debian/0000755000000000000000000000000011744622502007171 5ustar debian/mummer.install0000644000000000000000000000024111352452227012060 0ustar debian/tmp/usr/bin/* usr/bin debian/tmp/usr/lib/mummer/* usr/lib/mummer scripts/Foundation.pm usr/share/perl5 scripts/tandem-repeat.awk usr/lib/mummer debian/source/0000755000000000000000000000000011714137124010467 5ustar debian/source/format0000644000000000000000000000001411714133344011675 0ustar 3.0 (quilt) debian/mummer.manpages0000644000000000000000000000002010714420714012175 0ustar debian/mummer.1 debian/README.source0000644000000000000000000000204011226502006011333 0ustar Modifications of the MUMmer sources in Debian. We removed the following files before redistributing MUMmer in Debian: ./docs/web/MUMmer.pdf ./docs/web/XFiles.pdf ./docs/web/MUMmer2.pdf ./docs/web/MUMmer3.pdf These documents are published scientific articles whose license does not comply with our social contract, ‘http://www.debian.org/social_contract’. We provide an automated way to download the upstream archive and remove these files via the command ‘debian/rules get-orig-source’. In addition to this, the MUMmer documentation is patched to accomodate with this deletion, using the Quilt patch system. You can find instructions of use in ‘/usr/share/doc/quilt/README.source’. Since our modification keeps the functionality of the documentation intact, by replacing a link to a local version of the PDF articles by a remote link, I think that it is acceptable to not rename the documentation files (MUMmer is released under the Artistic license version 1). -- Charles Plessy Mon, 13 Jul 2009 08:28:17 +0900 debian/copyright0000644000000000000000000000222311712410344011115 0ustar Format: http://www.debian.org/doc/packaging-manuals/copyright-format/1.0/ Source: http://cdnetworks-kr-1.dl.sourceforge.net/project/mummer/mummer/3.23/MUMmer3.23.tar.gz Files: * Copyright: © 2003 by Stefan Kurtz and The Institute for Genomic Research. © 1999 by The Institute for Genomic Research. License: Artistic Comment: MUMmer 1.0 code and documentation are copyright (c) 1999 by The Institute for Genomic Research. The principle architect for the system was Arthur Delcher. Files: debian/* Copyright: © 2005-2007, Steffen Moeller , and Andreas Tille License: GPL Available at `/usr/share/common-licenses/GPL'. License: Artistic This program is free software; you can redistribute it and/or modify it under the terms of the "Artistic License" which comes with Debian. . THIS PACKAGE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE. Comment: On Debian systems, the complete text of the Artistic License can be found in ‘/usr/share/common-licenses/Artistic’. debian/upstream0000644000000000000000000000112511736650333010757 0ustar Archive: SourceForge Homepage: http://mummer.sourceforge.net/ Reference: Author: Kurtz, Stefan and Phillippy, Adam and Delcher, Arthur L. and Smoot, Michael and Shumway, Martin and Antonescu, Corina and Salzberg, Steven L. Title: Versatile and open software for comparing large genomes Journal: Genome Biology Volume: 5 Year: 2004 Number: 2 Pages: R12 URL: http://genomebiology.com/2004/5/2/R12 PMID: 14759262 DOI: 10.1186/gb-2004-5-2-r12 ISSN: 1465-6906 Repository: http://mummer.cvs.sourceforge.net/mummer/ Screenshots: http://sourceforge.net/project/screenshots.php?group_id=133157 debian/mummer-doc.links0000644000000000000000000000011110714420714012266 0ustar usr/share/doc/mummer-doc/html/examples usr/share/doc/mummer-doc/examples debian/rules0000755000000000000000000000327511717554366010274 0ustar #!