Step_01_Load_and_Inspect_Mouse_Data.tex

% Options for packages loaded elsewhere
% Options for packages loaded elsewhere
\PassOptionsToPackage{unicode}{hyperref}
\PassOptionsToPackage{hyphens}{url}
\PassOptionsToPackage{dvipsnames,svgnames,x11names}{xcolor}
%
\documentclass[
]{article}
\usepackage{xcolor}
\usepackage{amsmath,amssymb}
\setcounter{secnumdepth}{5}
\usepackage{iftex}
\ifPDFTeX
  \usepackage[T1]{fontenc}
  \usepackage[utf8]{inputenc}
  \usepackage{textcomp} % provide euro and other symbols
\else % if luatex or xetex
  \usepackage{unicode-math} % this also loads fontspec
  \defaultfontfeatures{Scale=MatchLowercase}
  \defaultfontfeatures[\rmfamily]{Ligatures=TeX,Scale=1}
\fi
\usepackage{lmodern}
\ifPDFTeX\else
  % xetex/luatex font selection
\fi
% Use upquote if available, for straight quotes in verbatim environments
\IfFileExists{upquote.sty}{\usepackage{upquote}}{}
\IfFileExists{microtype.sty}{% use microtype if available
  \usepackage[]{microtype}
  \UseMicrotypeSet[protrusion]{basicmath} % disable protrusion for tt fonts
}{}
\makeatletter
\@ifundefined{KOMAClassName}{% if non-KOMA class
  \IfFileExists{parskip.sty}{%
    \usepackage{parskip}
  }{% else
    \setlength{\parindent}{0pt}
    \setlength{\parskip}{6pt plus 2pt minus 1pt}}
}{% if KOMA class
  \KOMAoptions{parskip=half}}
\makeatother
% Make \paragraph and \subparagraph free-standing
\makeatletter
\ifx\paragraph\undefined\else
  \let\oldparagraph\paragraph
  \renewcommand{\paragraph}{
    \@ifstar
      \xxxParagraphStar
      \xxxParagraphNoStar
  }
  \newcommand{\xxxParagraphStar}[1]{\oldparagraph*{#1}\mbox{}}
  \newcommand{\xxxParagraphNoStar}[1]{\oldparagraph{#1}\mbox{}}
\fi
\ifx\subparagraph\undefined\else
  \let\oldsubparagraph\subparagraph
  \renewcommand{\subparagraph}{
    \@ifstar
      \xxxSubParagraphStar
      \xxxSubParagraphNoStar
  }
  \newcommand{\xxxSubParagraphStar}[1]{\oldsubparagraph*{#1}\mbox{}}
  \newcommand{\xxxSubParagraphNoStar}[1]{\oldsubparagraph{#1}\mbox{}}
\fi
\makeatother

\usepackage{color}
\usepackage{fancyvrb}
\newcommand{\VerbBar}{|}
\newcommand{\VERB}{\Verb[commandchars=\\\{\}]}
\DefineVerbatimEnvironment{Highlighting}{Verbatim}{commandchars=\\\{\}}
% Add ',fontsize=\small' for more characters per line
\usepackage{framed}
\definecolor{shadecolor}{RGB}{241,243,245}
\newenvironment{Shaded}{\begin{snugshade}}{\end{snugshade}}
\newcommand{\AlertTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\AnnotationTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{#1}}
\newcommand{\AttributeTok}[1]{\textcolor[rgb]{0.40,0.45,0.13}{#1}}
\newcommand{\BaseNTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\BuiltInTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{#1}}
\newcommand{\CharTok}[1]{\textcolor[rgb]{0.13,0.47,0.30}{#1}}
\newcommand{\CommentTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{#1}}
\newcommand{\CommentVarTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{\textit{#1}}}
\newcommand{\ConstantTok}[1]{\textcolor[rgb]{0.56,0.35,0.01}{#1}}
\newcommand{\ControlFlowTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{\textbf{#1}}}
\newcommand{\DataTypeTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\DecValTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\DocumentationTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{\textit{#1}}}
\newcommand{\ErrorTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\ExtensionTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{#1}}
\newcommand{\FloatTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\FunctionTok}[1]{\textcolor[rgb]{0.28,0.35,0.67}{#1}}
\newcommand{\ImportTok}[1]{\textcolor[rgb]{0.00,0.46,0.62}{#1}}
\newcommand{\InformationTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{#1}}
\newcommand{\KeywordTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{\textbf{#1}}}
\newcommand{\NormalTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{#1}}
\newcommand{\OperatorTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{#1}}
\newcommand{\OtherTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{#1}}
\newcommand{\PreprocessorTok}[1]{\textcolor[rgb]{0.68,0.00,0.00}{#1}}
\newcommand{\RegionMarkerTok}[1]{\textcolor[rgb]{0.00,0.23,0.31}{#1}}
\newcommand{\SpecialCharTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{#1}}
\newcommand{\SpecialStringTok}[1]{\textcolor[rgb]{0.13,0.47,0.30}{#1}}
\newcommand{\StringTok}[1]{\textcolor[rgb]{0.13,0.47,0.30}{#1}}
\newcommand{\VariableTok}[1]{\textcolor[rgb]{0.07,0.07,0.07}{#1}}
\newcommand{\VerbatimStringTok}[1]{\textcolor[rgb]{0.13,0.47,0.30}{#1}}
\newcommand{\WarningTok}[1]{\textcolor[rgb]{0.37,0.37,0.37}{\textit{#1}}}

\usepackage{longtable,booktabs,array}
\usepackage{calc} % for calculating minipage widths
% Correct order of tables after \paragraph or \subparagraph
\usepackage{etoolbox}
\makeatletter
\patchcmd\longtable{\par}{\if@noskipsec\mbox{}\fi\par}{}{}
\makeatother
% Allow footnotes in longtable head/foot
\IfFileExists{footnotehyper.sty}{\usepackage{footnotehyper}}{\usepackage{footnote}}
\makesavenoteenv{longtable}
\usepackage{graphicx}
\makeatletter
\newsavebox\pandoc@box
\newcommand*\pandocbounded[1]{% scales image to fit in text height/width
  \sbox\pandoc@box{#1}%
  \Gscale@div\@tempa{\textheight}{\dimexpr\ht\pandoc@box+\dp\pandoc@box\relax}%
  \Gscale@div\@tempb{\linewidth}{\wd\pandoc@box}%
  \ifdim\@tempb\p@<\@tempa\p@\let\@tempa\@tempb\fi% select the smaller of both
  \ifdim\@tempa\p@<\p@\scalebox{\@tempa}{\usebox\pandoc@box}%
  \else\usebox{\pandoc@box}%
  \fi%
}
% Set default figure placement to htbp
\def\fps@figure{htbp}
\makeatother





\setlength{\emergencystretch}{3em} % prevent overfull lines

\providecommand{\tightlist}{%
  \setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}



 


\usepackage{amsmath}
\usepackage{amssymb}
\usepackage{booktabs}
\usepackage{geometry}
\geometry{margin=1in}
\makeatletter
\@ifpackageloaded{caption}{}{\usepackage{caption}}
\AtBeginDocument{%
\ifdefined\contentsname
  \renewcommand*\contentsname{Table of contents}
\else
  \newcommand\contentsname{Table of contents}
\fi
\ifdefined\listfigurename
  \renewcommand*\listfigurename{List of Figures}
\else
  \newcommand\listfigurename{List of Figures}
\fi
\ifdefined\listtablename
  \renewcommand*\listtablename{List of Tables}
\else
  \newcommand\listtablename{List of Tables}
\fi
\ifdefined\figurename
  \renewcommand*\figurename{Figure}
\else
  \newcommand\figurename{Figure}
\fi
\ifdefined\tablename
  \renewcommand*\tablename{Table}
\else
  \newcommand\tablename{Table}
\fi
}
\@ifpackageloaded{float}{}{\usepackage{float}}
\floatstyle{ruled}
\@ifundefined{c@chapter}{\newfloat{codelisting}{h}{lop}}{\newfloat{codelisting}{h}{lop}[chapter]}
\floatname{codelisting}{Listing}
\newcommand*\listoflistings{\listof{codelisting}{List of Listings}}
\makeatother
\makeatletter
\makeatother
\makeatletter
\@ifpackageloaded{caption}{}{\usepackage{caption}}
\@ifpackageloaded{subcaption}{}{\usepackage{subcaption}}
\makeatother
\usepackage{bookmark}
\IfFileExists{xurl.sty}{\usepackage{xurl}}{} % add URL line breaks if available
\urlstyle{same}
\hypersetup{
  pdftitle={Step 01 - Load and Inspect Mouse Data},
  pdfauthor={Jason van Leuven},
  colorlinks=true,
  linkcolor={blue},
  filecolor={Maroon},
  citecolor={Blue},
  urlcolor={Blue},
  pdfcreator={LaTeX via pandoc}}


