[med-svn] r16950 - in trunk/packages/genometools/trunk/debian: . patches
Sascha Steinbiss
sascha-guest at moszumanska.debian.org
Thu May 15 22:25:00 UTC 2014
Author: sascha-guest
Date: 2014-05-15 22:25:00 +0000 (Thu, 15 May 2014)
New Revision: 16950
Added:
trunk/packages/genometools/trunk/debian/patches/split-manuals
Removed:
trunk/packages/genometools/trunk/debian/patches/split_manuals
Modified:
trunk/packages/genometools/trunk/debian/changelog
trunk/packages/genometools/trunk/debian/patches/series
Log:
Address LaTeX build problems for manuals
Modified: trunk/packages/genometools/trunk/debian/changelog
===================================================================
--- trunk/packages/genometools/trunk/debian/changelog 2014-05-15 14:30:23 UTC (rev 16949)
+++ trunk/packages/genometools/trunk/debian/changelog 2014-05-15 22:25:00 UTC (rev 16950)
@@ -1,3 +1,9 @@
+genometools (1.5.2-2) unstable; urgency=low
+
+ * Split manuals into separate documents to avoid strange LaTeX build issues.
+
+ -- Sascha Steinbiss <satta at tetrinetsucht.de> Thu, 15 May 2014 23:23:20 +0000
+
genometools (1.5.2-1) unstable; urgency=low
* New upstream release.
Modified: trunk/packages/genometools/trunk/debian/patches/series
===================================================================
--- trunk/packages/genometools/trunk/debian/patches/series 2014-05-15 14:30:23 UTC (rev 16949)
+++ trunk/packages/genometools/trunk/debian/patches/series 2014-05-15 22:25:00 UTC (rev 16950)
@@ -7,3 +7,4 @@
mips-64
no-xmllint
spelling
+split-manuals
Added: trunk/packages/genometools/trunk/debian/patches/split-manuals
===================================================================
--- trunk/packages/genometools/trunk/debian/patches/split-manuals (rev 0)
+++ trunk/packages/genometools/trunk/debian/patches/split-manuals 2014-05-15 22:25:00 UTC (rev 16950)
@@ -0,0 +1,410 @@
+Description: Split manuals into separate documents to avoid strange LaTeX build issues.
+Author: Sascha Steinbiss <steinbiss at zbh.uni-hamburg.de>
+--- a/doc/manuals/matstat.tex
++++ b/doc/manuals/matstat.tex
+@@ -1,2 +1,160 @@
+-\def\BuildMatstat{}
+-\input{uniquesub}
++\documentclass[12pt]{article}
++\usepackage[a4paper,top=20mm,bottom=20mm,left=20mm,right=20mm]{geometry}
++\usepackage{url}
++\usepackage{alltt}
++\usepackage{xspace}
++\usepackage{times}
++\usepackage{listings}
++
++\usepackage{verbatim}
++\usepackage{ifthen}
++\usepackage{optionman}
++
++\newcommand{\Substring}[3]{#1[#2..#3]}
++
++\newcommand{\Program}[0]{\texttt{matstat}\xspace}
++\newcommand{\MS}[1]{\mathit{ms(s,#1)}}
++\title{\Program: a program for computing\\
++ matching statistics\\
++ a manual}
++
++\author{\begin{tabular}{c}
++ \textit{Stefan Kurtz}\\
++ Center for Bioinformatics,\\
++ University of Hamburg
++ \end{tabular}}
++
++\begin{document}
++\maketitle
++
++\section{The program \Program}
++
++The program \Program is called as follows:
++\par
++\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
++\par
++\Showoptionarg{files} is a white space separated list of at least one
++filename. Any sequence occurring in any file specified in \Showoptionarg{files}
++is called \textit{unit} in the following.
++In addition to the mandatory option \Showoption{query}, the program
++must be called with either option \Showoption{pck} or \Showoption{esa}
++which specify to use a packed index or an enhanced suffix array for
++a given set of subject sequences.
++
++\Program computes the \textit{matching statistics} for each unit. That is,
++for each position \(i\) in
++each unit, say \(s\) of length \(n\), \(\MS{i}=(l,j)\) is computed. Here
++\(l\) is the largest integer such that \(\Substring{s}{i}{i+l-1}\) matches
++a substring represented by the index and \(j\) is a start position of the
++matching substring in the index. We say that \(l\) is the length of \(\MS{i}\)
++and \(j\) is the subject position of \(\MS{i}\).
++
++The following options are available in \Program:
++
++\begin{Justshowoptions}
++\begin{comment}
++\Option{fmi}{$\Showoptionarg{indexname}$}{
++Use the old implementation of the FMindex. This option is not recommended.