/usr/bin/make -f %: dh $@ CFLAGS += $(shell dpkg-buildflags --get CFLAGS) # src/kurtz/mm3src/Makefile and src/kurtz/streesrc/Makefile make a use of CFLAGS that does not allow to override it, hence the following is added: CFLAGS += -DSTREEHUGE -I$(CURDIR)/src/kurtz/libbasedir -I$(CURDIR)/src/kurtz/streesrc TMPDIR = $(CURDIR)/debian/tmp BIN_DIR = $(TMPDIR)/usr/bin AUX_BIN_DIR = $(TMPDIR)/usr/lib/mummer FINAL_BIN_DIR = /usr/bin FINAL_AUX_BIN_DIR = /usr/lib/mummer FINAL_SCRIPT_DIR = /usr/share/perl5/ override_dh_auto_build: [ -d $(BIN_DIR) ] || mkdir -p $(BIN_DIR) [ -d $(AUX_BIN_DIR) ] || mkdir -p $(AUX_BIN_DIR) $(MAKE) BIN_DIR=$(BIN_DIR) AUX_BIN_DIR=$(AUX_BIN_DIR) \ FINAL_BIN_DIR=$(FINAL_BIN_DIR) FINAL_AUX_BIN_DIR=$(FINAL_AUX_BIN_DIR) \ FINAL_SCRIPT_DIR=$(FINAL_SCRIPT_DIR) \ CFLAGS="$(CFLAGS)" $(MAKE) -C docs override_dh_auto_test: $(MAKE) check override_dh_prep: # Unfortunately the upstream makefile does not separate the build and install steps. dh_prep -X debian/tmp override_dh_auto_install: # /usr/bin/annotate renamed /usr/bin/mummer-annotate for namespace and license (Artistic) reasons. mv $(BIN_DIR)/annotate $(BIN_DIR)/mummer-annotate override_dh_compress: dh_compress -Xpdf NAME = $(shell dpkg-parsechangelog | sed -n 's/^Source: //p') VERSION = $(shell dpkg-parsechangelog | sed -n 's/^Version: //p' | sed 's/~dfsg.*//') TARBALL = MUMmer$(VERSION).tar.gz get-orig-source: wget http://downloads.sourceforge.net/sourceforge/$(NAME)/$(TARBALL) rm -rf tmp mkdir tmp cd tmp ;\ tar -xzf ../$(TARBALL) ;\ rm -vf `find . -maxdepth 4 -name [MX]*.pdf` ;\ GZIP="--best --no-name" tar -czf ../$(NAME)_$(VERSION)~dfsg.orig.tar.gz * rm -rf tmp debian/mummer-doc.install0000644000000000000000000000005110714420714012617 0ustar docs/web/* usr/share/doc/mummer-doc/html debian/mummer-doc.docs0000644000000000000000000000003110714420714012077 0ustar docs/*.README docs/*.pdf debian/patches/0000755000000000000000000000000011744620343010621 5ustar debian/patches/enable_building_with_tetex.patch0000644000000000000000000000046311744620343017214 0ustar --- mummer-3.23~dfsg.orig/docs/maxmat3man.tex +++ mummer-3.23~dfsg/docs/maxmat3man.tex @@ -7,7 +7,7 @@ % \documentclass[12pt]{article} -\usepackage{a4wide,alltt,xspace,times} +\usepackage{a4,alltt,xspace,times} \usepackage{skaff} \usepackage{optionman} \newcommand{\MMthree}{\texttt{maxmat3}\xspace} debian/patches/series0000644000000000000000000000011211744620255012032 0ustar 10_install_dirs.patch 02at_docs_web.diff enable_building_with_tetex.patch debian/patches/02at_docs_web.diff0000644000000000000000000000636411712410120014060 0ustar Description: Some PDFs were removed and have to be downloaded from the upstream website instead. Origin: vendor : Debian Forwarded: not-needed --- a/docs/web/index.html +++ b/docs/web/index.html @@ -25,11 +25,11 @@ detect similarity, then the PROmer program can generate alignments based upon the six-frame translations of both input sequences. The original MUMmer system, version 1.0, is described in our 1999 Nucleic Acids Research paper. + href="http://mummer.sourceforge.net/MUMmer.pdf">1999 Nucleic Acids Research paper. Version 2.1 appeared a few years later and is described in our 2002 Nucleic Acids Research paper, + href="http://mummer.sourceforge.net/MUMmer2.pdf">2002 Nucleic Acids Research paper, while MUMmer 3.0 was recently described in our 2004 Genome Biology paper. We have also developed a GPU accelerated version of MUMmer called MUMmerGPU.

