diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Gen2Phen.eps b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Gen2Phen.eps
new file mode 120000
index 0000000000000000000000000000000000000000..0f79cba2730d21e82f1df0dc33021e70c13c7ba8
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Gen2Phen.eps
@@ -0,0 +1 @@
+../LUMC_Presentation_Skeleton/Gen2Phen.eps
\ No newline at end of file
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Makefile b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Makefile
new file mode 120000
index 0000000000000000000000000000000000000000..a9e2361a4c145915e0cce54e7941fe7abe92c6dd
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/Makefile
@@ -0,0 +1 @@
+../LUMC_Presentation_Skeleton/Makefile
\ No newline at end of file
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg.eps b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg.eps
new file mode 120000
index 0000000000000000000000000000000000000000..e0b2d3a6794f2fbb93edf264ee607c374330d311
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg.eps
@@ -0,0 +1 @@
+../LUMC_Presentation_Skeleton/bg.eps
\ No newline at end of file
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg2.eps b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg2.eps
new file mode 120000
index 0000000000000000000000000000000000000000..f444c639acb4a9e28ea3087c22da8e68106e819e
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/bg2.eps
@@ -0,0 +1 @@
+../LUMC_Presentation_Skeleton/bg2.eps
\ No newline at end of file
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/demo.txt b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/demo.txt
new file mode 100644
index 0000000000000000000000000000000000000000..3af2806d03a759ae35e3004653e0ee1871d193c3
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/demo.txt
@@ -0,0 +1 @@
+AL449423.14(CDKN2A_v001):c.247_250delinsCTTT
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/leftover.txt b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/leftover.txt
new file mode 100644
index 0000000000000000000000000000000000000000..49b03543e0630be0f42bc3c4e800d90505ecb4a7
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/leftover.txt
@@ -0,0 +1,271 @@
+% - Mutalyzer 1.0.4
+\begin{slide}
+ \slideheading{Mutalyzer 1.0.4}
+
+ \begin{itemize}
+ \item Developed in over four years by multiple people.
+ \item Originally a command line program.
+ \item Web interface added later.
+ \end{itemize}
+ \vfill
+\end{slide}
+
+% - Design flaws:
+% - Nomenclature rules interwoven with the code.
+% - No modularity (reuse of code is very hard).
+% - Reference sequence parsing not abstracted.
+% - HTML output interwoven with the code.
+\begin{slide}
+ \slideheading{Mutalyzer 1.0.4}
+
+ Design flaws:
+
+ \begin{itemize}
+ \item Nomenclature rules interwoven with the code.
+ \item HTML output interwoven with the code.
+ \item No modularity (reuse of code is very hard).
+ \item Reference sequence parsing not abstracted.
+ \end{itemize}
+ \vfill
+\end{slide}
+
+% - Implementation flaws:
+% - Inheritance of types (del on DNA -> del on PROT).
+% - Disambiguation not general.
+% - Support up/downstream exons.
+% - Speed
+\begin{slide}
+ \slideheading{Mutalyzer 1.0.4}
+
+ Implementation flaws:
+
+ \begin{itemize}
+ \item Inheritance of types (del on DNA -> del on PROT).
+ \item Disambiguation not general.
+ \item Support up/downstream exons.
+ \item Nothing was ever redesigned, only wrapped in loops.
+ \begin{itemize}
+ \item Debugging, altering code made impossible.
+ \item Speed drastically deminished.
+ \end{itemize}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+% - Programming flaws:
+% - Excessive usage of exceptions.
+% - Incomprehensible error messages.
+% - Poor documentation.
+\begin{slide}
+ \slideheading{Mutalyzer 1.0.4}
+
+ Programming flaws:
+
+ \begin{itemize}
+ \item Excessive usage of exceptions.
+ \item Incomprehensible error messages.
+ \item Poor documentation.
+ \end{itemize}
+ \vfill
+\end{slide}
+
+% - Feature requests:
+% - Extension of HGVS nomenclature rules.
+% - Support for other reference files (LRG)
+% - Programmatic access to internal functions.
+% - Solving all problems mentioned above.
+% - Since the nomenclature has changed, a rewrite was in order.
+%
+
+\begin{slide}
+ \slideheading{Mutalyzer 1.0.4}
+
+ Feature requests:
+
+ \begin{itemize}
+ \item Solving all problems mentioned above.
+ \item Support for other reference files (LRG).
+ \item Programmatic access to internal functions.
+ \end{itemize}
+ Since the HGVS nomenclature rules were changed in the mean time, and the
+ language was no longer regular (but context free), the only possible couse of
+ action was a complete redesign.
+ \vfill
+\end{slide}
+
+% - Preparations for version 2.0
+% - Gathering and archiving all old versions (for comparison).
+% - Setting up a version control repository.
+% - Talking for months.
+% - Figuring out what the HGVS language is.
+% - Formalising that language (BNF).
+% - Semantic rules.
+% - Chopping everything up in functional modules.
