diff --git a/introduction_extended/Makefile b/introduction/Makefile
similarity index 100%
rename from introduction_extended/Makefile
rename to introduction/Makefile
diff --git a/introduction_extended/assembly.png b/introduction/assembly.png
similarity index 100%
rename from introduction_extended/assembly.png
rename to introduction/assembly.png
diff --git a/introduction_extended/assemblyline.jpg b/introduction/assemblyline.jpg
similarity index 100%
rename from introduction_extended/assemblyline.jpg
rename to introduction/assemblyline.jpg
diff --git a/introduction_extended/base-pacbio.ppm b/introduction/base-pacbio.ppm
similarity index 100%
rename from introduction_extended/base-pacbio.ppm
rename to introduction/base-pacbio.ppm
diff --git a/introduction_extended/base-torrent.ppm b/introduction/base-torrent.ppm
similarity index 100%
rename from introduction_extended/base-torrent.ppm
rename to introduction/base-torrent.ppm
diff --git a/introduction_extended/beamerthemelumc.sty b/introduction/beamerthemelumc.sty
similarity index 100%
rename from introduction_extended/beamerthemelumc.sty
rename to introduction/beamerthemelumc.sty
diff --git a/introduction_extended/gapss3.dot b/introduction/gapss3.dot
similarity index 100%
rename from introduction_extended/gapss3.dot
rename to introduction/gapss3.dot
diff --git a/introduction_extended/gen2phen_logo.eps b/introduction/gen2phen_logo.eps
similarity index 100%
rename from introduction_extended/gen2phen_logo.eps
rename to introduction/gen2phen_logo.eps
diff --git a/introduction_extended/hgap.png b/introduction/hgap.png
similarity index 100%
rename from introduction_extended/hgap.png
rename to introduction/hgap.png
diff --git a/introduction_extended/hiseq_2000.jpg b/introduction/hiseq_2000.jpg
similarity index 100%
rename from introduction_extended/hiseq_2000.jpg
rename to introduction/hiseq_2000.jpg
diff --git a/introduction_extended/introduction_extended.tex b/introduction/introduction.tex
similarity index 57%
rename from introduction_extended/introduction_extended.tex
rename to introduction/introduction.tex
index e36a8676039770c7da4630600ed2aff107bb632d..a8ef57cce6a02a4015cfab71b1c21ed5f1de15a3 100644
--- a/introduction_extended/introduction_extended.tex
+++ b/introduction/introduction.tex
@@ -1,7 +1,7 @@
\documentclass[slidestop]{beamer}
\title{Introduction to NGS data analysis}
-\providecommand{\myConference}{Workshop NGS, Hogeschool Leiden}
+\providecommand{\myConference}{Introduction NGS Data Analysis}
\providecommand{\myDate}{Thursday, May 22, 2014}
\author{Jeroen F. J. Laros}
\providecommand{\myGroup}{Leiden Genome Technology Center}
@@ -340,93 +340,7 @@
\end{itemize}
\end{pframe}
-\section{Resequencing}
-\subsection{Data analysis}
-\begin{pframe}
- Resequencing pipelines can roughly be divided in five steps.
- \pause
- \begin{enumerate}
- \item Pre-alignment.
- \begin{itemize}
- \item Quality control.
- \item Data cleaning.
- \end{itemize}
- \pause
- \item Alignment.
- \begin{itemize}
- \item Post-alignment quality control.
- \end{itemize}
- \pause
- \item Variant calling.
- \pause
- \item Filtering.
- \begin{itemize}
- \item Post-variant calling quality control.
- \end{itemize}
- \pause
- \item Annotation.
- \end{enumerate}
-\end{pframe}
-
-\section{Pre-alignment}
-\subsection{Data cleaning}
-\begin{pframe}
- Depending on the sequencing platform, parts of the reads need to be removed.
- \begin{itemize}
- \item Remove linker sequences (\emph{Cutadapt}, \emph{FASTX toolkit}).
- \item Clip low quality reads at the end of the read (\emph{Sickle},
- \emph{Trimmomatic}, \emph{FASTX toolkit}).
- \item Length filtering (\emph{Fastools}).
- \end{itemize}
-
- \vfill
- \permfoot{http://code.google.com/p/cutadapt/}
-
- \permfoot{http://hannonlab.cshl.edu/fastx\_toolkit/}
-
- \permfoot{https://github.com/najoshi/sickle}
-
- \permfoot{http://www.usadellab.org/cms/index.php?page=trimmomatic}
-
- \permfoot{https://pypi.python.org/pypi/fastools}
-\end{pframe}
-
-\subsection{Trimming}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.85\textheight]{pretrimmed_qscores}
- \end{center}
- \caption{Quality score per position.}
- \end{figure}
-\end{pframe}
-
-\subsection{Clipping}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.85\textheight]{linker-clip}
- \end{center}
- \caption{Sequencing linkers.}
- \end{figure}
-\end{pframe}
-
\subsection{Quality control}
-\begin{pframe}
- The \emph{FastQC toolkit} can be used for quality control (both before and
- after the data cleaning step).