+ href="http://mummer.sourceforge.net/MUMmer3.pdf">2004 Genome Biology paper. We have also developed a GPU accelerated version of MUMmer called MUMmerGPU.

For more information regarding the MUMmer package, please refer to the:

@@ -174,7 +174,7 @@

Applications

MUMmer 1 was used to detect numerous large-scale inversions in bacterial genomes, leading to a new model of chromosome - inversions, reported in this 2000 Genome + inversions, reported in this 2000 Genome Biology paper. It was also used to discover evidence for a recent whole-genome duplication in Arabidopsis thaliana, reported in "Analysis of the genome sequence of the @@ -229,14 +229,14 @@

MUMmer 3 user manual

MUMmer 3 examples

Open source MUMmer 3.0 is described in "Versatile and open software for comparing large genomes." + href="http://mummer.sourceforge.net/MUMmer3.pdf">Versatile and open software for comparing large genomes." S. Kurtz, A. Phillippy, A.L. Delcher, M. Smoot, M. Shumway, C. Antonescu, and S.L. Salzberg, Genome Biology (2004), 5:R12.

-

MUMmer 2.1, NUCmer, and PROmer are described in "Fast +

MUMmer 2.1, NUCmer, and PROmer are described in "Fast Algorithms for Large-scale Genome Alignment and Comparision." A.L. Delcher, A. Phillippy, J. Carlton, and S.L. Salzberg, Nucleic Acids Research (2002), Vol. 30, No. 11 2478-2483.

-

MUMmer 1.0 is described in "Alignment of Whole Genomes." +

MUMmer 1.0 is described in "Alignment of Whole Genomes." A.L. Delcher, S. Kasif, R.D. Fleischmann, J. Peterson, O. White, and S.L. Salzberg, Nucleic Acids Research, 27:11 (1999), 2369-2376.

