe}}{\bl}{405204} and \SI{2}{ul}
\product{\acd{45}-\gls{af647}}{\bl}{368538}, incubating for \SI{1}{\hour}, and
imaging on a spinning disk confocal microscope.

In the case of Grex bioreactors, we either used a \product{24 well plate}{Wilson
  Wolf}{P/N 80192M} or a \product{6 well plate}{P/N 80240M}.

\subsection{Quantifying cells on DMS interior}

% TODO add a product number to MTT (if I can find it)
Cells were stained and visualized using \gls{mtt}. \glspl{dms} with attached and
loosely attached cells were sampled as desired and filtered through a
\SI{40}{\um} cell strainer. While still in the cell strainer, \glspl{dms} were
washed twice with \gls{pbs} and then dried by pulling liquid through the bottom
of the cell strainer via a micropipette and dabbing with a KimWipe. \glspl{dms}
were transferred to a 24 well plate with \SI{400}{\ul} media. \SI{40}{\ul}
\gls{mtt} was added to each well and allowed to incubate for \SI{3}{\hour},
after which \glspl{dms} with cell were visualized via a brightfield microscope.

To quantify cells on the interior of \glspl{dms}, cells and \glspl{dms} were
isolated analogously to those for the \gls{mtt} stain up until the drying step.
Cells were then transferred to a tube containing \SI{400}{\ul} at
\SI{5}{\mg\per\ml} dispase solution. \glspl{dms} were incubated and rotated for
\SI{45}{\minute} at \SI{37}{\degreeCelsius}, after which cells were counted as
already described in \cref{sec:tcellculture}.

\subsection{quantification of apoptosis using Annexin-V}

Apoptosis was quantified using \gls{anv} according to the manufacturer's
instructions. Briefly, cells were transferred to flow tubes and washed twice
with \gls{pbs} by adding \SI{3}{\ml} to each tube, centrifuging for
\SI{400}{\gforce}, and aspirating the liquid down to \SI{200}{\ul}. The cells
were analogously washed a third time with staining buffer (\SI{10}{\mM} HEPES,
\SI{140}{\mM} NaCl, \SI{2.5}{\mM} CaCl\textsubscript{2}) and aspirated down to a
final volume of \SI{100}{\ul}. Cells were stained in this volume with
\SI{1}{\ul} \product{\gls{anv}-\gls{fitc}}{\bl}{640906} and \SI{5}{\ul}
\product{\gls{pi}}{\thermo}{P3566} and incubated for \SI{15}{\minute} at gls{rt}
in the dark. After incubation, \SI{400}{\ul} staining buffer was added to each
tube. Each tube was then analyzed via flow cytometry.

\subsection{quantification of Caspase-3/7}

\Gls{cas37} was quantified using \product{CellEvent dye}{\thermo}{C10723}
according the manufacturer's instructions. Briefly, a 2X (\SI{8}{\mM}) working
solution of CellEvent dye was added to \SI{100}{\ul} cell suspension (at least
\num{5e4} cells) and incubated at \SI{37}{\degreeCelsius} for \SI{30}{\minute}.
After incubation, cells were immediately analyzed via flow cytometry.

\subsection{quantification of BCL-2}

\Gls{bcl2} was quantified using an \product{Human Total Bcl-2 DuoSet \gls{elisa}
  kit}{Rnd Systems}{DYC827B-2} according to the manufacturer's instructions and
supplemented with \product{5X diluent buffer}{\bl}{421203}, \product{\gls{tmb}
  substrate solution}{eBioscience}{00-4201-56}, and \SI{2}{\normal}
H\textsubscript{2}SO\textsubscript{4} stop solution made in house. Briefly,
cells were lysed using \product{10X lysis buffer}{Cell Signaling}{9803S}, and
the lysate was quantified for protein using a \product{\gls{bca}
  assay}{\thermo}{23225} as directed. Standardized lysates were measured using
the \gls{elisa} kit as directed.

\subsection{chemotaxis assay}

% TODO not sure about the transwell product number
Migratory function was assayed using a transwell chemotaxis assay as previously
described\cite{Hromas1997}. Briefly, \SI{3e5}{\cell} were loaded into a
\product{transwell plate with \SI{5}{\um} pore size}{Corning}{3421} with the
basolateral chamber loaded with \SI{600}{\ul} media and 0, 250, or
\SI{1000}{\ng\per\mL} \product{CCL21}{Peprotech}{250-13}. The plate was
incubated for \SI{4}{\hour} after loading, and the basolateral chamber of each
transwell was quantified for total cells using \product{countbright
  beads}{\thermo}{C36950}. The final readout was normalized using the
\SI{0}{\ng\per\mL} concentration as background.

\subsection{degranulation assay}

Cytotoxicity of expanded \gls{car} T cells was assessed using a degranulation
assay as previously described\cite{Schmoldt1975}. Briefly, \num{3e5} T cells
were incubated with \num{1.5e5} target cells consisting of either \product{K562
wild type cells}{ATCC}{CCL-243} or CD19- expressing K562 cells transformed
with \gls{crispr} (kindly provided by Dr.\ Yvonne Chen, UCLA)\cite{Zah2016}.
Cells were seeded in a flat bottom 96 well plate with \SI{1}{\ug\per\ml}
\product{\acd{49d}}{eBioscience}{16-0499-81}, \SI{2}{\micro\molar} \product{monensin}{eBioscience}{
00-4505-51}, and \SI{1}{\ug\per\ml} \product{\acd{28}}{eBioscience}{302914} (all
functional grade \glspl{mab}) with \SI{250}{\ul} total volume. After
\SI{4}{\hour} incubation at \SI{37}{\degreeCelsius}, cells were stained for CD3,
CD4, and CD107a and analyzed on a BD LSR Fortessa. Readout was calculated as the
percent \cdp{107a} cells of the total \cdp{8} fraction.

\subsection{car expression}

\gls{car} expression was quantified as previously described\cite{Zheng2012}.
Briefly, cells were washed once and stained with \product{biotinylated
  \gls{ptnl}}{\thermo}{29997}. After a subsequent wash, cells were stained with
\product{\gls{pe}-\gls{stp}}{\bl}{405204}, washed again, and analyzed on a
BD Accuri. Readout was percent \gls{pe}+ cells as compared to secondary controls
(\gls{pe}-\gls{stp} with no \gls{ptnl}).

% TODO add BCMA-CAR stuff
\subsection{car plasmid and lentiviral transduction}

The anti-CD19-CD8-CD137-CD3z \gls{car} with the EF1$\upalpha$
promotor\cite{Milone2009} was synthesized (Aldevron) and subcloned into a
\product{FUGW}{Addgene}{14883} kindly provided by the Emory Viral Vector Core.
Lentiviral vectors were synthesized by the Emory Viral Vector Core or the
Cincinnati Children's Hospital Medical Center Viral Vector Core. To transduce
primary human T cells, \product{retronectin}{Takara}{T100A} was coated onto
non-TC treated 96 well plates and used to immobilize lentiviral vector particles
according to the manufacturer's instructions. Briefly, retronectin solution was
adsorbed overnight at \SI{4}{\degreeCelsius} and blocked the next day using
\gls{bsa}. Prior to transduction, lentiviral supernatant was spinoculated at
\SI{2000}{\gforce} for \SI{2}{\hour} at \SI{4}{\degreeCelsius}. T cells were
activated in 96 well plates using beads or \glspl{dms} for \SI{24}{\hour}, and
then cells and beads/\glspl{dms} were transferred onto lentiviral vector coated
plates and incubated for another \SI{24}{\hour}. Cells and beads/\glspl{dms}
were removed from the retronectin plates using vigorous pipetting and
transferred to another 96 well plate wherein expansion continued.

\subsection{sulfo-NHS-biotin hydrolysis quantification}

The equation for hydrolysis of \gls{snb} was assumed to follow
\cref{chem:snb_hydrolysis}. 

% TODO make this look prettier
\begin{equation}
  \label{chem:snb_hydrolysis}
  \ce{NHS-CO-Biotin + OH- -> NHS- + Biotin-COOH}
\end{equation}

The hydrolysis of \gls{snb} was performed spectroscopically. \gls{snb} was added
to either \gls{di} water or \gls{pbs} in a UV-transparent 96 well plate. Kinetic
analysis using a Biotech Plate Reader began immediately after prep, and readings
at \SI{260}{\nm} were taken every minute for \SI{2}{\hour}.

\subsection{reaction kinetics quantification}

The diffusion of \gls{stp} into biotin-coated microcarriers was determined
experimentally. \SI{40}{\ug\per\ml} \gls{stp} was added to multiple batches of
biotin-coated microcarriers, and supernatents were taken at fixed intervals and
quantified for \gls{stp} protein using the \gls{bca} assay.

% TODO defend why the microcarriers were saturated with stp
The effective diffusivity of the microcarriers was determined using a
pseudo-steady-state model. Each microcarrier was assumed to be a porous sphere
with a fixed number of `\gls{stp} binding sites' equal to the maximum number of
\gls{stp} molecules that could binding to the surface per area (eg, we assumed
the surface was fully covered by \gls{stp}). Because the reaction rate between
biotin and \gls{stp} was so fast, we assumed that the interface of free biotin
shrunk as a function of \gls{stp} bound until the center of the microcarriers
was reached. We also assumed that the pores in the microcarriers were large
enough that the interactions between the \gls{stp} and surfaces would be small,
thus the apparent diffusivity could be represented as a fraction of the
diffusion coefficient of \gls{stp} in water. This model was given by
\cref{eqn:stp_diffision_1,eqn:stp_diffision_2}:

% TODO actually derive these equations, eg state the initial conditions and
% governing equation
\begin{equation}
  \label{eqn:stp_diffision_1}
  \frac{dr}{dt} = \frac{-D_{app}C}{Br(1-r/R)}
\end{equation}

\begin{equation}
  \label{eqn:stp_diffision_2}
  \frac{dC}{dt} = \frac{-4 \pi n D_{app} C}{V(1/r-1/R)}
\end{equation}

\noindent where
\begin{itemize}[label={}]
\item $D_{app}$ is the apparent diffusion rate which is equal to $D_{STP}\beta$
\item $D_{STP}$ the diffusion rate of \gls{stp} in water
\item $\beta$ a fractional parameter representing the tortuousity and void
  fraction of the microcarriers.
\item $r$ is the interfatial radius of the unbound biotin within a microcarrier
\item $t$ is the reaction time
\item $C$ is the concentration of \gls{stp} in the bulk solution
\item $V$ is the volume of the bulk medium
\item $R$ is the average radius of the microcarriers
\item $n$ is the number of microcarriers in the reaction volume
\end{itemize}

% TODO cite the diffusion rate of stp
The diffusion rate of \gls{stp} was assumed to be
\SI{3.89e-7}{\cm\squared\per\second} {\#}{diffusion rate citation}. Since all
but $\beta$ was known, the experimental data was fit using these equations using
\inlinecode{ode45} in MATLAB and least squares as the fitting error.

% TODO this diffusion rate isn't actually reflected in the code
These equations were then used analogously to describe the reaction profile of
\glspl{mab} assuming a diffusion rate of
\SI{4.8e-7}{\cm\squared\per\second}\cite{Sherwood1992}.

% METHOD add the equation governing the washing steps

\subsection{Luminex Analysis}\label{sec:luminex_analysis}

Luminex was performed using a \product{ProcartaPlex kit}{\thermo}{custom} for
the markers outlined in \cref{tab:luminex_panel} with modifications (note that
some markers were run in separate panels to allow for proper dilutions).
Briefly, media supernatents from cells were sampled as desired and immediately
placed in a \SI{-80}{\degreeCelsius} freezer until use. Before use, samples were
thawed at \gls{rt} and vortexed to ensure homogeneity. To run the plate,
\SI{25}{\ul} of magnetic beads were added to the plate and washed 3X using
\SI{300}{\ul} of wash buffer. \SI{25}{\ul} of samples or standard were added to
the plate and incubated for \SI{120}{\minute} at \SI{850}{\rpm} at \gls{rt}
before washing analogously 3X with wash. \SI{12.5}{\ul} detection \glspl{mab}
and \SI{25}{\ul} \gls{stppe} were sequentially added, incubated for
\SI{30}{\minute} and vortexed, and washed analogously to the sample step.
Finally, samples were resuspended in \SI{120}{\ul} reading buffer and analyzed
via a BioRad Bioplex 200 plate reader. An 8 point log2 standard curve was used,
and all samples were run with single replicates.

Luminex data was preprocessed using R for inclusion in downstream analysis as
follows. Any cytokine level that was over-range (`OOR >' in output spreadsheet)
was set to the maximum value of the standard curve for that cytokine. Any value
that was under-range (`OOR <l in output spreadsheet) was set to zero. All values
that were extrapolated from the standard curve were left unchanged.

\begin{table}[!h] \centering
  \caption{Luminex Panel}
  \label{tab:luminex_panel}
  \input{../tables/luminex_panel.tex}
\end{table}

\subsection{data aggregation and meta-analysis}

% TODO explain what the colors mean
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/metaanalysis.png}

  \endgroup
  \caption[Meta-analysis overview]
  {Overview of strategy used for meta-analysis}
  \label{fig:meta_overview}
\end{figure*}

In order to perform meta-analysis on all experimental data generate using the
\gls{dms} system, we developed a program to curate and aggregate the raw
datafiles into a \gls{sql} database (\cref{fig:meta_overview}).

The data files to be aggregated included Microsoft Excel files which held
timeseries measurements for cell cultures (eg cell counts, viability, glucose,
\gls{il2} added, media added, and media removed), \gls{fcs} files for cellular
phenotypes, and FlowJo files which held gating parameters and statistics based
on the \gls{fcs} files. Additional information which was held in electronic lab
notebooks (eg OneNote files) was not easily parsable, and thus this data was
summarized in YAML files. The data included in these YAML files included reagent
characteristics (vendor, catalog number, lot number, manufacturing date), cell
donor characteristics (age, \gls{bmi}, phenotype, demographic, gender), and all
experimental parameters such as the number of bead or \gls{dms} added.

To aggregate the data in a database, we wrote a program using Python, R, and
Docker which retrieved the data from its source location and inserted the data
in a Postgres database. This program included checks to ensure the integrity of
source data (for example, flagging entries which had a reagent whose
manufacturing date was after the date the experiment started, which signifies a
human input error).

\subsection{statistical analysis}\label{sec:statistics}

For 1-way \gls{anova} analysis with Tukey multiple comparisons test,
significance was assessed using the \inlinecode{stat\_compare\_means} function
with the \inlinecode{t.test} method from the \inlinecode{ggpubr} library in R.
For 2-way \gls{anova} analysis, the significance of main and interaction effects
was determined using the car library in R.

% TODO not all of this stuff applied to my regressions
For least-squares linear regression, statistical significance was evaluated the
\inlinecode{lm} function in R. Stepwise regression models were obtained using
the \inlinecode{stepAIC} function from the \inlinecode{MASS} package with
forward and reverse stepping. All results with categorical variables are
reported relative to baseline reference. Each linear regression was assessed for
validity using residual plots (to assess constant variance and independence
assumptions), QQplots and Shapiro-Wilk normality test (to assess normality
assumptions), Box-Cox plots (to assess need for power transformations), and
lack-of-fit tests where replicates were present (to assess model fit in the
context of pure error). Statistical significance was evaluated at $\upalpha$ =
0.05.

\subsection{flow cytometry}\label{sec:flow_cytometry}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/gating_strategy.png}

  \endgroup
  \caption[Gating Strategy]
  {Gating strategy for quantifying \ptmemp{}, \pthp{}, and \ptcarp{}.}
  \label{fig:gating_strategy}
\end{figure*}

% METHOD add flow cytometry

\begin{table}[!h] \centering
  \caption{\glspl{mab} used for flow cytometry}
  \label{tab:flow_mabs}
  \input{../tables/flow_mabs.tex}
\end{table}

\section{results}

\subsection{DMSs can be fabricated in a controlled manner}

Two types of gelatin-based microcariers, \gls{cus} and \gls{cug}, were
covalently conjugated with varying concentration of \gls{snb} and then coated
with \gls{stp} and \glspl{mab} to make \glspl{dms}. Aside from slight
differences in swelling ratio and crosslinking chemistry {\#}[Purcell
documentation], the properties of \gls{cus} and \gls{cug} were the same
(\cref{tab:carrier_props}). We chose to continue with the \gls{cus}-based
\glspl{dms}, which showed higher overall \gls{stp} binding compared to
\gls{cug}-based \glspl{dms} (\cref{fig:cug_vs_cus}). We showed that by varying
the concentration of \gls{snb}, we were able to precisely control the amount of
attached biotin (\cref{fig:biotin_coating}), mass of attached \gls{stp}
(\cref{fig:stp_coating}), and mass of attached \glspl{mab}
(\cref{fig:mab_coating}). Furthermore, we showed that the microcarriers were
evenly coated with \gls{stp} on the surface and throughout the interior as
evidenced by the presence of biotin-binding sites occupied with \gls{stp}-\gls{fitc}
on the microcarrier surfaces after the \gls{stp}-coating step
(\cref{fig:stp_carrier_fitc}). Finally, we confirmed that biotinylated
\glspl{mab} were bound to the \glspl{dms} by staining either \gls{stp} or
\gls{stp} and \gls{mab}-coated carriers with \antim{\gls{igg}-\gls{fitc}} and imaging
on a confocal microscope (\cref{fig:mab_carrier_fitc}). Taking this together, we
noted that the maximal \gls{mab} binding capacity occurred near \SI{50}{\nmol}
biotin input (which corresponded to \SI{2.5}{\nmol\per\mg\of{\dms}}) thus we
used this in subsequent processes.