\title{Step 01 - Load and Inspect Mouse Data}
\author{Jason van Leuven}
\date{2025-10-25}
\begin{document}
\maketitle

\renewcommand*\contentsname{Table of contents}
{
\hypersetup{linkcolor=}
\setcounter{tocdepth}{3}
\tableofcontents
}

\section{Step 01 - Load and Inspect Mouse
Data}\label{step-01---load-and-inspect-mouse-data}

This first step establishes the analytical foundation of the entire
pipeline. It imports and inspects the mouse wound-healing dataset,
ensuring that all subsequent analyses rest on structurally sound and
biologically coherent data. The dataset represents wound closure and
bacterial clearance trajectories collected from controlled mouse models,
where time, treatment group, and outcome variables must align precisely
before any statistical modelling can proceed.

The key objectives here are integrity, completeness, and
reproducibility. The script begins by checking column structure,
verifying that variable names, data types, and units conform to the
expected schema. It then performs completeness checks on key
identifiers, ensuring that each mouse and wound record is unique,
chronologically ordered, and free from structural anomalies such as
missing time points or duplicate measurements. These checks are informed
by reproducible data principles outlined by Wickham et al.~(2019),
allowing each cleaning step to be traceable and verifiable.

Descriptive summaries and diagnostic plots follow. The code produces
simple histograms, scatterplots, and boxplots to visualise wound-area
progression, bacterial counts, and treatment group distributions. These
outputs help confirm whether the observed biological patterns match
expectations --- for example, whether wound size consistently decreases
across days, and whether CFU counts exhibit the expected log-linear
decline under phage or antibiotic treatment. When anomalies appear, such
as reversed healing trends or sudden CFU spikes, they are flagged for
correction or exclusion in later steps.

Finally, Step 01 exports two well-defined intermediate files:\\
- \texttt{closure\_data.csv}, capturing wound-area trajectories for
closure analysis.\\
- \texttt{clearance\_data.csv}, representing bacterial load decay over
time.

These files serve as the clean, structured inputs for \textbf{Step 02},
where they will undergo more formal validation and preparation for
Weibull-based parameter estimation and later allometric scaling to human
data (Wei et al., 2017; Cukjati et al., 2001). The emphasis here is not
just data hygiene but analytical transparency --- establishing a
pipeline where every transformation from raw measurement to model input
can be reproduced and justified.

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# Load V2 Infrastructure}
\CommentTok{\# This replaces hardcoded paths and adds validation \& logging}

\FunctionTok{source}\NormalTok{(}\StringTok{"config/paths.R"}\NormalTok{)}
\FunctionTok{source}\NormalTok{(}\StringTok{"src/R/utils.R"}\NormalTok{)}
\FunctionTok{source}\NormalTok{(}\StringTok{"src/R/data\_validation.R"}\NormalTok{)}
\FunctionTok{source}\NormalTok{(}\StringTok{"src/R/logging.R"}\NormalTok{)}

\CommentTok{\# Get standardized paths}
\NormalTok{paths }\OtherTok{\textless{}{-}} \FunctionTok{get\_project\_paths}\NormalTok{()}

\CommentTok{\# Setup logging}
\FunctionTok{setup\_logging}\NormalTok{(}\AttributeTok{log\_dir =}\NormalTok{ paths}\SpecialCharTok{$}\NormalTok{logs, }\AttributeTok{log\_level =} \StringTok{"INFO"}\NormalTok{)}

\CommentTok{\# Load required packages}
\FunctionTok{suppressPackageStartupMessages}\NormalTok{(\{}
  \FunctionTok{library}\NormalTok{(tidyverse)}
  \FunctionTok{library}\NormalTok{(janitor)}
  \FunctionTok{library}\NormalTok{(readr)}
  \FunctionTok{library}\NormalTok{(glue)}
\NormalTok{\})}

\FunctionTok{log\_info}\NormalTok{(}\StringTok{"="} \SpecialCharTok{\%\textgreater{}\%} \FunctionTok{rep}\NormalTok{(}\DecValTok{70}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{paste}\NormalTok{(}\AttributeTok{collapse =} \StringTok{""}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"STEP 01: Load and Inspect Mouse Data"}\NormalTok{)}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"="} \SpecialCharTok{\%\textgreater{}\%} \FunctionTok{rep}\NormalTok{(}\DecValTok{70}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{paste}\NormalTok{(}\AttributeTok{collapse =} \StringTok{""}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# STEP 01 : Load and Inspect Mouse Data}
\CommentTok{\# Purpose: Import wound closure and bacterial CFU datasets.}
\CommentTok{\# Reference: Wickham et al. (2019) {-} The Tidyverse approach to reproducible data science.}

\CommentTok{\# Define input paths using new infrastructure}
\NormalTok{closure\_path }\OtherTok{\textless{}{-}} \FunctionTok{file.path}\NormalTok{(paths}\SpecialCharTok{$}\NormalTok{data\_raw, }\StringTok{"mouse\_closure\_filled.csv"}\NormalTok{)}
\NormalTok{cfu\_path     }\OtherTok{\textless{}{-}} \FunctionTok{file.path}\NormalTok{(paths}\SpecialCharTok{$}\NormalTok{data\_raw, }\StringTok{"mouse\_cfu\_filled.csv"}\NormalTok{)}

\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{STEP 01 {-} LOAD MOUSE DATASETS}\SpecialCharTok{\textbackslash{}n}\StringTok{============================}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

STEP 01 - LOAD MOUSE DATASETS
============================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Loading mouse datasets from data/raw/"}\NormalTok{)}

\CommentTok{\# Load data}
\NormalTok{closure }\OtherTok{\textless{}{-}} \FunctionTok{read\_csv}\NormalTok{(closure\_path, }\AttributeTok{show\_col\_types =} \ConstantTok{FALSE}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{clean\_names}\NormalTok{()}
\NormalTok{cfu     }\OtherTok{\textless{}{-}} \FunctionTok{read\_csv}\NormalTok{(cfu\_path,     }\AttributeTok{show\_col\_types =} \ConstantTok{FALSE}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{clean\_names}\NormalTok{()}

\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Loaded closure dataset: \{nrow(closure)\} rows x \{ncol(closure)\} columns"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Loaded CFU dataset: \{nrow(cfu)\} rows x \{ncol(cfu)\} columns"}\NormalTok{))}