++}
++\end{comment}
++
++\Option{esa}{$\Showoptionarg{indexname}$}{
++Use the given enhanced suffix array to compute the matches.
++}
++
++\Option{pck}{$\Showoptionarg{indexname}$}{
++Use the packed index (an efficient representation of the FMindex)
++to compute the matches.
++}
++
++
++\Option{query}{$\Showoptionarg{files}$}{
++Specify a white space separated list of query files containing the units.
++At least one query file must be given. The files may be in
++gzipped format, in which case they have to end with the suffix \texttt{.gz}.
++}
++
++\Option{min}{$\ell$}{
++Specify the minimum value $\ell$ for the length of the matching statistics.
++That is, for each unit \(s\) and each position \(i\) in \(s\), the program
++reports all values \(i\) and \(\MS{i}\) if the
++length of \(\MS{i}\) is at least \(\ell\).
++}
++
++\Option{max}{$\ell$}{
++Specify the maximum length $\ell$ for the length of the matching statistics.
++That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
++reports the values \(i\) and \(\MS{i}\) if the length of \(\MS{i}\)
++is at most \(\ell\).
++}
++
++\Option{output}{(\Showoptionkey{subjectpos}$\mid$\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
++Specify what to output. At least one of the three keys words
++$\Showoptionkey{subjectpos}$,
++$\Showoptionkey{querypos}$, and
++$\Showoptionkey{sequence}$ must be used.
++Using the keyword $\Showoptionkey{subjectpos}$ shows the
++subject position of the matching statistics.
++Using the keyword $\Showoptionkey{querypos}$ shows the query position.
++Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
++}
++
++\Helpoption
++
++\end{Justshowoptions}
++The following conditions must be satisfied:
++\begin{enumerate}
++\item
++Either option \Showoption{min} or option \Showoption{max} must be used.
++\item
++If both options \Showoption{min} and \Showoption{max} are used, then
++the value specified by option \(\Showoption{min}\) must be smaller
++than the value specified by option \(\Showoption{max}\).
++\item
++Either option \Showoption{pck} or \Showoption{esa} must be used. Both cannot
++be combined.
++\end{enumerate}
++
++\section{Examples}
++
++Suppose that in some directory, say \texttt{homo-sapiens}, we have 25 gzipped
++fasta files containing all 24 human chromomsomes plus one file with
++mitrochondrial sequences. These may have been downloaded from
++\url{ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens_47_36i/dna}.
++
++In the first step, we construct the packed index for the entire genome:
++
++\begin{Output}
++gt packedindex mkindex -dna -dir rev -parts 15 -bsize 10 -locfreq 32
++ -indexname human-all -db homo-sapiens/*.gz
++\end{Output}
++
++The program runs for almost two hours and delivers
++an index \texttt{human-all} consisting of three files:
++
++\begin{Output}
++ls -lh human-all.*
++-rw-r----- 1 kurtz gistaff 37 2008-01-24 00:47 human-all.al1
++-rw-r----- 1 kurtz gistaff 1.9G 2008-01-24 02:37 human-all.bdx
++-rw-r----- 1 kurtz gistaff 3.4K 2008-01-24 02:37 human-all.prj
++\end{Output}
++
++This is used in the following call to the program \Program:
++
++\begin{Output}
++gt matstat -output subjectpos querypos sequence -min 20 -max 30
++ -query queryfile.fna -pck human-all
++unit 0 (Mus musculus, chr 1, complete sequence)
++22 20 390765125 actgtatctcaaaatataaa
++253 21 258488266 gggaataaacatgtcattgag
++254 20 258488267 ggaataaacatgtcattgag
++275 20 900483549 taattctatttttctttctt
++480 20 1008274536 gcttgaagatcatgatccag
++..
++\end{Output}
++Here, the first column shows the relative positions in unit 0 for which the
++length of the matching statistics is between 20 and 30. The second column is
++the corresponding length value. The third column shows position of the
++matching sequence in the index, and the fourth shows the sequence content.