Space efficent suffix trees are described in " $(BIN_DIR)/exact-tandems +exact-tandems: ../debian/sh-replacement-scripts/exact-tandems + cp -a $^ $(BIN_DIR) chmod 755 $(BIN_DIR)/exact-tandems mapview: mapview.pl $(SED) -e 's?__PERL_PATH?$(PERL)?g' \ - -e 's?__SCRIPT_DIR?$(SCRIPT_DIR)?g' \ + -e 's?__SCRIPT_DIR?$(FINAL_SCRIPT_DIR)?g' \ mapview.pl > $(BIN_DIR)/mapview chmod 755 $(BIN_DIR)/mapview mummerplot: mummerplot.pl Foundation.pm $(SED) -e 's?__PERL_PATH?$(PERL)?g' \ - -e 's?__SCRIPT_DIR?$(SCRIPT_DIR)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ + -e 's?__SCRIPT_DIR?$(FINAL_SCRIPT_DIR)?g' \ + -e 's?__BIN_DIR?$(FINAL_BIN_DIR)?g' \ mummerplot.pl > $(BIN_DIR)/mummerplot chmod 755 $(BIN_DIR)/mummerplot dnadiff: dnadiff.pl Foundation.pm $(SED) -e 's?__PERL_PATH?$(PERL)?g' \ - -e 's?__SCRIPT_DIR?$(SCRIPT_DIR)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ + -e 's?__SCRIPT_DIR?$(FINAL_SCRIPT_DIR)?g' \ + -e 's?__BIN_DIR?$(FINAL_BIN_DIR)?g' \ dnadiff.pl > $(BIN_DIR)/dnadiff chmod 755 $(BIN_DIR)/dnadiff nucmer: nucmer.pl Foundation.pm $(SED) -e 's?__PERL_PATH?$(PERL)?g' \ - -e 's?__SCRIPT_DIR?$(SCRIPT_DIR)?g' \ - -e 's?__AUX_BIN_DIR?$(AUX_BIN_DIR)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ + -e 's?__SCRIPT_DIR?$(FINAL_SCRIPT_DIR)?g' \ + -e 's?__AUX_BIN_DIR?$(FINAL_AUX_BIN_DIR)?g' \ + -e 's?__BIN_DIR?$(FINAL_BIN_DIR)?g' \ nucmer.pl > $(BIN_DIR)/nucmer chmod 755 $(BIN_DIR)/nucmer promer: promer.pl Foundation.pm $(SED) -e 's?__PERL_PATH?$(PERL)?g' \ - -e 's?__SCRIPT_DIR?$(SCRIPT_DIR)?g' \ - -e 's?__AUX_BIN_DIR?$(AUX_BIN_DIR)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ + -e 's?__SCRIPT_DIR?$(FINAL_SCRIPT_DIR)?g' \ + -e 's?__AUX_BIN_DIR?$(FINAL_AUX_BIN_DIR)?g' \ + -e 's?__BIN_DIR?$(FINAL_BIN_DIR)?g' \ promer.pl > $(BIN_DIR)/promer chmod 755 $(BIN_DIR)/promer -run-mummer1: run-mummer1.csh - $(SED) -e 's?__CSH_PATH?$(CSH)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ - run-mummer1.csh > $(BIN_DIR)/run-mummer1 +run-mummer1: ../debian/sh-replacement-scripts/run-mummer1 + cp -a $^ $(BIN_DIR) chmod 755 $(BIN_DIR)/run-mummer1 -run-mummer3: run-mummer3.csh - $(SED) -e 's?__CSH_PATH?$(CSH)?g' \ - -e 's?__BIN_DIR?$(BIN_DIR)?g' \ - run-mummer3.csh > $(BIN_DIR)/run-mummer3 +run-mummer3: ../debian/sh-replacement-scripts/run-mummer3 + cp -a $^ $(BIN_DIR) chmod 755 $(BIN_DIR)/run-mummer3 nucmer2xfig: nucmer2xfig.pl debian/mummer-doc.doc-base0000644000000000000000000000202110771072112012623 0ustar Document: mummer-doc Title: MUMmer user manual Author: Arthur L. Delcher, Stefan Kurtz and others Abstract: MUMmer is a system for rapidly aligning entire genomes, whether in complete or draft form. For example, MUMmer 3.0 can find all 20-basepair or longer exact matches between a pair of 5-megabase genomes in 13.7 seconds, using 78 MB of memory, on a 2.4 GHz Linux desktop computer. MUMmer can also align incomplete genomes; it handles the 100s or 1000s of contigs from a shotgun sequencing project with ease, and will align them to another set of contigs or a genome using the NUCmer program included with the system. If the species are too divergent for DNA sequence alignment to detect similarity, then the PROmer program can generate alignments based upon the six-frame translations of both input sequences. Section: Science/Biology Format: pdf Files: /usr/share/doc/mummer-doc/*.pdf /usr/share/doc/mummer-doc/*.pdf Format: HTML Index: /usr/share/doc/mummer-doc/html/index.html Files: /usr/share/doc/mummer-doc/html/*.html debian/mummer.README.Debian0000644000000000000000000000031710714420714012531 0ustar mummer for Debian ----------------- The program annotate was renamed to mummer-annotate to avoid name space pollution with libgd-tools. -- Andreas Tille , Mon, 7 May 2007 14:46:27 +0200 debian/watch0000644000000000000000000000012411223034726010214 0ustar version=3 opts=dversionmangle=s/\~dfsg// \ http://sf.net/mummer/MUMmer(.