+% - Designing interfaces (web, webservice, command line, etc.)
+\begin{slide}
+ \slideheading{Preparing for a new version}
+
+
+ \begin{itemize}
+ \item Setting up a version control repository.
+ \item Gathering all old versions and putting then under version control.
+ \begin{itemize}
+ \item Critical bugfixes until there is a new version.
+ \item Easy to search and track changes.
+ \item Point of reference for the new version.
+ \end{itemize}
+ \item Talking for months.
+ \begin{itemize}
+ \item Figuring out what the HGVS language is.
+ \item Formalising that language (BNF).
+ \item Semantic rules.
+ \end{itemize}
+ \item Chopping everything up in functional modules.
+ \item Designing interfaces (web, webservice, command line, etc.).
+ \end{itemize}
+ \vfill
+\end{slide}
+
+%
+% - Then finally, after months of talking and drawing with pencil and paper..
+% - Implementing the modules.
+% - Implementing the interfaces.
+\begin{slide}
+ \slideheading{Mutalyzer 2.0}
+
+ Then finally, after months of talking and drawing with pencil and paper..
+
+ \begin{itemize}
+ \item Implementing the modules.
+ \item Implementing the interfaces.
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+%
+% - Mutalyzer 2.0
+% - Core functionalities.
+% - Webservices.
+% - ...
+
+
+\begin{slide}
+ \slideheading{TAL}
+
+ \begin{lstlisting}[language = HTML, caption = {TAL example}]
+ <table class = "raTable">
+ <tr>
+ <td>Number</td>
+ <td>Start (g.)</td>
+ <td>Stop (g.)</td>
+ <td>Start (c.)</td>
+ <td>Stop (c.)</td>
+ </tr>
+ <tr tal:repeat = "i exonInfo">
+ <td tal:content = "repeat/i/number"></td>
+ <td tal:repeat = "j i" tal:content = "j"></td>
+ </tr>
+ </table>
+ \end{lstlisting}
+
+ When we give a list of exon coordinates, a table is generated.
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{BNF}
+
+ \begin{lstlisting}[language = BNF, caption = {Abstract HGVS nomenclature}]
+ TransVar -> `_v' Number
+ ProtIso -> `_i' Number
+ GeneSymbol -> `(' Name (TransVar | ProtIso)? `)'
+ \end{lstlisting}
+
+ \begin{lstlisting}[caption = {HGVS nomenclature in Python}]
+ TransVar = Suppress("_v") + Number("TransVar")
+ ProtIso = Suppress("_i") + Number("ProtIso")
+ GeneSymbol = Suppress('(') + Group(Name("GeneSymbol") + \
+ Optional(TransVar ^ ProtIso))("Gene") + Suppress(')')
+ \end{lstlisting}
+
+ \bt{(CDKN2A\_v001)}
+ \begin{lstlisting}[caption = {Python object}]
+ Gene.GeneSymbol = CDKN2A
+ Gene.TransVar = 001
+ \end{lstlisting}
+
+ \bt{(CDKN2A\_i002)}
+ \begin{lstlisting}[caption = {Python object}]
+ Gene.GeneSymbol = CDKN2A
+ Gene.ProtIso = 002
+ \end{lstlisting}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Comparison to the old version (1.0.4)}
+
+ \renewcommand{\arraystretch}{0.99}
+ \begin{tabular}{l|c|c}
+ & Mutalyzer 1.0.4 & Mutalyzer 2.0\\
+ \hline
+ Disambiguation & $\pm$ & $++$\\
+ Complex variants & $--$ & $++$\\
+ Protein description & $\pm$ & $+$\\
+ Up / downstream descriptions & $--$ & $++$\\
+ Comprehensible error messages & $-$ & $++$\\
+ Using a protein reference & $\pm$ & $--$\\
+ Batch checkers & $\pm$ & $++$\\
+ GenBank uploader & $+$ & $++$\\
+ Position conversion & $--$ & $++$\\
+ Programmatic access & $--$ & $++$\\
+ Other organisms / organelles & $\pm$ & $++$\\
+ \end{tabular}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Comparison to the old version (1.0.4): runtime}
+ \begin{center}
+ \colorbox{white} {
+ \includegraphics[scale = 0.65]{genes}
+ }
+ \end{center}
+ A $229\times$ speedup was measured (from almost $12min$ to about $3s$).
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Comparison to the old version (1.0.4): code}
+
+ \begin{tabular}{l|r|r}
+ & Mutalyzer 1.0.4 & Mutalyzer 2.0\\
+ \hline
+ Total (lines) & $7,\!752$ & $11,\!396$\\
+ Total (bytes) & $365,\!736$ & $390,\!316$\\
+ Minimised (lines) & $5,\!102$ & $4,\!320$\\
+ Minimised (bytes) & $232,\!611$ & $156,\!803$\\
+ Percentage of code (lines) & $66\%$ & $38\%$\\
+ Percentage of code (bytes) & $64\%$ & $42\%$
+ \end{tabular}
+ \bigskip
+ \bigskip
+
+ The total amount of \emph{source code} in Mutalyzer~2.0 is $107\%$ of that in
+ Mutalyzer~1.0.4, but the amount of \emph{program code} is only $67\%$.