\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Loaded closure dataset: \{nrow(closure)\} rows x \{ncol(closure)\} columns}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Loaded closure dataset: 140 rows x 11 columns
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Loaded CFU dataset: \{nrow(cfu)\} rows x \{ncol(cfu)\} columns}\SpecialCharTok{\textbackslash{}n\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Loaded CFU dataset: 140 rows x 12 columns
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{glimpse}\NormalTok{(closure)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Rows: 140
Columns: 11
$ cohort            <chr> "ABX", "ABX", "ABX", "ABX", "ABX", "ABX", "ABX", "AB~
$ treatment_group   <chr> "DAPTO", "DAPTO", "DAPTO_LINEZ", "DAPTO_LINEZ", "LIN~
$ mouse_id          <chr> "ABX_DAPTO_M3", "ABX_DAPTO_M4", "ABX_DAPTO_LINEZ_M7"~
$ parameter         <chr> "nd_wound_size_mm^2", "nd_wound_size_mm^2", "nd_woun~
$ day               <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1~
$ wound_area_mm2    <dbl> 40.70, 29.20, 28.10, 25.60, 26.90, 33.80, 31.80, 36.~
$ last_obs_day      <dbl> 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, ~
$ wound_area_interp <dbl> 40.70, 29.20, 28.10, 25.60, 26.90, 33.80, 31.80, 36.~
$ wound_area_filled <dbl> 40.70, 29.20, 28.10, 25.60, 26.90, 33.80, 31.80, 36.~
$ imputed_flag      <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FAL~
$ method_used       <chr> "observed", "observed", "observed", "observed", "obs~
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{glimpse}\NormalTok{(cfu)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Rows: 140
Columns: 12
$ cohort          <chr> "ABX", "ABX", "ABX", "ABX", "ABX", "ABX", "ABX", "ABX"~
$ treatment_group <chr> "DAPTO", "DAPTO", "DAPTO_LINEZ", "DAPTO_LINEZ", "LINEZ~
$ mouse_id        <chr> "ABX_DAPTO_M3", "ABX_DAPTO_M4", "ABX_DAPTO_LINEZ_M7", ~
$ parameter       <chr> "nd_cfu_per_ml", "nd_cfu_per_ml", "nd_cfu_per_ml", "nd~
$ day             <dbl> 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ~
$ cfu_per_ml      <dbl> 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, ~
$ last_obs_day    <dbl> 11, 11, 11, 11, 2, 11, 11, 11, 11, 11, 11, 11, 11, 11,~
$ log_cfu         <dbl> 7.740363, 7.740363, 7.740363, 7.740363, 7.740363, 7.74~
$ log_cfu_interp  <dbl> 7.740363, 7.740363, 7.740363, 7.740363, 7.740363, 7.74~
$ cfu_filled      <dbl> 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, 5.5e+07, ~
$ imputed_flag    <lgl> FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE~
$ method_used     <chr> "observed", "observed", "observed", "observed", "obser~
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# V2 Enhancement: Validate data structure}
\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{[checkmark] Running data validation checks...}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

[checkmark] Running data validation checks...
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Running data validation checks"}\NormalTok{)}

\FunctionTok{tryCatch}\NormalTok{(\{}
  \CommentTok{\# Validate closure data structure}
  \FunctionTok{validate\_mouse\_data}\NormalTok{(}
\NormalTok{    closure, }
    \AttributeTok{required\_cols =} \FunctionTok{c}\NormalTok{(}\StringTok{"mouse\_id"}\NormalTok{, }\StringTok{"day"}\NormalTok{, }\StringTok{"wound\_area\_filled"}\NormalTok{, }\StringTok{"treatment\_group"}\NormalTok{, }\StringTok{"cohort"}\NormalTok{)}
\NormalTok{  )}
  
  \CommentTok{\# Validate closure data quality}
\NormalTok{  closure\_validation }\OtherTok{\textless{}{-}} \FunctionTok{validate\_closure\_data}\NormalTok{(closure)}
  
  \ControlFlowTok{if}\NormalTok{ (closure\_validation}\SpecialCharTok{$}\NormalTok{all\_pass) \{}
    \FunctionTok{cat}\NormalTok{(}\StringTok{"[checkmark] All closure data validation checks passed}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
    \FunctionTok{log\_info}\NormalTok{(}\StringTok{"All closure data validation checks passed"}\NormalTok{)}
\NormalTok{  \} }\ControlFlowTok{else}\NormalTok{ \{}
    \FunctionTok{cat}\NormalTok{(}\StringTok{"[!] Some validation checks failed {-} see warnings above}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
    \FunctionTok{log\_warn}\NormalTok{(}\StringTok{"Some closure data validation checks failed"}\NormalTok{)}
\NormalTok{  \}}
  
  \CommentTok{\# Validate CFU data structure}
  \FunctionTok{validate\_mouse\_data}\NormalTok{(}
\NormalTok{    cfu,}
    \AttributeTok{required\_cols =} \FunctionTok{c}\NormalTok{(}\StringTok{"mouse\_id"}\NormalTok{, }\StringTok{"day"}\NormalTok{, }\StringTok{"cfu\_filled"}\NormalTok{, }\StringTok{"treatment\_group"}\NormalTok{, }\StringTok{"cohort"}\NormalTok{)}
\NormalTok{  )}
  
  \FunctionTok{cat}\NormalTok{(}\StringTok{"[checkmark] All CFU data structure checks passed}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
  \FunctionTok{log\_info}\NormalTok{(}\StringTok{"All CFU data structure checks passed"}\NormalTok{)}
  
\NormalTok{\}, }\AttributeTok{error =} \ControlFlowTok{function}\NormalTok{(e) \{}
  \FunctionTok{log\_error}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Validation failed: \{e$message\}"}\NormalTok{))}
  \FunctionTok{stop}\NormalTok{(e)}
\NormalTok{\})}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
[!] Some validation checks failed - see warnings above
\end{verbatim}

\begin{verbatim}
[checkmark] All CFU data structure checks passed
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{Numeric Range Checks}\SpecialCharTok{\textbackslash{}n}\StringTok{{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

Numeric Range Checks
----------------------------
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"Closure (wound\_area\_filled):}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{); }\FunctionTok{summary}\NormalTok{(closure}\SpecialCharTok{$}\NormalTok{wound\_area\_filled)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Closure (wound_area_filled):
\end{verbatim}

\begin{verbatim}
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   6.40   27.95   35.42   33.71   40.30   57.80 
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{CFU (cfu\_filled):}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{);           }\FunctionTok{summary}\NormalTok{(cfu}\SpecialCharTok{$}\NormalTok{cfu\_filled)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

CFU (cfu_filled):
\end{verbatim}

\begin{verbatim}
     Min.   1st Qu.    Median      Mean   3rd Qu.      Max.      NA's 
        0   5681405  14400000  37646258  55000000 290000000         5 
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{[checkmark] Step 01 inspection complete {-} datasets structurally validated.}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

[checkmark] Step 01 inspection complete - datasets structurally validated.
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Step 01 inspection complete {-} datasets structurally validated"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# STEP 02 : Cohort \& Treatment Summary}
\CommentTok{\# Purpose: Summarise cohort and treatment composition.}

\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{STEP 02 {-} COHORT \& TREATMENT SUMMARY}\SpecialCharTok{\textbackslash{}n}\StringTok{============================}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

STEP 02 - COHORT & TREATMENT SUMMARY
============================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Generating cohort and treatment summaries"}\NormalTok{)}

\NormalTok{closure\_counts }\OtherTok{\textless{}{-}}\NormalTok{ closure }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{count}\NormalTok{(cohort, treatment\_group)}
\NormalTok{cfu\_counts     }\OtherTok{\textless{}{-}}\NormalTok{ cfu }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{count}\NormalTok{(cohort, treatment\_group)}

\FunctionTok{print}\NormalTok{(closure\_counts)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
# A tibble: 6 x 3
  cohort treatment_group     n
  <chr>  <chr>           <int>
1 ABX    DAPTO              14
2 ABX    DAPTO_LINEZ        14
3 ABX    LINEZ              42
4 ABX    VANCO              28
5 PHA    PHAGE              21
6 PHA    PHAGEGEL           21
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{print}\NormalTok{(cfu\_counts)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
# A tibble: 6 x 3
  cohort treatment_group     n
  <chr>  <chr>           <int>
1 ABX    DAPTO              14
2 ABX    DAPTO_LINEZ        14
3 ABX    LINEZ              42
4 ABX    VANCO              28
5 PHA    PHAGE              21
6 PHA    PHAGEGEL           21
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Closure dataset: \{nrow(closure\_counts)\} cohort{-}treatment combinations"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"CFU dataset: \{nrow(cfu\_counts)\} cohort{-}treatment combinations"}\NormalTok{))}

\NormalTok{aligned }\OtherTok{\textless{}{-}} \FunctionTok{identical}\NormalTok{(}\FunctionTok{sort}\NormalTok{(}\FunctionTok{unique}\NormalTok{(closure}\SpecialCharTok{$}\NormalTok{mouse\_id)), }\FunctionTok{sort}\NormalTok{(}\FunctionTok{unique}\NormalTok{(cfu}\SpecialCharTok{$}\NormalTok{mouse\_id)))}
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{Mouse ID alignment across datasets: \{aligned\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Mouse ID alignment across datasets: TRUE
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Mouse ID alignment: \{aligned\}"}\NormalTok{))}