- \begin{itemize}
- \item GC content.
- \item GC distribution.
- \item Quality scores distribution.
- \item \ldots
- \end{itemize}
-
- \vfill
- \permfoot{http://www.bioinformatics.babraham.ac.uk/projects/fastqc/}
-\end{pframe}
-
-\subsection{Example QC output}
\begin{pframe}
\begin{figure}
\includegraphics[width=\textwidth, height=0.35\textheight]
@@ -464,55 +378,6 @@
\end{minipage}
\end{pframe}
-\subsection{Choose an aligner}
-\begin{pframe}
- Not all aligners can deal with indels.
- \begin{itemize}
- \item Only a couple of years ago, only SNPs were considered.
- \begin{itemize}
- \item \emph{Bowtie}.
- \end{itemize}
- \end{itemize}
- \medskip
- \pause
-
- Few aligners can work with large deletions.
- \begin{itemize}
- \item Spliced RNA.
- \begin{itemize}
- \item \emph{GMAP} / \emph{GSNAP}.
- \item \emph{Tophat}.
- \end{itemize}
- \item \emph{BWA-MEM}.
- \end{itemize}
-
- \vfill
- \permfoot{http://bowtie-bio.sourceforge.net/index.shtml}
-
- \permfoot{http://research-pub.gene.com/gmap/}
-
- \permfoot{http://tophat.cbcb.umd.edu/}
-
- \permfoot{http://bio-bwa.sourceforge.net/}
-\end{pframe}
-
-\begin{pframe}
- The choice of aligner may be restricted by the sequencer.
- \begin{itemize}
- \item For the Ion Torrent: \emph{Tmap}.
- \begin{itemize}
- \item Combination of three different aligners.
- \item Deals with errors in homopolymer stretches.
- \end{itemize}
- \item For the PacBio: \emph{BLASR}.
- \end{itemize}
-
- \vfill
- \permfoot{https://github.com/iontorrent/TS/tree/master/Analysis/TMAP}
-
- \permfoot{https://github.com/PacificBiosciences/blasr}
-\end{pframe}
-
\section{Variant calling}
\subsection{Consistent deviations from the reference}
\begin{pframe}
@@ -524,181 +389,8 @@
\end{figure}
\end{pframe}
-\subsection{Some considerations}
-\begin{pframe}
- Things a variant caller might take into account:
- \begin{itemize}
- \item Strand balance.
- \item Base quality.
- \item Mapping quality.
- \begin{itemize}
- \item Distribution within the reads.
- \end{itemize}
- \item Ploidity of the organism in question.
- \end{itemize}
- \medskip
- \pause
-
- Complicating factors:
- \begin{itemize}
- \item Pooled samples.
- \pause
- \item RNA.
- \begin{itemize}
- \item Allele specific expression.
- \item RNA editing.
- \end{itemize}
- \pause
- \item Strand specific sampleprep.
- \end{itemize}
-\end{pframe}
-
-\subsection{Choice of variant caller}
-\begin{pframe}
- Rules of thumb:
- \begin{itemize}
- \item Well known organism and experiment: Statistical model.
- \item Use a simpler variant caller otherwise.
- \end{itemize}
- \bigskip
- \pause
-
- Popular variant callers:
- \begin{itemize}
- \item \emph{Samtools}.
- \item \emph{GATK}.
- \item \emph{VarScan}.
- \end{itemize}
-
- \vfill
- \permfoot{http://samtools.sourceforge.net/}
-
- \permfoot{https://www.broadinstitute.org/gatk/}
-
- \permfoot{http://varscan.sourceforge.net/}
-\end{pframe}
-
-\section{Variant filtering}
-\subsection{Filtering on coverage}
-\begin{pframe}
- We can set some thresholds:
- \begin{itemize}
- \item Minimum.
- \item Maximum.
- \end{itemize}
- \bigskip
- \pause
-
- We filter for a maximum coverage because of copy number variation.
- \bigskip
- \pause
-
- A good way to calculate the maximum:
- \begin{itemize}
- \item Calculate the mean coverage.
- \begin{itemize}
- \item Only of the covered (targeted) regions.
- \end{itemize}
- \item Multiply this number with a reasonable factor e.g., $2.5$.
