Merge branch 'leiden_2014' of git.lumc.nl:humgen/ngs-intro-course into leiden_2014

quality_control/quality_control.tex

+\documentclass[slidestop]{beamer}
+\title{Quality control}
+\providecommand{\myConference}{NGS introduction}
+\providecommand{\myDate}{Thursday, 22 May 2014}
+\author{Michiel van Galen}
+\providecommand{\myGroup}{Leiden Genome Technology Center}
+\providecommand{\myDepartment}{Department of Human Genetics}
+\providecommand{\myCenter}{Center for Human and Clinical Genetics}
+\providecommand{\lastCenterLogo}{
+  \raisebox{-0.1cm}{
+    %\includegraphics[height=1cm]{lgtc_logo}
+    %\includegraphics[height=0.7cm]{ngi_logo}
+  }
+}
+\providecommand{\lastRightLogo}{
+  %\includegraphics[height=0.7cm]{nbic_logo}
+  %\includegraphics[height=0.8cm]{nwo_logo_en}
+  %\hspace{1.5cm}\includegraphics[height=0.7cm]{gen2phen_logo}
+}
+
+\usetheme{lumc}
+
+\begin{document}
+
+% This disables the \pause command, handy in the editing phase.
+%\renewcommand{\pause}{}
+
+% Make the title page.
+\bodytemplate
+
+\section{Introduction}
+\subsection{Overview}
+\begin{pframe}
+  \begin{itemize}
+    \item Data and the flaws
+    \item Quality control basics
+    \item Tools and advanced methods
+  \end{itemize}
+\end{pframe}
+
+\subsection{The data}
+\begin{pframe}
+  \begin{itemize}
+    \item FastQ: Expanded two line Fasta format
+    \item Four lines per entry
+    \item Sequence and per base phred quality combined 
+    \item Beware of different score offsets
+  \end{itemize}
+  \begin{lstlisting}[caption={FastQ format}]
+    @SEQ_ID
+    GATTTGGGGTTCAAAGCAGTA
+    +
+    !''*((((***+))%%%++)(
+  \end{lstlisting}
+\end{pframe}
+
+\subsection{The flaws}
+\begin{pframe}
+  At any point from the start of the experiment until beginning analyses,
+  quality can be jeopardized.
+  \bigskip
+
+  \begin{itemize}
+    \item Gathering material and sample prep
+      \begin{itemize}
+        \item Contamination, degradation, sample swap
+      \end{itemize}
+    \item Sequencing
+      \begin{itemize}
+        \item Exhausted chemicals, technical issues
+      \end{itemize}
+    \item Data integrity
+      \begin{itemize}
+        \item File corruption 
+      \end{itemize}
+    \item Many other unexpected external factors
+  \end{itemize}
+\end{pframe}
+
+\subsection{The consequence}
+\begin{pframe}
+  \bigskip
+
+  Low quality greatly influences the downstream analyses. 
+  \bigskip
+
+  \begin{figure}
+    \caption{Garbage in garbage out}
+    \centering
+    \includegraphics[width=0.5\textwidth]{garbage}
+  \end{figure}
+\end{pframe}
+
+\section{Quality control basics}
+\subsection{Quality assessment}
+\begin{pframe}
+  \begin{itemize} 
+    \item FastQC: A quality control tool for high throughput sequence data.
+    \item Assess the quality of your data in a fastq file
+  \end{itemize}
+  \begin{figure}
+    \caption{FastQC}
+    \centering
+    \includegraphics[width=0.5\textwidth]{pretrimmed_qscores}
+  \end{figure}
+\end{pframe}
+
+\subsection{Data properties}
+\begin{pframe}
+  Properties which can indicate possible biases in your data:
+  \begin{itemize}
+    \item Quality scores - Higher is better
+    \item GC content - Expected vs observed
+    \item Duplication rate - Lower is usually better
+    \item N content - Less is more