++
++\end{document}
+--- a/doc/manuals/uniquesub.tex
++++ b/doc/manuals/uniquesub.tex
+@@ -8,38 +8,15 @@
+
+ \usepackage{verbatim}
+ \usepackage{ifthen}
+-\usepackage{comment}
+ \usepackage{optionman}
+
+-\ifthenelse{\isundefined{\BuildMatstat}}{%
+-\includecomment{AboutUniquesub}
+-\excludecomment{AboutMatstat}
+-\newcommand{\AboutUniquesubcmd}[1]{#1}
+-\newcommand{\AboutMatstatcmd}[1]{}
+-}{%
+-\includecomment{AboutMatstat}
+-\excludecomment{AboutUniquesub}
+-\newcommand{\AboutMatstatcmd}[1]{#1}
+-\newcommand{\AboutUniquesubcmd}[1]{}
+-}
+-
+ \newcommand{\Substring}[3]{#1[#2..#3]}
+
+-\begin{AboutUniquesub}
+ \newcommand{\Program}[0]{\texttt{uniquesub}\xspace}
+ \newcommand{\Mup}[1]{\mathit{mup(s,#1)}}
+ \title{\Program: a program for computing\\
+ minimum unique substrings\\
+ a manual}
+-\end{AboutUniquesub}
+-
+-\begin{AboutMatstat}
+-\newcommand{\Program}[0]{\texttt{matstat}\xspace}
+-\newcommand{\MS}[1]{\mathit{ms(s,#1)}}
+-\title{\Program: a program for computing\\
+- matching statistics\\
+- a manual}
+-\end{AboutMatstat}
+
+ \author{\begin{tabular}{c}
+ \textit{Stefan Kurtz}\\
+@@ -54,47 +31,35 @@
+
+ The program \Program is called as follows:
+ \par
+-\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
++\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
+ \par
+-\Showoptionarg{files} is a white space separated list of at least one
++\Showoptionarg{files} is a white space separated list of at least one
+ filename. Any sequence occurring in any file specified in \Showoptionarg{files}
+ is called \textit{unit} in the following.
+ In addition to the mandatory option \Showoption{query}, the program
+ must be called with either option \Showoption{pck} or \Showoption{esa}
+-which specify to use a packed index or an enhanced suffix array for
++which specify to use a packed index or an enhanced suffix array for
+ a given set of subject sequences.
+
+-\begin{AboutUniquesub}
+ \Program computes for all positions \(i\) in each unit, say \(s\) of length
+-\(n\), the length \(\Mup{i}\) of the minimum unique prefix
++\(n\), the length \(\Mup{i}\) of the minimum unique prefix
+ at position \(i\), if it exists. Uniqueness always refers to all substrings
+-represented by the index. \(\Mup{i}\) is defined by the following two
++represented by the index. \(\Mup{i}\) is defined by the following two
+ statements:
+ \begin{itemize}
+ \item
+ If \(\Substring{s}{i}{n-1}\) is not unique in the index, then \(\Mup{i}=\bot\).
+ That is, it is undefined.
+ \item
+-If \(\Substring{s}{i}{n-1}\) is unique in the index, then \(\Mup{i}=m\), where
+-\(m\) is the smallest value such that \(i+m-1\leq n-1\) and
++If \(\Substring{s}{i}{n-1}\) is unique in the index, then \(\Mup{i}=m\), where
++\(m\) is the smallest value such that \(i+m-1\leq n-1\) and
+ \(\Substring{s}{i}{i+m-1}\) occurs exactly once as a substring in the index.
+ \end{itemize}
+-Note that it is possible that for all \(i\in[0,n-1]\) we have
+-\(\Mup{i}=\bot\), which means that unit \(s\) does not contain any unique
++Note that it is possible that for all \(i\in[0,n-1]\) we have
++\(\Mup{i}=\bot\), which means that unit \(s\) does not contain any unique
+ substring. In this case, the program reports nothing for the corresponding
+ unit. The program was developed for designing whole genome tiling arrays.
+ The corresponding publication is \cite{GRAE:NIE:KUR:HUY:BIR:STU:FLI:2007}.
+-\end{AboutUniquesub}
+-
+-\begin{AboutMatstat}
+-\Program computes the \textit{matching statistics} for each unit. That is,
+-for each position \(i\) in
+-each unit, say \(s\) of length \(n\), \(\MS{i}=(l,j)\) is computed. Here
+-\(l\) is the largest integer such that \(\Substring{s}{i}{i+l-1}\) matches
+-a substring represented by the index and \(j\) is a start position of the
+-matching substring in the index. We say that \(l\) is the length of \(\MS{i}\)
+-and \(j\) is the subject position of \(\MS{i}\).
+-\end{AboutMatstat}
+
+ The following options are available in \Program:
+
+@@ -117,58 +82,29 @@
+
+ \Option{query}{$\Showoptionarg{files}$}{
+ Specify a white space separated list of query files containing the units.
+-At least one query file must be given. The files may be in
++At least one query file must be given. The files may be in
+ gzipped format, in which case they have to end with the suffix \texttt{.gz}.
+ }
+
+-\begin{AboutUniquesub}
+ \Option{min}{$\ell$}{
+ Specify the minimum length $\ell$ of the minimum unique prefixes.
+-That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
+-reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\geq\ell\).
++That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
++reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\geq\ell\).