+)\.tar.gz debian/mummer.links0000644000000000000000000000215510716124621011535 0ustar usr/share/man/man1/mummer.1 usr/share/man/man1/mummer-annotate.1 usr/share/man/man1/mummer.1 usr/share/man/man1/combineMUMs.1 usr/share/man/man1/mummer.1 usr/share/man/man1/dnadiff.1 usr/share/man/man1/mummer.1 usr/share/man/man1/delta-filter.1 usr/share/man/man1/mummer.1 usr/share/man/man1/exact-tandems.1 usr/share/man/man1/mummer.1 usr/share/man/man1/gaps.1 usr/share/man/man1/mummer.1 usr/share/man/man1/mapview.1 usr/share/man/man1/mummer.1 usr/share/man/man1/mgaps.1 usr/share/man/man1/mummer.1 usr/share/man/man1/mummerplot.1 usr/share/man/man1/mummer.1 usr/share/man/man1/nucmer.1 usr/share/man/man1/mummer.1 usr/share/man/man1/nucmer2xfig.1 usr/share/man/man1/mummer.1 usr/share/man/man1/promer.1 usr/share/man/man1/mummer.1 usr/share/man/man1/repeat-match.1 usr/share/man/man1/mummer.1 usr/share/man/man1/run-mummer1.1 usr/share/man/man1/mummer.1 usr/share/man/man1/run-mummer3.1 usr/share/man/man1/mummer.1 usr/share/man/man1/show-aligns.1 usr/share/man/man1/mummer.1 usr/share/man/man1/show-coords.1 usr/share/man/man1/mummer.1 usr/share/man/man1/show-snps.1 usr/share/man/man1/mummer.1 usr/share/man/man1/show-tiling.1 debian/mummer-doc.README.Debian0000644000000000000000000000104210714420714013270 0ustar mummer for Debian ----------------- The original tarball contained four papers about MUMmer in PDF format. Because we have neither an explicite license nor the source of these PDFs they were removed from the tarball. All these papers are published at http://mummer.sourceforge.net/ See the paragraphs "Applications" and "References". The index.html file in the mummer-doc package is a copy of the URL above and the links were adjusted to point to the external copy. -- Andreas Tille , Mon, 7 May 2007 14:46:27 +0200 debian/changelog0000644000000000000000000001257111744622502011051 0ustar mummer (3.23~dfsg-2) unstable; urgency=low * debian/enable_building_with_tetex.patch: enable building with recent tetex by changing the layout slightly (s/a4wide/a4/) Closes: #669521 * debian/control: Standards-Version: 3.9.3 (no changes needed) * Debhelper 9 (control+compat) -- Andreas Tille Sat, 21 Apr 2012 22:43:17 +0200 mummer (3.23~dfsg-1) unstable; urgency=low * New upstream release adding -D and --banded option to nucmer. * Updated debian/patches/02at_docs_web.diff. * Corrected VCS URLs (debian/control). * Conforms to Policy 3.9.2 (debian/control, no other changes needed). * Using Debhelper 8 (debian/control, debian/compat). * Support DEB_BUILD_OPTIONS via Debhelper (debian/rules). * Use dpkg source format 3.0 (quilt) as a patch system (debian/rules, debian/control, debian/source/format). * Simplify debian/rules using dh. * Pass Dpkg build flags in CFLAGS (debian/rules). -- Charles Plessy Tue, 07 Feb 2012 15:01:26 +0900 mummer (3.22~dfsg-2) unstable; urgency=low [ Andreas Tille ] * Make sure scripts will use the installation path instead of the temporary build path Closes: #575105 * Make real use of debian/sh-replacement-scripts and drop csh (build-)dependency * incremented Standards-Version to reflect concordance with Debian Policy 3.8.4 (no changes needed). * install tandem-repeat.awk which was lacking from installation previousely [ Charles Plessy ] * Updated upstream-metadata.yaml to use simple key=value form instead of BibTeX entry -- Andreas Tille Wed, 24 Mar 2010 17:10:43 +0000 mummer (3.22~dfsg-1) unstable; urgency=low * New upstream release: 3.22 - Significant 'dnadiff' bug fixes. - Unaligned contig output format switched to match show-diff format. - Dynamic memory allocation for run-mummer1. - Turned off output of the near useless .cluster files from nucmer and promer (let us know if you still want them). 3.21 - gcc compatibility fix. * debian/get-orig-source: rename mutilated upstream tarball. * debian/control: - incremented Standards-Version to reflect concordance with Debian Policy 3.8.3 (no changes needed). - mummer-docs depends on ${misc:Depends}. - dropped versionned dependencies when they are even satisfied in oldstable. - dropped dependency on CDBS and patchutils, and added dependency on quilt. - using Debhelper 7 (debian/compat). - build-depend on csh for correct interpreter path detection. * debian/patches: - replaces some Makefile patches by environment variables in debian/rules. - replaced 02at_scripts.diff by separate files in sh-replacement-scripts. - added a series file to use Quilt. - dropped the patch ‘01sm_src_tigr.diff’ that allowed to use MUMmer on computers with less that 512 Mo of memory and is now obsoleted by this release. - refreshed the 02at_docs_web.diff patch that redirects the links for the suppressed PDF files to the upstream website. * debian/rules converted to debhelper (the build system is too odd to be handled gently by CDBS without patches). * Mangled ‘~dfsg’ from the Debian version number in debian/watch. * Converted debian/copyright to a machine-readable format. * Documented the PDF deletion and the patching in ‘debian/README.source’. * Turned the get-orig-source shell script into a debian/rule target. * Added