% TODO flip the rows of this figure (right now the text is backward)
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_coating.png}
  \phantomsubcaption\label{fig:stp_carrier_fitc}
  \phantomsubcaption\label{fig:mab_carrier_fitc}
  \phantomsubcaption\label{fig:cug_vs_cus}
  \phantomsubcaption\label{fig:biotin_coating}
  \phantomsubcaption\label{fig:stp_coating}
  \phantomsubcaption\label{fig:mab_coating}

  \endgroup
  \caption[\gls{dms} Coating]
  {\gls{dms} functionalization results.
    \subcap{fig:stp_carrier_fitc}{\gls{stp}-coated or uncoated \glspl{dms}
      treated with \gls{fitcbt} and imaged using a lightsheet microscope.}
    \subcap{fig:mab_carrier_fitc}{\gls{mab}-coated or \gls{stp}-coated
      \glspl{dms} treated with \anti{\gls{igg}} \glspl{mab} and imaged using a
      lightsheet microscope.} \subcap{fig:cug_vs_cus}{Bound \gls{stp} surface
      density on either \gls{cus} or \gls{cug} microcarriers. Surface density
      was estimated using the properties in~\cref{tab:carrier_props}} Total
    binding curve of \subcap{fig:biotin_coating}{biotin},
    \subcap{fig:stp_coating}{\gls{stp}}, and
    \subcap{fig:mab_coating}{\glspl{mab}} as a function of biotin added. }
  \label{fig:dms_coating}
\end{figure*}

% TODO these caption titles suck
% TODO combine this DOE figure into one interaction plot
\begin{table}[!h] \centering
  \caption{Properties of the microcarriers used}
  \label{tab:carrier_props}
  \input{../tables/carrier_properties.tex}
\end{table}

% TODO add chemical equation for which reactions I am describing here

We then asked how sensitive the \gls{dms} manufacturing process was to a variety
of variables. In particular, we focused on the biotin-binding step, since it
appeared that the \gls{mab} binding was quadratically related to biotin binding
(\cref{fig:mab_coating}) and thus controlling the biotin binding step would be
critical to controlling the amount and \glspl{mab} and thus the amount of signal
the T cells receive downstream.

To answer this question, we first performed a \gls{doe} to understand the effect
of reaction parameters on biotin binding. The parameters included in this
\gls{doe} were temperature, microcarrier mass, and \gls{snb} input mass. These
were parameters that we specifically controlled but hypothesized might have some
sensitivity on the final biotin mass attachment rate depending on their noise
and uncertainty. In particular, temperature was `controlled' only by allowing
the microcarrier suspension to come to \gls{rt} after autoclaving. After
performing a full factorial \gls{doe} with three center points as the target
reaction conditions, we found that the final biotin binding mass is only highly
dependent on biotin input concentration (\cref{fig:dms_qc_doe}). Overall,
temperature had no effect and carrier mass had no effect at higher temperatures,
but carrier mass had a slightly positive effect when temperature was low. This
could be because lower temperature might make spontaneous decay of \gls{snb}
occur slower, which would give \gls{snb} molecule more opportunity to diffuse
into the microcarriers and react with amine groups to form attachments. It seems
that concentration only has a linear effect and doesn't interact with any of the
other variables, which is not surprisingly given the behavior observed in
(\cref{fig:biotin_coating})

We also observed that the reaction pH does not influence the amount of biotin
attached (\cref{fig:dms_qc_ph}), which indicates that while higher pH might
increase the number of deprotonated amines on the surface of the microcarrier,
it also increases the number of \ce{OH-} groups which can spontaneously
hydrolyze the \gls{snb} in solution.

Furthermore, we observed that washing the microcarriers after autoclaving
increases the biotin binding rate (\cref{fig:dms_qc_washes}). While we did not
explore this further, one possible explanation for this behavior is that the
microcarriers have some loose protein in the form of powder or soluble peptides
that competes for \gls{snb} binding against the surface of the microcarriers,
and when measuring the supernatent using the \gls{haba} assay, these soluble or
lightly-suspended peptides/protein fragments are also measured and therefore
inflate the readout.

Lastly, we asked what the effect on reaction pH had on spontaneous degradation
of \gls{snb} while in solution. If the \gls{snb} significantly degrades within
minutes of preparation, then it is important to carefully control the timing
between \gls{snb} solution preparation and addition to the microcarriers. We
found that in the presence of \gls{di} water, \gls{snb} is extremely stable
(\cref{fig:dms_snb_decay_curves}) where it decays rapidly in the presence of
\gls{pbs} buffered to pH of 7.1. In fact, the \gls{di} water curve actually
decreases slightly, possibly due to \gls{snb} absorbing to the plate surface.
\gls{snb} is known to hydrolyze in the presence of \ce{OH-}, but the lack of
hydrolysis in \gls{di} water can be explained by the fact that biotin itself is
acidic, and thus the reaction is self-inhibitory in an unbuffered and neutral pH
system. Because we dissolve our \gls{snb} in \gls{di} water prior to adding it
to the microcarrier suspension (which itself is in \gls{pbs}) this result
indicated that hydrolysis is not of concern when adding \gls{snb} within
minutes.

% TODO use the water vs pbs curve here
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_qc.png}
  \phantomsubcaption\label{fig:dms_qc_doe}
  \phantomsubcaption\label{fig:dms_qc_ph}
  \phantomsubcaption\label{fig:dms_qc_washes}
  \phantomsubcaption\label{fig:dms_snb_decay_curves}

  \endgroup
  \caption[\gls{dms} Quality Control]
  {\gls{dms} quality control investigation and development
    \subcap{fig:dms_qc_doe}{\gls{doe} investigating the effect of initial mass
      of microcarriers, reaction temperature, and biotin concentration on
      biotin attachment.}
    \subcap{fig:dms_qc_ph}{Effect of reaction ph on biotin attachment.}
    \subcap{fig:dms_qc_washes}{effect of post-autoclave washing of the
      microcarriers on biotin attachment.}
    \subcap{fig:dms_snb_decay_curves}{Hydrolysis curves of \gls{snb} in
      \gls{pbs} or \gls{di} water.}
    All statistical tests where p-values are noted are given by two-tailed t
    tests.
  }
  \label{fig:dms_flowchart}
\end{figure*}

We also investigated the reaction kinetics of all three coating steps.

To quantify the reaction kinetics of the biotin binding step, we reacted
multiple batches of \SI{20}{\mg\per\ml} microcarriers in \gls{pbs} at \gls{rt}
with \gls{snb} in parallel and sacrificially analyzed each at varying timepoints
using the \gls{haba} assay. This was performed at two different concentrations.
We observed that for either concentration, the reaction was over in
\SIrange{20}{30}{\minute} (\cref{fig:dms_biotin_rxn_mass}). Furthermore, when
put in terms of fraction of input \gls{snb}, we observed that the curves are
almost identical (\cref{fig:dms_biotin_rxn_frac}). Given this, the reaction step
for biotin attached was set to \SI{30}{\minute}.

% TODO these numbers might be totally incorrect
Next, we quantified the amount of \gls{stp} reacted with the surface of the
biotin-coated microcarriers. Different batches of biotin-coated \glspl{dms} were
coated with \SI{40}{\ug\per\ml} \gls{stp} and sampled at various timepoints
using the \gls{bca} assay to indirectly quantify the amount of attached
\gls{stp} mass. We found this reaction took \SI{45}{\minute}
(\cref{fig:dms_stp_per_time}).

% TODO find real numbers for this
Finally, we used the reaction data from the \gls{stp} binding curve to estimate
the \gls{mab} binding curve. Assuming a quasi-steady-state paradigm, we
estimated that the diffusion rate coefficient for the microcarriers was
{\#}{diffusion rate}. Using this diffusion rate and the maximum mass of
\glspl{mab} bound the microcarriers (\cref{fig:mab_coating}), we estimated that
the \gls{mab} reaction should proceed in {\#}{mab curve}.

% TODO add additional paragraph about how this diffusion coefficient was used to
% estimate the wash step times.

% RESULT talk about the kinetic stuff in this figure more
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_timing.png}
  \phantomsubcaption\label{fig:dms_biotin_rxn_mass}
  \phantomsubcaption\label{fig:dms_biotin_rxn_frac}
  \phantomsubcaption\label{fig:dms_stp_per_time}
  \phantomsubcaption\label{fig:dms_mab_per_time}
  \phantomsubcaption\label{fig:dms_biotin_washed}

  \endgroup
  \caption[\gls{dms} Reaction kinetics]
  {Reaction kinetics for microcarrier functionalization.
    \subcap{fig:dms_biotin_rxn_mass}{Biotin mass bound per time}
    \subcap{fig:dms_biotin_rxn_frac}{Fraction of input biotin bound per time}
    \subcap{fig:dms_stp_per_time}{\Gls{stp} bound per time. Each dot is an
      experimental run and the line is the fitted model.}
    \subcap{fig:dms_mab_per_time}{Simulated \glspl{mab} bound per time.}
    \subcap{fig:dms_biotin_washed}{Biotin quantification via the \gls{haba}
      assay after washing.}
  }
  \label{fig:dms_kinetics}
\end{figure*}

\subsection{DMSs can efficiently expand T cells compared to beads}

% TODO add other subfigures here
We next sought to determine how our \glspl{dms} could expand T cells compared to
state-of-the-art methods used in industry. All bead expansions were performed as
per the manufacturer’s protocol, with the exception that the starting cell
densities were matched between the beads and carriers to
~\SI{2.5e6}{\cell\per\ml}. Throughout the culture we observed that T cells in
\gls{dms} culture grew in tight clumps on the surface of the \glspl{dms} as well
as inside the pores of the \glspl{dms}
(\cref{fig:dms_cells_phase,fig:dms_cells_fluor}). Furthermore, we observed that
the \glspl{dms} conferred greater expansion compared to traditional beads, and
significantly greater expansion after \SI{12}{\day} of culture {Figure X}. We
also observed no T cell expansion using \glspl{dms} coated with an isotype
control mAb compared to \glspl{dms} coated with \acd{3}/\acd{28} \glspl{mab}
{Figure X}, confirming specificity of the expansion method.

% TODO make sure the day on these is correct
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/cells_on_dms.png}
  \phantomsubcaption\label{fig:dms_cells_phase}
  \phantomsubcaption\label{fig:dms_cells_fluor}

  \endgroup
  \caption[T cells growing on \glspl{dms}]
  {Cells grow in tight clusters in and around functionalized \gls{dms}.
    \subcap{fig:dms_cells_phase}{Phase-contrast image of T cells growing on
      \glspl{dms} on day 7}
    \subcap{fig:dms_cells_fluor}{Confocal images of T cells in varying z-planes
      growing on \glspl{dms} on day 9. \Glspl{dms} were stained using
      \gls{stppe} (red) and T cells were stained using \acd{45}-\gls{af647}.}
  }
  \label{fig:dms_cells}
\end{figure*}

% RESULT for this figure
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_expansion.png}
  \phantomsubcaption\label{fig:dms_expansion_bead}
  \phantomsubcaption\label{fig:dms_expansion_isotype}

  \endgroup
  \caption[\glspl{dms} selectively expand T cells]
  {T cells are selectively expanded on \gls{dms}.
    \subcap{fig:dms_expansion_bead}{T cells expanded with either \glspl{dms} or
      bead for 12 days. Significance was assessed using a two-tailed
      heteroschodastic T test.}
    \subcap{fig:dms_expansion_isotype}{T cells grown on \glspl{dms} coated with
      either activating \glspl{mab} or \gls{igg} isotype control \glspl{mab}.}
  }
  \label{fig:dms_expansion}
\end{figure*}

% RESULT talk about this table somewhere
\begin{table}[!h] \centering
  \caption{Regression for fraction of cells in \gls{dms} at day 14}
  \label{tab:inside_regression}
  \input{../tables/inside_fraction_regression.tex}
\end{table}

% TODO state the CI of what are inside the carriers
We also asked how many cells were inside the \glspl{dms} vs. free-floating in
suspension and/or loosely attached to the surface. We qualitatively verified the
presence of cells inside the \glspl{dms} using a \gls{mtt} stain to opaquely
mark cells and enable visualization on a brightfield microscope
(\cref{fig:dms_inside_bf}). After seeding \glspl{dms} at different densities and
expanding for \SI{14}{\day}, we filtered the \glspl{dms} out of the cell
suspension and digested them using dispase to free any cells attached on the
inner surface. We observed that approximately \SI{15}{\percent} of the total
cells after \SI{14}{\day} were on the interior surface of the \glspl{dms}
(\cref{fig:dms_inside_regression}).

%, and this did not significantly change with initial seeding density (Supplemental Table 1).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/apoptosis.png}
  \phantomsubcaption\label{fig:apoptosis_annV}
  \phantomsubcaption\label{fig:apoptosis_cas}
  \phantomsubcaption\label{fig:apoptosis_bcl2}

  \endgroup
  \caption[Apoptosis Quantification for \glspl{dms}]
  {\glspl{dms} produce cells with lower apoptosis marker expression on average
    compared to bead.
    \subcap{fig:apoptosis_annV}{Quantification of apoptosis and necrosis by
      \gls{anv} and \gls{pi}.}
    \subcap{fig:apoptosis_cas}{Quantification of Caspase-3/7 expression using
      CellEvent dye.}
    \subcap{fig:apoptosis_bcl2}{Quantification of BCL-2 expression using
      \gls{elisa}. All statistical tests shown are two-tailed homoschodastic
      t-tests.}
  }
  \label{fig:dms_flowchart}
\end{figure*}

% TODO double check the timing of this experiment (it might not be day 14)

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_inside.png}
  \phantomsubcaption\label{fig:dms_inside_bf}
  \phantomsubcaption\label{fig:dms_inside_regression}

  \endgroup
  \caption[A subset of T cells grow in interior of \glspl{dms}]
  {A percentage of T cells grow in the interior of \glspl{dms}.
    \subcap{fig:dms_inside_bf}{T cells stained dark with \gls{mtt} after
      growing on either coated or uncoated \glspl{dms} for 14 days visualized
      with brightfield microscope.}
    \subcap{fig:dms_inside_regression}{Linear regression performed on T cell
      percentages harvested on the interior of the \glspl{dms} vs the initial
      starting cell density.}
  }
  \label{fig:dms_inside}
\end{figure*}

\subsection{DMSs lead to greater expansion and memory and CD4+ phenotypes}

After observing differences in expansion, we further hypothesized that the
\gls{dms} cultures could lead to a different T cell phenotype. In particular, we
were interested in the formation of naïve and memory T cells, as these represent
a subset with higher replicative potential and therefore improved clinical
prognosis\cite{Gattinoni2011, Wang2018}. We measured naïve and memory T cell
frequency staining for CCR7 and CD62L (both of which are present on lower
differentiated T cells such as naïve, central memory, and stem memory
cells\cite{Gattinoni2012}). Using three donors, we noted again \glspl{dms}
produced more T cells over a \SI{14}{\day} expansion than beads, with
significant differences in number appearing as early after \SI{5}{\day}
(\cref{fig:dms_exp_fold_change}). Furthermore, we noted that \glspl{dms}
produced more memory/naïve cells after \SI{14}{\day} when compared to beads for
all donors (\cref{fig:dms_exp_mem,fig:dms_exp_cd4}) showing that the \gls{dms}
platform is able to selectively expand potent, early differentiation T cells.

Of additional interest was the preservation of the CD4+ compartment. In healthy
donor samples (such as those used here), the typical CD4:CD8 ratio is 2:1. We
noted that \glspl{dms} produced more CD4+ T cells than bead cultures as well as
naïve/memory, showing that the \gls{dms} platform can selectively expand CD4 T
cells to a greater degree than beads (Figure 2c). The trends held true when
observing the CD4+ and CD8+ fractions of the naïve/memory subset (CD62L+CCR7+)
(\cref{fig:dms_exp_mem4,fig:dms_exp_mem8}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_vs_bead_expansion.png}
  \phantomsubcaption\label{fig:dms_exp_fold_change}
  \phantomsubcaption\label{fig:dms_exp_mem}
  \phantomsubcaption\label{fig:dms_exp_cd4}
  \phantomsubcaption\label{fig:dms_exp_mem4}
  \phantomsubcaption\label{fig:dms_exp_mem8}

  \endgroup
  \caption[\gls{dms} vs bead expansion]
  {\gls{dms} lead to superior expansion of T cells compared to beads across
    multiple donors.
    \subcap{fig:dms_exp_fold_change}{Longitudinal fold change of T cells grown
      using either \glspl{dms} or beads. Significance was evaulated using t
      tests at each timepoint}
    Fold change of subpopulations expanded using either \gls{dms} or beads at
    day 14, including 
    \subcap{fig:dms_exp_mem}{\ptmem{} cells},
    \subcap{fig:dms_exp_cd4}{\pth{} cells},
    \subcap{fig:dms_exp_mem4}{\ptmemh{} cells}, and
    \subcap{fig:dms_exp_mem8}{\ptmemk{} cells}. \sigkey{}
  }
  \label{fig:dms_exp}
\end{figure*}

% TODO add a paragraph for this figure

% TODO this figure has weird proportions
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/dms_phenotypes.png}
  \phantomsubcaption\label{fig:dms_phenotype_mem}
  \phantomsubcaption\label{fig:dms_phenotype_cd4}

  \endgroup
  \caption[Representative flow plots of \ptmem{} and \pth{} T cells]
  {Representative flow plots of \ptmem{} and \pth{} T cells at day 14 of
    expansion using either beads or \glspl{dms}. For three representative donor
    samples, phenotypes are shown for \subcap{fig:dms_phenotype_mem}{\ptmem{}}
    and \subcap{fig:dms_phenotype_cd4}{\pth}. Each population was also gated on
    \cdp{3} T cells.
  }
  \label{fig:dms_phenotype}
\end{figure*}

\subsection*{DMSs can be used to produce functional CAR T cells}

After optimizing for naïve/memory and CD4 yield, we sought to determine if the
\glspl{dms} were compatible with lentiviral transduction protocols used to
generate \gls{car} T cells27,28. We added a \SI{24}{\hour} transduction step on
day 1 of the \SI{14}{\day} expansion to insert an anti-CD19 \gls{car}29 and
subsequently measured the surface expression of the \gls{car} on day 14
\cref{fig:car_production_flow_pl,fig:car_production_endpoint_pl}. We noted that
there was robust \gls{car} expression in over \SI{25}{\percent} of expanded T
cells, and there was no observable difference in \gls{car} expression between
beads and \glspl{dms}.