+ }
+
+ \Option{max}{$\ell$}{
+ Specify the maximum length $\ell$ of the minimum unique prefixes.
+-That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
++That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
+ reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\leq\ell\).
+ }
+
+ \Option{output}{(\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
+ Specify what to output. At least one of the two keys words
+-$\Showoptionkey{querypos}$ and $\Showoptionkey{sequence}$ must be used.
++$\Showoptionkey{querypos}$ and $\Showoptionkey{sequence}$ must be used.
+ Using the keyword $\Showoptionkey{querypos}$ shows the query position.
+ Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
+ of the match.
+ }
+-\end{AboutUniquesub}
+-
+-\begin{AboutMatstat}
+-\Option{min}{$\ell$}{
+-Specify the minimum value $\ell$ for the length of the matching statistics.
+-That is, for each unit \(s\) and each position \(i\) in \(s\), the program
+-reports all values \(i\) and \(\MS{i}\) if the
+-length of \(\MS{i}\) is at least \(\ell\).
+-}
+-
+-\Option{max}{$\ell$}{
+-Specify the maximum length $\ell$ for the length of the matching statistics.
+-That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
+-reports the values \(i\) and \(\MS{i}\) if the length of \(\MS{i}\)
+-is at most \(\ell\).
+-}
+-
+-\Option{output}{(\Showoptionkey{subjectpos}$\mid$\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
+-Specify what to output. At least one of the three keys words
+-$\Showoptionkey{subjectpos}$,
+-$\Showoptionkey{querypos}$, and
+-$\Showoptionkey{sequence}$ must be used.
+-Using the keyword $\Showoptionkey{subjectpos}$ shows the
+-subject position of the matching statistics.
+-Using the keyword $\Showoptionkey{querypos}$ shows the query position.
+-Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
+-}
+-\end{AboutMatstat}
+
+ \Helpoption
+
+@@ -189,7 +125,7 @@
+ \section{Examples}
+
+ Suppose that in some directory, say \texttt{homo-sapiens}, we have 25 gzipped
+-fasta files containing all 24 human chromomsomes plus one file with
++fasta files containing all 24 human chromomsomes plus one file with
+ mitrochondrial sequences. These may have been downloaded from
+ \url{ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens_47_36i/dna}.
+
+@@ -200,7 +136,7 @@
+ -indexname human-all -db homo-sapiens/*.gz
+ \end{Output}
+
+-The program runs for almost two hours and delivers
++The program runs for almost two hours and delivers
+ an index \texttt{human-all} consisting of three files:
+
+ \begin{Output}
+@@ -212,9 +148,8 @@
+
+ This is used in the following call to the program \Program:
+
+-\begin{AboutUniquesub}
+ \begin{Output}
+-gt uniquesub -output querypos -min 20 -max 30 -query queryfile.fna
++gt uniquesub -output querypos -min 20 -max 30 -query queryfile.fna
+ -pck human-all
+ unit 0 (Mus musculus, chr 1, complete sequence)
+ 1007 20
+@@ -227,7 +162,7 @@
+
+ For all units \(s\) in the multiple \Fasta file \texttt{queryfile.fna},
+ a line is shown, reporting the number of the unit and the original fasta
+-header. Also, all for positions \(i\) in \(s\) satisfying
++header. Also, all for positions \(i\) in \(s\) satisfying
+ \(20\leq \Mup{i}\leq 30\), \(i\) and \(\Mup{i}\) is reported.
+
+ The first column is the relative position in the unit sequence (counting
+@@ -238,7 +173,7 @@
+ \Showoption{output}:
+
+ \begin{Output}
+-gt uniquesub -output querypos sequence -min 20 -max 30
++gt uniquesub -output querypos sequence -min 20 -max 30
+ -query queryfile.fna -pck human-all
+ unit 0 (Mus musculus, chr 1, complete sequence)
+ 1007 20 ctgacagtttttttttttta
+@@ -248,27 +183,7 @@
+ 1013 21 gttttttttttttactttata
+ ...
+ \end{Output}
+-\end{AboutUniquesub}
+-
+-\begin{AboutMatstat}
+-\begin{Output}
+-gt matstat -output subjectpos querypos sequence -min 20 -max 30
+- -query queryfile.fna -pck human-all
+-unit 0 (Mus musculus, chr 1, complete sequence)
+-22 20 390765125 actgtatctcaaaatataaa
+-253 21 258488266 gggaataaacatgtcattgag
+-254 20 258488267 ggaataaacatgtcattgag
+-275 20 900483549 taattctatttttctttctt
+-480 20 1008274536 gcttgaagatcatgatccag
+-..