- \end{itemize}
-\end{pframe}
-
-\section{Annotation}
-\subsection{What is already known about a variant}
-\begin{pframe}
- A selection of SeattleSeq annotation:
- \begin{itemize}
- \item Is the variant known?
- \item Does it hit a gene?
- \pause
- \begin{itemize}
- \item Is it in an intron?
- \begin{itemize}
- \item Does it hit a splice site?
- \end{itemize}
- \pause
- \item Is it in the coding region?
- \begin{itemize}
- \item Is there a gain/loss of a stop codon?
- \item Does the variant result in a frameshift?
- \item \ldots
- \end{itemize}
- \pause
- \item Is it in the 5'/3' UTR of a gene?
- \item \ldots
- \end{itemize}
- \pause
- \item Is it in a regulatory region?
- \item \ldots
- \end{itemize}
-\end{pframe}
-
-\section{Full genome sequencing}
-\subsection{Copy number variation}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[trim=0 5cm 0 0, clip, height=0.9\textheight, width=\textwidth]{cnv}
- \end{center}
- \caption{Coverage patterns over a whole chromosome.}
- \end{figure}
-\end{pframe}
-
-\begin{pframe}
- Per sample:
- \begin{itemize}
- \item The reference needs to be very good.
- \item Sequencability biases.
- \item Mapping biases.
- \end{itemize}
- \bigskip
- \pause
-
- Within a population:
- \begin{itemize}
- \item Mixture of distributions.
- \item Not sensitive to aforementioned biases.
- \item Needs a lot of controls.
- \end{itemize}
-\end{pframe}
-
-\subsection{Structural variation}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.9\textheight, width=\textwidth]{poorly_mapped}
- \end{center}
- \caption{Multiple issues while mapping.}
- \end{figure}
-\end{pframe}
-
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[trim=0 19cm 0 0, clip, width=\textwidth]{discordant}
- \end{center}
- \caption{Discordant and split reads.}
- \end{figure}
-
- \vfill
- \permfoot{http://breakdancer.sourceforge.net/}
-
- \permfoot{http://sourceforge.net/projects/pindel/}
-\end{pframe}
-
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.9\textheight]{sv}
- \end{center}
- \caption{Different types of structural variation.}
- \end{figure}
-\end{pframe}
-
-
\section{De Novo assembly}
\subsection{Assesmbly}
-
\begin{pframe}
\begin{figure}[]
\begin{center}
@@ -708,35 +400,6 @@
\end{figure}
\end{pframe}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[width=\textwidth]{contig}
- \end{center}
- \caption{Overlaps are used to reconstruct a genome.}
- \end{figure}
-\end{pframe}
-
-\subsection{Scaffolding}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.9\textheight]{scaffold}
- \end{center}
- \caption{Paired end or mate pair reads can be used.}
- \end{figure}
-\end{pframe}
-
-\subsection{Easier assembly with PacBio}
-\begin{pframe}
- \begin{figure}[]
- \begin{center}
- \includegraphics[height=0.9\textheight]{hgap}
- \end{center}
- \caption{Correcting PacBio reads.}
- \end{figure}
-\end{pframe}
-
\section{Pipelines}
\subsection{Pipelines}
\begin{pframe}
@@ -797,42 +460,6 @@
\end{lstlisting}
\end{pframe}
-\section{Graphical interfaces}
-\subsection{Galaxy}
-\begin{pframe}
- Galaxy: a graphical user interface:
- \begin{itemize}
- \item Wrapper for command line utilities.
- \item User friendly.
- \item Point and click.
- \pause
- \item Workflows.
- \begin{itemize}
- \item Save all the steps you did in your analysis.
- \item Rerun the entire analysis on a new dataset.
- \item Share your workflow with other people.