\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Closure missing wound\_area\_filled: \{sum(is.na(closure$wound\_area\_filled))\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Closure missing wound_area_filled: 0
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"CFU missing cfu\_filled: \{sum(is.na(cfu$cfu\_filled))\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
CFU missing cfu_filled: 5
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Closure missing values: \{sum(is.na(closure$wound\_area\_filled))\}"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"CFU missing values: \{sum(is.na(cfu$cfu\_filled))\}"}\NormalTok{))}

\FunctionTok{cat}\NormalTok{(}\StringTok{"[checkmark] Step 02 summary complete {-} datasets aligned and merge{-}ready.}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
[checkmark] Step 02 summary complete - datasets aligned and merge-ready.
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Step 02 summary complete"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# STEP 03 : Merge and Export Datasets}
\CommentTok{\# Purpose: Consolidate closure and CFU data for unified analysis.}

\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{STEP 03 {-} MERGE \& EXPORT DATASETS}\SpecialCharTok{\textbackslash{}n}\StringTok{============================}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

STEP 03 - MERGE & EXPORT DATASETS
============================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Merging datasets"}\NormalTok{)}

\NormalTok{merged }\OtherTok{\textless{}{-}}\NormalTok{ closure }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{select}\NormalTok{(cohort, treatment\_group, mouse\_id, day, wound\_area\_filled) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{left\_join}\NormalTok{(cfu }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{select}\NormalTok{(cohort, treatment\_group, mouse\_id, day, cfu\_filled),}
            \AttributeTok{by =} \FunctionTok{c}\NormalTok{(}\StringTok{"cohort"}\NormalTok{, }\StringTok{"treatment\_group"}\NormalTok{, }\StringTok{"mouse\_id"}\NormalTok{, }\StringTok{"day"}\NormalTok{))}

\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Merged dataset created: \{nrow(merged)\} rows x \{ncol(merged)\} columns}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Merged dataset created: 140 rows x 6 columns
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Missing CFU entries: \{sum(is.na(merged$cfu\_filled))\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Missing CFU entries: 5
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Merged dataset: \{nrow(merged)\} rows x \{ncol(merged)\} columns"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Missing CFU entries: \{sum(is.na(merged$cfu\_filled))\}"}\NormalTok{))}

\CommentTok{\# Use new path structure for outputs}
\NormalTok{closure\_out   }\OtherTok{\textless{}{-}} \FunctionTok{file.path}\NormalTok{(paths}\SpecialCharTok{$}\NormalTok{outputs, }\StringTok{"closure\_data.csv"}\NormalTok{)}
\NormalTok{clearance\_out }\OtherTok{\textless{}{-}} \FunctionTok{file.path}\NormalTok{(paths}\SpecialCharTok{$}\NormalTok{outputs, }\StringTok{"clearance\_data.csv"}\NormalTok{)}
\NormalTok{merged\_out    }\OtherTok{\textless{}{-}} \FunctionTok{file.path}\NormalTok{(paths}\SpecialCharTok{$}\NormalTok{outputs, }\StringTok{"merged\_data.csv"}\NormalTok{)}

\FunctionTok{write\_csv}\NormalTok{(merged }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{select}\NormalTok{(cohort, treatment\_group, mouse\_id, day, wound\_area\_filled), closure\_out)}
\FunctionTok{write\_csv}\NormalTok{(merged }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{select}\NormalTok{(cohort, treatment\_group, mouse\_id, day, cfu\_filled),      clearance\_out)}
\FunctionTok{write\_csv}\NormalTok{(merged, merged\_out)}

\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Saved closure data {-}\textgreater{} \{closure\_out\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Saved closure data -> /Users/vanl0030/Documents/weibull_pipeline_v2/outputs/closure_data.csv
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Saved clearance data {-}\textgreater{} \{clearance\_out\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Saved clearance data -> /Users/vanl0030/Documents/weibull_pipeline_v2/outputs/clearance_data.csv
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Saved merged data {-}\textgreater{} \{merged\_out\}}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Saved merged data -> /Users/vanl0030/Documents/weibull_pipeline_v2/outputs/merged_data.csv
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Exported: closure\_data.csv, clearance\_data.csv, merged\_data.csv"}\NormalTok{)}

\FunctionTok{cat}\NormalTok{(}\StringTok{"[checkmark] Step 03 complete {-} datasets exported to outputs/}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
[checkmark] Step 03 complete - datasets exported to outputs/
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Step 03 complete"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# STEP 03A : Comprehensive Merge Diagnostics}
\CommentTok{\# Purpose: Multi{-}faceted view of data coverage and overlap}
\CommentTok{\# Reference: Ensures dataset integrity for later KM survival modelling.}

\FunctionTok{suppressPackageStartupMessages}\NormalTok{(\{}
  \FunctionTok{library}\NormalTok{(ggvenn)}
  \FunctionTok{library}\NormalTok{(gridExtra)}
  \FunctionTok{library}\NormalTok{(grid)}
\NormalTok{\})}

\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Generating comprehensive merge diagnostics"}\NormalTok{)}

\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\CommentTok{\# 1. Overall Closure vs CFU Overlap}
\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\NormalTok{closure\_keys }\OtherTok{\textless{}{-}}\NormalTok{ closure }\SpecialCharTok{\%\textgreater{}\%} 
  \FunctionTok{mutate}\NormalTok{(}\AttributeTok{join\_key =} \FunctionTok{paste}\NormalTok{(cohort, treatment\_group, mouse\_id, day, }\AttributeTok{sep =} \StringTok{"\_"}\NormalTok{)) }\SpecialCharTok{\%\textgreater{}\%} 
  \FunctionTok{pull}\NormalTok{(join\_key)}

\NormalTok{cfu\_keys }\OtherTok{\textless{}{-}}\NormalTok{ cfu }\SpecialCharTok{\%\textgreater{}\%} 
  \FunctionTok{mutate}\NormalTok{(}\AttributeTok{join\_key =} \FunctionTok{paste}\NormalTok{(cohort, treatment\_group, mouse\_id, day, }\AttributeTok{sep =} \StringTok{"\_"}\NormalTok{)) }\SpecialCharTok{\%\textgreater{}\%} 
  \FunctionTok{pull}\NormalTok{(join\_key)}

\CommentTok{\# Calculate overlap statistics}
\NormalTok{total\_closure }\OtherTok{\textless{}{-}} \FunctionTok{length}\NormalTok{(}\FunctionTok{unique}\NormalTok{(closure\_keys))}
\NormalTok{total\_cfu }\OtherTok{\textless{}{-}} \FunctionTok{length}\NormalTok{(}\FunctionTok{unique}\NormalTok{(cfu\_keys))}
\NormalTok{overlap }\OtherTok{\textless{}{-}} \FunctionTok{length}\NormalTok{(}\FunctionTok{intersect}\NormalTok{(}\FunctionTok{unique}\NormalTok{(closure\_keys), }\FunctionTok{unique}\NormalTok{(cfu\_keys)))}
\NormalTok{closure\_only }\OtherTok{\textless{}{-}} \FunctionTok{length}\NormalTok{(}\FunctionTok{setdiff}\NormalTok{(}\FunctionTok{unique}\NormalTok{(closure\_keys), }\FunctionTok{unique}\NormalTok{(cfu\_keys)))}
\NormalTok{cfu\_only }\OtherTok{\textless{}{-}} \FunctionTok{length}\NormalTok{(}\FunctionTok{setdiff}\NormalTok{(}\FunctionTok{unique}\NormalTok{(cfu\_keys), }\FunctionTok{unique}\NormalTok{(closure\_keys)))}

\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{===========================================================}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