+-\end{Output}
+-Here, the first column shows the relative positions in unit 0 for which the
+-length of the matching statistics is between 20 and 30. The second column is
+-the corresponding length value. The third column shows position of the
+-matching sequence in the index, and the fourth shows the sequence content.
+-\end{AboutMatstat}
+
+-\begin{AboutUniquesub}
+ %\bibliographystyle{plain}
+ %\bibliography{defines,kurtz}
+ \begin{thebibliography}{1}
+@@ -280,5 +195,4 @@
+ \newblock {\em {Bioinformatics}}, {23 ISMB/ECCB 2007}:{i195--i204}, 2007.
+
+ \end{thebibliography}
+-\end{AboutUniquesub}
+ \end{document}
Deleted: trunk/packages/genometools/trunk/debian/patches/split_manuals
===================================================================
--- trunk/packages/genometools/trunk/debian/patches/split_manuals 2014-05-15 14:30:23 UTC (rev 16949)
+++ trunk/packages/genometools/trunk/debian/patches/split_manuals 2014-05-15 22:25:00 UTC (rev 16950)
@@ -1,409 +0,0 @@
-Description: split manuals into individual LaTeX files
- On some platforms, LaTeX will not build manuals properly when
- they share a single file in which text sections are marked or
- unmarked as comments using includecomment/excludecomment.
-Author: Sascha Steinbiss <steinbiss at zbh.uni-hamburg.de>
---- a/doc/manuals/matstat.tex
-+++ b/doc/manuals/matstat.tex
-@@ -1,2 +1,158 @@
--\def\BuildMatstat{}
--\input{uniquesub}
-+\documentclass[12pt]{article}
-+\usepackage[a4paper,top=20mm,bottom=20mm,left=20mm,right=20mm]{geometry}
-+\usepackage{url}
-+\usepackage{alltt}
-+\usepackage{xspace}
-+\usepackage{times}
-+\usepackage{listings}
-+\usepackage{verbatim}
-+\usepackage{optionman}
-+
-+\newcommand{\Substring}[3]{#1[#2..#3]}
-+
-+\newcommand{\Program}[0]{\texttt{matstat}\xspace}
-+\newcommand{\MS}[1]{\mathit{ms(s,#1)}}
-+\title{\Program: a program for computing\\
-+ matching statistics\\
-+ a manual}
-+
-+\author{\begin{tabular}{c}
-+ \textit{Stefan Kurtz}\\
-+ Center for Bioinformatics,\\
-+ University of Hamburg
-+ \end{tabular}}
-+
-+\begin{document}
-+\maketitle
-+
-+\section{The program \Program}
-+
-+The program \Program is called as follows:
-+\par
-+\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
-+\par
-+\Showoptionarg{files} is a white space separated list of at least one
-+filename. Any sequence occurring in any file specified in \Showoptionarg{files}
-+is called \textit{unit} in the following.
-+In addition to the mandatory option \Showoption{query}, the program
-+must be called with either option \Showoption{pck} or \Showoption{esa}
-+which specify to use a packed index or an enhanced suffix array for
-+a given set of subject sequences.
-+
-+\Program computes the \textit{matching statistics} for each unit. That is,
-+for each position \(i\) in
-+each unit, say \(s\) of length \(n\), \(\MS{i}=(l,j)\) is computed. Here
-+\(l\) is the largest integer such that \(\Substring{s}{i}{i+l-1}\) matches
-+a substring represented by the index and \(j\) is a start position of the
-+matching substring in the index. We say that \(l\) is the length of \(\MS{i}\)
-+and \(j\) is the subject position of \(\MS{i}\).
-+
-+The following options are available in \Program:
-+
-+\begin{Justshowoptions}
-+\begin{comment}
-+\Option{fmi}{$\Showoptionarg{indexname}$}{
-+Use the old implementation of the FMindex. This option is not recommended.
-+}
-+\end{comment}
-+
-+\Option{esa}{$\Showoptionarg{indexname}$}{
-+Use the given enhanced suffix array to compute the matches.
-+}
-+
-+\Option{pck}{$\Showoptionarg{indexname}$}{
-+Use the packed index (an efficient representation of the FMindex)
-+to compute the matches.
-+}
-+
-+
-+\Option{query}{$\Showoptionarg{files}$}{
-+Specify a white space separated list of query files containing the units.
-+At least one query file must be given. The files may be in
-+gzipped format, in which case they have to end with the suffix \texttt{.gz}.
-+}
-+
-+\Option{min}{$\ell$}{
-+Specify the minimum value $\ell$ for the length of the matching statistics.
-+That is, for each unit \(s\) and each position \(i\) in \(s\), the program
-+reports all values \(i\) and \(\MS{i}\) if the
-+length of \(\MS{i}\) is at least \(\ell\).