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Scalability: runtime with increasing complexity}
+ \begin{center}
+ \colorbox{white} {
+ \includegraphics[scale = 0.65]{allele}
+ }
+ \end{center}
+ The overhead ($\pm 2.5s$) is due to loading the reference sequence.
+ \vfill
+\end{slide}
+
diff --git a/doc/Presentation_24-02-11_HumGen_Mutalyzer2/presentation.tex b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/presentation.tex
new file mode 100644
index 0000000000000000000000000000000000000000..03d86b3ae721a958752bc2f28b323f512209b356
--- /dev/null
+++ b/doc/Presentation_24-02-11_HumGen_Mutalyzer2/presentation.tex
@@ -0,0 +1,798 @@
+% LUMC presentation template by J. F. J. Laros.
+% Last alteration on 20-02-2011.
+%
+% The packages texlive-latex-recommended, texlive-latex-base and
+% texlive-latex-extra should be installed.
+%
+
+% Alter these four lines for a new presentation.
+\providecommand{\me}{Jeroen F. J. Laros}
+\providecommand{\myTitle}{Mutalyzer 2.0}
+\providecommand{\myConference}{Work discussion}
+\providecommand{\myDate}{Thursday, 24 February 2011}
+
+% Now go to %%% BEGIN PRESENTATION %%%
+
+\documentclass[a4, portrait]{seminar}
+
+\usepackage{semcolor} % For coloured text.
+\usepackage{slidesec} % For section headings.
+\usepackage{newcent} % This is a better font for presentations.
+\usepackage{listings}
+\input{seminar.bug}
+
+\usepackage{graphicx} % For pictures.
+\usepackage{fancybox} % For the background picture.
+\usepackage[labelfont={color=white}, textfont={color=white}]{caption}
+
+\definecolor{Blue}{rgb}{0.,0.11372,0.37647} % Custom LUMC color
+
+\renewcommand{\labelitemi}{\textcolor{white}{$\bullet$}} % Make the bullets for
+\renewcommand{\labelitemii}{\textcolor{white}{--}} % itemising white.
+\renewcommand{\labelitemiii}{\textcolor{white}{$\ast$}}
+\renewcommand{\labelitemiv}{\textcolor{white}{$\circ$}}
+\renewcommand{\labelenumi}{\textcolor{white}{\arabic{enumi}.}}
+
+\newcommand{\bt}[1]{\texttt{\textbf{#1}}}
+
+\lstdefinelanguage{BNF}{
+ sensitive = true,
+ otherkeywords = {-,>,|,',`,?,(,)},
+ morestring = [b][keywordstyle]',
+ morecomment = [l]{\#},
+}
+
+
+\newslideframe{TITLE}{ % Template for the title.
+ \boxput{
+ \rput(0, 0){\includegraphics[angle=90, scale=.485]{bg}}
+ }{#1}
+}
+
+\newslideframe{PRES}{ % Template for the body.
+ \boxput{
+ \rput(0, 0){\includegraphics[angle=90, scale=.485]{bg2}}
+ }{
+ \textcolor{Blue}{
+ \rput[l]{90}(8.57, -1.5){\scriptsize{\myConference}}
+ \rput[c]{90}(8.57, 5.35){\scriptsize{\theslide/\pageref{LastPage}}}
+ \rput[r]{90}(8.57, 12.2){\scriptsize{\myDate}}
+ }
+ \white #1
+ }
+}
+
+\renewcommand{\makeslideheading}[1]{ % Put the slide headings on top.
+ \rput[l](0.2, .40){
+ \textbf{
+ \textcolor{Blue}{#1}
+ }
+ }
+ \newline
+}
+
+\pagestyle{empty}
+
+\begin{document}
+
+\slideframe{TITLE} % Use the title template.
+
+\begin{slide}
+ \setcounter{slide}{0}
+ \vspace*{1.5cm}
+ \begin{center}
+ {\bf\Large{\myTitle}}\\
+ \vfill
+ \textcolor{Blue}{
+ {\bf
+ \small{\me}\\
+ \small{Leiden Genome Technology Center}\\
+ \small{Department of Human Genetics}\\
+ \small{Center for Human and Clinical Genetics}
+ }
+ }
+ \vspace{1.1cm}
+ \end{center}
+\end{slide}
+
+\slideframe{PRES} % Use the body template.
+
+%%% BEGIN PRESENTATION %%%
+\providecommand{\positionpicture}{
+ \vspace{-0.5cm}
+ \begin{center}
+ \fbox{
+ \begin{picture}(300, 60)(0, 0)
+ \put(0, 30){\line(1, 0){300}} % Genomic sequence.