an experimental collection of upstream metadata in YAML format (debian/upstream-metadata.yaml). -- Charles Plessy Mon, 12 Oct 2009 18:12:18 +0900 mummer (3.20-3) unstable; urgency=low * Changed the doc-base section according to the new policy. * Added myself to the `Uploaders' field in `debian/control'. * Removed `debian/mummer.dirs', that was only creating empty directories. -- Charles Plessy Mon, 07 Jul 2008 10:33:20 +0900 mummer (3.20-2) unstable; urgency=low [ Charles Plessy ] * XS-DM-Upload-Allowed: Yes [ Steffen Moeller ] * Changed e-mail address in uploaders * Stripped long description of mummer-doc [ Andreas Tille ] * Do not install mummer.desktop because it is a command line application (Fixed debian/mummer.desktop anyway) * Standards-Version: 3.7.3 (no changes needed) -- Andreas Tille Thu, 10 Jan 2008 12:13:24 +0100 mummer (3.20-1) unstable; urgency=low * New upstream version * Fixed watch file (Thanks to Nelson A. de Oliveira ) Closes: #450211 * Do not autogenerate debian/control * debian/rules: get-orig-source target that removes non-free docs * debian/rules: Fixed building docs * Separated patches tigr and kurtz; better Makefile for scripts * Added manpage link for dnadiff and mentioned dnadiff in debian/mummer.1 * Used "Office" as main Freedesktop.Org category (not sure whether this is a really good choice) -- Andreas Tille Wed, 07 Nov 2007 13:25:34 +0100 mummer (3.19-1) unstable; urgency=low * Initial Release (Closes: Bug#201761). Thanks to Steffen Moeller who prepared a package for version 3.17 and just some cleanups were left. * New Standards-Version (no changes needed) * Switched to cdbs to simplify handling of patches * debian/compat: 5 -- Andreas Tille Mon, 07 May 2007 14:11:09 +0200 debian/mummer.10000644000000000000000000005105510716124621010560 0ustar .\" Hey, EMACS: -*- nroff -*- .\" First parameter, NAME, should be all caps .\" Second parameter, SECTION, should be 1-8, maybe w/ subsection .\" other parameters are allowed: see man(7), man(1) .TH MUMMER 1 "May 21, 2005" .\" Please adjust this date whenever revising the manpage. .\" .\" Some roff macros, for reference: .\" .nh disable hyphenation .\" .hy enable hyphenation .\" .ad l left justify .\" .ad b justify to both left and right margins .\" .nf disable filling .\" .fi enable filling .\" .br insert line break .\" .sp insert n+1 empty lines .\" for manpage-specific macros, see man(7) .SH NAME mummer \- package for sequence alignment of multiple genomes .SH SYNOPSIS .B mummer-annotate .RI .br .B combineMUMs .RI .br .B delta-filter .RI [options] .br .B dnadiff .RI [options] or .RI [options] -d .br .B exact-tandems .RI .br .B gaps .br .B mapview .RI [options] [UTR coords] [CDS coords] .br .B mgaps .RI [-d ] [-f ] [-l ] [-s ] .br .B mummer .RI [ options ] .br .B mummerplot .RI [options] .br .B nucmer .RI [options] .br .B nucmer2xfig .br .B promer .RI [options] .br .B repeat-match .RI [options] .br .B run-mummer1 .RI [-r] .br .B run-mummer3 .RI .br .B show-aligns .RI [options] .PP Input is the .delta output of either the "nucmer" or the "promer" program passed on the command line. .PP Output is to stdout, and consists of all the alignments between the query and reference sequences identified on the command line. .PP NOTE: No sorting is done by default, therefore the alignments will be ordered as found in the input. .br .B show-coords .RI [options] .br .B show-snps .RI [options] .br .B show-tiling .RI [options] .br .SH DESCRIPTION .SH OPTIONS All tools (exept for gaps) obey to the -h, --help, -V and --version options as one would expect. This help is excellent and makes these man pages basically obsolete. .br .B combineMUMs Combines MUMs in by extending matches off ends and between MUMs. is a fasta file of the reference sequence. is a multi-fasta file of the sequences matched against the reference .PP -D Only output to stdout the difference positions and characters -n Allow matches only between nucleotides, i.e., ACGTs -N num Break matches at or more consecutive non-ACGTs -q tag Used to label query match -r tag Used to label reference match -S Output all differences in strings -t Label query matches with query fasta header -v num Set verbose level for extra output -W file Reset the default output filename witherrors.gaps -x Don't output .cover files -e Set error-rate cutoff to e (e.g. 0.02 is two percent) .br .B dnadiff Run comparative analysis of two sequence sets using nucmer and its associated utilities with recommended parameters. See MUMmer