-+}
-+
-+\Option{max}{$\ell$}{
-+Specify the maximum length $\ell$ for the length of the matching statistics.
-+That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
-+reports the values \(i\) and \(\MS{i}\) if the length of \(\MS{i}\)
-+is at most \(\ell\).
-+}
-+
-+\Option{output}{(\Showoptionkey{subjectpos}$\mid$\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
-+Specify what to output. At least one of the three keys words
-+$\Showoptionkey{subjectpos}$,
-+$\Showoptionkey{querypos}$, and
-+$\Showoptionkey{sequence}$ must be used.
-+Using the keyword $\Showoptionkey{subjectpos}$ shows the
-+subject position of the matching statistics.
-+Using the keyword $\Showoptionkey{querypos}$ shows the query position.
-+Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
-+}
-+
-+\Helpoption
-+
-+\end{Justshowoptions}
-+The following conditions must be satisfied:
-+\begin{enumerate}
-+\item
-+Either option \Showoption{min} or option \Showoption{max} must be used.
-+\item
-+If both options \Showoption{min} and \Showoption{max} are used, then
-+the value specified by option \(\Showoption{min}\) must be smaller
-+than the value specified by option \(\Showoption{max}\).
-+\item
-+Either option \Showoption{pck} or \Showoption{esa} must be used. Both cannot
-+be combined.
-+\end{enumerate}
-+
-+\section{Examples}
-+
-+Suppose that in some directory, say \texttt{homo-sapiens}, we have 25 gzipped
-+fasta files containing all 24 human chromomsomes plus one file with
-+mitrochondrial sequences. These may have been downloaded from
-+\url{ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens_47_36i/dna}.
-+
-+In the first step, we construct the packed index for the entire genome:
-+
-+\begin{Output}
-+gt packedindex mkindex -dna -dir rev -parts 15 -bsize 10 -locfreq 32
-+ -indexname human-all -db homo-sapiens/*.gz
-+\end{Output}
-+
-+The program runs for almost two hours and delivers
-+an index \texttt{human-all} consisting of three files:
-+
-+\begin{Output}
-+ls -lh human-all.*
-+-rw-r----- 1 kurtz gistaff 37 2008-01-24 00:47 human-all.al1
-+-rw-r----- 1 kurtz gistaff 1.9G 2008-01-24 02:37 human-all.bdx
-+-rw-r----- 1 kurtz gistaff 3.4K 2008-01-24 02:37 human-all.prj
-+\end{Output}
-+
-+This is used in the following call to the program \Program:
-+
-+\begin{Output}
-+gt matstat -output subjectpos querypos sequence -min 20 -max 30
-+ -query queryfile.fna -pck human-all
-+unit 0 (Mus musculus, chr 1, complete sequence)
-+22 20 390765125 actgtatctcaaaatataaa
-+253 21 258488266 gggaataaacatgtcattgag
-+254 20 258488267 ggaataaacatgtcattgag
-+275 20 900483549 taattctatttttctttctt
-+480 20 1008274536 gcttgaagatcatgatccag
-+..
-+\end{Output}
-+Here, the first column shows the relative positions in unit 0 for which the
-+length of the matching statistics is between 20 and 30. The second column is
-+the corresponding length value. The third column shows position of the
-+matching sequence in the index, and the fourth shows the sequence content.
-+\end{document}
---- a/doc/manuals/uniquesub.tex
-+++ b/doc/manuals/uniquesub.tex
-@@ -7,37 +7,14 @@
--\usepackage{ifthen}
--\usepackage{comment}
- \usepackage{optionman}
--
--\ifthenelse{\isundefined{\BuildMatstat}}{%
--\includecomment{AboutUniquesub}
--\excludecomment{AboutMatstat}
--\newcommand{\AboutUniquesubcmd}[1]{#1}
--\newcommand{\AboutMatstatcmd}[1]{}
--}{%
--\includecomment{AboutMatstat}
--\excludecomment{AboutUniquesub}
--\newcommand{\AboutMatstatcmd}[1]{#1}
--\newcommand{\AboutUniquesubcmd}[1]{}
--}
--
- \newcommand{\Substring}[3]{#1[#2..#3]}
-
--\begin{AboutUniquesub}
- \newcommand{\Program}[0]{\texttt{uniquesub}\xspace}
- \newcommand{\Mup}[1]{\mathit{mup(s,#1)}}
- \title{\Program: a program for computing\\
- minimum unique substrings\\
- a manual}
--\end{AboutUniquesub}
--
--\begin{AboutMatstat}
--\newcommand{\Program}[0]{\texttt{matstat}\xspace}
--\newcommand{\MS}[1]{\mathit{ms(s,#1)}}
--\title{\Program: a program for computing\\
-- matching statistics\\
-- a manual}
--\end{AboutMatstat}
-
- \author{\begin{tabular}{c}
- \textit{Stefan Kurtz}\\
-@@ -54,47 +29,35 @@
-
- The program \Program is called as follows:
- \par
--\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
-+\noindent\Program [\textit{options}] \Showoption{query} \Showoptionarg{files} [\textit{options}]
- \par
--\Showoptionarg{files} is a white space separated list of at least one
-+\Showoptionarg{files} is a white space separated list of at least one
- filename. Any sequence occurring in any file specified in \Showoptionarg{files}
- is called \textit{unit} in the following.