We also verified the functionality of expanded \gls{car} T cells using a
degranulation assay\cite{Zheng2012}. Briefly, T cells were cocultured with
target cells (either wild-type K562 or CD19-expressing K562 cells) for
\SI{4}{\hour}, after which the culture was analyzed via flow cytometry for the
appearance of CD107a on CD8+ T cells. CD107a is found on the inner-surface of
cytotoxic granules and will emerge on the surface after cytotoxic T cells are
activated and degranulate. Indeed, we observed degranulation in T cells expanded
with both beads and \glspl{dms}, although not to an observably different degree
\cref{fig:car_production_flow_degran,fig:car_production_endpoint_degran}. Taken
together, these results indicated that the \glspl{dms} provide similar
transduction efficiency compared to beads.

We also verified that expanded T cells were migratory using a chemotaxis assay
for CCL21; since \glspl{dms} produced a larger percentage of naïve and memory T
cells (which have CCR7, the receptor for CCL21) we would expect higher migration
in \gls{dms}-expanded cells vs.\ their bead counterparts. Indeed, we noted a
significantly higher migration percentage for T cells grown using \glspl{dms}
versus beads (\cref{fig:car_production_migration}). Interestingly, there also
appeared to be a decrease in CCL21 migration between transduced and untransduced
T cells expanded using beads, but this interaction effect was only weakly
significant (p = 0.068). No such effect was seen for \gls{dms}-expanded T cells,
showing that migration was likely independent of \gls{car} transduction.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/car_production.png}
  \phantomsubcaption\label{fig:car_production_flow_pl}
  \phantomsubcaption\label{fig:car_production_endpoint_pl}
  \phantomsubcaption\label{fig:car_production_flow_degran}
  \phantomsubcaption\label{fig:car_production_endpoint_degran}
  \phantomsubcaption\label{fig:car_production_migration}

  \endgroup
  \caption[\glspl{dms} produce functional \gls{car} T cells]
  {\glspl{dms} produce functional \gls{car} T cells.
    \subcap{fig:car_production_flow_pl}{Representative flow cytometry plot for
      transduced or untransduced T cells stained with \gls{ptnl}.}
    \subcap{fig:car_production_endpoint_pl}{Endpoint plots with \gls{anova} for
      transduced or untransduced T cells stained with \gls{ptnl}.}
    \subcap{fig:car_production_flow_degran}{Representative flow plot for
      degenerating T cells.}
    \subcap{fig:car_production_endpoint_degran}{Endpoint plots for transduced or
    untransduced T cells stained with \cd{107a} for the degranulation assay.}
    \subcap{fig:car_production_migration}{Endpoint plot for transmigration assay
    with \gls{anova}.} All data is from T cells expanded for \SI{14}{\day}.
  }
  \label{fig:car_production}
\end{figure*}

In addition to CD19 \gls{car} T cells, we also demonstrated that the \gls{dms}
platform can be used to expand \gls{car} T cells against \gls{bcma}. Analogously
to the case with CD19, \gls{dms} and bead produced similar fractions of \ptcar{}
cells (albeit in this case at day 7 and with an undefined \gls{moi})
(\cref{fig:car_bcma_percent}). Also consistent with CD19 and non-\gls{car} data,
we also found that the number of \ptcar{} T cells was greater for \gls{dms} than
for bead (\cref{fig:car_bcma_total}).

% TODO the right half if bigger than the left half
% TODO add memory stuff to this since I have it (it wasn't the right size so I
% haven't included it yet)?
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/car_bcma.png}
  \phantomsubcaption\label{fig:car_bcma_percent}
  \phantomsubcaption\label{fig:car_bcma_total}

  \endgroup
  \caption[BMCA Transduction Results]
  {\glspl{dms} produce larger numbers of \gls{bcma} \gls{car} T cells compared
    to beads.
    \subcap{fig:car_bcma_percent}{\ptcarp{} at day 14.}
    \subcap{fig:car_bcma_total}{Total number of \ptcarp{} cells at day 14.}
  }
  \label{fig:car_bcma}
\end{figure*}


\subsection{DMSs efficiently expand T cells in Grex bioreactors}

% RESULT update this in light of the grex data
We also asked if the \gls{dms} platform could expand T cells in a static
bioreactor such a Grex. We incubated T cells in a Grex analogously to that for
plates and found that T cells in Grex bioreactors expanded as efficiently as
bead over \SI{14}{\day} and had similar viability
(\cref{fig:grex_results_fc,fig:grex_results_viability}). Furthermore, consistent
with past results, \glspl{dms}-expanded T cells had higher \pthp{} compared to
beads, but only had slightly higher \ptmemp{} compared to beads
(\cref{fig:grex_mem,fig:grex_cd4}).

% TODO is this discussion stuff?
These discrepancies might be explained in light of our other data as follows.
The Grex bioreactor has higher media capacity relative to its surface area, and
we did not move the T cells to a larger bioreactor as they grew in contrast with
our plate cultures. This means that the cells had higher growth area
constraints, which may have nullified any advantage to the expansion that we
seen elsewhere (\cref{fig:dms_exp_fold_change}). Furthermore, the higher growth
area could mean higher signaling and higher differentiation rate to effector T
cells, which was why the \ptmemp{} was so low compared to other data
(\cref{fig:dms_phenotype_mem}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/grex_results.png}
  \phantomsubcaption\label{fig:grex_results_fc}
  \phantomsubcaption\label{fig:grex_results_viability}
  \phantomsubcaption\label{fig:grex_mem}
  \phantomsubcaption\label{fig:grex_cd4}

  \endgroup
  \caption[Grex bioreactor results]
  {\glspl{dms} expand T cells robustly in Grex bioreactors.
    \subcap{fig:grex_results_fc}{Fold change of T cells over time.}
    \subcap{fig:grex_results_viability}{Viability of T cells over time.}
    \subcap{fig:grex_mem}{\ptmemp{}} and 
    \subcap{fig:grex_cd4}{\pthp{}} of T cells after \SI{14}{\day}
    of expansion. Significance tests were performed using the Wilcoxon
   non-parametric test.
  }
  \label{fig:grex_results}
\end{figure*}

We also quantified the cytokines released during the Grex expansion using
Luminex. We noted that in nearly all cases, the \gls{dms}-expanded T cells
released higher concentrations of cytokines compared to beads
(\cref{fig:grex_luminex}). This included higher concentrations of
pro-inflammatory cytokines such as GM-CSF, \gls{ifng}, and \gls{tnfa}. This
demonstrates that \gls{dms} could lead to more robust activation and fitness.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/grex_luminex.png}

  \endgroup
  \caption[Grex luminex results]
  {\gls{dms} lead to higher cytokine production in Grex bioreactors.}
  \label{fig:grex_luminex}
\end{figure*}

% FIGURE grex + car (maybe, IDK if I actually have this data)

\subsection{DMSs do not leave antibodies attached to cell product}

We asked if \glspl{mab} from the \glspl{dms} detached from the \gls{dms} surface
and could be detected on the final T cell product. This test is important for
clinical translation as any residual \glspl{mab} on T cells injected into the
patient could elicit an undesirable \antim{\gls{igg}} immune response. We did
not detect the presence of either \ahcd{3} or \ahcd{28} \glspl{mab} (both of
which were \gls{igg}) on the final T cell product after \SI{14}{\day} of
expansion (\cref{fig:nonstick}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/nonstick.png}

  \endgroup
  \caption[\glspl{mab} do not detach from \glspl{dms}]
  {\glspl{mab} do not detach from microcarriers onto T cells in a detectable
    manner. Plots are representative manufacturing runs harvest after
    \SI{14}{\day} of expansion and stained with \anti{\gls{igg}}.
  }
  \label{fig:nonstick}
\end{figure*}

\subsection{DMSs consistently outperform bead-based expansion compared to
beads in a variety of conditions}

n order to establish the robustness of our method, we combined all experiments
performed in our lab using beads or \glspl{dms} and combined them into one
dataset. Since each experiment was performed using slightly different process
conditions, we hypothesized that performing causal inference on such a dataset
would not only indicate if the \glspl{dms} indeed led to better results under a
variety of conditions, but would also indicate other process parameters that
influence the outcome. The dataset was curated by compiling all experiments and
filtering those that ended at day 14 and including flow cytometry results for
the \ptmem{} and \pth{} populations. We further filtered our data to only
include those experiments where the surface density of the CD3 and CD28
\gls{mab} were held constant (since some of our experiments varied these on the
\glspl{dms}). This ultimately resulted in a dataset with 162 runs spanning 15
experiments between early 2017 and early 2021.

% TODO add some correlation analysis to this

Since the aim of the analysis was to perform causal inference, we determined 6
possible treatment variables which we controlled when designing the experiments
included in this dataset. Obviously the principle treatment parameter was
‘activation method’ which represented the effect of activating T cells with
either beads or our DMS method. We also included ‘bioreactor’ which was a
categorical for growing the T cells in a Grex bioreactor vs polystyrene plates,
‘feed criteria’ which represented the criteria used to feed the cells (using
media color or a glucose meter), ‘IL2 Feed Conc’ as a continuous parameter for
the concentration of IL2 added each feed cycle, and ‘CD19-CAR Transduced’
representing if the cells were lentivirally transduced or not. Unfortunately,
many of these parameters correlated with each other highly despite the large
size of our dataset, so the only two parameters for which causal relationships
could be evaluated were ‘activation method’ and ‘bioreactor’. We should also
note that these were not the only set of theoretical treatment parameters that
we could have used. For example, media feed rate is an important process
parameter, but this was dependent on the feeding criteria and the growth rate of
the cells, which in turn is determined by activation method. Therefore, ‘media
feed rate’ (or similar) is a ‘post-treatment parameter’ and would have violated
the backdoor criteria and severely biased our estimates of the treatment
parameters themselves.

In addition to these treatment parameters, we also included covariates to
improve the precision of our model. Among these were donor parameters including
age, \gls{bmi}, demographic, and gender, as well as the initial viability and
CD4/CD8 ratio of the cryopreserved cell lots used in the experiments. We also
included the age of key reagents such as IL2, media, and the anti-aggregate
media used to thaw the T cells prior to activation. Each experiment was
performed by one of three operators, so this was included as a three-level
categorical parameter. Lastly, some of our experiments were sampled
longitudinally, so we included a boolean categorical to represented this
modification as removing conditioned media as the cell are expanding could
disrupt signaling pathways.

% TODO the real reason we log-transformed was because box-cox and residual plots
We first asked what the effect of each of our treatment parameters was on the
responses of interest, which were fold change of the cells, the \ptmemp{}, and
\dpthp{} (the shift in \pthp{} at day 14 compared to the initial \pthp{}). We
performed a linear regression using activation method and bioreactor as
predictors (the only treatments that were shown to be balanced)
(\cref{tab:ci_treat}). Note that fold change was log transformed to reflect the
exponential nature of T cell growth. We observe that the treatments are
significant in all cases except for the \dpthp{}; however, we also observe that
relatively little of the variability is explained by these simple models ($R^2$
between 0.17 and 0.44).

% TODO add the regression diagnostics to this
We then included all covariates and unbalanced treatment parameters and
performed linear regression again
(\cref{tab:ci_controlled,fig:metaanalysis_fx}). We observe that after
controlling for additional noise, the models explained much more variability
($R^2$ between 0.76 and 0.87) and had relatively constant variance and small
deviations for normality as per the assumptions of regression analysis {Figure
  X}. Furthermore, the coefficient for activation method in the case of fold
change changed very little but still remained quite high (note the
log-transformation) with \SI{143}{\percent} increase in fold change compared to
beads. Furthermore, the coefficient for \ptmemp{} dropped to about
\SI{2.7}{\percent} different and almost became non-significant at $\upalpha$ =
0.05, and the \dpthp{} response increased to almost a \SI{9}{\percent} difference
and became highly significant. Looking at the bioreactor treatment, we see that
using the bioreactor in the case of fold change and \ptmemp{} is actually harmful
to the response, while at the same time it seems to increase the \dpthp{}
response. We should note that this parameter merely represents whether or not
the choice was made experimentally to use a bioreactor or not; it does not
indicate why the bioreactor helped or hurt a certain response. For example,
using a Grex entails changing the cell surface and feeding strategy for the T
cells, and any one of these ‘mediating variables’ might actually be the cause of
the responses.

% TODO these tables have extra crap in them that I don't need to show
\begin{table}[!h] \centering
  \caption{Causal Inference on treatment variables only}
  \label{tab:ci_treat}
  \input{../tables/causal_inference_treat.tex}
\end{table}

\begin{table}[!h] \centering
  \caption{Causal Inference on treatment variables and control variables}
  \label{tab:ci_controlled}
  \input{../tables/causal_inference_control.tex}
\end{table}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/metaanalysis_effects.png}
  \phantomsubcaption\label{fig:metaanalysis_fx_exp}
  \phantomsubcaption\label{fig:metaanalysis_fx_mem}
  \phantomsubcaption\label{fig:metaanalysis_fx_cd4}

  \endgroup
  \caption[Meta-analysis effect sizes]
  {\glspl{dms} exhibit superior performance compared to beads controlling for
    many experimental and process conditions. Effect sizes for
    \subcap{fig:metaanalysis_fx_exp}{fold change},
    \subcap{fig:metaanalysis_fx_mem}{\ptmemp{}}, and
    \subcap{fig:metaanalysis_fx_cd4}{\dpthp{}}. The dotted line represents
    the mean of the bead population. The red and blue dots represent the effect
    size of using \gls{dms} instead of beads only considering treatment
    variables (\cref{tab:ci_treat}) or treatment and control variables
    (\cref{tab:ci_controlled}) respectively.
  }
  \label{fig:metaanalysis_fx}
\end{figure*}

\section{discussion}

% TODO this is fluffy
We have developed a T cell expansion system that recapitulates key features of
the in vivo lymph node microenvironment using DMSs functionalized with
activating mAbs. This strategy provided superior expansion with higher number of
naïve/memory and CD4+ T cells compared to state-of-the-art microbead technology
(Figure 2). Other groups have used biomaterials approaches to mimic the in vivo
microenvironment13–15,17,34; however, to our knowledge this is the first system
that specifically drives naïve/memory and CD4+ T cell formation in a scalable,
potentially bioreactor-compatible manufacturing process.

Memory and naïve T cells have been shown to be important clinically. Compared to
effectors, they have a higher proliferative capacity and are able to engraft for
months; thus they are able to provide long-term immunity with smaller
doses19,35. Indeed, less differentiated T cells have led to greater survival
both in mouse tumor models and human patients20,36,37. Furthermore, clinical
response rates have been positively correlated with T cell expansion, implying
that highly-proliferative naïve and memory T cells are a significant
contributor18,38. Circulating memory T cells have also been found in complete
responders who received CAR T cell therapy39.

Similarly, CD4 T cells have been shown to play an important role in CAR T cell
immunotherapy. It has been shown that CAR T doses with only CD4 or a mix of CD4
and CD8 T cells confer greater tumor cytotoxicity than only CD8 T cells22,40.
There are several possible reasons for these observations. First, CD4 T cells
secrete proinflammatory cytokines upon stimulation which may have a synergistic
effect on CD8 T cells. Second, CD4 T cells may be less prone to exhaustion and
may more readily adopt a memory phenotype compared to CD8 T cells22. Third, CD8
T cells may be more susceptible than CD4 T cells to dual stimulation via the CAR
and endogenous T Cell Receptor (TCR), which could lead to overstimulation,
exhaustion, and apoptosis23. Despite evidence for the importance of CD4 T cells,
more work is required to determine the precise ratios of CD4 and CD8 T cell
subsets to be included in CAR T cell therapy given a disease state.

% TODO this mentions the DOE which is in the next aim
When analyzing all our experiments comprehensively using causal inference, we
found that all three of our responses were significantly increased when
controlling for covariates (Figure 3, Table 2). By extension, this implies that
not only will DMSs lead to higher fold change overall, but also much higher fold
change in absolute numbers of memory and CD4+ T cells. Furthermore, we found
that using a Grex bioreactor is detrimental to fold change and memory percent
while helping CD4+. Since there are multiple consequences to using a Grex
compared to tissue-treated plates, we can only speculate as to why this might be
the case. Firstly, when using a Grex we did not expand the surface area on which
the cells were growing in a comparable way to that of polystyrene plates. In
conjunction with our DOE data {Figure X} which shows that high DMS
concentrations favor CD4+ and don’t favor memory fraction, one possible
explanation is that the T cells spent longer times in highly activating
conditions (since the beads and DMSs would have been at higher per-area
concentrations in the Grex vs polystyrene plates). Furthermore, the simple fact
that the T cells spent more time at high surface densities could simply mean
that the T cells didn’t expands as much due to spacial constraints. This would
all be despite the fact that Grex bioreactors are designed to lead to better T
cell expansion due to their gas-permeable membranes and higher media-loading
capacities. If anything, our data suggests we were using the bioreactor
sub-optimally, and the hypothesized causes for why our T cells did not expand
could be verified with additional experiments varying the starting cell density
and/or using larger bioreactors.