- \item \ldots
- \end{itemize}
- \end{itemize}
-
- \vfill
- \permfoot{http://galaxy.psu.edu/}
-\end{pframe}
-
-\begin{pframe}
- \begin{figure}
- \includegraphics[trim=0 0 0 2cm, clip, width=\textwidth]{galaxy}
- \caption{Galaxy main user interface}
- \end{figure}
-\end{pframe}
-
-\begin{pframe}
- \begin{figure}
- \includegraphics[width=\textwidth, height=0.9\textheight]{galaxy_mpileup}
- \caption{User friendly interface with Galaxy}
- \end{figure}
-\end{pframe}
-
\subsection{Workflow of a parallel pipeline}
\begin{pframe}
\begin{figure}
diff --git a/introduction_extended/ion-proton-chip.jpg b/introduction/ion-proton-chip.jpg
similarity index 100%
rename from introduction_extended/ion-proton-chip.jpg
rename to introduction/ion-proton-chip.jpg
diff --git a/introduction_extended/ion-proton.jpg b/introduction/ion-proton.jpg
similarity index 100%
rename from introduction_extended/ion-proton.jpg
rename to introduction/ion-proton.jpg
diff --git a/introduction_extended/ion-torrent-chip-close.gif b/introduction/ion-torrent-chip-close.gif
similarity index 100%
rename from introduction_extended/ion-torrent-chip-close.gif
rename to introduction/ion-torrent-chip-close.gif
diff --git a/introduction_extended/ion-torrent-chip.jpg b/introduction/ion-torrent-chip.jpg
similarity index 100%
rename from introduction_extended/ion-torrent-chip.jpg
rename to introduction/ion-torrent-chip.jpg
diff --git a/introduction_extended/ion-torrent-wells.jpg b/introduction/ion-torrent-wells.jpg
similarity index 100%
rename from introduction_extended/ion-torrent-wells.jpg
rename to introduction/ion-torrent-wells.jpg
diff --git a/introduction_extended/ion-torrent.jpg b/introduction/ion-torrent.jpg
similarity index 100%
rename from introduction_extended/ion-torrent.jpg
rename to introduction/ion-torrent.jpg
diff --git a/introduction_extended/k_align.png b/introduction/k_align.png
similarity index 100%
rename from introduction_extended/k_align.png
rename to introduction/k_align.png
diff --git a/introduction_extended/k_basecall.png b/introduction/k_basecall.png
similarity index 100%
rename from introduction_extended/k_basecall.png
rename to introduction/k_basecall.png
diff --git a/introduction_extended/k_bridge2.png b/introduction/k_bridge2.png
similarity index 100%
rename from introduction_extended/k_bridge2.png
rename to introduction/k_bridge2.png
diff --git a/introduction_extended/k_flowcell.png b/introduction/k_flowcell.png
similarity index 100%
rename from introduction_extended/k_flowcell.png
rename to introduction/k_flowcell.png
diff --git a/introduction_extended/k_image.jpg b/introduction/k_image.jpg
similarity index 100%
rename from introduction_extended/k_image.jpg
rename to introduction/k_image.jpg
diff --git a/introduction_extended/lgtc_logo.eps b/introduction/lgtc_logo.eps
similarity index 100%
rename from introduction_extended/lgtc_logo.eps
rename to introduction/lgtc_logo.eps
diff --git a/introduction_extended/lumc_logo.eps b/introduction/lumc_logo.eps
similarity index 100%
rename from introduction_extended/lumc_logo.eps
rename to introduction/lumc_logo.eps
diff --git a/introduction_extended/lumc_logo_small.eps b/introduction/lumc_logo_small.eps
similarity index 100%
rename from introduction_extended/lumc_logo_small.eps
rename to introduction/lumc_logo_small.eps
diff --git a/introduction_extended/miseq.jpg b/introduction/miseq.jpg
similarity index 100%
rename from introduction_extended/miseq.jpg
rename to introduction/miseq.jpg
diff --git a/introduction_extended/nbic_logo.eps b/introduction/nbic_logo.eps
similarity index 100%
rename from introduction_extended/nbic_logo.eps
rename to introduction/nbic_logo.eps
diff --git a/introduction_extended/ngi_logo.eps b/introduction/ngi_logo.eps
similarity index 100%
rename from introduction_extended/ngi_logo.eps
rename to introduction/ngi_logo.eps
diff --git a/introduction_extended/nwo_logo_en.eps b/introduction/nwo_logo_en.eps
similarity index 100%
rename from introduction_extended/nwo_logo_en.eps
rename to introduction/nwo_logo_en.eps
diff --git a/introduction_extended/nwo_logo_nl.eps b/introduction/nwo_logo_nl.eps
similarity index 100%
rename from introduction_extended/nwo_logo_nl.eps
rename to introduction/nwo_logo_nl.eps
diff --git a/introduction_extended/pacbio.jpg b/introduction/pacbio.jpg
similarity index 100%
rename from introduction_extended/pacbio.jpg
rename to introduction/pacbio.jpg
diff --git a/introduction_extended/paired_end_2.gif b/introduction/paired_end_2.gif
similarity index 100%
rename from introduction_extended/paired_end_2.gif
rename to introduction/paired_end_2.gif
diff --git a/introduction_extended/per_base_sequence_content.png b/introduction/per_base_sequence_content.png