+ \linethickness{4pt}
+ \put(50, 30){\line(1, 0){30}} % Non-coding parts of the exons.
+ \put(220, 30){\line(1, 0){10}}
+ \linethickness{12pt}
+ \put(80, 30){\line(1, 0){20}} % Coding parts of the exons.
+ \put(150, 30){\line(1, 0){20}}
+ \put(200, 30){\line(1, 0){20}}
+
+ \linethickness{0.5pt}
+ \put(20, 50){\scriptsize{Transcription start}}
+ \put(50, 45){\vector(0, -1){10}}
+ \put(200, 50){\scriptsize{Transcription end}}
+ \put(230, 45){\vector(0, -1){10}}
+
+ \put(70, 0){\scriptsize{CDS start}}
+ \put(80, 10){\vector(0, 1){10}}
+ \put(210, 0){\scriptsize{CDS stop}}
+ \put(220, 10){\vector(0, 1){10}}
+
+ \put(0, 0){\scriptsize{Genomic end}}
+ \put(0, 10){\vector(0, 1){10}}
+ \put(255, 0){\scriptsize{Genomic start}}
+ \put(300, 10){\vector(0, 1){10}}
+
+ \put(95, 50){\yellow \scriptsize{Variant A}\white}
+ \put(115, 45){\yellow \vector(0, -1){10}\white}
+
+ \put(140, 50){\yellow \scriptsize{Variant B}\white}
+ \put(160, 45){\yellow \vector(0, -1){10}\white}
+ \end{picture}
+ }
+ \end{center}
+ \bigskip
+}
+
+\providecommand{\positionshiftexampleheader}{
+ We observe a change from \bt{GG\underline{ATCATC}G} to
+ \bt{GG\underline{ATCATCATC}G}.
+
+}
+
+\providecommand{\positionshiftexamplebody}{
+ \bt{\,123456789}
+ \vspace{-0.3cm}
+
+ \bt{GGATCATCG}
+
+}
+
+\providecommand{\inversionexampleheader}{
+ We observe a change from \bt{GCT\underline{TTAATT}AGG} to
+ \bt{GCT\underline{AATTAA}AGG}.
+
+}
+
+\lstset{
+ language = Python,
+ basicstyle = \footnotesize,
+ lineskip = -0.5ex,
+ frame = shadowbox,
+ rulesepcolor = \color{black},
+ captionpos = b,
+ numbers = left,
+ numbersep = -1em,
+ numberstyle = \tiny
+}
+
+\begin{slide}
+ \slideheading{Introduction}
+
+ A curational tool for \emph{Locus Specific Mutation Databases} (LSDBs).
+
+ \bigskip
+ \begin{itemize}
+ \item Variant nomenclature checker applying \emph{Human Genome Variation
+ Society} (HGVS) guidelines.
+ \begin{itemize}
+ \item Is the syntax of the variant description valid?
+ \item Does the reference sequence exist?
+ \item Is the variant possible on this reference sequence?
+ \item Is this variant description the recommended one?
+ \end{itemize}
+ \item Basic effect prediction.
+ \begin{itemize}
+ \item Is the description of the transcript product as expected?
+ \item Is the predicted protein as expected?
+ \end{itemize}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature}
+
+ Genomic orientated positions:
+ \begin{center}
+ \bt{AL449423.14:g.[65449\_65463del;65564\yellow T\white >\yellow C\white]}
+ \end{center}
+ \bigskip
+ Coding sequence orientated positions:
+ \begin{center}
+ \bt{AL449423.14(CDKN2A\_v001):c.[5\yellow A\white >\yellow G\white
+ ;106\_120del]}
+ \end{center}
+ \bigskip
+ \begin{itemize}
+ \item \bt{AL449423.14} -- reference sequence.
+ \item \bt{CDKN2A\_v001}$\;$ -- transcript variant \bt{1} of gene CDKN2A.
+ \item \bt{c.[5\yellow A\white >\yellow G\white ;106\_120del]}
+ \begin{itemize}
+ \item A \emph{substitution} at position \bt{5} counting from the start
+ codon.
+ \item A \emph{deletion} from position \bt{106} to position \bt{120}.
+ \end{itemize}
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: positions}
+
+ \positionpicture
+
+ This gene is on the reverse strand.
+
+ \bigskip
+ \begin{tabular}{l|l|l}
+ Name & & Description\\
+ \hline
+ Genomic & \bt{g.} & From {\scriptsize Genomic start} to
+ {\scriptsize Genomic end}. \\
+ Transcript & \bt{n.} & From {\scriptsize Transcription start} to
+ {\scriptsize Transcription end}, skip introns.\\
+ Coding & \bt{c.} & From {\scriptsize CDS start} to
+ {\scriptsize CDS stop}, skip introns.
+ \end{tabular}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: positions}
+
+ \positionpicture
+
+ \bt{c.} positions:
+ \begin{itemize}
+ \item Positions in introns are relative to the nearest exonic position.