A key question in the space of cell manufacturing is that of donor variability.
To state this precisely, this is a second order interaction effect that
represents the change in effect of treatment (eg bead vs DMS) given the donor.
While our meta-analysis was relatively large compared to many published
experiments usually seen for technologies at this developmental stage, we have a
limited ability in answering this question. We can control for donor as a
covariate, and indeed our models show that many of the donor characteristics are
strongly associated with each response on average, but these are first order
effects and represent the association of age, gender, demographic, etc given
everything else in the model is held constant. Second order interactions require
that our treatments be relatively balanced and random across each donor, which
is a dubious assumption for our dataset. However, this can easily be solved by
performing more experiments with these restrictions in mind, which will be a
subject of our future work.

Furthermore, this dataset offers an interesting insight toward novel hypothesis
that might be further investigated. One limitation of our dataset is that we
were unable to investigate the effects of time using a method such as
autoregression, and instead relied on aggregate measures such as the total
amount of a reagent added over the course of the expansion. Further studies
should be performed to investigate the temporal relationship between phenotype,
cytokine concentrations, feed rates, and other measurements which may perturb
cell cultures, as this will be the foundation of modern process control
necessary to have a fully-automated manufacturing system.

In addition to larger numbers of potent T cells, other advantages of our DMS
approach are that the DMSs are large enough to be filtered (approximately 300
µm) using standard 40 µm cell filters or similar. If the remaining cells inside
that DMSs are also desired, digestion with dispase or collagenase may be used.
Collagenase D may be selective enough to dissolve the DMSs yet preserve surface
markers which may be important to measure as critical quality attributes CQAs
{Figure X}. Furthermore, our system should be compatible with
large-scale static culture systems such as the G-Rex bioreactor or perfusion
culture systems, which have been previously shown to work well for T cell
expansion12,50,51. The microcarriers used to create the DMSs also have a
regulatory history in human cell therapies that will aid in clinical
translation.; they are already a component in an approved retinal pigment
epithelial cell product for Parkinson’s patients, and are widely available in 30
countries26.

It is important to note that all T cell cultures in this study were performed up
to 14 days. Others have demonstrated that potent memory T cells may be obtained
simply by culturing T cells as little as 5 days using traditional beads30. It is
unknown if the naïve/memory phenotype of our DMS system could be further
improved by reducing the culture time, but we can hypothesize that similar
results would be observed given the lower number of doublings in a 5 day
culture. We should also note that we investigated one subtype (\ptmem{}) in
this study. Future work will focus on other memory subtypes such as tissue
resident memory and stem memory T cells, as well as the impact of using the DMS
system on the generation of these subtypes.

% TODO this sounds sketchy
Another advantage is that the DMS system appears to induce a faster growth rate
of T cells given the same IL2 concentration compared to beads (Supplemental
Figure 8) along with retaining naïve and memory phenotype. This has benefits in
multiple contexts. Firstly, some patients have small starting T cell populations
(such as infants or those who are severely lymphodepleted), and thus require
more population doublings to reach a usable dose. Our data suggests the time to
reach this dose would be reduced, easing scheduling a reducing cost. Secondly,
the allogeneic T cell model would greatly benefit from a system that could
create large numbers of T cells with naïve and memory phenotype. In contrast to
the autologous model which is currently used for Kymriah and Yescarta,
allogeneic T cell therapy would reduce cost by spreading manufacturing expenses
across many doses for multiple patients52. Since it is economically advantageous
to grow as many T cells as possible in one batch in the allogeneic model
(reduced start up and harvesting costs, fewer required cell donations), the DMSs
offer an advantage over current technology.

% TODO this is already stated in the innovation section
It should be noted that while we demonstrate a method providing superior
performance compared to bead-based expansion, the cell manufacturing field would
tremendously benefit from simply having an alternative to state-of-the-art
methods. The patents for bead-based expansion are owned by few companies and
licensed accordingly; having an alternative would provide more competition in
the market, reducing costs and improving access for academic researchers and
manufacturing companies.

% TODO this isn't relevent to this aim but should be said somewhere
Finally, while we have demonstrated the DMS system in the context of CAR T
cells, this method can theoretically be applied to any T cell immunotherapy
which responds to anti-CD3/CD28 mAb and cytokine stimulation. These include
\glspl{til}, virus-specific T cells (VSTs), T cells engineered to express
$\upgamma\updelta$TCR (TEGs), $\upgamma\updelta$ T cells, T cells with
transduced-TCR, and CAR-TCR T cells53–58. Similar to CD19-CARs used in liquid
tumors, these T cell immunotherapies would similarly benefit from the increased
proliferative capacity, metabolic fitness, migration, and engraftment potential
characteristic of naïve and memory phenotypes59–61. Indeed, since these T cell
immunotherapies are activated and expanded with either soluble mAbs or
bead-immobilized mAbs, our system will likely serve as a drop-in substitution to
provide these benefits.

\chapter{aim 2a}\label{aim2a}

\section{introduction}
\section{methods}

\subsection{study design}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/modeling_overview.png}
  \phantomsubcaption\label{fig:mod_overview_flow}
  \phantomsubcaption\label{fig:mod_overview_doe}

  \endgroup
  \caption[Modeling Overview]
  {Overview of modeling experiments.
    \subcap{fig:mod_overview_flow}{Relationship
      between \gls{doe} experiments and AI driven prediction. \glspl{doe} will
      be used to determine optimal process input conditions, and longitudinal
      multiomics data will be used to fit predictive models. Together, these
      will reveal predictive species that may be used for \glspl{cqa} and
      \glspl{cpp}.}
    \subcap{fig:mod_overview_doe}{Overview of the two \gls{doe} experiments; the
      initial \gls{doe} is given by the blue points and the augmented \gls{doe}
      is given by the blue points.}
  }
  \label{fig:mod_overview}
\end{figure*}

The first DOE resulted in a randomized 18-run I-optimal custom design where each
DMS parameter was evaluated at three levels: IL2 concentration (10, 20, and 30
U/uL), DMS concentration (500, 1500, 2500 carrier/uL), and functionalized
antibody percent (60\%, 80\%, 100\%). These 18 runs consisted of 14 unique
parameter combinations where 4 of them were replicated twice to assess
prediction error. Process parameters for the ADOE were evaluated at multiple
levels: IL2 concentration (30, 35, and 40 U/uL), DMS concentration (500, 1000,
1500, 2000, 2500, 3000, 3500 carrier/uL), and functionalized antibody percent
(100\%) as depicted in Fig.1b. To further optimize the initial region explored
(DOE) in terms of total live CD4+ TN+TCM cells, a sequential adaptive
design-of-experiment (ADOE) was designed with 10 unique parameter combinations,
two of these replicated twice for a total of 12 additional samples (Fig.1b). The
fusion of cytokine and NMR profiles from media to model these responses included
30 cytokines from a custom Thermo Fisher ProcartaPlex Luminex kit and 20 NMR
features. These 20 spectral features from NMR media analysis were selected out
of approximately 250 peaks through the implementation of a variance-based
feature selection approach and some manual inspection steps.

\subsection{DMS fabrication}

\glspl{dms} were fabricated as described in \cref{sec:dms_fab} with the
following modifications in order to obtain a variable functional \gls{mab}
surface density. During the \gls{mab} coating step, the anti-CD3/anti-CD28 mAb
mixture was further combined with a biotinylated isotype control to reduce the
overall fraction of targeted \glspl{mab} (for example the \SI{60}{\percent}
\gls{mab} surface density corresponded to 3 mass parts \acd{3}, 3 mass parts
\acd{28}, and 4 mass parts isotype control).

\subsection{T cell culture}

T cell culture was performed as described in \cref{sec:tcellculture} with the
following modifications. At days 4, 6, 8, and 11, \SI{100}{\ul} media were
collected for the Luminex assay and \gls{nmr} analysis. The volume of removed
media was equivalently replaced during the media feeding step, which took place
immediately after sample collection. Additionally, the same media feeding
schedule was followed for the DOE and ADOE to improve consistency, and the same
donor lot was used for both experiments. All cell counts were performed using
\gls{aopi}.

\subsection{flow cytometry}

Flow cytometry was performed analogously to \cref{sec:flow_cytometry}.

\subsection{Cytokine quantification}

Cytokines were quantified via Luminex as described in
\cref{sec:luminex_analysis}.

\subsection{NMR metabolomics}

Prior to analysis, samples were centrifuged at \SI{2990}{\gforce} for
\SI{20}{\minute} at \SI{4}{\degreeCelsius} to clear any debris\footnote{all
  \gls{nmr} analysis was done by our collaborators at the University of
  Georgia}. 5 uL of 100/3 mM DSS-D6 in deuterium oxide (Cambridge Isotope
Laboratories) were added to 1.7 mm NMR tubes (Bruker BioSpin), followed by 45 uL
of media from each sample that was added and mixed, for a final volume of 50 uL
in each tube. Samples were prepared on ice and in predetermined, randomized
order. The remaining volume from each sample in the rack (approx. 4 uL) was
combined to create an internal pool. This material was used for internal
controls within each rack as well as metabolite annotation.

\gls{nmr} spectra were collected on a Bruker Avance III HD spectrometer at 600
MHz using a 5-mm TXI cryogenic probe and TopSpin software (Bruker BioSpin).
One-dimensional spectra were collected on all samples using the noesypr1d pulse
sequence under automation using ICON NMR software. Two-dimensional \gls{hsqc}
and TOCSY spectra were collected on internal pooled control samples for
metabolite annotation.

One-dimensional spectra were manually phased and baseline corrected in TopSpin.
Two-dimensional spectra were processed in NMRpipe37. One dimensional spectra
were referenced, water/end regions removed, and normalized with the PQN
algorithm38 using an in-house MATLAB (The MathWorks, Inc.) toolbox.

% TODO add the supplemental figure alluded to here?
To reduce the total number of spectral features from approximately 250 peaks and
enrich for those that would be most useful for statistical modeling, a
variance-based feature selection was performed within MATLAB. For each digitized
point on the spectrum, the variance was calculated across all experimental
samples and plotted. Clearly-resolved features corresponding to peaks in the
variance spectrum were manually binned and integrated to obtain quantitative
feature intensities across all samples (Supp.Fig.S24). In addition to highly
variable features, several other clearly resolved and easily identifiable
features were selected (glucose, BCAA region, etc). Some features were later
discovered to belong to the same metabolite but were included in further
analysis.

Two-dimensional spectra collected on pooled samples were uploaded to COLMARm web
server10, where \gls{hsqc} peaks were automatically matched to database peaks.
\gls{hsqc} matches were manually reviewed with additional 2D and proton spectra
to confirm the match. Annotations were assigned a confidence score based upon
the levels of spectral data supporting the match as previously described11.
Annotated metabolites were matched to previously selected features used for
statistical analysis.

% I'm pretty sure this isn't relevant
% Using the list of annotated metabolites obtained above, an approximation of a
% representative experimental spectrum was generated using the GISSMO mixture
% simulation tool.39,40 With the simulated mixture of compounds, generated at 600
% MHz to match the experimental data, a new simulation was generated at 80 MHz to
% match the field strength of commercially available benchtop NMR spectrometers.
% The GISSMO tool allows visualization of signals contributed from each individual
% compound as well as the mixture, which allows annotation of features in the
% mixture belonging to specific compounds.

Several low abundance features selected for analysis did not have database
matches and were not annotated. Statistical total correlation spectroscopy41
suggested that some of these unknown features belonged to the same molecules
(not shown). Additional multidimensional NMR experiments will be required to
determine their identity.

% TODO add footnote saying what I did in this
\subsection{machine learning and statistical analysis}

Linear regression analysis of the \glspl{doe} was performed as described in
\cref{sec:statistics}.

Seven \gls{ml} techniques were implemented to predict three responses related to
the memory phenotype of the cultured T cells under different process parameters
conditions (i.e. Total Live CD4+ TN and TCM, Total Live CD8+ TN+TCM, and Ratio
CD4+/CD8+ TN+TCM). The \gls{ml} methods executed were \gls{rf}, \gls{gbm},
\gls{cif}, \gls{lasso}, \gls{plsr}, \gls{svm}, and DataModeler’s
\gls{sr}\footnote{of these seven methods, all except \gls{lasso} were performed
  by collaborators}. Primarily, \gls{sr} models were used to optimize process
parameter values based on TN+TCM phenotype and to extract early predictive
variable combinations from the multi-omics experiments. Furthermore, all
regression methods were executed, and the high-performing models were used to
perform a consensus analysis of the important variables to extract potential
critical quality attributes and critical process parameters predictive of T-cell
potency, safety, and consistency at the early stages of the manufacturing
process.

\gls{sr} was done using Evolved Analytics’ DataModeler software (Evolved
Analytics LLC, Midland, MI). DataModeler utilizes genetic programming to evolve
symbolic regression models (both linear and non-linear) rewarding simplicity and
accuracy. Using the selection criteria of highest accuracy (R2>90\% or
noise-power) and lowest complexity, the top-performing models were identified.
Driving variables, variable combinations, and model dimensionality tables were
generated. The top-performing variable combinations were used to generate model
ensembles. In this analysis, DataModeler’s SymbolicRegression function was used
to develop explicit algebraic (linear and nonlinear) models. The fittest models
were analyzed to identify the dominant variables using the VariablePresence
function, the dominant variable combinations using the VariableCombinations
function, and the model dimensionality (number of unique variables) using the
ModelDimensionality function. CreateModelEnsemble was used to define trustable
model ensembles using selected variable combinations and these were summarized
(model expressions, model phenotype, model tree plot, ensemble quality, model
quality, variable presence map, \gls{anova} tables, model prediction plot, exportable
model forms) using the ModelSummaryTable function. Ensemble prediction and
residual performance were respectively assessed via the EnsemblePredictionPlot
and EnsembleResidualPlot subroutines. Model maxima (ModelMaximum function) and
model minima (ModelMinimum function) were calculated and displayed using the
ResponsePlotExplorer function. Trade-off performance of multiple responses was
explored using the MultiTargetResponseExplorer and ResponseComparisonExplorer
with additional insights derived from the ResponseContourPlotExplorer. Graphics
and tables were generated by DataModeler. These model ensembles were used to
identify predicted response values, potential optima in the responses, and
regions of parameter values where the predictions diverge the most.

Non-parametric tree-based ensembles were done through the
\inlinecode{randomForest}, inlinecode{gbm}, and \inlinecode{cforest} regression
functions in R, for \gls{rf}, \gls{gbm}, and \gls{cif} models, respectively.
Both \gls{rf} and \gls{cif} construct multiple decision trees in parallel, by
randomly choosing a subset of features at each decision tree split, in the
training stage. Random forest individual decision trees are split using the Gini
Index, while conditional inference forest uses a statistical significance test
procedure to select the variables at each split, reducing correlation bias. In
contrast, \gls{gbm} construct regression trees in series through an iterative
procedure that adapts over the training set. This model learns from the mistakes
of previous regression trees in an iterative fashion to correct errors from its
precursors’ trees (i.e. minimize \gls{mse}). Prediction performance was
evaluated using \gls{loocv} and permutation-based
variable importance scores assessing \% increase of \gls{mse}, relative
influence based on the increase of prediction error, coefficient values for
\gls{rf}, \gls{gbm}, and \gls{cif}, respectively. \gls{plsr} was executed using
the \inlinecode{plsr} function from the \inlinecode{pls} package in R while
\gls{lasso} regression was performed using the \inlinecode{cv.glmnet} R package,
both using leave-one-out cross-validation. Finally, the \inlinecode{kernlab} R
package was used to construct the \gls{svm} models.

Parameter tuning was done for all models in a grid search manner using the train
function from the \inlinecode{caret} R package using \gls{loocv} as the
optimization criteria. Specifically, the number of features randomly sampled as
candidates at each split (\inlinecode{mtry}) and the number of trees to grow
(\inlinecode{ntree}) were tuned parameters for random forest and conditional
inference forest. In particular, minimum sum of weights in a node to be
considered for splitting and the minimum sum of weights in a terminal node were
manually tuned for building the \gls{cif} models. Moreover, \gls{gbm} parameters
such as the number of trees to grow, maximum depth of each tree, learning rate,
and the minimal number of observations at the terminal node, were tuned for
optimum \gls{loocv} performance as well. For \gls{plsr}, the optimal number of
components to be used in the model was assessed based on the standard error of
the cross-validation residuals using the function \inlinecode{selectNcomp} from
the \inlinecode{pls} package. Moreover, \gls{lasso} regression was performed
using the \inlinecode{cv.glmnet} package with alpha = 1. The best lambda for
each response was chosen using the minimum error criteria. Lastly, a fixed
linear kernel (i.e. \inlinecode{svmLinear}) was used to build the \gls{svm}
regression models evaluating the cost parameter value with best \gls{loocv}.
Prediction performance was measured for all models using the final model with
\gls{loocv} tuned parameters.

% TODO do I need this?
% Table M2 shows the parameter values evaluated per model
% at the final stages of results reporting.

\subsection{consensus analysis}

Consensus analysis of the relevant variables extracted from each machine
learning model was done to identify consistent predictive features of quality at
the early stages of manufacturing. First importance scores for all features were
measured across all \gls{ml} models using \inlinecode{varImp} with
\inlinecode{caret} R package except for scores for \gls{svm} which
\inlinecode{rminer} R package was used. These importance scores were percent
increase in \gls{mse}, relative importance through average increase in
prediction error when a given predictor is permuted, permuted coefficients
values, absolute coefficient values, weighted sum of absolute coefficients
values, and relative importance from sensitivity analysis determined for
\gls{rf}, \gls{gbm}, \gls{cif}, \gls{lasso}, \gls{plsr}, and \gls{svm},
respectively. Using these scores, key predictive variables were selected if
their importance scores were within the 80th percentile ranking for the
following \gls{ml} methods: \gls{rf}, \gls{gbm}, \gls{cif}, \gls{lasso},
\gls{plsr}, \gls{svm} while for \gls{sr} variables present in >30\% of the
top-performing \gls{sr} models from DataModeler (R2>= 90\%, Complexity >= 100)
were chosen to investigate consensus except for \gls{nmr} media models at day 4
which considered a combination of the top-performing results of models excluding
lactate ppms, and included those variables which were in > 40\% of the best
performing models. Only variables with those high percentile scoring values were
evaluated in terms of their logical relation (intersection across \gls{ml}
models) and depicted using a Venn diagram from the \inlinecode{venn} R package.