===========================================================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"MERGE DIAGNOSTICS SUMMARY}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
MERGE DIAGNOSTICS SUMMARY
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"===========================================================}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
===========================================================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"Total Closure observations:     \%5d}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{, total\_closure))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Total Closure observations:       140
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"Total CFU observations:         \%5d}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{, total\_cfu))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Total CFU observations:           140
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"Perfect overlap (both):         \%5d (\%.1f\%\%)}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{, }
\NormalTok{    overlap, }\DecValTok{100} \SpecialCharTok{*}\NormalTok{ overlap }\SpecialCharTok{/} \FunctionTok{max}\NormalTok{(total\_closure, total\_cfu)))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Perfect overlap (both):           140 (100.0%)
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"Closure only (no CFU):          \%5d}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{, closure\_only))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
Closure only (no CFU):              0
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"CFU only (no Closure):          \%5d}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{, cfu\_only))}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
CFU only (no Closure):              0
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"===========================================================}\SpecialCharTok{\textbackslash{}n\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
===========================================================
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{sprintf}\NormalTok{(}\StringTok{"Data overlap: \%d/\%d observations (\%.1f\%\%)"}\NormalTok{, }
\NormalTok{                 overlap, }\FunctionTok{max}\NormalTok{(total\_closure, total\_cfu), }
                 \DecValTok{100} \SpecialCharTok{*}\NormalTok{ overlap }\SpecialCharTok{/} \FunctionTok{max}\NormalTok{(total\_closure, total\_cfu)))}

\CommentTok{\# Overall Venn diagram with better sizing}
\NormalTok{p1 }\OtherTok{\textless{}{-}} \FunctionTok{ggvenn}\NormalTok{(}
  \FunctionTok{list}\NormalTok{(}
    \StringTok{"Wound Closure}\SpecialCharTok{\textbackslash{}n}\StringTok{Data"} \OtherTok{=} \FunctionTok{unique}\NormalTok{(closure\_keys), }
    \StringTok{"Bacterial CFU}\SpecialCharTok{\textbackslash{}n}\StringTok{Data"} \OtherTok{=} \FunctionTok{unique}\NormalTok{(cfu\_keys)}
\NormalTok{  ), }
  \AttributeTok{fill\_color =} \FunctionTok{c}\NormalTok{(}\StringTok{"\#0073C2FF"}\NormalTok{, }\StringTok{"\#EFC000FF"}\NormalTok{),}
  \AttributeTok{stroke\_size =} \FloatTok{1.5}\NormalTok{,}
  \AttributeTok{set\_name\_size =} \DecValTok{6}\NormalTok{,}
  \AttributeTok{text\_size =} \FloatTok{5.5}
\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{labs}\NormalTok{(}\AttributeTok{title =} \StringTok{"A. Overall Data Coverage"}\NormalTok{,}
       \AttributeTok{subtitle =} \FunctionTok{sprintf}\NormalTok{(}\StringTok{"Overlap: \%d observations (\%.1f\%\%)"}\NormalTok{, }
\NormalTok{                         overlap, }\DecValTok{100} \SpecialCharTok{*}\NormalTok{ overlap }\SpecialCharTok{/} \FunctionTok{max}\NormalTok{(total\_closure, total\_cfu))) }\SpecialCharTok{+}
  \FunctionTok{theme}\NormalTok{(}\AttributeTok{plot.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{16}\NormalTok{, }\AttributeTok{face =} \StringTok{"bold"}\NormalTok{),}
        \AttributeTok{plot.subtitle =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{13}\NormalTok{))}

\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\CommentTok{\# 2. Coverage by Treatment Group}
\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\NormalTok{treatment\_coverage }\OtherTok{\textless{}{-}}\NormalTok{ merged }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{group\_by}\NormalTok{(treatment\_group) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{summarise}\NormalTok{(}
    \AttributeTok{n\_mice =} \FunctionTok{n\_distinct}\NormalTok{(mouse\_id),}
    \AttributeTok{n\_obs =} \FunctionTok{n}\NormalTok{(),}
    \AttributeTok{closure\_complete =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(wound\_area\_filled)),}
    \AttributeTok{cfu\_complete =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(cfu\_filled)),}
    \AttributeTok{both\_complete =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(wound\_area\_filled) }\SpecialCharTok{\&} \SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(cfu\_filled)),}
    \AttributeTok{.groups =} \StringTok{"drop"}
\NormalTok{  ) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{mutate}\NormalTok{(}
    \AttributeTok{closure\_pct =} \DecValTok{100} \SpecialCharTok{*}\NormalTok{ closure\_complete }\SpecialCharTok{/}\NormalTok{ n\_obs,}
    \AttributeTok{cfu\_pct =} \DecValTok{100} \SpecialCharTok{*}\NormalTok{ cfu\_complete }\SpecialCharTok{/}\NormalTok{ n\_obs,}
    \AttributeTok{both\_pct =} \DecValTok{100} \SpecialCharTok{*}\NormalTok{ both\_complete }\SpecialCharTok{/}\NormalTok{ n\_obs}
\NormalTok{  )}

\NormalTok{p2 }\OtherTok{\textless{}{-}} \FunctionTok{ggplot}\NormalTok{(treatment\_coverage, }\FunctionTok{aes}\NormalTok{(}\AttributeTok{x =}\NormalTok{ treatment\_group)) }\SpecialCharTok{+}
  \FunctionTok{geom\_col}\NormalTok{(}\FunctionTok{aes}\NormalTok{(}\AttributeTok{y =}\NormalTok{ both\_pct), }\AttributeTok{fill =} \StringTok{"\#2ECC71"}\NormalTok{, }\AttributeTok{alpha =} \FloatTok{0.8}\NormalTok{, }\AttributeTok{width =} \FloatTok{0.7}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{geom\_col}\NormalTok{(}\FunctionTok{aes}\NormalTok{(}\AttributeTok{y =}\NormalTok{ closure\_pct), }\AttributeTok{fill =} \StringTok{"\#0073C2FF"}\NormalTok{, }\AttributeTok{alpha =} \FloatTok{0.5}\NormalTok{, }\AttributeTok{width =} \FloatTok{0.5}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{geom\_col}\NormalTok{(}\FunctionTok{aes}\NormalTok{(}\AttributeTok{y =}\NormalTok{ cfu\_pct), }\AttributeTok{fill =} \StringTok{"\#EFC000FF"}\NormalTok{, }\AttributeTok{alpha =} \FloatTok{0.5}\NormalTok{, }\AttributeTok{width =} \FloatTok{0.3}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{geom\_text}\NormalTok{(}\FunctionTok{aes}\NormalTok{(}\AttributeTok{y =}\NormalTok{ both\_pct }\SpecialCharTok{+} \DecValTok{5}\NormalTok{, }\AttributeTok{label =} \FunctionTok{sprintf}\NormalTok{(}\StringTok{"\%.0f\%\%"}\NormalTok{, both\_pct)), }
            \AttributeTok{size =} \DecValTok{5}\NormalTok{, }\AttributeTok{fontface =} \StringTok{"bold"}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{scale\_y\_continuous}\NormalTok{(}\AttributeTok{limits =} \FunctionTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\DecValTok{105}\NormalTok{), }\AttributeTok{expand =} \FunctionTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\DecValTok{0}\NormalTok{)) }\SpecialCharTok{+}
  \FunctionTok{labs}\NormalTok{(}
    \AttributeTok{title =} \StringTok{"B. Data Completeness by Treatment Group"}\NormalTok{,}
    \AttributeTok{subtitle =} \StringTok{"Green = Both measurements | Blue = Closure | Yellow = CFU"}\NormalTok{,}
    \AttributeTok{x =} \StringTok{"Treatment Group"}\NormalTok{,}
    \AttributeTok{y =} \StringTok{"\% Complete"}
\NormalTok{  ) }\SpecialCharTok{+}
  \FunctionTok{theme\_minimal}\NormalTok{(}\AttributeTok{base\_size =} \DecValTok{14}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{theme}\NormalTok{(}
    \AttributeTok{panel.grid.major.x =} \FunctionTok{element\_blank}\NormalTok{(),}
    \AttributeTok{plot.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{face =} \StringTok{"bold"}\NormalTok{, }\AttributeTok{size =} \DecValTok{16}\NormalTok{),}
    \AttributeTok{plot.subtitle =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{),}
    \AttributeTok{axis.text.x =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{angle =} \DecValTok{0}\NormalTok{, }\AttributeTok{hjust =} \FloatTok{0.5}\NormalTok{, }\AttributeTok{size =} \DecValTok{12}\NormalTok{)}
\NormalTok{  )}