+    \item Adapter contaminants - More adapter, less sample
+    \item kMer statistics - Expected vs observed
+  \end{itemize}
+\end{pframe}
+
+\subsection{Improving your data}
+\begin{pframe}
+  After identification of some issues, correction may be possible
+  \bigskip
+
+  \begin{itemize}
+    \item Low quality bases can be discarded
+    \item Adapter sequences can be removed 
+    \item Downstream analyses can be tailored to identified problems
+  \end{itemize}
+\end{pframe}
+
+\subsection{Quality trimming}
+\begin{pframe}
+  \begin{itemize}
+    \item Getting rid of low quality bases
+    \item Only want to maintain the high-quality bases 
+  \end{itemize}
+  \begin{lstlisting}[language=none, caption={}]
+    @Header
+    ACGTACGTACGT
+    +
+    !#II!JJJI##!
+
+    Will result in:
+    --GTACGTA---
+  \end{lstlisting}
+\end{pframe}
+
+\subsection{Clipping adapters}
+\begin{pframe}
+  \begin{itemize}
+    \item FastQC can identify adapter contaminants which can hamper later analyses
+    \item Specific tools can remove these specific sequences
+  \end{itemize}
+  \begin{figure}
+    \caption{Adapter Sequencing}
+    \centering
+    \includegraphics[width=0.8\textwidth]{adapter_sequencing}
+  \end{figure}
+\end{pframe}
+
+\subsection{Digital data quality}
+\begin{pframe}
+  Also digital date can be of low quality
+  \bigskip
+
+  \begin{itemize}
+    \item Hardware failure
+    \begin{itemize}
+      \item Data corruption, insufficient disk space
+    \end{itemize}
+    \item Human failure
+    \begin{itemize}
+      \item Sample swaps, unclear file names, incomplete copies
+    \end{itemize}
+  \end{itemize}
+\end{pframe}
+
+\section{Tools and advanced methods}
+\subsection{kMer analysis}
+\begin{pframe}
+  \begin{itemize}
+    \item Analyzing the frequencies of words of length K
+    \item Proven to detect all sorts of factors which influence the data
+    \begin{itemize}
+      \item Contamination, quality, duplication
+    \end{itemize}
+    \item Also used to determine sample complexity
+  \end{itemize}
+\end{pframe} 
+
+\subsection{Overview of tools}
+\begin{pframe}
+  \begin{itemize}
+    \item{Quality assessment}
+    \begin{itemize}
+      \item FastQC, kMer, QCDB
+    \end{itemize}
+    \item{Trimming}
+    \begin{itemize}
+      \item Sickle: A windowed adaptive trimming tool
+    \end{itemize}
+    \item{Adapter clipping}
+    \begin{itemize}
+      \item Cutadapt
+    \end{itemize}
+    \item{File integrity}
+    \begin{itemize}
+      \item Md5checksums, GRP
+    \end{itemize}
+  \end{itemize}
+\end{pframe}  
+
+\subsection{QC process}
+\begin{pframe}
+  Good QC practice can be performed following the next steps:
+  \begin{itemize}
+    \item Assess the quality of raw data
+    \item Identify possible factors that impact the data
+    \item Apply the tools to improve the data 
+    \item Assess the quality again and evaluate the results
+  \end{itemize}
+  \bigskip
+
+  Preferably this can be done in a precompiled pipeline
+\end{pframe}
+
+\section{Questions?}
+\lastpagetemplate
+\begin{pframe}
+  \begin{center}
+    Acknowledgements:
+    \bigskip
+    \bigskip
+
+    Jeroen Laros
+    \bigskip
+
+    Martijn Vermaat
+    \bigskip
+
+    Jeroen Frank
+    \bigskip
+
+    LGTC    
+
+  \end{center}
+\end{pframe}
+
+\end{document}