\section{results}

\subsection{T cells can be grown on DMSs with lower IL2 concentrations}

Prior to the main experiments in this aim, we performed a preliminary experiment
to assess the effect of lowering the \gls{il2} concentration on the T cells
grown with either bead or \gls{dms}. One of the hypotheses for the \gls{dms}
system was that the higher cell density would enable more efficient cross-talk
between T cells. Since \gls{il2} is secreted by activated T cells themselves,
T cells in the \gls{dms} system may need less or no \gls{il2} if this hypothesis
were true.

% TODO this plots proportions look dumb
% TODO explain what the NLS lines are in b
% TODO plot the differences in lower IL2 concentrations to better show this
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/il2_modulation.png}
  \phantomsubcaption\label{fig:il2_mod_timecourse}
  \phantomsubcaption\label{fig:il2_mod_total}
  \phantomsubcaption\label{fig:il2_mod_mem}
  \phantomsubcaption\label{fig:il2_mod_flow}

  \endgroup
  \caption[T cells grown at varying IL2 concentrations]
  {\glspl{dms} grow T cells effectively at lower IL2 concentrations.
    \subcap{fig:il2_mod_timecourse}{Longitudinal cell counts of T cells grown
      with either bead or \glspl{dms} using varying IL2 concentrations}
    Day 14 counts of either \subcap{fig:il2_mod_total}{total cells} or
    \subcap{fig:il2_mod_mem}{\ptmem{} cells} plotted against \gls{il2}
    concentration.
    \subcap{fig:il2_mod_flow}{Flow cytometry plots of the \ptmem{} gated
      populations at day 14 of culture for each \gls{il2} concentration.}
  }
  \label{fig:il2_mod}
\end{figure*}

% TODO the nls stuff is a bit iffy
We varied the concentration of \gls{il2} from \SIrange{0}{100}{\IU\per\ml} and
expanded T cells as described in \cref{sec:tcellculture}. T cells grown with
either method expanded robustly as \gls{il2} concentration was increased
(\cref{fig:il2_mod_timecourse}). Surprisingly, neither the bead or the \gls{dms}
group expanded at all with \SI{0}{\IU\per\ml} \gls{il2}. When examining the
endpoint fold change after \SI{14}{\day}, we observe that the difference between
the bead and \gls{dms} appears to be greater at lower \gls{il2} concentrations
(\cref{fig:il2_mod_total}). This is further supported by fitting a non-linear
least squares equation to the data following a hyperbolic curve (which should be
a plausible model given that this curve describes receptor-ligand kinetics,
which we can assume \gls{il2} to follow). Furthermore, the same trend can be
seen when only examining the \ptmem{} cell expansion at day 14
(\cref{fig:il2_mod_mem}). In this case, the \ptmemp{} of the T cells seemed to
be relatively close at higher \gls{il2} concentrations, but separated further at
lower concentrations (\cref{fig:il2_mod_flow})

Taken together, these data do not support the hypothesis that the \gls{dms}
system does not need \gls{il2} at all; however, it appears to have a modest
advantage at lower \gls{il2} concentrations compared to beads. For this reason,
we decided to investigate the lower range of \gls{il2} concentrations starting
at \SI{10}{\IU\per\ml} throughout the remainder of this aim.

% TODO this is not consistent with the next section since the responses are
% different
\subsection{DOE shows optimal conditions for expanded potent T cells}

% TODO not all of these were actually use, explain why by either adding columns
% or marking with an asterisk
\begin{table}[!h] \centering
  \caption{DOE Runs}
  \label{tab:doe_runs}
  \input{../tables/doe_runs.tex}
\end{table}

% RESULT integrate this figure into the results paragraph
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/doe_responses_first.png}
  \phantomsubcaption\label{fig:doe_response_first_mem}
  \phantomsubcaption\label{fig:doe_response_first_cd4}

  \endgroup
  \caption[Response plots for first DOE]
  {Response plots from the first \gls{doe} experiment for
    \subcap{fig:doe_response_first_mem}{\ptmemp{}} and
    \subcap{fig:doe_response_first_cd4}{\pthp{}}. Each point is one run.
  }
  \label{fig:doe_response_first}
\end{figure*}

We conducted two consecutive \glspl{doe} to optimize the \pth{} and \ptmem{}
responses for the \gls{dms} system. In the first \gls{doe} we, tested \pilII{} in
the range of \SIrange{10}{30}{\IU\per\ml}, \pdms{} in the range of
\SIrange{500}{2500}{\dms\per\ml}, and \pmab{} in the range of
\SIrange{60}{100}{\percent}.

% TODO explain why not all runs were used
After performing the first \gls{doe} we augmented the original design matrix
with an \gls{adoe} which was built with three goals in mind. Firstly we wished
to validate the first \gls{doe} by assessing the strength and responses of each
effect. Secondly, we wished to improve our confidence in regions that showed
high complexity, such as the peak in the \gls{dms} concentration for the total
\ptmem{} cell response. Thirdly, we wished to explore additional ranges of each
response. Since \pilII{} and \pdms{} appeared to continue positively influence
multiple responses beyond our tested range, we were curious if there was an
optimum at some higher setting of either of these values. For this reason, we
increased the \pilII{} to include \SI{40}{\IU\per\ml} and the \pdms{} to
\SI{3500}{\dms\per\ml}. Note that it was impossible to go beyond
\SI{100}{\percent} for the \pmab{}, so runs were positioned for this parameter
with validation and confidence improvements in mind. The runs for each \gls{doe}
were shown in \cref{tab:doe_runs}.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/doe_responses.png}
  \phantomsubcaption\label{fig:doe_responses_mem}
  \phantomsubcaption\label{fig:doe_responses_cd4}
  \phantomsubcaption\label{fig:doe_responses_mem4}
  \phantomsubcaption\label{fig:doe_responses_ratio}

  \endgroup
  \caption[T cell optimization through Design of Experiments]
  {\gls{doe} methodology reveals optimal conditions for expanding T cell
    subsets. Responses vs IL2 concentration, \gls{dms} concentration, and
    functional \gls{mab} percentage are shown for 
    \subcap{fig:doe_responses_mem}{total \ptmem{} T cells},
    \subcap{fig:doe_responses_cd4}{total \pth{} T cells},
    \subcap{fig:doe_responses_mem4}{total \ptmemh{} T cells}, and 
    \subcap{fig:doe_responses_ratio}{ratio of CD4 and CD8 T cells in the
      \ptmem{} compartment}. Each point represents one run.
  }
  \label{fig:doe_responses}
\end{figure*}

\begin{table}[!h] \centering
  \caption{Total CD62L+CCR7+ T cell response (first order regression)}
  \label{tab:doe_mem1.tex}
  \input{../tables/doe_mem1.tex}
\end{table}

\begin{table}[!h] \centering
  \caption{Total CD62L+CCR7+ T cell response (third order regression)}
  \label{tab:doe_mem2.tex}
  \input{../tables/doe_mem2.tex}
\end{table}

\begin{table}[!h] \centering
  \caption{Total CD4+ T cell response}
  \label{tab:doe_cd4.tex}
  \input{../tables/doe_cd4.tex}
\end{table}

\begin{table}[!h] \centering
  \caption{Linear regression for total \ptmemh{} cells}
  \label{tab:doe_mem4.tex}
  \input{../tables/doe_mem4.tex}
\end{table}

\begin{table}[!h] \centering
  \caption{Linear regression for CD4:CD8 ratio in the \ptmem{} compartment}
  \label{tab:doe_ratio.tex}
  \input{../tables/doe_ratio.tex}
\end{table}

The response plots from both \glspl{doe} are shown in \cref{fig:doe_responses}
for total \ptmem{} cells, total \pth{} cells, total \ptmemh{} cells, and CD4:CD8
ratio in the \ptmem{} compartment. In general, the responses for the first and
second \gls{doe} seemed to overlap, although not perfectly. Interestingly, only
the \ptmem{} response seemed to have anything more complex than a linear
relationship, particularly in the case of \pilII{} and \pdms{}, which showed
intermediate optimums (\cref{fig:doe_responses_mem}). In the case of \pilII{},
it was not clear if this optimum was simply due to a batch effect of being from
the first or second \gls{doe}. The optimum for \pdms{} appeared in the same
location albeit more pronounced in the second \gls{doe} so, giving more
confidence to the location of this second order feature. The remainder of the
responses showed mostly linear relationships in all parameter cases
(\cref{fig:doe_responses_cd4,fig:doe_responses_mem4,fig:doe_responses_ratio}).

% TODO it seems arbitrary that I went straight to a third order model, the real
% reason is because it seemed weird that a second order model didn't find
% anything to be significant
We performed linear regression on the three input parameters as well as a binary
parameter representing if a given run came from the first or second \gls{doe}
(called `dataset'). Starting with the total \ptmem{} cells response, we fit a
first order regression model using these four parameters
(\cref{tab:doe_mem1.tex}). While \pilII{} was found to be a significant
predictor, the model fit was extremely poor ($R^2$ of 0.331). This was not
surprising given the apparent complexity of this response
(\cref{fig:doe_responses_mem}). To obtain a better fit, we added second and
third degree terms (\cref{tab:doe_mem2.tex}). Note that the dataset parameter
was not included in the second order interaction as this was treated as a
blocking variable, which are typically not assumed to have interaction effects.
Also note that the response was log-transformed, which yielded a better fit. In
this model many more parameters emerged as being significant, including the
quadratic terms for \pdms{} and \pilII{}, in agreement with what can be
qualitatively observed in the response plot (\cref{fig:doe_responses_mem}).
Furthermore, the dataset parameter was weakly significant, indicating a possible
batch effect between the \glspl{doe}. We should also note that despite many
parameters being significant, this model was still only mediocre in describing
this response; the $R^2$ was 0.741 but the adjusted $R^2$ was 0.583, indicating
that our data might be underpowered for a model this complex. Further
experiments beyond what was performed here may be needed to fully describe this
response.

% TODO combine these tables into one
We performed linear regression on the other three responses, all of which
performed much better than the \ptmem{} response as expected given the much
lower apparent complexity in the response plots
(\cref{fig:doe_responses_cd4,fig:doe_responses_mem4,fig:doe_responses_ratio}).
All these models appeared to fit will, with $R^2$ and adjusted $R^2$ upward of
0.8. In all but the CD4:CD8 \ptmem{} ratio, the dataset parameter emerged as
significant, indicating a batch effect between the \glspl{doe}. All other
parameters except \pilII{} in the case of CD4:CD8 \ptmem{} ratio were
significant predictors.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/doe_sr_contour.png}
  \phantomsubcaption\label{fig:doe_sr_contour_mem4}
  \phantomsubcaption\label{fig:doe_sr_contour_ratio}

  \endgroup
  \caption[Contour plots for DOE responses]
  {Symbolic regression and contour plots reveal optimal conditions for
    \subcap{fig:doe_sr_contour_mem4}{\ptmemh{} cells} and 
    \subcap{fig:doe_sr_contour_ratio}{CD4:CD8 ratio in the \ptmem{}
      compartment}.
  }
  \label{fig:doe_sr_contour}
\end{figure*}

We then visualized the total \ptmemh{} cells and CD4:CD8 \ptmem{} ratio using
the response explorer in DataModeler to create contour plots around the maximum
responses. For both, it appeared that maximizing all three input parameters
resulted in the maximum value for either response (\cref{fig:doe_responses}).
While not all combinations at and around this optimum were tested, the model
nonetheless showed that there were no other optimal values or regions elsewhere
in the model.

% TODO this section header sucks
\subsection{AI modeling reveals highly predictive species}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/doe_luminex.png}

  \endgroup
  \caption[Cytokine release profile of T cells from DOE]
  {T cells show robust and varying cytokine responses over time}
  \label{fig:doe_luminex}
\end{figure*}

Due to the heterogeneity of the multivariate data collected and knowing that no
single model structure is perfect for all applications, we implemented an
agnostic modeling approach to better understand these TN+TCM responses. To
achieve this, a consensus analysis using seven machine learning (ML) techniques,
Random Forest (RF), Gradient Boosted Machine (GBM), Conditional Inference Forest
(CIF), Least Absolute Shrinkage and Selection Operator (LASSO), Partial
Least-Squares Regression (PLSR), Support Vector Machine (SVM), and DataModeler’s
Symbolic Regression (SR), was implemented to molecularly characterize TN+TCM
cells and to extract predictive features of quality early on their expansion
process (Fig.1d-e).

% TODO this table looks like crap, break it up into smaller tables
\begin{table}[!h] \centering
  \caption{Results for data-driven modeling}
  \label{tab:mod_results}
  \input{../tables/model_results.tex}
\end{table}

SR models achieved the highest predictive performance (R2>93\%) when using
multi-omics predictors for all endpoint responses (\cref{tab:mod_results}). SR
achieved R2>98\% while GBM tree-based ensembles showed leave-one-out
cross-validated R2 (LOO-R2) >95\% for CD4+ and CD4+/CD8+ TN+TCM responses.
Similarly, LASSO, PLSR, and SVM methods showed consistent high LOO-R2, 92.9\%,
99.7\%, and 90.5\%, respectively, to predict the CD4+/CD8+ TN+TCM. Yet, about
10\% reduction in LOO-R2, 72.5\%-81.7\%, was observed for CD4+ TN+TCM with these
three methods. Lastly, SR and PLSR achieved R2>90\% while other ML methods
exhibited exceedingly variable LOO-R2 (0.3\%,RF-51.5\%,LASSO) for CD8+ TN+TCM
cells.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/sr_omics.png}

  \endgroup
  \caption[Symbolic Regression Cytokine Dependencies]
  {Multi-omics culturing media prediction profiles at day 6 using symbolic
    regression.}
  \label{fig:sr_omics}
\end{figure*}

The top-performing technique, SR, showed that the median aggregated predictions
for CD4+ and CD8+ TN+TCM cells increases when IL2 concentration, IL15, and IL2R
increase while IL17a decreases in conjunction with other features. These
patterns combined with low values of DMS concentration and GM-CSF uniquely
characterized maximum CD8+ TN+TCM. Meanwhile, higher glycine but lower IL13 in
combination with others showed maximum CD4+ TN+TCM predictions
(\cref{fig:sr_omics}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/modeling_flower.png}
  \phantomsubcaption\label{fig:mod_flower_48r}
  \phantomsubcaption\label{fig:mod_flower_cd4}

  \endgroup
  \caption[Data-Driven \gls{cqa} identification]
  {Data-driven modeling using techniques with regularization reveals species
    predictive species which are candidates for \glspl{cqa}. Flower plots are
    shown for \subcap{fig:mod_flower_48r}{CD4:CD8 ratio} and
    \subcap{fig:mod_flower_cd4}{total \ptmemh{} cells}. The left and right
    columns includes models that were trained only on the secretome and
    metabolome respectively. Each flower on each plot represents one model,
    moving toward the center indicates higher agreement between models.}
  \label{fig:mod_flower}
\end{figure*}

Selecting CPPs and CQAs candidates consistently for T cell memory is desired.
Here, \gls{tnfa} was found in consensus across all seven ML methods for predicting
CD4+/CD8+ TN+TCM when considering features with the highest importance scores
across models (Fig.3a;Methods). Other features, IL2R, IL4, IL17a, and DMS
concentration, were commonly selected in >=5 ML methods (Fig.3a,c). Moreover,
IL13 and IL15 were found predictive in combination with these using SR
(Supp.Table.S4).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/nmr_cors.png}
  \phantomsubcaption\label{fig:nmr_cors_lactate}
  \phantomsubcaption\label{fig:nmr_cors_formate}
  \phantomsubcaption\label{fig:nmr_cors_glucose}
  \phantomsubcaption\label{fig:nmr_cors_matrix}

  \endgroup
  \caption[NMR Day 4 correlations]
  {\gls{nmr} features at day 4 are strongly correlated with each other and the
    response variables. Highly correlated relationships are shown for
    \subcap{fig:nmr_cors_lactate}{lactate},
    \subcap{fig:nmr_cors_formate}{formate}, and
    \subcap{fig:nmr_cors_glucose}{glucose}. Blue and blue connections indicate
    positive and negative correlations respectively. The threshold for
    visualizing connections in all cases was 0.8.
    \subcap{fig:nmr_cors_matrix}{The correlation matrix for all predictive
      features and the total \ptmemh{} response.}
  }
  \label{fig:nmr_cors}
\end{figure*}

\section{discussion}

% optimization of process features
% TODO this sounds like total fluff

CPPs modeling and understanding are critical to new product development and in
cell therapy development, it can have life-saving implications. The challenges
for effective modeling grow with the increasing complexity of processes due to
high dimensionality, and the potential for process interactions and nonlinear
relationships. Another critical challenge is the limited amount of available
data, mostly small DOE datasets. SR has the necessary capabilities to resolve
the issues of process effects modeling and has been applied across multiple
industries12. SR discovers mathematical expressions that fit a given sample and
differs from conventional regression techniques in that a model structure is not
defined a priori13. Hence, a key advantage of this methodology is that
transparent, human-interpretable models can be generated from small and large
datasets with no prior assumptions14,15.