\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\CommentTok{\# 3. Coverage by Cohort}
\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\NormalTok{cohort\_coverage }\OtherTok{\textless{}{-}}\NormalTok{ merged }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{group\_by}\NormalTok{(cohort, treatment\_group) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{summarise}\NormalTok{(}
    \AttributeTok{n\_mice =} \FunctionTok{n\_distinct}\NormalTok{(mouse\_id),}
    \AttributeTok{both\_complete =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(wound\_area\_filled) }\SpecialCharTok{\&} \SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(cfu\_filled)),}
    \AttributeTok{n\_obs =} \FunctionTok{n}\NormalTok{(),}
    \AttributeTok{.groups =} \StringTok{"drop"}
\NormalTok{  ) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{mutate}\NormalTok{(}\AttributeTok{complete\_pct =} \DecValTok{100} \SpecialCharTok{*}\NormalTok{ both\_complete }\SpecialCharTok{/}\NormalTok{ n\_obs)}

\NormalTok{p3 }\OtherTok{\textless{}{-}} \FunctionTok{ggplot}\NormalTok{(cohort\_coverage, }\FunctionTok{aes}\NormalTok{(}\AttributeTok{x =}\NormalTok{ cohort, }\AttributeTok{y =}\NormalTok{ complete\_pct, }\AttributeTok{fill =}\NormalTok{ treatment\_group)) }\SpecialCharTok{+}
  \FunctionTok{geom\_col}\NormalTok{(}\AttributeTok{position =} \StringTok{"dodge"}\NormalTok{, }\AttributeTok{width =} \FloatTok{0.7}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{geom\_text}\NormalTok{(}\FunctionTok{aes}\NormalTok{(}\AttributeTok{label =} \FunctionTok{sprintf}\NormalTok{(}\StringTok{"n=\%d}\SpecialCharTok{\textbackslash{}n}\StringTok{\%.0f\%\%"}\NormalTok{, n\_mice, complete\_pct)),}
            \AttributeTok{position =} \FunctionTok{position\_dodge}\NormalTok{(}\AttributeTok{width =} \FloatTok{0.7}\NormalTok{),}
            \AttributeTok{vjust =} \SpecialCharTok{{-}}\FloatTok{0.3}\NormalTok{, }\AttributeTok{size =} \DecValTok{4}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{scale\_y\_continuous}\NormalTok{(}\AttributeTok{limits =} \FunctionTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\DecValTok{115}\NormalTok{), }\AttributeTok{expand =} \FunctionTok{c}\NormalTok{(}\DecValTok{0}\NormalTok{, }\DecValTok{0}\NormalTok{)) }\SpecialCharTok{+}
  \FunctionTok{scale\_fill\_brewer}\NormalTok{(}\AttributeTok{palette =} \StringTok{"Set2"}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{labs}\NormalTok{(}
    \AttributeTok{title =} \StringTok{"C. Data Completeness by Cohort \& Treatment"}\NormalTok{,}
    \AttributeTok{subtitle =} \StringTok{"Showing mice per group and \% with both measurements"}\NormalTok{,}
    \AttributeTok{x =} \StringTok{"Cohort"}\NormalTok{,}
    \AttributeTok{y =} \StringTok{"\% Complete (Both Measurements)"}\NormalTok{,}
    \AttributeTok{fill =} \StringTok{"Treatment"}
\NormalTok{  ) }\SpecialCharTok{+}
  \FunctionTok{theme\_minimal}\NormalTok{(}\AttributeTok{base\_size =} \DecValTok{14}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{theme}\NormalTok{(}
    \AttributeTok{legend.position =} \StringTok{"bottom"}\NormalTok{,}
    \AttributeTok{legend.text =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{11}\NormalTok{),}
    \AttributeTok{legend.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{, }\AttributeTok{face =} \StringTok{"bold"}\NormalTok{),}
    \AttributeTok{panel.grid.major.x =} \FunctionTok{element\_blank}\NormalTok{(),}
    \AttributeTok{plot.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{face =} \StringTok{"bold"}\NormalTok{, }\AttributeTok{size =} \DecValTok{16}\NormalTok{),}
    \AttributeTok{plot.subtitle =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{),}
    \AttributeTok{axis.text =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{)}
\NormalTok{  )}

\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\CommentTok{\# 4. Temporal Coverage (by Day)}
\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\NormalTok{temporal\_coverage }\OtherTok{\textless{}{-}}\NormalTok{ merged }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{group\_by}\NormalTok{(day) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{summarise}\NormalTok{(}
    \AttributeTok{n\_observations =} \FunctionTok{n}\NormalTok{(),}
    \AttributeTok{closure\_available =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(wound\_area\_filled)),}
    \AttributeTok{cfu\_available =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(cfu\_filled)),}
    \AttributeTok{both\_available =} \FunctionTok{sum}\NormalTok{(}\SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(wound\_area\_filled) }\SpecialCharTok{\&} \SpecialCharTok{!}\FunctionTok{is.na}\NormalTok{(cfu\_filled)),}
    \AttributeTok{.groups =} \StringTok{"drop"}
\NormalTok{  ) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{pivot\_longer}\NormalTok{(}\AttributeTok{cols =} \FunctionTok{c}\NormalTok{(closure\_available, cfu\_available, both\_available),}
               \AttributeTok{names\_to =} \StringTok{"measurement\_type"}\NormalTok{,}
               \AttributeTok{values\_to =} \StringTok{"count"}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%}
  \FunctionTok{mutate}\NormalTok{(}
    \AttributeTok{measurement\_type =} \FunctionTok{factor}\NormalTok{(}
\NormalTok{      measurement\_type,}
      \AttributeTok{levels =} \FunctionTok{c}\NormalTok{(}\StringTok{"both\_available"}\NormalTok{, }\StringTok{"closure\_available"}\NormalTok{, }\StringTok{"cfu\_available"}\NormalTok{),}
      \AttributeTok{labels =} \FunctionTok{c}\NormalTok{(}\StringTok{"Both Complete"}\NormalTok{, }\StringTok{"Closure Data"}\NormalTok{, }\StringTok{"CFU Data"}\NormalTok{)}
\NormalTok{    )}
\NormalTok{  )}

\NormalTok{p4 }\OtherTok{\textless{}{-}} \FunctionTok{ggplot}\NormalTok{(temporal\_coverage, }\FunctionTok{aes}\NormalTok{(}\AttributeTok{x =}\NormalTok{ day, }\AttributeTok{y =}\NormalTok{ count, }\AttributeTok{color =}\NormalTok{ measurement\_type)) }\SpecialCharTok{+}
  \FunctionTok{geom\_line}\NormalTok{(}\AttributeTok{linewidth =} \FloatTok{1.5}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{geom\_point}\NormalTok{(}\AttributeTok{size =} \FloatTok{3.5}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{scale\_color\_manual}\NormalTok{(}\AttributeTok{values =} \FunctionTok{c}\NormalTok{(}\StringTok{"Both Complete"} \OtherTok{=} \StringTok{"\#2ECC71"}\NormalTok{, }
                                 \StringTok{"Closure Data"} \OtherTok{=} \StringTok{"\#0073C2FF"}\NormalTok{,}
                                 \StringTok{"CFU Data"} \OtherTok{=} \StringTok{"\#EFC000FF"}\NormalTok{)) }\SpecialCharTok{+}
  \FunctionTok{labs}\NormalTok{(}
    \AttributeTok{title =} \StringTok{"D. Temporal Coverage Across Study Period"}\NormalTok{,}
    \AttributeTok{subtitle =} \StringTok{"Number of observations available at each time point"}\NormalTok{,}
    \AttributeTok{x =} \StringTok{"Study Day"}\NormalTok{,}
    \AttributeTok{y =} \StringTok{"Number of Observations"}\NormalTok{,}
    \AttributeTok{color =} \StringTok{"Data Type"}
\NormalTok{  ) }\SpecialCharTok{+}
  \FunctionTok{theme\_minimal}\NormalTok{(}\AttributeTok{base\_size =} \DecValTok{14}\NormalTok{) }\SpecialCharTok{+}
  \FunctionTok{theme}\NormalTok{(}
    \AttributeTok{legend.position =} \StringTok{"bottom"}\NormalTok{,}
    \AttributeTok{legend.text =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{11}\NormalTok{),}
    \AttributeTok{legend.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{, }\AttributeTok{face =} \StringTok{"bold"}\NormalTok{),}
    \AttributeTok{plot.title =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{face =} \StringTok{"bold"}\NormalTok{, }\AttributeTok{size =} \DecValTok{16}\NormalTok{),}
    \AttributeTok{plot.subtitle =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{),}
    \AttributeTok{axis.text =} \FunctionTok{element\_text}\NormalTok{(}\AttributeTok{size =} \DecValTok{12}\NormalTok{)}
\NormalTok{  )}