+ \item Positions before the CDS are indicated with a \bt{-} sign.
+ \item Positions after the CDS are indicated with a \bt{*} sign.
+ \end{itemize}
+
+ Position \bt{-1} and \bt{1} are adjacent.
+
+ If \bt{60} is the last position of the CDS, then \bt{60} and \bt{*1} are
+ adjacent.
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: positions}
+
+ \positionpicture
+
+ \renewcommand{\arraystretch}{1}
+ \begin{center}
+ \begin{tabular}{l|r|r|r}
+ Name & \bt{g.} & \bt{n.} & \bt{c.} \\
+ \hline
+ {\scriptsize Genomic start} & \bt{1} & \bt{100+d70} &
+ \bt{*10+d70} \\
+ {\scriptsize Genomic end} & \bt{300} & \bt{1-u50} &
+ \bt{-30-u50} \\
+ {\scriptsize Transcription start} & \bt{250} & \bt{1} & \bt{-30} \\
+ {\scriptsize Transcription end} & \bt{70} & \bt{100} & \bt{*10} \\
+ {\scriptsize CDS start} & \bt{220} & \bt{30} & \bt{1} \\
+ {\scriptsize CDS stop} & \bt{80} & \bt{90} & \bt{60} \\
+ \end{tabular}
+ \end{center}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: positions}
+
+ \positionpicture
+
+ \renewcommand{\arraystretch}{1}
+ \begin{center}
+ \begin{tabular}{l|r|r|r}
+ Name & \bt{g.} & \bt{n.} & \bt{c.} \\
+ \hline
+ {\scriptsize Variant A} & \bt{185} & \bt{50+15} & \bt{20+15} \\
+ {\scriptsize Variant B} & \bt{140} & \bt{60} & \bt{30} \\
+ \end{tabular}
+ \end{center}
+
+ \bigskip
+ \bt{NG\_001234.1:g.185\yellow A\white >\yellow C\white}
+
+ \bt{NG\_001234.1(GEN\_v001):n.50+15\yellow T\white >\yellow G\white }
+
+ \bt{NG\_001234.1(GEN\_v001):c.20+15\yellow T\white >\yellow G\white }
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: the position shift rule}
+
+ \positionshiftexampleheader
+ \begin{center}
+ \positionshiftexamplebody
+ \begin{picture}(0, 0)(0, 0)
+ \put(-15.6, 5){\vector(0, 1){10}}
+ % \put(-9.5, 5){\vector(0, 1){10}}
+ % \put(-3.7, 5){\vector(0, 1){10}}
+ \put(2.5, 5){\vector(0, 1){10}}
+ % \put(8.8, 5){\vector(0, 1){10}}
+ % \put(15.1, 5){\vector(0, 1){10}}
+ \put(21.4, 5){\vector(0, 1){10}}
+ \end{picture}
+ \end{center}
+
+ Which can be described as an insertion of \bt{ATC} at three places:
+ \begin{itemize}
+ \item \bt{g.2\_3ins\yellow ATC\white}
+ \item \bt{g.5\_6ins\yellow ATC\white}% \ \ or \ \ \bt{g.3\_5dup}
+ \item \bt{g.8\_9ins\yellow ATC\white}% \ \ or \ \ \bt{g.6\_8dup}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: the position shift rule}
+
+ \positionshiftexampleheader
+ \begin{center}
+ \positionshiftexamplebody
+ \begin{picture}(0, 0)(0, 0)
+ % \put(-15.6, 5){\vector(0, 1){10}}
+ \put(-9.5, 5){\vector(0, 1){10}}
+ % \put(-3.7, 5){\vector(0, 1){10}}
+ % \put(2.5, 5){\vector(0, 1){10}}
+ \put(8.8, 5){\vector(0, 1){10}}
+ % \put(15.1, 5){\vector(0, 1){10}}
+ % \put(21.4, 5){\vector(0, 1){10}}
+ \end{picture}
+ \end{center}
+
+ \ldots or an insertion of \bt{TCA} at two places:
+ \begin{itemize}
+ \item \bt{g.3\_4ins\yellow TCA\white}
+ \item \bt{g.6\_7ins\yellow TCA\white}% \ \ or \ \ \bt{g.4\_6dup}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: the position shift rule}
+
+ \positionshiftexampleheader
+ \begin{center}
+ \positionshiftexamplebody
+ \begin{picture}(0, 0)(0, 0)
+ % \put(-15.6, 5){\vector(0, 1){10}}
+ % \put(-9.5, 5){\vector(0, 1){10}}
+ \put(-3.7, 5){\vector(0, 1){10}}
+ % \put(2.5, 5){\vector(0, 1){10}}
+ % \put(8.8, 5){\vector(0, 1){10}}
+ \put(15.1, 5){\vector(0, 1){10}}
+ %\put(21.4, 5){\vector(0, 1){10}}
+ \end{picture}
+ \end{center}
+
+ \ldots or an insertion of \bt{CAT} at two places:
+ \begin{itemize}
+ \item \bt{g.4\_5ins\yellow CAT\white}
+ \item \bt{g.7\_8ins\yellow CAT\white}% \ \ or \ \ \bt{g.5\_7dup}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: the position shift rule}
+
+ \positionshiftexampleheader
+ \begin{center}
+ \positionshiftexamplebody
+ \begin{picture}(0, 0)(0, 0)
+ % \put(-15.6, 5){\vector(0, 1){10}}
+ % \put(-9.5, 5){\vector(0, 1){10}}
+ % \put(-3.7, 5){\vector(0, 1){10}}
+ % \put(2.5, 5){\vector(0, 1){10}}
+ % \put(8.8, 5){\vector(0, 1){10}}
+ % \put(15.1, 5){\vector(0, 1){10}}
+ \put(21.4, 5){\vector(0, 1){10}}
+ \end{picture}
+ \end{center}
+
+ The only correct one is the insertion on the 3' end.