Since the model search process lets the data determine the model, diverse and
competitive (e.g., accuracy, complexity) model structures are typically
discovered. An ensemble of diverse models can be formed where its constituent
models will tend to agree when constrained by observed data yet diverge in new
regions. Collecting data in these regions helps to ensure that the target system
is accurately modeled, and its optimum is accurately located14,15. Exploiting
these features allows adaptive data collection and interactive modeling.
Consequently, this adaptive-DOE approach is useful in a variety of scenarios,
including maximizing model validity for model-based decision making, optimizing
processing parameters to maximize target yields, and developing emulators for
online optimization and human understanding14,15.

% predictive features

An in-depth characterization of potential DMS-based T-cell CQAs includes a list
of cytokine and NMR features from media samples that are crucial in many aspects
of T cell fate decisions and effector functions of immune cells. Cytokine
features were observed to slightly improve prediction and dominated the ranking
of important features and variable combinations when modeling together with NMR
media analysis and process parameters (Fig.3b,d).

Predictive cytokine features such as \gls{tnfa}, IL2R, IL4, IL17a, IL13, and
IL15 were biologically assessed in terms of their known functions and activities
associated with T cells. T helper cells secrete more cytokines than T cytotoxic
cells, as per their main functions, and activated T cells secrete more cytokines
than resting T cells. It is possible that some cytokines simply reflect the
CD4+/CD8+ ratio and the activation degree by proxy proliferation. However, the
exact ratio of expected cytokine abundance is less clear and depends on the
subtypes present, and thus examination of each relevant cytokine is needed.

IL2R is secreted by activated T cells and binds to IL2, acting as a sink to
dampen its effect on T cells16. Since IL2R was much greater than IL2 in
solution, this might reduce the overall effect of IL2, which could be further
investigated by blocking IL2R with an antibody. In T cells, TNF can increase
IL2R, proliferation, and cytokine production18. It may also induce apoptosis
depending on concentration and alter the CD4+ to CD8+ ratio17. Given that TNF
has both a soluble and membrane-bound form, this may either increase or decrease
CD4+ ratio and/or memory T cells depending on the ratio of the membrane to
soluble TNF18. Since only soluble TNF was measured, membrane TNF is needed to
understand its impact on both CD4+ ratio and memory T cells. Furthermore, IL13
is known to be critical for Th2 response and therefore could be secreted if
there are significant Th2 T cells already present in the starting population19.
This cytokine has limited signaling in T cells and is thought to be more of an
effector than a differentiation cytokine20. It might be emerging as relevant due
to an initially large number of Th2 cells or because Th2 cells were
preferentially expanded; indeed, IL4, also found important, is the conical
cytokine that induces Th2 cell differentiation (Fig.3). The role of these
cytokines could be investigated by quantifying the Th1/2/17 subsets both in the
starting population and longitudinally. Similar to IL13, IL17 is an effector
cytokine produced by Th17 cells21 thus may reflect the number of Th17 subset of
T cells. GM-CSF has been linked with activated T cells, specifically Th17 cells,
but it is not clear if this cytokine is inducing differential expansion of CD8+
T cells or if it is simply a covariate with another cytokine inducing this
expansion22. Finally, IL15 has been shown to be essential for memory signaling
and effective in skewing CAR-T cells toward the Tscm phenotype when using
membrane-bound IL15Ra and IL15R23. Its high predictive behavior goes with its
ability to induce large numbers of memory T cells by functioning in an
autocrine/paracrine manner and could be explored by blocking either the cytokine
or its receptor.

Moreover, many predictive metabolites found here are consistent with metabolic
activity associated with T cell activation and differentiation, yet it is not
clear how the various combinations of metabolites relate with each other in a
heterogeneous cell population. Formate and lactate were found to be highly
predictive and observed to positively correlate with higher values of total live
CD4+ TN+TCM cells (Fig.5a-b;Supp.Fig.28-S30,S38). Formate is a byproduct of the
one-carbon cycle implicated in promoting T cell activation24. Importantly, this
cycle occurs between the cytosol and mitochondria of cells and formate
excreted25. Mitochondrial biogenesis and function are shown necessary for memory
cell persistence26,27. Therefore, increased formate in media could be an
indicator of one-carbon metabolism and mitochondrial activity in the culture.

In addition to formate, lactate was found as a putative CQA of TN+TCM. Lactate
is the end-product of aerobic glycolysis, characteristic of highly proliferating
cells and activated T cells28,29. Glucose import and glycolytic genes are
immediately upregulated in response to T cell stimulation, and thus generation
of lactate. At earlier time-points, this abundance suggests a more robust
induction of glycolysis and higher overall T cell proliferation. Interestingly,
our models indicate that higher lactate predicts higher CD4+, both in total and
in proportion to CD8+, seemingly contrary to previous studies showing that CD8+
T cells rely more on glycolysis for proliferation following activation30. It may
be that glycolytic cells dominate in the culture at the early time points used
for prediction, and higher lactate reflects more cells.

% TODO not sure how much I should include here since I didn't do this analysis
% AT ALL
% Ethanol patterns are difficult to interpret since its production in mammalian
% cells is still poorly understood31. Fresh media analysis indicates ethanol
% presence in the media used, possibly utilized as a carrier solvent for certain
% formula components. However, this does not explain the high variability and
% trend of ethanol abundance across time (Supp.Fig.S25-S27). As a volatile
% chemical, variation could be introduced by sample handling throughout the
% analysis process. Nonetheless, it is also possible that ethanol excreted into
% media over time, impacting processes regulating redox and reactive oxygen
% species which have previously been shown to be crucial in T cell signaling and
% differentiation32.

% this looks fine since it is just parroting sources, just need to paraphrase a
% little
Metabolites that consistently decreased over time are consistent with the
primary carbon source (glucose) and essential amino acids (BCAA, histidine) that
must be continually consumed by proliferating cells. Moreover, the inclusion of
glutamine in our predictive models also suggests the importance of other carbon
sources for certain T cell subpopulations. Glutamine can be used for oxidative
energy metabolism in T cells without the need for glycolysis30. Overall, these
results are consistent with existing literature that show different T cell
subtypes require different relative levels of glycolytic and oxidative energy
metabolism to sustain the biosynthetic and signaling needs of their respective
phenotypes33,34. It is worth noting that the trends of metabolite abundance here
are potentially confounded by the partial replacement of media that occurred
periodically during expansion (Methods), thus likely diluting some metabolic
byproducts (i.e. formate, lactate) and elevating depleted precursors (i.e.
glucose, amino acids). More definitive conclusions of metabolic activity across
the expanding cell population can be addressed by a closed system, ideally with
on-line process sensors and controls for formate, lactate, along with ethanol
and glucose.

\chapter{aim 2b}\label{aim2b}

\section{introduction}
\section{methods}

\subsection{DMSs temporal modulation}

% TODO The concentration for the surface marker cleavage experiment was much
% higher, if that matters
\glspl{dms} were digested in active T cell cultures via addition of sterile
\product{\gls{colb}}{Sigma}{11088807001} or
\product{\gls{cold}}{Sigma}{11088858001}. Collagenase was dissolved in
\product{\gls{hbss}}{Gibco}{14025-076} or
\product{TexMACS}{\miltenyi}{170-076-307} at approximately \SI{100}{\ug\per\ml}.
This solution was added to T cell cultures at a 1:1 ratio in place of plain
media normally used to feed the cells during the regular media addition cycle at
day 4. Cultures were then incubated as described in \cref{sec:tcellculture}, and
the \glspl{dms} were verified to have been digested after \SI{24}{\hour}.

Adding \gls{dms} was relatively much simpler; the number of \gls{dms} used per
area on day 0 was scaled up by 3 on day 4 to match the change from a 96 well
plate to a 24 well plate, effectively producing a constant activation signal.

\subsection{mass cytometry and clustering analysis}

T cells were stained using a \product{34 \gls{cytof} marker
  panel}{Fluidigm}{201322} and \product{cisplatin}{Fluidigm}{201064} which were
used according to the manufacturer’s instructions. \numrange{2e6}{3e6} stained
cells per group were analyzed on a Fluidigm Helios.

Unbiased cell clusters were obtained using \gls{spade} analysis by pooling three
representative \gls{fcs} files and running the \gls{spade} pipeline with k-means
clustering (k = 100), arcsinh transformation with cofactor 5, density
calculation neighborhood size of 5 and local density approximation factor of
1.5, target density of 20000 cells, and outlier density cutoff of
\SI{1}{\percent}. All markers in the \gls{cytof} panel were used in the analysis

\subsection{integrin blocking experiments}

To block \gls{a2b1} and \gls{a2b2}, active T cell cultures with \gls{dms} were
supplemented with \product{\anti{\gls{a2b1}}}{Sigma}{MAB1973Z} and
\product{\anti{\gls{a2b2}}}{Sigma}{MAB1950Z} (both \gls{leaf}) at indicated
concentrations and timepoints. T cells were grown as described in
\cref{sec:tcellculture}.

\gls{a2b1} and \gls{a2b2} were verified to be present on active T cell cultures
by staining with \product{\anti{\gls{a2b1}}-\gls{apc}}{\bl}{328313} and
\product{\anti{\gls{a2b2}}-\gls{fitc}}{\bl}{359305} on day 6 of culture and
analyzing via a BD Accuri flow cytometer.

\subsection{IL15 blocking experiments}

To block the \gls{il15r}, we supplemented T cell
cultures activated with \gls{dms} with either
\product{\anti{\gls{il15r}}}{Rnd}{AF247} or \product{\gls{igg} isotype
  control}{RnD}{AB-108-C} at the indicated timepoints and concentrations. T
cells were grown as otherwise described in \cref{sec:tcellculture} with the
exception that volumes were split by $\frac{1}{3}$ to keep the culture volume
constant and minimize the amount of \gls{mab} required.

To block soluble \gls{il15}, we supplemented analogously with
\product{\anti{\gls{il15}}}{RnD}{EEP0419081} or \product{\gls{igg} isotype
  control}{\bl}{B236633}.

\section{results}

\subsection{adding or removing DMSs alters expansion and phenotype}

% TODO state what collagenase actually targets
We hypothesized that adding or removing \gls{dms} in the middle of an active
culture would alter the activation signal and hence the growth trajectory and
phenotype of T cells. While adding \glspl{dms} was simple, the easiest way to
remove \glspl{dms} was to use enzymatic digestion. Collagenase is an enzyme that
specifically targets the blabla domain on collagen. Since our \glspl{dms} are
composed of porcine-derived collagen, this enzyme should target the \gls{dms}
while sparing the cells. We tested this specific hypothesis using either
\gls{colb}, \gls{cold} or \gls{hbss}, and stained the cells using a typical
marker panel to assess if any of the markers were cleaved off by the enzyme
which would bias our final readout. We observed that the marker histograms in
the \gls{cold} group were similar to that of the buffer group, while the
\gls{colb} group visibly lowered CD62L and CD4, indicating partial
enzymatic cleavage (\cref{fig:collagenase_fx}). Based on this result, we used
\gls{cold} moving forward.

% TODO this figure is tall and skinny like me
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/collagenase.png}

  \endgroup
  \caption[Effects Collagenase Treatment on T cells]
  {T cells treated with either \gls{colb}, \gls{cold}, or buffer and then
    stained for various surface markers and analyzing via flow cytometry.}
  \label{fig:collagenase_fx}
\end{figure*}

When either adding more \glspl{dms}, removing \glspl{dms} using \gls{cold}, or
doing nothing, we observed that, counterintuitively, cell growth seemed to be
inhibited in the \textit{added} group while the cells seemed to grow faster in
the \textit{removed} group relative to the \textit{no change} group
(\cref{fig:add_rem_growth}). Additionally, the \textit{removed} group seemed to
have a negative growth rate in the final \SI{4}{\day} of culture, indicating
that either the lack activation signal had slowed the cell growth down or that
the cells were growing fast enough to outpace the media feeding schedule. The
viability was the same between all groups, indicating that this negative growth
rate and the lower growth rate in the \textit{added} group were likely not due
to cell death (\cref{fig:add_rem_viability}). Interestingly, the \textit{added}
group had significantly higher \pth{} cells compared to the \textit{no change}
group, and the inverse was true for the \textit{removed} group
(\cref{fig:add_rem_cd4}). These results show that the growth rate and phenotype
are fundamentally altered by changing the number of \glspl{dms} temporally.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/add_remove_endpoint.png}
  \phantomsubcaption\label{fig:add_rem_growth}
  \phantomsubcaption\label{fig:add_rem_viability}
  \phantomsubcaption\label{fig:add_rem_cd4}

  \endgroup
  \caption[Endpoint results from adding/removing \gls{dms} on day 4]
  {Changing \gls{dms} concentration on day 4 has profound effects on phenotype
    and growth.
    \subcap{fig:add_rem_growth}{Longitudinal fold change}, 
    \subcap{fig:add_rem_viability}{longitudinal viability}, and
    \subcap{fig:add_rem_cd4}{day 14 \pthp{}} of T cell cultures with \glspl{dms}
    added, removed, or kept the same on day 4.
  }
  \label{fig:add_rem}
\end{figure*}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/spade_gates.png}

  \endgroup
  \caption[SPADE Gating Strategy]
  {Gating strategy for quantifying early-differentiated T cells via
    \gls{spade}.}
  \label{fig:spade_gates}
\end{figure*}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/add_remove_spade.png}
  \phantomsubcaption\label{fig:spade_msts}
  \phantomsubcaption\label{fig:spade_quant}
  \phantomsubcaption\label{fig:spade_tsne_all}
  \phantomsubcaption\label{fig:spade_tsne_stem}

  \endgroup
  \caption[SPADE and tSNE analysis temporally-modified DMS concentration]
  {Removing \glspl{dms} leads to a higher fraction of potent stem-memory T
    cells compared to both adding and not changing the \gls{dms} concentration
    at day 4.
    \subcap{fig:spade_msts}{SPADE plots of CD4, CD45RA, CD27, and CD45RO
      expression on T cells. All cells from the added, removed, or no change
      groups were pooled and clustered at once.}
    \subcap{fig:spade_quant}{T cells from SPADE plots clustered by expression in
      (\subref{fig:spade_msts}) quantified against total cell number from each
      group.}
    \subcap{fig:spade_tsne_all}{\gls{tsne} plots of all cells pooled from all
      groups.}
    \subcap{fig:spade_tsne_stem}{\gls{tsne} plots of T cells from all groups
      manually gated on \cdp{8}\cdp{27}\cdp{45RO}.}
  }
  \label{fig:spade}
\end{figure*}

We next asked what the effect of removing the \glspl{dms} would have on other
phenotypes, specifically \gls{tcm} and \gls{tscm} cells. To this end we stained
cells using a 34-marker mass cytometry panel and analyzed them using a Fluidigm
Helios. After pooling the \gls{fcs} file events from each group and analyzing
them via \gls{spade} we see that there is a strong bifurcation of CD4 and CD8 T
cells. We also observe that among CD27, CD45RA, and CD45RO (markers commonly
used to identify \gls{tcm} and \gls{tscm} subtypes) we see clear `metaclusters'
composed of individual \gls{spade} clusters which are high for that marker
(\cref{fig:spade_msts,fig:spade_gates}). We then gated each of these
metaclusters according to their marker levels and assigned them to one of three
phenotypes for both the CD4 and CD8 compartments: \gls{tcm} (high CD45RO, low
CD45RA, high CD27), \gls{tscm} (low CD45RO, high CD45RA, high CD27), and
`transitory' \gls{tscm} cells (mid CD45RO, mid CD45RA, high CD27). Together
these represent low differentiated cells which should be highly potent as
anti-tumor therapies.

When quantifying the number of cells from each experimental group in these
phenotypes, we clearly see that the number of lower differentiated cells is much
higher in the \textit{no change} or \textit{removed} groups compared to the
\textit{added} group (\cref{fig:spade_quant}). Furthermore, the \textit{removed}
group had a much higher fraction of \gls{tscm} cells compared to the \textit{no
  change} group, which had more `transitory \gls{tscm} cells'. The majority of
these cells were \cdp{8} cells. When analyzing the same data using \gls{tsne},
we observe a higher fraction of CD27 and lower fraction of CD45RO in the the
\textit{removed} group (\cref{fig:spade_tsne_all}). When manually gating on the
CD27+CD45RO- population, we see there is higher density in the \textit{removed}
group, indicating more of this population (\cref{fig:spade_tsne_stem}).
Together, these data indicate that removing \glspl{dms} at lower timepoints
leads to potentially higher expansion, lower \pthp{}, and higher fraction of
lower differentiated T cells such as \gls{tscm}, and adding \gls{dms} seems to
do the inverse.

\subsection{blocking integrin binding does not alter expansion or phenotype}

% BACKGROUND add background into why integrins are important

One of the reasons the \gls{dms} platform might be performing better than the
beads is the fact that they are composed of gelatin, which is a collagen
derivative. The beads are simply \gls{mab} attached to a polymer resin coated
onto an iron oxide core, and thus have no analogue for collagen. Collagen
domains present on the \gls{dms} group could be creating pro-survival and
pro-expansion signals to the T cells through \gls{a2b1} and \gls{a2b2}, causing
them to grow better in the \gls{dms} system.

