Finished most figures.

lectures/data_sharing/data_sharing.tex

@@ -25,11 +25,17 @@
 
 \subsection{Types of variants}
 \begin{pframe}
-  % Data sharing at the LUMC:
-  % - Variant interpretations.
-  % - Variant frequencies.
+  Society for Clinical Genetic Laboratory Diagnostics (VKGL).
+  \bigskip
+
+  Two types of variants:
+  \begin{itemize}
+    \item Bulk data (frequencies, VCF files).
+    \item Interpretations (typically a few per analysis).
+  \end{itemize}
 \end{pframe}
 
+\section{Bulk data}
 \subsection{Requirements}
 \begin{pframe}
   We aim for a solution that has the following properties:
@@ -44,24 +50,13 @@
   Labels allow for queries like:
   \begin{itemize}
     \item How many times have we seen this variant in non-diabetes patients?
-    \item How many times was this variant observed in Nijmegen?
+    \item How many times was this variant observed in institute X?
   \end{itemize}
   \bigskip
 
   Timestamps are essential for \emph{reproducibility}.
 \end{pframe}
 
-\begin{pframe}
-  \begin{figure}[]
-    \vspace{-0.5cm}
-    \begin{center}
-      \includegraphics[height=0.8\textheight]{gq}
-    \end{center}
-    \vspace{-0.3cm}
-    \caption{Callable region ($584$--$1596$).}
-  \end{figure}
-\end{pframe}
-
 \begin{pframe}
   \begin{figure}[]
     \vspace{-0.5cm}
@@ -79,58 +74,15 @@
 
 \begin{pframe}
   \begin{figure}[]
+    \vspace{-0.5cm}
     \begin{center}
-      \Large\texttt{TTGAATCCT \color{red}TGCTC \color{black}TGCGATGGA}
-    \end{center}
-    \caption{\bt{NM\_003002.2:c.262\_266del}.}
-  \end{figure}
-
-  \begin{figure}[]
-    \begin{center}
-      \Large\texttt{TTGAATCCT \color{red}TGCTC \color{black}TGCGATGGA}\\
-      \Large\texttt{TTGAATCCTT \color{red}GCTCT \color{black}GCGATGGA}\\
-      \Large\texttt{TTGAATCCTTG \color{red}CTCTG \color{black}CGATGGA}\\
-      \Large\texttt{TTGAATCCTTGC \color{red}TCTGC \color{black}GATGGA}
-    \end{center}
-    %\caption{\bt{NM\_003002.2:c.262\_266del}.}
-  \end{figure}
-
-  \begin{figure}[]
-    \begin{center}
-      \Large\texttt{TTGAATCCTTGC \color{red}TCTGC \color{black}GATGGA}
-    \end{center}
-    \caption{\bt{NM\_003002.2:c.265\_269del}.}
-  \end{figure}
-\end{pframe}
-
-\begin{pframe}
-  \begin{figure}[]
-    \begin{center}
-      Genome\\
-      {\Large\texttt{AACTTAGGA \color{red}ACGAG \color{black}ACGCTACCT}}\\
-      {\Large\texttt{TTGAATCCTTGC \color{red}TCTGC \color{black}GATGGA}}\\
-      Transcript
+      \includegraphics[height=0.8\textheight]{gq}
     \end{center}
-    \caption{}
+    \vspace{-0.3cm}
+    \caption{Callable region ($584$--$1596$).}
   \end{figure}
 \end{pframe}
 
-\subsection{Options}
-\begin{pframe}
-  Choices for the database layout:
-  \begin{itemize}
-    \item \emph{Sample} oriented.
-    \item \emph{Variant} oriented.
-  \end{itemize}
-  \bigskip
-
-  Choices for the infrastructure:
-  \begin{itemize}
-    \item Centralised.
-    \item Decentralised.
-  \end{itemize}
-\end{pframe}
-
 \subsection{Basic client set up}
 \begin{pframe}
   \begin{minipage}[t]{0.47\textwidth}
@@ -146,28 +98,49 @@
     From a \emph{gVCF}:
     \begin{itemize}
       \item Variants.
-      \item Regions with sufficient ``coverage''.
-      \begin{itemize}
-        \item We use \emph{genotype quality}.
-      \end{itemize}
+      \item Regions with sufficient \emph{genotype quality}.
     \end{itemize}
     \bigskip
 
     Metadata:
     \begin{itemize}
       \item Labels.
+      \item Time stamp.
     \end{itemize}
   \end{minipage}
 \end{pframe}
 