+ \begin{itemize}
+ \item \bt{g.8\_9ins\yellow ATC}
+ \end{itemize}
+
+ However, this can also be described as a \emph{duplication}, which has
+ precedence over the \emph{insertion}.
+
+ The final description therefore is:
+ \begin{itemize}
+ \item \bt{g.6\_8dup}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: the position shift rule}
+
+ However, the \bt{c.} notation of a gene on the reverse strand:
+
+ \begin{minipage}{0.4\textwidth}
+ \begin{center}
+ Genomic
+
+ \bt{\,123456789}
+ \vspace{-0.15cm}
+
+ \bt{GGATC\green\underline{\white ATC}\white G}
+ \end{center}
+ \end{minipage}
+ \begin{minipage}{0.4\textwidth}
+ \begin{center}
+ Coding
+
+ \bt{\,123456789}
+ \vspace{-0.15cm}
+
+ \bt{C\green\underline{\white GAT}\yellow\underline{\white GAT}\white CC}
+ \end{center}
+ \end{minipage}
+ \bigskip
+
+ \begin{itemize}
+ \item \bt{g.6\_8dup}
+ \item \bt{c.\yellow 5\white \_\yellow 7\white dup}\white \ \ \ and not \ \
+ \bt{c.\green 2\white \_\green 4\white dup}
+ \end{itemize}
+
+ A substitution on position \bt{g.8}, \emph{would} be converted to \bt{c.2}.
+
+ \begin{itemize}
+ \item \bt{g.8\yellow C\white >\yellow A\white}
+ \item \bt{c.2\yellow G\white >\yellow T\white}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: disambiguation}
+
+ \inversionexampleheader
+ \begin{center}
+ \bt{\,\ \ \ \ \ \ \ \ \ 111}
+ \vspace{-0.3cm}
+
+ \bt{\,\,123456789012}
+ \vspace{-0.3cm}
+
+ \bt{G\underline{CTTTAATTAG}G}
+ \end{center}
+
+ We can describe it as follows:
+ \begin{itemize}
+ \item \bt{g.2\_11inv}
+ \end{itemize}
+ \begin{center}
+ \bt{\,\ \ \ \ \ \ \ \ \ 111}
+ \vspace{-0.3cm}
+
+ \bt{\,\,123456789012}
+ \vspace{-0.3cm}
+
+ \bt{GCT\underline{TTAATT}AGG}
+ \end{center}
+ \begin{itemize}
+ \item \bt{g.4\_9delins\yellow AATTAA\white}
+ \end{itemize}
+
+ But the correct way is:
+ \begin{itemize}
+ \item \bt{g.4\_9inv}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{HGVS nomenclature: disambiguation}
+
+ Other pitfalls:
+ \begin{itemize}
+ \item A deletion-insertion can actually be:
+ \begin{tabular}{llll}
+ --\, An inversion & \bt{2\_3del\yellow AC\white ins\yellow GT\white}
+ & $\Rightarrow$ & \bt{2\_3inv}\\
+ --\, An insertion & \bt{2del\yellow T\white ins\yellow TAA\white}
+ & $\Rightarrow$ & \bt{2\_3ins\yellow AA\white}\\
+ --\, A substitution & \bt{2del\yellow A\white ins\yellow T\white}
+ & $\Rightarrow$ & \bt{2\yellow A\white >\yellow T\white}\\
+ --\, A deletion & \bt{2\_3del\yellow TA\white ins\yellow A\white}
+ & $\Rightarrow$ & \bt{2del}\\
+ \end{tabular}
+ \item An inversion can actually be a substitution
+ (\bt{2\_4inv\yellow ACT\white}).
+ \item An insertion can actually be a duplication.
+ \item A variant can have no effect (\bt{2\_5inv\yellow ACGT\white},
+ \bt{2\yellow A\white >\yellow A\white}, etc.).
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: name checker}
+
+ \begin{center}
+ \bt{NM\_002001.2:c.[12\_14del;102\yellow G\white >\yellow T\white]}
+ \end{center}
+ \begin{enumerate}
+ \item Parse the variant description.