% TODO perhaps these figs should be combined
% TODO actually make the captions for these
% TODO add some background into why integrins are important and the proposed mechanism
% TODO add an experimental timeline to these showing when I added the mabs
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/integrin_1.png}
  \phantomsubcaption\label{fig:inegrin_1_overview}
  \phantomsubcaption\label{fig:inegrin_1_fc}
  \phantomsubcaption\label{fig:inegrin_1_mem}
  \phantomsubcaption\label{fig:inegrin_1_cd49}

  \endgroup
  \caption[Integrin blocking I]
  {Blocking with integrin does not lead to differences in memory or growth.
    \subcap{fig:inegrin_1_overview}{Experimental overview}
    \subcap{fig:inegrin_1_fc}{Fold change of \gls{dms}-activated T cell over
      time with each blocking condition.}
    \subcap{fig:inegrin_1_mem}{\ptmemp{} at day 14 for each blocked condition.}
    \subcap{fig:inegrin_1_cd49}{\gls{a2b1} and \gls{a2b2} expression over time.}
    `A' and `B' refer to the inclusion of \anti{\gls{a2b1}} or \anti{\gls{a2b2}}
    respectively.
  }
  \label{fig:integrin_1}
\end{figure*}

% RESULT alude to these tables

\begin{table}[!h] \centering
  \caption{Linear regression for day 14 phenotype shown in \cref{fig:integrin_1}}
  \label{tab:integrin_1_reg}
  \input{../tables/integrin_1_reg.tex}
\end{table}

We tested this hypothesis by adding blocking \glspl{mab} against \gls{a2b1}
and/or \gls{a2b2} to running T cell cultures activated using the \glspl{dms}.
These block \glspl{mab} were added at day 6 of culture when \gls{a2b1} and
\gls{a2b2} were known to be expressed {\#}. We found that the fold expansion was
identical in all the blocked groups vs the unblocked control group
(\cref{fig:inegrin_1_fc}). Furthermore, we observed that the \ptmemp{} (total
and across the CD4/CD8 compartments) was not significantly different between any
of the groups (\cref{fig:inegrin_1_mem}). We also noted that \gls{a2b1} and
\gls{a2b2} were present on the surface of a significant subset of T cells at day
6, showing that the target we wished to block was present
(\cref{fig:inegrin_1_cd49}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/integrin_2.png}
  \phantomsubcaption\label{fig:inegrin_2_overview}
  \phantomsubcaption\label{fig:inegrin_2_fc}
  \phantomsubcaption\label{fig:inegrin_2_mem}

  \endgroup
  \caption[Integrin blocking II]
  {Blocking with integrin does not lead to differences in memory or growth.
    \subcap{fig:inegrin_1_fc}{Fold change of \gls{dms}-activated T cell over
      time with each blocking condition.}
    \subcap{fig:inegrin_1_mem}{\ptmemp{} at day 14 for each blocked condition.}
    `A' and `B' refer to the inclusion of \anti{\gls{a2b1}} or \anti{\gls{a2b2}}
    respectively.
  }
  \label{fig:integrin_2}
\end{figure*}

\begin{table}[!h] \centering
  \caption{Linear regression for day 14 phenotype shown in \cref{fig:integrin_2}}
  \label{tab:integrin_2_reg}
  \input{../tables/integrin_2_reg.tex}
\end{table}

Since this last experiment gave a negative result, we decided to hit \gls{a2b1}
and \gls{a2b2} harder by adding blocking \glspl{mab} at more timepoints between
day 0 and day 6, hypothesizing that the majority of the signaling would be
during the period of culture where the \gls{dms} surface concentration was at
its maximum. Once again, we observed no difference between any of the blocked
conditions and the unblocked controls in regard to expansion
(\cref{fig:inegrin_2_fc}). Furthermore, none of the \ptmemp{} readouts (total,
CD4, or CD8) were statistically different between groups
(\cref{fig:inegrin_2_mem}).

Taken together, these data suggest that the advantage of the \gls{dms} platform
is not due to signaling through \gls{a2b1} or \gls{a2b2}.

\subsection{blocking IL15 signaling does not alter expansion or phenotype}

% BACKGROUND why is IL15 important?

% TODO cite the luminex data
\gls{il15} is a cytokine responsible for memory T cell survival and maintenance.
Furthermore, we observed in other experiments that it is secreted to a much
greater extend in \gls{dms} compared to bead cultures. One of our driving
hypotheses in designing the \gls{dms} system was that the higher cell density
would lead to greater local signaling. Since we observed higher \ptmemp{} across
many conditions, we hypothesized that \gls{il15} may be responsible for this,
and further that the unique \textit{cis/trans} activity of \gls{il15} may be
more active in the \gls{dms} system due to higher cell density.

% TODO add some background into why IL15 is important and the proposed mechanism
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/il15_blockade_1.png}
  \phantomsubcaption\label{fig:il15_1_overview}
  \phantomsubcaption\label{fig:il15_1_fc}
  \phantomsubcaption\label{fig:il15_1_viability}
  \phantomsubcaption\label{fig:il15_1_mem}

  \endgroup
  \caption[IL15 blocking I]
  {Blocking IL15Ra does not lead to differences in memory or growth.
    \subcap{fig:il15_1_overview}{Experimental overview}
    Longitudinal measurements of
    \subcap{fig:il15_1_fc}{fold change} and
    \subcap{fig:il15_1_viability}{viability} for blocked and unblocked
    conditions expanded with either beads or \glspl{dms}.
    \subcap{fig:il15_1_mem}{Flow cytometry markers for \gls{dms}-expanded T
      cells at day 14 for blocked and unblocked groups.}.
  }
  \label{fig:il15_1}
\end{figure*}

% TODO how did I determine how much to add?
% TODO just gate these as normal because this looks sketchy
We first tested this hypothesis by blocking \gls{il15r} with either a specific
\gls{mab} or an \gls{igg} isotype control. We observed no difference in the
expansion rate of blocked or unblocked cells (this experiment also had
bead-based groups but they did not expand well and thus were not included)
(\cref{fig:il15_1_fc}). Furthermore, there were no differences in viability
between any group (\cref{fig:il15_1_viability}). We also performed flow
cytometry to asses the \ptmemp{} and \pthp{} outputs. Without even gating the
samples, simply lining up their histograms showed no difference between any of
the markers, and by extension showing no difference in phenotype
(\cref{fig:il15_1_mem}).

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/il15_blockade_2.png}
  \phantomsubcaption\label{fig:il15_2_overview}
  \phantomsubcaption\label{fig:il15_2_fc}
  \phantomsubcaption\label{fig:il15_2_viability}
  \phantomsubcaption\label{fig:il15_2_mem}

  \endgroup
  \caption[IL15 blocking II]
  {Blocking soluble IL15 does not lead to differences in memory or growth.
    \subcap{fig:il15_2_overview}{Experimental overview}
    Longitudinal measurements of
    \subcap{fig:il15_2_fc}{fold change} and
    \subcap{fig:il15_2_viability}{viability} for blocked and unblocked
    conditions expanded with \glspl{dms}.
    \subcap{fig:il15_2_mem}{Flow cytometry markers for \gls{dms}-expanded T
      cells at day 14 for blocked and unblocked groups.}.
  }
  \label{fig:il15_2}
\end{figure*}

We next tried blocking soluble \gls{il15} itself using either a \gls{mab} or an
\gls{igg} isotype control. Similarly, we observed no difference between fold
change, viability, or marker histograms between any of these markers, showing
that blocking \gls{il15} led to no difference in growth or phenotype.

% TODO this can probably be worded more specifically in terms of the cis/trans
% action of IL15
In summary, this data did not support the hypothesis that the \gls{dms} platform
gains its advantages via the \gls{il15} pathway.

\section{discussion}

This work provides insight for how the \gls{dms} operates and may be optimized
further. The data showing increased \pthp{} when \glspl{dms} are added and the
reverse when removed is consistent with other data we produced via \gls{doe}
showing that higher \gls{dms} concentrations lead to higher \pthp{}
(\cref{fig:doe_responses_cd4,fig:add_rem_cd4}). The difference in this case is
that we showed that altering activation signal analogously affects the \pthp{}
in the dimension of time as well as space. A similar trend was observed with
memory T cells in this aim. Our previous \gls{doe} data showed that, to a point,
lower \gls{dms} concentration leads to higher \ptmemp{}
(\cref{fig:doe_responses_mem}). In this aim, we showed that decreasing
activation signal temporally by removing \glspl{dms} leads to the same effect in
the \gls{tcm}, \gls{tscm} and `transitory' \gls{tscm} populations, (all of which
are included in the \ptmem{} phenotype). Taken together, these imply that
temporally or spatially altering the \gls{dms} concentration, and thus the
activation signal, has similar effects.

% TODO this sounds like background?
% There are several plausible explanations for the observed phenotypic differences
% between beads and DMSs. First, the DMSs are composed of a collagen derivative
% (gelatin); collagen has been shown to costimulate activated T cells via
% \gls{a2b1} and \gls{a2b2}, leading to enhanced proliferation, increased
% \gls{ifng} production, and upregulated CD25 (IL2R$\upalpha$) surface
% expression8,10,11,41,42.

While we did not find support for our hypothesis that the \gls{dms} signal
through the \gls{a2b1} and/or \gls{a2b2} receptors, we can speculate as to why
either this experiment failed and may be done better in the future, or why these
receptors may simply be irrelevant for our system.

On the first point, we did not verify that these \glspl{mab} indeed blocked the
receptor we were targeting. There has been evidence from other groups that these
particular clones work at the concentrations we used {\#}. This does not
necessarily mean that the \glspl{mab} we obtained were functional in blocking
their intended targets (although they were from a reputable manufacturer, \bl).
Furthermore, we can safely rule out the possibility that the \glspl{mab} never
reached their targets, as they were added immediately after the T cells were
resuspended as required for cell counting, hence their resting clustered state
was disrupted.

% TODO define Bite
On the second point, the collagen domains may not even be relevant to our system
depending on the nature of the \gls{stp} coating. We intended by design for the
system to be fully coated or nearly fully-coated with \gls{stp}
(\cref{fig:stp_coating}). Thus the domains that \gls{a2b1} and \gls{a2b2} may be
targeting could be sterically hindered by a layer of \gls{stp}, and if not that,
also a layer of CD3/CD28 \glspl{mab}. The other possibility is that these
domains are simply denatured to beyond recognition due to the fabrication
process for the microcarriers we used (which involves a proprietary
cross-linking step to make the material autoclave-safe). Either of these could
be tested and verified by staining the \glspl{dms} with a fluorescently-tagged
\gls{mab} (or something smaller such as a BiTE to reduce the possibility of
steric hindrance) and verifying binding via confocal microscopy or indirect
protein quantification as we do for the \gls{qc} of the \gls{dms}. If this test
came back negative, we would be fairly confident that the \gls{a2b1} and
\gls{a2b1} domains are either unreachable or unrecognizable.

% DISCUSSION not sure exactly how to explain this
We also failed to uphold our hypothesis that the \gls{dms} system gains its
advantage via \gls{il15} signaling.

% TODO not sure if this belongs here, although it might make sense to offer
% alternative explanations of why the DMSs "work" given this negative data
% Second, there is evidence that providing a larger
% contact area for T cell activation provides greater stimulation16,43; the DMSs
% have a rougher interface than the 5 µm magnetic beads, and thus could facilitate
% these larger contact areas. Third, the DMSs may allow the T cells to cluster
% more densely compared to beads, as evidenced by the large clusters on the
% outside of the DMSs (Figure 1f) as well as the significant fraction of DMSs
% found within their interiors (Supplemental Figure 2a and b). This may alter the
% local cytokine environment and trigger different signaling pathways.
% Particularly, IL15 and IL21 are secreted by T cells and known to drive memory
% phenotype44–46. We noted that the IL15 and IL21 concentration was higher in a
% majority of samples when comparing beads and DMSs across multiple timepoints
% (Supplemental Figure 18) in addition to many other cytokines. IL15 and IL21 are
% added exogenously to T cell cultures to enhance memory frequency,45,47 and our
% data here suggest that the DMSs are better at naturally producing these
% cytokines and limiting this need. Furthermore, IL15 unique signals in a trans
% manner in which IL15 is presented on IL15R to neighboring cells48. The higher
% cell density in the DMS cultures would lead to more of these trans interactions,
% and therefore upregulate the IL15 pathway and lead to more memory T cells.

\chapter{aim 3}\label{aim3}

\section{introduction}
\section{methods}

\subsection{CD19-CAR T cell generation}

% METHOD describe how T cells were grown for this aim

% METHOD describe how the luciferase cells were generated (eg the kwong lab)

\subsection{\invivo{} therapeutic efficacy in NSG mice model}

% TODO use actual product numbers for mice
All mice in this study were male \gls{nsg} mice from Jackson Laboratories. At
day 0 (-7 day relative to T cell injection), 1e6 firefly luciferase-expressing
\product{Nalm-6 cells}{ATCC}{CRL-3273} suspended in ice-cold PBS were injected
via tail vein into each mouse. At day 7, saline or CAR T cells at the indicated
doses from either bead or DMS-expanded T cell cultures (for 14 days) were
injected into each mouse via tail vein. Tumor burden was quantified
longitudinally via an \gls{ivis} Spectrum (Perkin Elmer). Briefly, 200ug/mice
luciferin at 15 mg/ml in PBS was injected intraperitoneally under isoflurane
anesthesia into each mouse and waited for at least 10 minutes before imaging.
Mice were anesthetized again and imaged using the \gls{ivis}. Mice from each
treatment group/dose were anesthetized, injected, and imaged together, and
exposure time of the \gls{ivis} was limited to avoid saturation based on the
signal from the saline group. \gls{ivis} images were processed by normalizing
them to common minimum and maximum photon counts and total flux was estimated in
terms of photons/second. Endpoint for each mouse was determined by \gls{iacuc}
euthanasia criteria (hunched back, paralysis, blindness, lethargy, and weight
loss). Mice were euthanized according to these endpoint criteria using carbon
dioxide asphyxiation.

\subsection{statistics}

For the \invivo{} model, the survival curves were created and statistically
analyzed using GraphPad Prism using the Mantel-Cox test to assess significance
between survival groups.

\section{results}

We asked if the higher memory/naive phenotype and more balanced CD4/CD8 ratio of
our \gls{dms}-expanded CAR T cells would lead to better anti-tumor potency in
vivo compared to bead-expanded CAR T cells. We also asked if this superior
anti-tumor potency would hold true at lower doses of CAR expressing T cells in
the DMS group vs the bead group. To test this, we used a human xenograft model
of B cell \gls{all} by intravenously injecting \gls{nsg} mice with \num{1e6}
Nalm-6 tumor cells expression firefly luciferase\cite{Fraietta2018}. After
\SI{7}{\day} of tumor cell growth (\cref{fig:mouse_dosing_overview}), we
intravenously injected saline or three doses (high, medium, and low) of
\gls{dms} T cells from either bead or DMS cultures expanded for \SI{14}{\day}.
We quantified total \gls{dms} expressing T cell percentage for bead and
\gls{dms} groups using the \gls{ptnl} assay (\cref{tab:mouse_dosing_results}).

Before injecting the T cells into the mice, we quantified their phenotype and
growth. We observed that for this expansion, the bead and \gls{dms} T cells
produced similar numbers of \ptmem{} T cells, and the beads even had a higher
fraction of CD45RA, which is present on lower-differentiated naive and
stem-memory T cells (\cref{fig:mouse_dosing_qc_mem}). However, the \pthp{} of
the final product was higher in \gls{dms} (\cref{fig:mouse_dosing_qc_cd4}). The
\gls{dms} T cells also expanded more robustly than the beads
(\cref{fig:mouse_dosing_qc_growth}).

In the Nalm-6/\gls{nsg} xenograft model, we observed lower tumor burden and
significantly longer survival of bead and \gls{dms}-treated mice at all doses
compared to the saline groups (\cref{fig:mouse_dosing_ivis}). Importantly, at
each dose we observed that the \gls{dms}-treated mice had much lower tumor
burden and significantly higher survival than their bead-treated counterparts
(\cref{fig:mouse_dosing_ivis_survival}). When factoring the percentage T cells
in each dose that expressed the \gls{car}, we note that survival of the low
\gls{dms} dose (which had similar total \gls{car} T cells compared to the bead
medium dose and less than the bead high dose) is significantly higher than that
of both the bead medium dose and the bead high dose
(\cref{fig:mouse_dosing_ivis_survival_comp}). Overall, the Kaplan-Meier survival
of Nalm-6 tumor bearing \gls{nsg} mice shown in the
\cref{fig:mouse_dosing_ivis_survival} was up to day 40 as reported
elsewhere\cite{Fraietta2018}. However, we also included a Kaplan-Meier figure up
to day 46 (\cref{fig:mouse_dosing_ivis_survival_full}) where most of the mice
euthanized from day 40 through day 46 from \gls{dms} groups showed no or very
small fragment of spleen which was due to \gls{gvhd} responses. Similar
\gls{gvhd} responses were reported earlier in \gls{nsg} mice where the mice
injected with human \gls{pbmc} exhibited acute \gls{gvhd} between
\SIrange{40}{50}{\day} post intravenous injection\cite{Ali2012}. Notably, both
survival analyses (up to day 40 in \cref{fig:mouse_dosing_ivis_survival} and up
to day 46 in \cref{fig:mouse_dosing_ivis_survival_full}) confirmed that
\gls{dms}-expanded groups outperformed bead-expanded groups in terms of
prolonging survival of Nalm-6 tumor challenged \gls{nsg} mice.

Together, these data suggested that \glspl{dms} produce T cells that are not
only more potent that bead-expanded T cells (even when accounting for
differences in \gls{car} expression) but also showed that \gls{dms} expanded T
cells are effective at lower doses. Given the quality control data of the T
cells prior to injecting into the mice, it seems that this advantage is either
due to the higher \pthp{} or the overall fitness of the T cells given the higher
expansion in the case of \gls{dms}
(\cref{fig:mouse_dosing_qc_cd4,fig:mouse_dosing_qc_growth}). It was likely not
due to the memory phenotype given that it was actually slightly higher in the
case of beads (\cref{fig:mouse_dosing_qc_mem}).