-%\subsection{Concerns}
-%\begin{pframe}
-%  Sample identification:
-%  \begin{itemize}
-%    \item The Netherlands: $17 \times 10^6$ inhabitants, $24$ SNPs.
-%    \item Global: $108 \times 10^9$ inhabitants, $37$ SNPs.
-%  \end{itemize}
-%\end{pframe}
+\subsection{Options}
+\begin{pframe}
+  Choices for the database layout:
+  \begin{itemize}
+    \item \emph{Sample} oriented.
+    \item \emph{Variant} oriented.
+  \end{itemize}
+  \bigskip
+
+  Choices for the infrastructure:
+  \begin{itemize}
+    \item Centralised.
+    \item Decentralised.
+  \end{itemize}
+\end{pframe}
+
+\subsection{Technical issues}
+\begin{pframe}
+  \begin{figure}[]
+    {\Large\texttt{
+      \begin{tabular}{llll}
+        \#CHROM & POS    & REF      & ALT\\
+        \onslide<1->{1       & 884551 & GAGA\color{red}AAGA & GAGA}\\
+        \onslide<2->{1       & 884552 & AGA\color{red}AAGA  & AGA}\\
+        \onslide<3->{1       & 884553 & GA\color{red}AAGA   & GA}\\
+        \onslide<4->{1       & 884554 & A\color{red}AAGA    & A}
+      \end{tabular}
+    }}
+    \caption{Deletion of \bt{AAGA}.}
+  \end{figure}
+\end{pframe}
 
 \section{Sample oriented server}
 \subsection{Database layout}
@@ -381,6 +354,69 @@
   \end{itemize}
 \end{pframe}
 
+\section{Interpreted data}
+\begin{pframe}
+  \begin{figure}[]
+    \begin{center}
+      {\Large\texttt{
+        \only<1>{TTGAATCCT \color{red}TGCTC \color{black}TGCGATGGA\\}%
+        \only<2>{TTGAATCCTT \color{red}GCTCT \color{black}GCGATGGA\\}%
+        \only<3>{TTGAATCCTTG \color{red}CTCTG \color{black}CGATGGA\\}%
+        \only<4->{TTGAATCCTTGC \color{red}TCTGC \color{black}GATGGA\\}%
+        \vspace{1cm}
+        \begin{tabular}{l}
+          \onslide<1->{NM\_003002.2:c.262\_266del}\\
+          \onslide<2->{NM\_003002.2:c.263\_267del}\\
+          \onslide<3->{NM\_003002.2:c.264\_268del}\\
+          \onslide<4->{NM\_003002.2:c.265\_269del}
+        \end{tabular}
+      }}
+    \end{center}
+    \caption{Deletion of \bt{TCTGC}.}
+  \end{figure}
+\end{pframe}
+
+\begin{pframe}
+  \begin{figure}[]
+    \begin{center}
+      Genome\\
+      {\Large\texttt{%
+        3' AACTTAGGA \color{red}ACGAG \color{black}ACGCTACCT 5'\\
+        5' TTGAATCCTTGC \color{red}TCTGC \color{black}GATGGA 3'\\
+      }}
+      Transcript
+    \end{center}
+    \caption{3' rule.}
+  \end{figure}
+\end{pframe}
+
+\begin{pframe}
+  \begin{figure}[]
+    {\Large\texttt{%
+      \only<1>{%
+      ATGGCTCC \color{red}TG- \color{black}CCATGGAA\\
+      ATGGCTCC \color{red}TGC \color{black}CCATGGAA\\
+      }%
+      \only<2>{%
+      ATGGCTCCTG \color{red}- \color{black}CCATGGAA\\
+      ATGGCTCCTG \color{red}C \color{black}CCATGGAA\\
+      }%
+      \only<3->{%
+      ATGGCTCCTGCC \color{red}- \color{black}ATGGAA\\
+      ATGGCTCCTGCC \color{red}C \color{black}ATGGAA\\
+      }%
+      \vspace{1cm}
+      \begin{tabular}{l}
+        \onslide<1->{NM\_002001.2:c.9\_10delinsTGC}\\
+        \onslide<2->{NM\_002001.2:c.10\_11insC}\\
+        \onslide<3->{NM\_002001.2:c.12\_13insC}\\
+        \onslide<4->{NM\_002001.2:c.12dup}
+      \end{tabular}
+    }}
+    \caption{}
+  \end{figure}
+\end{pframe}
+
 % Issues with sharing interpretations:
 % - ...