- In addition to the mandatory option \Showoption{query}, the program
- must be called with either option \Showoption{pck} or \Showoption{esa}
--which specify to use a packed index or an enhanced suffix array for
-+which specify to use a packed index or an enhanced suffix array for
- a given set of subject sequences.
-
--\begin{AboutUniquesub}
- \Program computes for all positions \(i\) in each unit, say \(s\) of length
--\(n\), the length \(\Mup{i}\) of the minimum unique prefix
-+\(n\), the length \(\Mup{i}\) of the minimum unique prefix
- at position \(i\), if it exists. Uniqueness always refers to all substrings
--represented by the index. \(\Mup{i}\) is defined by the following two
-+represented by the index. \(\Mup{i}\) is defined by the following two
- statements:
- \begin{itemize}
- \item
- If \(\Substring{s}{i}{n-1}\) is not unique in the index, then \(\Mup{i}=\bot\).
- That is, it is undefined.
- \item
--If \(\Substring{s}{i}{n-1}\) is unique in the index, then \(\Mup{i}=m\), where
--\(m\) is the smallest value such that \(i+m-1\leq n-1\) and
-+If \(\Substring{s}{i}{n-1}\) is unique in the index, then \(\Mup{i}=m\), where
-+\(m\) is the smallest value such that \(i+m-1\leq n-1\) and
- \(\Substring{s}{i}{i+m-1}\) occurs exactly once as a substring in the index.
- \end{itemize}
--Note that it is possible that for all \(i\in[0,n-1]\) we have
--\(\Mup{i}=\bot\), which means that unit \(s\) does not contain any unique
-+Note that it is possible that for all \(i\in[0,n-1]\) we have
-+\(\Mup{i}=\bot\), which means that unit \(s\) does not contain any unique
- substring. In this case, the program reports nothing for the corresponding
- unit. The program was developed for designing whole genome tiling arrays.
- The corresponding publication is \cite{GRAE:NIE:KUR:HUY:BIR:STU:FLI:2007}.
--\end{AboutUniquesub}
--
--\begin{AboutMatstat}
--\Program computes the \textit{matching statistics} for each unit. That is,
--for each position \(i\) in
--each unit, say \(s\) of length \(n\), \(\MS{i}=(l,j)\) is computed. Here
--\(l\) is the largest integer such that \(\Substring{s}{i}{i+l-1}\) matches
--a substring represented by the index and \(j\) is a start position of the
--matching substring in the index. We say that \(l\) is the length of \(\MS{i}\)
--and \(j\) is the subject position of \(\MS{i}\).
--\end{AboutMatstat}
-
- The following options are available in \Program:
-
-@@ -117,58 +80,29 @@
-
- \Option{query}{$\Showoptionarg{files}$}{
- Specify a white space separated list of query files containing the units.
--At least one query file must be given. The files may be in
-+At least one query file must be given. The files may be in
- gzipped format, in which case they have to end with the suffix \texttt{.gz}.
- }
-
--\begin{AboutUniquesub}
- \Option{min}{$\ell$}{
- Specify the minimum length $\ell$ of the minimum unique prefixes.
--That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
--reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\geq\ell\).
-+That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
-+reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\geq\ell\).
- }
-
- \Option{max}{$\ell$}{
- Specify the maximum length $\ell$ of the minimum unique prefixes.
--That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
-+That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
- reports the values \(i\) and \(\Mup{i}\) whenever \(\Mup{i}\leq\ell\).
- }
-
- \Option{output}{(\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
- Specify what to output. At least one of the two keys words
--$\Showoptionkey{querypos}$ and $\Showoptionkey{sequence}$ must be used.
-+$\Showoptionkey{querypos}$ and $\Showoptionkey{sequence}$ must be used.
- Using the keyword $\Showoptionkey{querypos}$ shows the query position.
- Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
- of the match.
- }
--\end{AboutUniquesub}
--
--\begin{AboutMatstat}
--\Option{min}{$\ell$}{
--Specify the minimum value $\ell$ for the length of the matching statistics.