\subsection{DMS-expanded T cells show greater anti-tumor activity \invivo{}
  compared to beads}

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_dosing_overview.png}

  \endgroup
  \caption[Mouse Dosing Experimental Overview]
  {Overview of \invivo{} experiment to test \gls{car} T cells expanded with
    either \glspl{dms} at different doses. }
  \label{fig:mouse_dosing_overview}
\end{figure*}

\begin{table}[!h] \centering
  \caption{Results for \gls{car} T cell \invivo{} dose study}
  \label{tab:mouse_dosing_results}
  \input{../tables/mouse_dose_car.tex}
\end{table}

% TODO put growth first in this figure
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_dosing_qc.png}
  \phantomsubcaption\label{fig:mouse_dosing_qc_mem}
  \phantomsubcaption\label{fig:mouse_dosing_qc_cd4}
  \phantomsubcaption\label{fig:mouse_dosing_qc_growth}

  \endgroup
  \caption[Mouse Dosing T cell Characteristics]
  {Characteristics of T cells harvested at day 14 injected into NSG
    mice at varying doses.
    Fractions of T cell subtypes in the day 14 product including
    \subcap{fig:mouse_dosing_qc_mem}{\ptmemp{}}.
    \subcap{fig:mouse_dosing_qc_cd4}{\pthp{}}, and
    \subcap{fig:mouse_dosing_qc_growth}{Fold change of T cells.}
  }
  \label{fig:mouse_dosing_qc}
\end{figure*}

% TODO explain what statistical test was used here
\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_dosing_ivis.png}
  \phantomsubcaption\label{fig:mouse_dosing_ivis_images}
  \phantomsubcaption\label{fig:mouse_dosing_ivis_plots}
  \phantomsubcaption\label{fig:mouse_dosing_ivis_survival}
  \phantomsubcaption\label{fig:mouse_dosing_ivis_survival_comp}
  \phantomsubcaption\label{fig:mouse_dosing_ivis_survival_full}

  \endgroup
  \caption[Mouse Dosing IVIS and Survival Results]
  {T cells expanded with \glspl{dms} confer greater anti-tumor potency \invivo{}
    even at lower doses.
    \subcap{fig:mouse_dosing_ivis_images}{IVIS images of Nalm-6 tumor-bearing
      \gls{nsg} mice injected with varying doses of T cells}
    \subcap{fig:mouse_dosing_ivis_plots}{Plots showing quantified photon counts
      of the results from (\subref{fig:mouse_dosing_ivis_plots}).}
    \subcap{fig:mouse_dosing_ivis_survival}{Survival plots of mice}
    \subcap{fig:mouse_dosing_ivis_survival_comp}{Survival plots of mice showing
      only those that received a comparable number of \gls{car} T cells.}
    \subcap{fig:mouse_dosing_ivis_survival_full}{The same data as
      \subref{fig:mouse_dosing_ivis_survival} except showing the full time until
    euthanasia for all mice (including those that died via \gls{gvhd}).}
  }
  \label{fig:mouse_dosing_ivis}
\end{figure*}

\subsection{Beads and DMSs perform similarly at earlier timepoints}

We then asked how T cells harvested using either beads or \gls{dms} performed
when harvested at earlier timepoints {\#}{levine paper with early timepoints}.
We performed the same experiments as described in
\cref{fig:mouse_dosing_overview} with the modification that T cells were only
grown and harvested after \SI{6}{\day}, \SI{10}{\day}, or \SI{14}{\day} of
expansion (\cref{fig:mouse_timecourse_overview}). T cells were frozen after
harvest, and all timepoints were thawed at the same time prior to injection. The
dose of T cells injected was \num{1.25e6} cells per mouse (the same as the high
dose in the first experiment). All other characteristics of the experiment were
the same.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_timecourse_overview.png}

  \endgroup
  \caption[Mouse Timecourse Experimental Overview]
  {Overview of \invivo{} experiment to test \gls{car} T cells using either
    \glspl{dms} or bead harvested at varying timepoints.
  }
  \label{fig:mouse_timecourse_overview}
\end{figure*}

% TODO find literature saying that CAR T cells grow slower
As was the case with the first \invivo{} experiment, T cells activated with
\glspl{dms} expanded much more efficiently compared to those expanded with beads
(\cref{fig:mouse_timecourse_qc_growth}). When we quantified the \ptcarp{} of T
cells harvested at each timepoint, we noted that the bead group had much higher
\ptcar{} expression at earlier timpoints compared to \gls{dms}, while they
equalized at later timepoints (\cref{fig:mouse_timecourse_qc_car}). In addition,
overall \ptcar{} expression decreased at later timepoints, indicating that
\gls{car} transduced T cells either grow slower or die faster compared to
untransduced cells. The \pthp{} of the harvested T cells was higher overall in
\gls{dms} expanded T cells but decreased with increasing timepoints 
(\cref{fig:mouse_timecourse_qc_cd4}). The \ptmemp{} was similar at day 6
between bead and \gls{dms} groups but the \gls{dms} group had higher \ptmemp{}
at day 14 despite the overall \ptmemp{} decreasing with time as shown elsewhere
(\cref{fig:mouse_timecourse_qc_mem}) {\#}{levine paper mem over time}.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_timecourse_qc.png}
  \phantomsubcaption\label{fig:mouse_timecourse_qc_growth}
  \phantomsubcaption\label{fig:mouse_timecourse_qc_car}
  \phantomsubcaption\label{fig:mouse_timecourse_qc_cd4}
  \phantomsubcaption\label{fig:mouse_timecourse_qc_mem}

  \endgroup
  \caption[Mouse Timecourse T cell Characteristics]
  {Characteristics of T cells harvested at varying timepoints injected into NSG
    mice.
    \subcap{fig:mouse_timecourse_qc_growth}{Fold change of T cells (each
      timepoint only includes the runs that were harvested at day 14).}
    Fractions of T cell subtypes in the day 14 product including
    \subcap{fig:mouse_timecourse_qc_car}{\ptcarp{}},
    \subcap{fig:mouse_timecourse_qc_cd4}{\pthp{}}, and
    \subcap{fig:mouse_timecourse_qc_mem}{\ptmemp{}}.
  }
  \label{fig:mouse_timecourse_qc}
\end{figure*}

We analyzed the tumor burden using \gls{ivis} which showed that mice that
received T cells from any group performed better than those that received only
saline (\cref{fig:mouse_timecourse_ivis}). Note that unlike the previous
experiment, many of the mice survived until day 40 at which point \gls{gvhd}
began to take effect (after euthanizing the mice at day 42, most had small or no
spleen). When comparing bead and \gls{dms} groups, the \gls{dms} T cells still
seemed superior to the bead group, at least initially (note that in this case
they had similar numbers of \ptcar{} cells). At day 6, both \gls{dms} and bead
groups seemed to eradicate the tumor initially, after which it came back after
day 21 for the bead and day 28 for the \gls{dms} group. The day 10 groups
performed somewhere in between, where they increased linearly unlike the day 6
groups but not as quickly as the day 14 groups. In the case of the \gls{dms} day
10 group, it also appeared like a few mice actually performed better than all
other groups in regard to the final tumor burden.

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_timecourse_ivis.png}
  \phantomsubcaption\label{fig:mouse_timecourse_ivis_images}
  \phantomsubcaption\label{fig:mouse_timecourse_ivis_plots}

  \endgroup
  \caption[Mouse Timecourse IVIS Results]
  {\glspl{dms} exhibit superior anti-tumor activity \invivo{} at day 14 compared
    to beads but are similar to beads at lower timepoints.
    \subcap{fig:mouse_timecourse_ivis_images}{IVIS images for day 6 to day 42 of
    mice treated with varying doses of \gls{car} T cells grown with beads or
    \glspl{dms}.}
    \subcap{fig:mouse_timecourse_ivis_plots}{Quantified dotplots of the images
      in (\subref{fig:mouse_timecourse_ivis_images}). Numbers beneath each dot
      represent the number of mice at that timepoint.},
  }
  \label{fig:mouse_timecourse_ivis}
\end{figure*}

% RESULT this figure
% DISCUSSION this figure

\begin{figure*}[ht!]
  \begingroup

  \includegraphics{../figures/mouse_summary.png}
  \phantomsubcaption\label{fig:mouse_summary_1}
  \phantomsubcaption\label{fig:mouse_summary_2}

  \endgroup
  \caption[Mouse Summary]
  {Summary of cells injected into mice during for
    \subcap{fig:mouse_summary_1}{the first mouse experiment} and 
    \subcap{fig:mouse_summary_2}{the second mouse experiment}. The y axis
    maximum is set to the maximum number of cells injected between both
    experiments (\num{1.25e6}).
  }
  \label{fig:mouse_summary}
\end{figure*}

\section{discussion}

% TABLE make a summary table showing the results from both experiments; this is
% tough to explain.

When we tested bead and DMS expanded \gls{car} T cells, we also found that the
\gls{dms} expanded CAR-T cells outperformed bead groups in prolonging survival
of Nalm-6 tumor challenged (intravenously injected) \gls{nsg} mice. DMS expanded
CAR-T cells were very effective in clearing tumor cells as early as 7 days post
CAR-T injection even at low total T cell dose compared to the bead groups where
tumor burden was higher than DMS groups across all the total T cell doses tested
here. More interestingly, when only CAR-expressing T cell doses between bead and
DMS groups were compared, DMS group had significantly higher survival effects
over similar or higher CAR expression T cell doses from bead group. All these
results suggest that the higher proportion of memory T cells in DMS groups
(compared to bead group) resulted in highly effective CAR-T cells that can
efficiently kill tumor cells as recently reported in
literature\cite{Fraietta2018, Sommermeyer2015}.

% TODO try and find literature explaining what the ideal ratio is
When testing \gls{car} T cells at earlier timepoints relative to day 14 as used
in the first \invivo{} experiment, we noted that none of the \gls{car}
treatments seemed to work as well as they did in the first experiment. However,
at day 14, we should note that the number of \gls{car} T cells injected in the
second experiment was lower than the lowest dose in the first for both bead and
\gls{dms} (\cref{fig:mouse_timecourse_qc_car,tab:mouse_dosing_results}). While
the \ptmemp{} generally increases with earlier timepoints in the second
experiment, the first experiment suggests that \ptmemp{} may not be the primary
driver in this particular model
(\cref{fig:mouse_timecourse_qc_mem,fig:mouse_dosing_qc_mem}). As with the first
experiment, the \pthp{} seems to be higher overall in the \gls{dms} group than
the bead group (\cref{fig:mouse_dosing_qc_cd4,fig:mouse_timecourse_qc_cd4}), and
this may explain the modest advantage that the \gls{dms} T cells seemed to have
in the second experiment in slowing the progression of tumor burden.

\chapter{conclusions and future work}\label{conclusions}

\section{conclusions}

This dissertation describes the development of a novel T cell expansion
platform, including the fabrication, quality control, and biological validation
of its performance both \invitro{} and \invivo{}. Development of such a system
would be meaningful even if it only performed as well as current methods, as
adding another method to the arsenal of the growing T cell manufacturing
industry would reduce the reliance on a small number of companies that currently
license magnetic bead-based T cell expansion technology. However, we
additionally show that the \gls{dms} platform expands more T cells on average,
including highly potent \ptmem{} and \pth{} T cells, and produces higher
percentages of both. If commercialized, this would be a compelling asset the T
cell manufacturing industry.

% TODO double check the numbers at the end
In \cref{aim1}, we develop the \gls{dms} platform and verified its efficacy
\invitro{}. Importantly, this included \gls{qc} steps at every critical step of
the fabrication process to ensure that the \gls{dms} can be made within a
targeted specification. These \gls{qc} steps all rely on common, relatively
cost-effective assays such as the \gls{haba} assay, \gls{bca} assay, and
\glspl{elisa}, thus other labs and commercial entities should be able to perform
them. The microcarriers themselves are an off-the-shelf product available from
reputable vendors, further enhancing translatability. On average, we
demonstrated that the \gls{dms} outperforms state-of-the-art bead-based T cell
expansion technology in terms of total fold expansion, \ptmemp{}, and \pthp{} by
\SI{143}{\percent}, \SI{2.5}{\percent}, and \SI{9.8}{\percent} controlling for
donor, operator, and a variety of process conditions.

In \cref{aim2a}, we developed a modeling pipeline that can be used by commercial
entities as the scale up this process to identify \glspl{cqa} and \gls{cpp}.
These are highly important for a variety of reasons. First, understanding
pertinent \glspl{cpp} allow manufacturers to operate their process at optimal
conditions. This is important for anti-tumor cell therapies, where the prospects
of a patient can urgently depend on receiving therapy in a timely manner.
Optimal process conditions allow T cells to be expanded as quickly as possible
for the patient, while also minimizing cost for the manufacturer. Second,
\glspl{cqa} can be used to define process control schemes as well as release
criteria. Process control, and with it the ability to predict future outcomes
based on data obtained at the present, is highly important for cell therapies
given that batch failures are extremely expensive {\#}, and predicting a batch
failure would allow manufacturers to restart the batch in a timely manner
without wasting resources. Furthermore, \glspl{cqa} can be used to define what a
`good' vs `bad' product is, which will important help anticipate dosing and
followup procedures in the clinic if the T cells are administered. In the aim,
we cannot claim to have found the ultimate set of \glspl{cqa} and \glspl{cpp},
as we used tissue culture plates instead of a bioreactor and we only used one
donor. However, we have indeed outlined a process that others may use to find
these for their process. In particular, the 2-phase modeling process we used
(starting with a \gls{doe} and collecting data longitudinally) is a strategy
that manufacturers can easily implement. Also, collecting secretome and
metabolome is easily generalized to any setting and to most bioreactors and
expansion systems, as they can be obtained with relatively inexpensive equipment
(Luminex assay, benchtop \gls{nmr}, etc) without disturbing the cell culture.

In \cref{aim2b}, we further explored additional tuning knobs that could be used
to control and optimize the \gls{dms} system. We determined that altering the
\gls{dms} concentration temporally has profound effects on the phenotype and
expansion rate. This agrees with other data we obtained in \cref{aim2a} and with
what others have generally reported about signal strength and T cell
differentiation {\#}. We did not find any mechanistic relationship between
either integrin signaling or \gls{il15} signaling. In the case of the former, it
may be more likely that the \glspl{dms} surfaces are saturated to the point of
sterically hindering any integrin interactions with the collagen surface. In the
case of \gls{il15} more experiments likely need to be done in order to plausibly
rule out this mechanism and/or determine if it is involved at all.

% TODO make this tighter and cite paper showing that this makes at least some
% sense
In \cref{aim3} we determined that the \glspl{dms} expand T cells that also
performed better than beads \invivo{}. In the first experiment we performed, the
results were very clearly in favor of the \glspl{dms}. In the second experiment,
even the \gls{dms} group failed to fully control the tumor burden, but this is
not surprising given the low \ptcarp{} across all groups. Also, despite this,
the \gls{dms} group appeared to control the tumor better on average for early,
mid, and late T cell harvesting timepoints. It was not clear if this effect was
due to increased \cdp{} or overall increased fitness of the \gls{dms}-expanded T
cells given their higher expansion rate. The \ptmemp{} did not seem to be a
factor given that it was nearly the same in the first experiment between
\gls{dms} and bead groups despite the clear advantage seen in the \gls{dms}
group.

\section{future directions}

There are several important next steps to perform with this work:

\subsection{Translation to GMP process}

While this work was done with translatability and \gls{qc} in mind, an important
feature that is missing from the process currently is the use of \gls{gmp}
methods and materials. The microcarriers themselves are made from
porcine-derived collagen, which itself is not \gls{gmp}-compliant due to its
non-human animal origins. However, using any other source of collagen should
work so long as the structure of the microcarriers remains relatively similar
and it has lysine groups that can react with the \gls{snb} to attach \gls{stp}
and \glspl{mab}. Obviously these would need to be tested and verified, but they
should not be insurmountable. Furthermore, the \gls{mab} binding step requires
\gls{bsa} to prevent adsorption to the non-polar polymer walls of the reaction
tubes. A human carrier protein such as \gls{hsa} could be used in its place to
eliminate the non-human animal origin material, but this could be much more
expensive. Alternatively, the use of protein could be replaced altogether by a
non-ionic detergent such as Tween-20 or Tween-80, which are already used for
commercial \gls{mab} formulations for precisely this purpose {\#}. Validating
the process with Tween would be the best next step to eliminate \gls{bsa} from
the process. The \gls{stp} and \glspl{mab} in this process were not
\gls{gmp}-grade; however, they are commonly used in clinical technology such as
dynabeads and thus the research-grade proteins used here could be easily
replaced. The \gls{snb} is a synthetic small molecule and thus does not have any
animal-origin concerns.

\subsection{Mechanistic investigation}

% why do the dms work?
% can we put anything on the dms to enhance their potency?

\subsection{Assessing performance using unhealthy donors}

All the work presented in this dissertation was performed using healthy donors.
This was mostly due to the fact that it was much easier to obtain healthy donor
cells and was much easier to control. However, it is indisputable that the most
relevant test cases of the \gls{dms} will be for unhealthy patient T cells, at
least in the case of autologous therapies. In particular, it will be interesting
to see how the \gls{dms} performs when assessed head-to-head with bead-based
expansion technology given that even in healthy donors, we observed the
\gls{dms} platform to work where the beads failed
(\cref{fig:dms_exp_fold_change}).

\subsection{translation to bioreactors}

% use dms in non-static bioreactors such as wave by first activating in a static
% environment

\onecolumn
\clearpage

% TODO some people put appendices here....not sure if I need to

\chapter{References}
\renewcommand{\section}[2]{} % noop the original bib section header

\bibliography{references}

\bibliographystyle{naturemag}

\end{document}