\documentclass{beamer}
\usepackage{booktabs}

\title{Duplicate Genes \& Tandemly Arrayed Genes in \textit{Glycine max} (soy)}
\subtitle{First results}
\author{Naïa Périnelle \and Samuel Ortion}
\institute{Université d'Évry Paris-Saclay}
\date{2024-11-15}

\begin{document}

\frame{\titlepage}

\begin{frame}{Cultivated soy plant: \textit{Glycine max}}
A species of legume native to East Asia.
{
\centering
\includegraphics{media/Glycine_max_plant1_Carol_Rose_(10220578213).jpg}
\vspace{1em}
% \includegraphics[width=0.5\textwidth]{media/Simplified-schematic-tree-of-legume-family-modified-from-Doyle-and-Luckow-2003-The.png}\footnote{Gepts et al. 2005}
\includegraphics[width=0.25\textwidth]{media/Soybeanvarieties.jpeg}
}


\end{frame}

\begin{frame}{Soybean industrial interest}
\begin{itemize}
    \item 353 million tonnes of soybean produced in 2020 
    \item Cattle feed 
    \item Human food
\end{itemize}

\end{frame}

\begin{frame}{\textit{Glycine max} genome statistics}
    \begin{itemize}
        \item 20 chromosomes
        \item 55897 protein coding genes (including supercontigs)
        \item 55589 protein coding genes (excluding supercontigs)
        \item 88412 protein isoforms
    \end{itemize}
\end{frame}

\begin{frame}{Datasets filter criteria and pipeline steps}
    \begin{tabular}{ccc}
    \toprule
    dataset stringency & low & high \\
    \midrule
    coverage & > 30\% & > 40\% \\
    identity & > 30\% & > 50\% \\
    \bottomrule
    \end{tabular}
    \only<2->{
    
    Steps:
    \begin{enumerate}
        \item<2-> Keep the longest isoform protein sequence per gene,
        \item<3-> Run BLASTp ``all against all'' on the proteome,
        \item<4-> Remove proteins of supercontigs,
        \item<5-> Filter the HSP\footnote{High-scoring Segment Pair} based on the dataset criteria  (coverage and identity percentages),
        \item<6-> Run Markov Clustering (\texttt{mcl} with default parameters) on the homology graph built with the highest \texttt{bitscore} values per homologous genes pairs,
        \item<7-> Detect \texttt{Tandemly Arrayed Genes} with a Rust program based on gene positions and gene families.
    \end{enumerate}
    }
\end{frame}

\begin{frame}{Gene families size}
    \includegraphics[width=0.47\textwidth]{media/Glycine_max_family_size_hist_coverage30_identity30.pdf}
    \includegraphics[width=0.47\textwidth]{media/Glycine_max_family_size_hist_coverage40_identity50.pdf}
\end{frame}

\begin{frame}{Duplicate genes statistics}
    \begin{tabular}{lcc}
        dataset stringency & low & high \\
        \toprule
        number of duplicate genes & 50254 (89.9\%) & 46769 (83.7\%) \\ 
        number of families & 8426 & 11997 \\
        number of singletons & 5643 (10.1\%) & 9128 (16.3\%) \\
        number of TAG\textsubscript{0} & 3208 & 2500 \\
        number of TAG\textsubscript{1} & 3481 & 2652 \\
        \bottomrule
    \end{tabular}
\end{frame}

\end{document}