quality_control/quality_control.tex.bak

+\documentclass[slidestop]{beamer}
+\title{Quality control}
+\providecommand{\myConference}{Work discussion}
+\providecommand{\myDate}{Thursday, 22 May 2014}
+\author{Michiel van Galen}
+\providecommand{\myGroup}{Leiden Genome Technology Center}
+\providecommand{\myDepartment}{Department of Human Genetics}
+\providecommand{\myCenter}{Center for Human and Clinical Genetics}
+\providecommand{\lastCenterLogo}{
+  \raisebox{-0.1cm}{
+    %\includegraphics[height=1cm]{lgtc_logo}
+    %\includegraphics[height=0.7cm]{ngi_logo}
+  }
+}
+\providecommand{\lastRightLogo}{
+  %\includegraphics[height=0.7cm]{nbic_logo}
+  %\includegraphics[height=0.8cm]{nwo_logo_en}
+  %\hspace{1.5cm}\includegraphics[height=0.7cm]{gen2phen_logo}
+}
+
+\usetheme{lumc}
+
+\begin{document}
+
+% This disables the \pause command, handy in the editing phase.
+%\renewcommand{\pause}{}
+
+% Make the title page.
+\bodytemplate
+
+\section{Introduction}
+\subsection{Overview}
+\begin{pframe}
+  \begin{itemize}
+    \item Data and the flaws
+    \item Quality control basics
+    \item Tools and advanced methods
+  \end{itemize}
+\end{pframe}
+
+\subsection{The data}
+\begin{pframe}
+  \begin{itemize}
+    \item FastQ: Expanded two line Fasta format
+    \item Four lines per entry
+    \item Sequence and per base phred quality combined 
+    \item Beware of different score offsets
+  \end{itemize}
+  \begin{lstlisting}[caption={FastQ format}]
+    @SEQ_ID
+    GATTTGGGGTTCAAAGCAGTA
+    +
+    !''*((((***+))%%%++)(
+  \end{lstlisting}
+\end{pframe}
+
+\subsection{The flaws}
+\begin{pframe}
+  At any point from the start of the experiment until beginning analyses,
+  quality can be jeopardized.
+  \bigskip
+
+  \begin{itemize}
+    \item Gathering material and sample prep
+      \begin{itemize}
+        \item Contamination, degradation, sample swap
+      \end{itemize}
+    \item Sequencing
+      \begin{itemize}
+        \item Exhausted chemicals, technical issues
+      \end{itemize}
+    \item Data integrity
+      \begin{itemize}
+        \item File corruption 
+      \end{itemize}
+    \item Many other unexpected external factors
+  \end{itemize}
+\end{pframe}
+
+\subsection{The consequence}
+\begin{pframe}
+  \bigskip
+
+  Low quality greatly influences the downstream analyses. 
+  \bigskip
+
+  \begin{figure}
+    \caption{Garbage in garbage out}
+    \centering
+    \includegraphics[width=0.5\textwidth]{garbage}
+  \end{figure}
+\end{pframe}
+
+\section{Quality control basics}
+\subsection{Quality assessment}
+\begin{pframe}
+  \begin{itemize} 
+    \item FastQC: A quality control tool for high throughput sequence data.
+    \item Assess the quality of your data in a fastq file
+  \end{itemize}
+  \begin{figure}
+    \caption{FastQC}
+    \centering
+    \includegraphics[width=0.5\textwidth]{pretrimmed_qscores}
+  \end{figure}
+\end{pframe}
+
+\subsection{Data properties}
+\begin{pframe}
+  Properties which can indicate possible biases in your data:
+  \begin{itemize}
+    \item Quality scores - Higer is better
+    \item GC content - Expected vs observed
+    \item Duplication rate - Lower is usually better
+    \item N content - Less is more
+    \item Adapter contaminants - More adapter, less sample
+    \item kMer statistics - Expected vs observed
+  \end{itemize}
+\end{pframe}
+
+\subsection{Improving your data}
+\begin{pframe}
+  After identification of some issues, correction may be possible
+  \bigskip
+
+  \begin{itemize}
+    \item Low quality bases can be discarded
+    \item Adapter sequences can be removed 
+    \item Downstream analyses can be tailored to identified problems
+  \end{itemize}
+\end{pframe}
+
+\subsection{Quality trimming}
+\begin{pframe}
+  \begin{itemize}
+    \item Getting rid of low quality bases
+    \item Only want to maintain the high-quality bases 
+  \end{itemize}
+  \begin{lstlisting}[language=none, caption={}]
+    @Header
+    ACGTACGTACGT
+    +
+    !#II!JJJI##!
+
+    Will result in:
+    --GTACGTA---
+  \end{lstlisting}
+\end{pframe}
+
+\subsection{Clipping adapters}
+\begin{pframe}
+  \begin{itemize}
+    \item FastQC can identify adapter contaminants which can hamper later analyses
+    \item Specific tools can remove these specific sequences
+  \end{itemize}
+  \begin{figure}
+    \caption{Adapter Sequencing}
+    \centering
+    \includegraphics[width=0.8\textwidth]{adapter_sequencing}
+  \end{figure}
+\end{pframe}
+
+\subsection{Digital data quality}
+\begin{pframe}
+  Also digital date can be of low quality
+  \bigskip
+
+  \begin{itemize}
+    \item Hardware failure
+    \begin{itemize}
+      \item Data corruption, insufficient disk space
+    \end{itemize}
+    \item Human failure
+    \begin{itemize}
+      \item Sample swaps, unclear filenames, incomplete copies
+    \end{itemize}
+  \end{itemize}
+\end{pframe}
+
+\section{Tools and advanced methods}
+\subsection{kMer analysis}
+\begin{pframe}
+  \begin{itemize}
+    \item Analyzing the frequencies of words of length K
+    \item Proven to detect all sorts of factors which influence the data
+    \begin{itemize}
+      \item Contamination, quality, duplication
+    \end{itemize}
+    \item Also used to determine sample complexity
+  \end{itemize}
+\end{pframe} 
+
+\subsection{Overview of tools}
+\begin{pframe}
+  \begin{itemize}
+    \item{Qualty assessment}
+    \begin{itemize}
+      \item FastQC, kMer, QCDB
+    \end{itemize}
+    \item{Trimming}
+    \begin{itemize}
+      \item Sickle: A windowed adaptive trimming tool
+    \end{itemize}
+    \item{Adapter clipping}
+    \begin{itemize}
+      \item Cutadapt
+    \end{itemize}
+    \item{File integrity}
+    \begin{itemize}
+      \item Md5checksums, GRP
+    \end{itemize}
+  \end{itemize}
+\end{pframe}  
+
+\subsection{QC process}
+\begin{pframe}
+  Good QC practice can be performed following the next steps:
+  \begin{itemize}
+    \item Assess the quality of raw data
+    \item Identify possible factors that impact the data
+    \item Apply the tools to improve the data 
+    \item Assess the quality again and evaluate the results
+  \end{itemize}
+  \bigskip
+
+  Preferably this can be done in a precompiled pipeline
+\end{pframe}
+
+\section{Questions?}
+\lastpagetemplate
+\begin{pframe}
+  \begin{center}
+    Acknowledgements:
+    \bigskip
+    \bigskip
+
+    Jeroen Laros
+    \bigskip
+
+    Martijn Vermaat
+    \bigskip
+
+    Jeroen Frank
+    \bigskip
+
+    LGTC    
+
+  \end{center}
+\end{pframe}
+
+\end{document}

quality_control/ul_logo.eps

+../presentation/ul_logo.eps
\ No newline at end of file