\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\CommentTok{\# Combine all plots with better spacing}
\CommentTok{\# {-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}{-}}
\FunctionTok{grid.arrange}\NormalTok{(}
\NormalTok{  p1, p2, p3, p4,}
  \AttributeTok{ncol =} \DecValTok{2}\NormalTok{,}
  \AttributeTok{nrow =} \DecValTok{2}\NormalTok{,}
  \AttributeTok{top =} \FunctionTok{textGrob}\NormalTok{(}\StringTok{"Comprehensive Data Coverage Analysis"}\NormalTok{,}
                 \AttributeTok{gp =} \FunctionTok{gpar}\NormalTok{(}\AttributeTok{fontsize =} \DecValTok{20}\NormalTok{, }\AttributeTok{fontface =} \StringTok{"bold"}\NormalTok{)),}
  \AttributeTok{padding =} \FunctionTok{unit}\NormalTok{(}\FloatTok{1.5}\NormalTok{, }\StringTok{"line"}\NormalTok{)}
\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\pandocbounded{\includegraphics[keepaspectratio]{Step_01_Load_and_Inspect_Mouse_Data_files/figure-pdf/merge_diagnostics-1.pdf}}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"[checkmark] Comprehensive merge diagnostics complete}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
[checkmark] Comprehensive merge diagnostics complete
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Generated 4{-}panel merge diagnostic visualization"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\section{-----------------------------------------------------------------------------}\label{section}

\section{1. Overall Closure vs CFU
Overlap}\label{overall-closure-vs-cfu-overlap}

\section{-----------------------------------------------------------------------------}\label{section-1}

closure\_keys \textless- closure \%\textgreater\% mutate(join\_key =
paste(cohort, treatment\_group, mouse\_id, day, sep = ``\_``))
\%\textgreater\% pull(join\_key)

cfu\_keys \textless- cfu \%\textgreater\% mutate(join\_key =
paste(cohort, treatment\_group, mouse\_id, day, sep = ``\_``))
\%\textgreater\% pull(join\_key)

\section{Calculate overlap
statistics}\label{calculate-overlap-statistics}

total\_closure \textless- length(unique(closure\_keys)) total\_cfu
\textless- length(unique(cfu\_keys)) overlap \textless-
length(intersect(unique(closure\_keys), unique(cfu\_keys)))
closure\_only \textless- length(setdiff(unique(closure\_keys),
unique(cfu\_keys))) cfu\_only \textless-
length(setdiff(unique(cfu\_keys), unique(closure\_keys)))

cat(``\n===========================================================\n'')
cat(``MERGE DIAGNOSTICS SUMMARY\n'')
cat(``===========================================================\n'')
cat(sprintf(``Total Closure observations: \%5d\n'', total\_closure))
cat(sprintf(``Total CFU observations: \%5d\n'', total\_cfu))
cat(sprintf(``Perfect overlap (both): \%5d (\%.1f\%\%)\n'', overlap, 100
* overlap / max(total\_closure, total\_cfu))) cat(sprintf(``Closure only
(no CFU): \%5d\n'', closure\_only)) cat(sprintf(``CFU only (no Closure):
\%5d\n'', cfu\_only))
cat(``===========================================================\n\n'')

log\_info(sprintf(``Data overlap: \%d/\%d observations (\%.1f\%\%)'',
overlap, max(total\_closure, total\_cfu), 100 * overlap /
max(total\_closure, total\_cfu)))

\section{Overall Venn diagram}\label{overall-venn-diagram}

p1 \textless- ggvenn( list( ``Wound Closure\nData'' =
unique(closure\_keys), ``Bacterial CFU\nData'' = unique(cfu\_keys) ),
fill\_color = c(``\#0073C2FF'', ``\#EFC000FF''), stroke\_size = 1,
set\_name\_size = 5, text\_size = 4 ) + labs(title = ``A. Overall Data
Coverage'', subtitle = sprintf(``Overlap: \%d observations
(\%.1f\%\%)'', overlap, 100 * overlap / max(total\_closure,
total\_cfu)))

\section{-----------------------------------------------------------------------------}\label{section-2}

\section{2. Coverage by Treatment
Group}\label{coverage-by-treatment-group}

\section{-----------------------------------------------------------------------------}\label{section-3}

treatment\_coverage \textless- merged \%\textgreater\%
group\_by(treatment\_group) \%\textgreater\% summarise( n\_mice =
n\_distinct(mouse\_id), n\_obs = n(), closure\_complete =
sum(!is.na(wound\_area\_filled)), cfu\_complete =
sum(!is.na(cfu\_filled)), both\_complete =
sum(!is.na(wound\_area\_filled) \& !is.na(cfu\_filled)), .groups =
``drop'' ) \%\textgreater\% mutate( closure\_pct = 100 *
closure\_complete / n\_obs, cfu\_pct = 100 * cfu\_complete / n\_obs,
both\_pct = 100 * both\_complete / n\_obs )

p2 \textless- ggplot(treatment\_coverage, aes(x = treatment\_group)) +
geom\_col(aes(y = both\_pct), fill = ``\#2ECC71'', alpha = 0.8, width =
0.7) + geom\_col(aes(y = closure\_pct), fill = ``\#0073C2FF'', alpha =
0.5, width = 0.5) + geom\_col(aes(y = cfu\_pct), fill = ``\#EFC000FF'',
alpha = 0.5, width = 0.3) + geom\_text(aes(y = both\_pct + 5, label =
sprintf(``\%.0f\%\%'', both\_pct)), size = 3.5, fontface = ``bold'') +
scale\_y\_continuous(limits = c(0, 105), expand = c(0, 0)) + labs( title
= ``B. Data Completeness by Treatment Group'', subtitle = ``Green = Both
measurements \textbar{} Blue = Closure \textbar{} Yellow = CFU'', x =
``Treatment Group'', y = ``\% Complete'' ) + theme\_minimal(base\_size =
11) + theme( panel.grid.major.x = element\_blank(), plot.title =
element\_text(face = ``bold'', size = 12) )

\section{-----------------------------------------------------------------------------}\label{section-4}

\section{3. Coverage by Cohort}\label{coverage-by-cohort}

\section{-----------------------------------------------------------------------------}\label{section-5}

cohort\_coverage \textless- merged \%\textgreater\% group\_by(cohort,
treatment\_group) \%\textgreater\% summarise( n\_mice =
n\_distinct(mouse\_id), both\_complete = sum(!is.na(wound\_area\_filled)
\& !is.na(cfu\_filled)), n\_obs = n(), .groups = ``drop'' )
\%\textgreater\% mutate(complete\_pct = 100 * both\_complete / n\_obs)

p3 \textless- ggplot(cohort\_coverage, aes(x = cohort, y =
complete\_pct, fill = treatment\_group)) + geom\_col(position =
``dodge'', width = 0.7) + geom\_text(aes(label =
sprintf(``n=\%d\n\%.0f\%\%'', n\_mice, complete\_pct)), position =
position\_dodge(width = 0.7), vjust = -0.3, size = 3) +
scale\_y\_continuous(limits = c(0, 110), expand = c(0, 0)) +
scale\_fill\_brewer(palette = ``Set2'') + labs( title = ``C. Data
Completeness by Cohort \& Treatment'', subtitle = ``Showing mice per
group and \% with both measurements'', x = ``Cohort'', y = ``\% Complete
(Both Measurements)'', fill = ``Treatment'' ) +
theme\_minimal(base\_size = 11) + theme( legend.position = ``bottom'',
panel.grid.major.x = element\_blank(), plot.title = element\_text(face =
``bold'', size = 12) )