--That is, for each unit \(s\) and each position \(i\) in \(s\), the program
--reports all values \(i\) and \(\MS{i}\) if the
--length of \(\MS{i}\) is at least \(\ell\).
--}
--
--\Option{max}{$\ell$}{
--Specify the maximum length $\ell$ for the length of the matching statistics.
--That is, for each unit \(s\) and each positions \(i\) in \(s\), the program
--reports the values \(i\) and \(\MS{i}\) if the length of \(\MS{i}\)
--is at most \(\ell\).
--}
--
--\Option{output}{(\Showoptionkey{subjectpos}$\mid$\Showoptionkey{querypos}$\mid$\Showoptionkey{sequence})}{
--Specify what to output. At least one of the three keys words
--$\Showoptionkey{subjectpos}$,
--$\Showoptionkey{querypos}$, and
--$\Showoptionkey{sequence}$ must be used.
--Using the keyword $\Showoptionkey{subjectpos}$ shows the
--subject position of the matching statistics.
--Using the keyword $\Showoptionkey{querypos}$ shows the query position.
--Using the keyword $\Showoptionkey{sequence}$ shows the sequence content
--}
--\end{AboutMatstat}
-
- \Helpoption
-
-@@ -189,7 +123,7 @@
- \section{Examples}
-
- Suppose that in some directory, say \texttt{homo-sapiens}, we have 25 gzipped
--fasta files containing all 24 human chromomsomes plus one file with
-+fasta files containing all 24 human chromomsomes plus one file with
- mitrochondrial sequences. These may have been downloaded from
- \url{ftp://ftp.ensembl.org/pub/current_fasta/homo_sapiens_47_36i/dna}.
-
-@@ -200,7 +134,7 @@
- -indexname human-all -db homo-sapiens/*.gz
- \end{Output}
-
--The program runs for almost two hours and delivers
-+The program runs for almost two hours and delivers
- an index \texttt{human-all} consisting of three files:
-
- \begin{Output}
-@@ -212,9 +146,8 @@
-
- This is used in the following call to the program \Program:
-
--\begin{AboutUniquesub}
- \begin{Output}
--gt uniquesub -output querypos -min 20 -max 30 -query queryfile.fna
-+gt uniquesub -output querypos -min 20 -max 30 -query queryfile.fna
- -pck human-all
- unit 0 (Mus musculus, chr 1, complete sequence)
- 1007 20
-@@ -227,7 +160,7 @@
-
- For all units \(s\) in the multiple \Fasta file \texttt{queryfile.fna},
- a line is shown, reporting the number of the unit and the original fasta
--header. Also, all for positions \(i\) in \(s\) satisfying
-+header. Also, all for positions \(i\) in \(s\) satisfying
- \(20\leq \Mup{i}\leq 30\), \(i\) and \(\Mup{i}\) is reported.
-
- The first column is the relative position in the unit sequence (counting
-@@ -238,7 +171,7 @@
- \Showoption{output}:
-
- \begin{Output}
--gt uniquesub -output querypos sequence -min 20 -max 30
-+gt uniquesub -output querypos sequence -min 20 -max 30
- -query queryfile.fna -pck human-all
- unit 0 (Mus musculus, chr 1, complete sequence)
- 1007 20 ctgacagtttttttttttta
-@@ -248,27 +181,7 @@
- 1013 21 gttttttttttttactttata
- ...
- \end{Output}
--\end{AboutUniquesub}
-
--\begin{AboutMatstat}
--\begin{Output}
--gt matstat -output subjectpos querypos sequence -min 20 -max 30
-- -query queryfile.fna -pck human-all
--unit 0 (Mus musculus, chr 1, complete sequence)
--22 20 390765125 actgtatctcaaaatataaa
--253 21 258488266 gggaataaacatgtcattgag
--254 20 258488267 ggaataaacatgtcattgag
--275 20 900483549 taattctatttttctttctt
--480 20 1008274536 gcttgaagatcatgatccag
--..
--\end{Output}
--Here, the first column shows the relative positions in unit 0 for which the
--length of the matching statistics is between 20 and 30. The second column is
--the corresponding length value. The third column shows position of the
--matching sequence in the index, and the fourth shows the sequence content.
--\end{AboutMatstat}
--
--\begin{AboutUniquesub}
- %\bibliographystyle{plain}
- %\bibliography{defines,kurtz}
- \begin{thebibliography}{1}
-@@ -280,5 +193,5 @@
- \newblock {\em {Bioinformatics}}, {23 ISMB/ECCB 2007}:{i195--i204}, 2007.
-
- \end{thebibliography}
--\end{AboutUniquesub}
-+
- \end{document}
More information about the debian-med-commit
mailing list