similarity index 100%
rename from introduction_extended/per_base_sequence_content.png
rename to introduction/per_base_sequence_content.png
diff --git a/introduction_extended/per_sequence_quality.png b/introduction/per_sequence_quality.png
similarity index 100%
rename from introduction_extended/per_sequence_quality.png
rename to introduction/per_sequence_quality.png
diff --git a/introduction_extended/pipeline.jpg b/introduction/pipeline.jpg
similarity index 100%
rename from introduction_extended/pipeline.jpg
rename to introduction/pipeline.jpg
diff --git a/introduction_extended/smrtbell.jpg b/introduction/smrtbell.jpg
similarity index 100%
rename from introduction_extended/smrtbell.jpg
rename to introduction/smrtbell.jpg
diff --git a/introduction_extended/ul_logo.eps b/introduction/ul_logo.eps
similarity index 100%
rename from introduction_extended/ul_logo.eps
rename to introduction/ul_logo.eps
diff --git a/introduction_extended/varcall.gif b/introduction/varcall.gif
similarity index 100%
rename from introduction_extended/varcall.gif
rename to introduction/varcall.gif
diff --git a/introduction_extended/zmw.jpg b/introduction/zmw.jpg
similarity index 100%
rename from introduction_extended/zmw.jpg
rename to introduction/zmw.jpg
diff --git a/introduction_extended/cnv.png b/introduction_extended/cnv.png
deleted file mode 120000
index 81a0d690388bfce337bd6c0d30eb8369c4f8d1f8..0000000000000000000000000000000000000000
--- a/introduction_extended/cnv.png
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/cnv.png
\ No newline at end of file
diff --git a/introduction_extended/contig.png b/introduction_extended/contig.png
deleted file mode 120000
index 305a2f1a6e93dc10491d36ea6ef2bcd710942ed0..0000000000000000000000000000000000000000
--- a/introduction_extended/contig.png
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/contig.png
\ No newline at end of file
diff --git a/introduction_extended/discordant.png b/introduction_extended/discordant.png
deleted file mode 120000
index 526ffe0646e9253a8400dea8792006ca971e763b..0000000000000000000000000000000000000000
--- a/introduction_extended/discordant.png
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/discordant.png
\ No newline at end of file
diff --git a/introduction_extended/galaxy.xcf b/introduction_extended/galaxy.xcf
deleted file mode 120000
index 7df9fa6117421b769f5d3f05a071f38c10fe63eb..0000000000000000000000000000000000000000
--- a/introduction_extended/galaxy.xcf
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/galaxy.xcf
\ No newline at end of file
diff --git a/introduction_extended/galaxy_mpileup.xcf b/introduction_extended/galaxy_mpileup.xcf
deleted file mode 120000
index 67d6d74971fe848ce597ee4546cc11b9be0617e8..0000000000000000000000000000000000000000
--- a/introduction_extended/galaxy_mpileup.xcf
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/galaxy_mpileup.xcf
\ No newline at end of file
diff --git a/introduction_extended/linker-clip.ppm b/introduction_extended/linker-clip.ppm
deleted file mode 120000
index 4e061f9163bcb5135fb33b1fd6a3b6a6e3f917ab..0000000000000000000000000000000000000000
--- a/introduction_extended/linker-clip.ppm
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/linker-clip.ppm
\ No newline at end of file
diff --git a/introduction_extended/poorly_mapped.png b/introduction_extended/poorly_mapped.png
deleted file mode 120000
index 46ecbb8d7ac533f1ee331ccddbf2cbc5b6c5fafa..0000000000000000000000000000000000000000
--- a/introduction_extended/poorly_mapped.png
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/poorly_mapped.png
\ No newline at end of file
diff --git a/introduction_extended/pretrimmed_qscores.png b/introduction_extended/pretrimmed_qscores.png
deleted file mode 120000
index 5fe738b8450d4dd0ee4d30f4dffc386f3f0fc5d5..0000000000000000000000000000000000000000
--- a/introduction_extended/pretrimmed_qscores.png
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/pretrimmed_qscores.png
\ No newline at end of file
diff --git a/introduction_extended/scaffold.jpg b/introduction_extended/scaffold.jpg
deleted file mode 120000
index d33da9b0af53aef6be3d2630a30a4b838ac40978..0000000000000000000000000000000000000000
--- a/introduction_extended/scaffold.jpg
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/scaffold.jpg
\ No newline at end of file
diff --git a/introduction_extended/sv.jpg b/introduction_extended/sv.jpg
deleted file mode 120000
index b86293dd24e9b61ceb70c11b059d64ac2b5fe00d..0000000000000000000000000000000000000000
--- a/introduction_extended/sv.jpg
+++ /dev/null
@@ -1 +0,0 @@
-../presentation-pics/pics/sv.jpg
\ No newline at end of file