\section{-----------------------------------------------------------------------------}\label{section-6}

\section{4. Temporal Coverage (by Day)}\label{temporal-coverage-by-day}

\section{-----------------------------------------------------------------------------}\label{section-7}

temporal\_coverage \textless- merged \%\textgreater\% group\_by(day)
\%\textgreater\% summarise( n\_observations = n(), closure\_available =
sum(!is.na(wound\_area\_filled)), cfu\_available =
sum(!is.na(cfu\_filled)), both\_available =
sum(!is.na(wound\_area\_filled) \& !is.na(cfu\_filled)), .groups =
``drop'' ) \%\textgreater\% pivot\_longer(cols = c(closure\_available,
cfu\_available, both\_available), names\_to = ``measurement\_type'',
values\_to = ``count'') \%\textgreater\% mutate( measurement\_type =
factor( measurement\_type, levels = c(``both\_available'',
``closure\_available'', ``cfu\_available''), labels = c(``Both
Complete'', ``Closure Data'', ``CFU Data'') ) )

p4 \textless- ggplot(temporal\_coverage, aes(x = day, y = count, color =
measurement\_type)) + geom\_line(linewidth = 1.2) + geom\_point(size =
2.5) + scale\_color\_manual(values = c(``Both Complete'' = ``\#2ECC71'',
``Closure Data'' = ``\#0073C2FF'', ``CFU Data'' = ``\#EFC000FF'')) +
labs( title = ``D. Temporal Coverage Across Study Period'', subtitle =
``Number of observations available at each time point'', x = ``Study
Day'', y = ``Number of Observations'', color = ``Data Type'' ) +
theme\_minimal(base\_size = 11) + theme( legend.position = ``bottom'',
plot.title = element\_text(face = ``bold'', size = 12) )

\section{-----------------------------------------------------------------------------}\label{section-8}

\section{Combine all plots}\label{combine-all-plots}

\section{-----------------------------------------------------------------------------}\label{section-9}

grid.arrange( p1, p2, p3, p4, ncol = 2, nrow = 2, top =
textGrob(``Comprehensive Data Coverage Analysis'', gp = gpar(fontsize =
16, fontface = ``bold'')) )

cat(``{[}checkmark{]} Comprehensive merge diagnostics complete\n'')
log\_info(``Generated 4-panel merge diagnostic visualization'')

\begin{verbatim}

------------------------------------------------------------------------


::: {.cell}

```{.r .cell-code}
# STEP 03B : Data Completeness Heatmap (Mouse x Day)
# Purpose: Assess missingness pattern using binary encoding.
# Reference: Follows standard exploratory completeness checks (Tidy Data principles).

log_info("Generating data completeness heatmap")

merged <- read_csv(file.path(paths$outputs, "merged_data.csv"), show_col_types = FALSE)

heatmap_data <- merged %>%
  mutate(wound_present = !is.na(wound_area_filled),
         cfu_present   = !is.na(cfu_filled)) %>%
  pivot_longer(cols = c(wound_present, cfu_present), names_to = "variable", values_to = "present") %>%
  mutate(variable = recode(variable, wound_present = "Wound Area", cfu_present = "CFU"),
         present = ifelse(present, "Present", "Missing"))

ggplot(heatmap_data, aes(x = day, y = mouse_id, fill = present)) +
  geom_tile(color = "grey60") +
  facet_grid(variable ~ cohort + treatment_group, scales = "free_y", space = "free_y") +
  scale_fill_manual(values = c("Present" = "#1B9E77", "Missing" = "#D95F02")) +
  theme_minimal(base_size = 13) +
  labs(title = "Data Completeness by Mouse and Day", 
       subtitle = "Green = data present, Orange = missing",
       x = "Study Day", 
       y = "Mouse ID", 
       fill = "Status") +
  theme(
    axis.text.x = element_text(angle = 45, hjust = 1, size = 11),
    axis.text.y = element_text(size = 9),
    panel.grid = element_blank(),
    strip.text = element_text(size = 11, face = "bold"),
    plot.title = element_text(size = 16, face = "bold"),
    plot.subtitle = element_text(size = 13),
    legend.position = "bottom",
    legend.text = element_text(size = 12),
    legend.title = element_text(size = 13, face = "bold")
  )
\end{verbatim}

\pandocbounded{\includegraphics[keepaspectratio]{Step_01_Load_and_Inspect_Mouse_Data_files/figure-pdf/completeness_heatmap-1.pdf}}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Completeness heatmap generated"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

:::

\begin{center}\rule{0.5\linewidth}{0.5pt}\end{center}

\begin{Shaded}
\begin{Highlighting}[]
\CommentTok{\# Step 01 Summary}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"="} \SpecialCharTok{\%\textgreater{}\%} \FunctionTok{rep}\NormalTok{(}\DecValTok{70}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{paste}\NormalTok{(}\AttributeTok{collapse =} \StringTok{""}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"STEP 01 COMPLETE"}\NormalTok{)}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"="} \SpecialCharTok{\%\textgreater{}\%} \FunctionTok{rep}\NormalTok{(}\DecValTok{70}\NormalTok{) }\SpecialCharTok{\%\textgreater{}\%} \FunctionTok{paste}\NormalTok{(}\AttributeTok{collapse =} \StringTok{""}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Closure data: \{nrow(closure)\} observations"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"CFU data: \{nrow(cfu)\} observations"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\FunctionTok{glue}\NormalTok{(}\StringTok{"Merged data: \{nrow(merged)\} observations"}\NormalTok{))}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Outputs saved to outputs/ directory"}\NormalTok{)}
\FunctionTok{log\_info}\NormalTok{(}\StringTok{"Ready for Step 02: Verify and Prepare Datasets"}\NormalTok{)}

\FunctionTok{cat}\NormalTok{(}\StringTok{"}\SpecialCharTok{\textbackslash{}n}\StringTok{[DONE] STEP 01 COMPLETE {-} All data loaded, validated, and exported}\SpecialCharTok{\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}

[DONE] STEP 01 COMPLETE - All data loaded, validated, and exported
\end{verbatim}

\begin{Shaded}
\begin{Highlighting}[]
\FunctionTok{cat}\NormalTok{(}\StringTok{"   Next: Run Step\_02\_Verify\_and\_Prepare\_Closure\_Clearance\_Datasets.qmd}\SpecialCharTok{\textbackslash{}n\textbackslash{}n}\StringTok{"}\NormalTok{)}
\end{Highlighting}
\end{Shaded}

\begin{verbatim}
   Next: Run Step_02_Verify_and_Prepare_Closure_Clearance_Datasets.qmd
\end{verbatim}

The two exported datasets from Step 01 act as the formal entry point
into Step 02. At this stage, the focus shifts from general inspection to
quantitative verification. Each file --- \texttt{closure\_data.csv} and
\texttt{clearance\_data.csv} --- is treated as a domain-specific record
of biological behaviour that must be validated before modelling. In
practice, Step 02 checks internal consistency between identifiers,
confirms that time sequences are monotonic, and examines the
completeness of both closure and clearance trajectories. The process
also generates early visual profiles to assess whether the raw
experimental data display plausible dynamics. This bridge between
exploratory inspection and structured verification ensures that only
coherent, reproducible inputs move forward into Weibull fitting,
parameter extraction, and subsequent cross-species scaling.

\emph{References:}

\begin{itemize}
\tightlist
\item
  Wickham, H. et al.~(2019). \emph{Welcome to the tidyverse.} Journal of
  Open Source Software, 4(43), 1686.\\
\item
  Wei, X. et al.~(2017). \emph{Allometric scaling of skin thickness,
  elasticity, viscoelasticity to mass for micro-medical device
  translation.} \emph{Journal of the Mechanical Behavior of Biomedical
  Materials, 68}, 303-310.\\
\item
  Cukjati, D., et al.~(2001). \emph{A reliable method of determining
  wound healing rate.} \emph{Medical and Biological Engineering and
  Computing, 39}(2), 263-271.
\end{itemize}




\end{document}