+ \begin{itemize}
+ \item Reference sequence e.g., \bt{NM\_002001.2}.
+ \item Position system (\bt{c.}, \bt{g.}, \bt{n.}, \ldots).
+ \item List of variants (\bt{12\_14del},
+ \bt{102\yellow G\white >\yellow T\white}).
+ \end{itemize}
+ \item Download the reference sequence.
+ \item Check the variants to the reference sequence.
+ \begin{itemize}
+ \item Is there a \bt{\yellow G\white } at position \bt{c.102}?
+ \end{itemize}
+ \item Mutate the reference sequence.
+ \item Predict the variant protein when applicable.
+ \item \ldots
+ \end{enumerate}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: name checker}
+
+ \bigskip
+ \bigskip
+ \bigskip
+ \bigskip
+ \bigskip
+ \begin{center}
+ \bt{AL449423.14(CDKN2A\_v001):c.247\_250delins\yellow CTTT\white}
+
+ \bigskip
+ \bt{http://www.mutalyzer.nl/2.0/check}
+ \end{center}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: name checker}
+
+ After a description is checked, other useful information is returned.
+ \begin{itemize}
+ \item Overview of the change on DNA level.
+ \item A genomic description.
+ \item A description on all affected transcripts.
+ \item Description of affected proteins.
+ \item Sequence of the original and affected protein with changes
+ highlighted.
+ \item Exon and CDS start / stop information.
+ \item Effects on restriction sites.
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: design}
+
+ This version was built from scratch.
+ \begin{itemize}
+ \item Modular design allows for partial functionality or other combinations.
+ \begin{itemize}
+ \item Convert positions.
+ \item Check the syntax of a variant only.
+ \item Get information about a gene.
+ \item \ldots
+ \end{itemize}
+ \item Strict separation of functionality and interface.
+ \begin{itemize}
+ \item Web interface.
+ \item Batch interface.
+ \item Command line interface.
+ \item Programmatic access (for LOVD and other programs).
+ \end{itemize}
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: position converter}
+
+ Next Generation Sequencing uses chromosomal positions.
+
+ LSDB's usually use transcripts.
+
+ The position converter:
+ \begin{itemize}
+ \item Works on both hg18 (NCBI Build 36.1) and hg19 (GRCh37).
+ \item Works in both ways:
+ \begin{itemize}
+ \item \bt{NM\_003002.2:c.274\yellow G\white >\yellow T\white} to
+ \bt{NC\_000011.9:g.111959695\yellow G\white >\yellow T\white}.
+ \item \bt{chr11:g.111959695\yellow G\white >\yellow T\white} to
+ \bt{NM\_003002.2:c.274\yellow G\white >\yellow T\white}.
+ \end{itemize}
+ \item Can be used to \emph{lift over} from hg18 to hg19 and vice versa.
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: other functionalities}
+
+ Other functionalities of Mutalyzer 2.0 include:
+ \begin{itemize}
+ \item SNP conversion (from dbSNP rsId to HGVS notation).
+ \item Name generator (to help people that don't use the HGVS notation that
+ often).
+ \item GenBank uploader (to make your own reference sequences).
+ \begin{itemize}
+ \item Automatically uses the correct strand when a HGNC gene symbol is
+ used.
+ \end{itemize}
+ \item Recently added functionality for the LRG (Locus Reference Genomic)
+ reference files.
+ \begin{itemize}
+ \item Other formats can easily be added.
+ \end{itemize}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Mutalyzer 2.0: other functionalities}
+
+ For a large number of checks, there are other interfaces.
+ \begin{itemize}
+ \item Batch interfaces (upload a table, receive the result by mail):
+ \begin{itemize}
+ \item Name checker.
+ \item Syntax checker.
+ \item Position converter.
+ \end{itemize}
+ \item Programmatic access (use from your own scripts).
+ \begin{itemize}
+ \item Currently $18$ functions available.
+ \begin{itemize}
+ \item Position conversion.
+ \item Mutate a reference sequence.
+ \item Retrieve all transcripts in a range of a chromosome.
+ \item Give extensive information of transcripts.
+ \item \ldots
+ \end{itemize}
+ \end{itemize}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{LOVD}
+
+ LOVD, the \emph{Leiden Open Variation Database} is a \emph{locus specific
+ database} (LSDB).
+
+ \begin{itemize}
+ \item Gene centred.
+ \item Variants are supposed to be stored in HGVS format.
+ \begin{itemize}
+ \item Mutalyzer name checker.
+ \end{itemize}
+ \item Variants are described on one \emph{transcript}.
+ \begin{itemize}
+ \item Mutalyzer name checker gives descriptions for all annotated
+ transcripts.
+ \end{itemize}
+ \item Variants must be mapped to the genome.
+ \begin{itemize}
+ \item Mutalyzer position converter.
+ \end{itemize}
+ \end{itemize}
+
+ \begin{center}
+ \bt{http://www.lovd.nl}
+ \end{center}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{LOVD: Mutalyzer 2.0 dependencies}
+
+ Creating a database:
+ \begin{itemize}
+ \item The curator knows the accession number of a transcript.
+ \begin{itemize}
+ \item Find the gene.
+ \item Find a genomic reference sequence.
+ \item Use the accession number of the genomic and transcript reference to
+ make a HGVS reference notation.
+ \begin{itemize}
+ \item \bt{NG\_007109.1} \ \ and \ \ \bt{NM\_000249.3} $\Rightarrow$
+ \bt{NG\_007109.1(MLH1\_v001)}.
+ \end{itemize}
+ \end{itemize}
+ \item The curator knows the gene name.
+ \begin{itemize}
+ \item Find a genomic reference sequence.
+ \item Retrieve a list of transcripts.
+ \item Show product information of each transcript.
+ \end{itemize}
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{LOVD: Mutalyzer 2.0 dependencies}
+
+ Adding a variant:
+ \begin{itemize}
+ \item Verify the validity.
+ \item Convert to genomic (chromosomal) positions.
+ \begin{itemize}
+ \item Used for visualisation in the UCSC genome browser.
+ \item Enables all LOVD installations to be searched.
+ \end{itemize}
+ \item Convert variant descriptions to other transcripts.
+ \item Provide a sortable \bt{c.}-like position.
+ \end{itemize}
+
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \slideheading{Conclusions and further research}
+
+ Short term:
+ \begin{itemize}
+ \item Using protein reference sequences.
+ \item Connection to SVEP.
+ \begin{itemize}
+ \item Splice prediction.
+ \item Alternative start.
+ \item Branch sites.
+ \item Transcription factors binding sites.
+ \item Protein effect prediction.
+ \item \ldots
+ \end{itemize}
+ \end{itemize}
+ \vfill
+\end{slide}
+
+\begin{slide}
+ \rput(11.4,0.6){\includegraphics[scale=0.1]{Gen2Phen}}
+ \slideheading{Questions?}
+ \begin{center}
+ Acknowledgements
+ \bigskip
+ \bigskip
+
+ Gerben Stouten\\
+ Martijn Vermaat\\
+ Gerard Schaafsma\\
+ Ivo Fokkema\\
+ Jacopo Celli\\
+ Johan den Dunnen\\
+ Peter Taschner
+ \bigskip
+
+ \bt{http://www.mutalyzer.nl/}
+ \end{center}
+ \vfill
+ \label{LastPage}
+\end{slide}
+
+\end{document}
diff --git a/src/Modules/GBparser.py b/src/Modules/GBparser.py
index a1e191be0547560f6c94a5f00dabef290e8d8289..433df8a8dce66921d0fe4ee053aa0174de691373 100644
--- a/src/Modules/GBparser.py
+++ b/src/Modules/GBparser.py
@@ -514,6 +514,7 @@ class GBparser() :
myGene.location = self.__location2pos(i.location)
geneDict[geneName] = tempGene(geneName)
#if
+ #if
if i.type in ["mRNA", "misc_RNA", "ncRNA", "rRNA", "tRNA",
"tmRNA"] :
diff --git a/src/Modules/Parser.py b/src/Modules/Parser.py
index 538076b366e4d69f369308780f10e07eb209743c..66f912f8d2a43ba67361f0c90109e8c75a17c0be 100644
--- a/src/Modules/Parser.py
+++ b/src/Modules/Parser.py
@@ -49,7 +49,8 @@ class Nomenclatureparser() :
# Nt -> `a' | `c' | `g' | `t' | `u' | `r' | `y' | `k' |
# `m' | `s' | `w' | `b' | `d' | `h' | `v' | `i' |
# `n' | `A' | `C' | `G' | `T' | `U'
- Nt = Word("acgtuACGTU", exact = 1)
+ #Nt = Word("acgtuACGTU", exact = 1)
+ Nt = Word("acgturykmswbdhvnACGTURYKMSWBDHVN", exact = 1)
# New:
NtString = Combine(OneOrMore(Nt))
diff --git a/src/Mutalyzer.py b/src/Mutalyzer.py
index 9d7564c062700279e05232912c1c1c296afc7446..4f503a3cdee21241de1acb43930fccdcd32bb1cd 100644
--- a/src/Mutalyzer.py
+++ b/src/Mutalyzer.py
@@ -656,6 +656,8 @@ def findFrameShift(str1, str2) :
lcp = __lcp(str1, str2)
if lcp == len(str2) : # NonSense mutation.
+ if lcp == len(str1) : # Is this correct?
+ return ("p.(=)", 0, 0, 0)
return ("p.(%s%i*)" % (seq3(str1[lcp]), lcp + 1), lcp, len(str1), lcp)
if lcp == len(str1) :
return ("p.(*%i%sext*%i)" % (len(str1) + 1, seq3(str2[len(str1)]),