documentation for a more detailed description of the output. Produces the following output files: .PP .report - Summary of alignments, differences and SNPs .delta - Standard nucmer alignment output .1delta - 1-to-1 alignment from delta-filter -1 .mdelta - M-to-M alignment from delta-filter -m .1coords - 1-to-1 coordinates from show-coords -THrcl .1delta .mcoords - M-to-M coordinates from show-coords -THrcl .mdelta .snps - SNPs from show-snps -rlTHC .1delta .rdiff - Classified ref breakpoints from show-diff -rH .mdelta .qdiff - Classified qry breakpoints from show-diff -qH .mdelta .unref - Unaligned reference IDs and lengths (if applicable) .unqry - Unaligned query IDs and lengths (if applicable) .PP MANDATORY: reference Set the input reference multi-FASTA filename query Set the input query multi-FASTA filename or delta file Unfiltered .delta alignment file from nucmer .PP OPTIONS: -d|delta Provide precomputed delta file for analysis -h --help Display help information and exit -p|prefix Set the prefix of the output files (default "out") -V --version Display the version information and exit .br .B delta-filter -e float For switches -g -r -q, keep repeats within e percent of the best LIS score [0, 100], no repeats by default -g Global alignment using length*identity weighted LIS. For every reference-query pair, leave only the aligns which form the longest mutually consistent set -h Display help information -i float Set the minimum alignment identity [0, 100], default 0 -l int Set the minimum alignment length, default 0 -q Query alignment using length*identity weighted LIS. For each query, leave only the aligns which form the longest consistent set for the query -r Reference alignment using length*identity weighted LIS. For each reference, leave only the aligns which form the longest consistent set for the reference -u float Set the minimum alignment uniqueness, i.e. percent of the alignment matching to unique reference AND query sequence [0, 100], default 0 -o float Set the maximum alignment overlap for -r and -q options as a percent of the alignment length [0, 100], default 100 .PP Reads a delta alignment file from either nucmer or promer and filters the alignments based on the command-line switches, leaving only the desired alignments which are output to stdout in the same delta format as the input. For multiple switches, order of operations is as follows: -i -l -u -q -r -g. If an alignment is excluded by a preceding operation, it will be ignored by the succeeding operations .PP An important distinction between the -g option and the -r -q options is that -g requires the alignments to be mutually consistent in their order, while the -r -q options are not required to be mutually consistent and therefore tolerate translocations, inversions, etc. Thus, -r provides a one-to-many, -q a many-to-one, -r -q a one-to-one local mapping, and -g a one-to-one global mapping of reference and query bases respectively. .br .B mapview .br -h .br --help Display help information and exit .br -m|mag Set the magnification at which the figure is rendered, this is an option for fig2dev which is used to generate the PDF and PS files (default 1.0) .br -n|num Set the number of output files used to partition the output, this is to avoid generating files that are too large to display (default 10) .br -p|prefix Set the output file prefix (default "PROMER_graph or NUCMER_graph") .br -v --verbose Verbose logging of the processed files .br -V --version Display the version information and exit .br -x1 coord Set the lower coordinate bound of the display .br -x2 coord Set the upper coordinate bound of the display .br -g|ref If the input file is provided by 'mgaps', set the reference sequence ID (as it appears in the first column of the UTR/CDS coords file) .br -I Display the name of query sequences .br -Ir Display the name of reference genes .br .B mummer Find and output (to stdout) the positions and length of all sufficiently long maximal matches of a substring in and -mum compute maximal matches that are unique in both sequences -mumcand same as -mumreference -mumreference compute maximal matches that are unique in the reference-sequence but not necessarily in the query-sequence (default) -maxmatch compute all maximal matches regardless of their uniqueness -n match only the characters a, c, g, or t they can be in upper or in lower case -l set the minimum length of a match if not set, the default value is 20 -b compute forward and reverse complement matches -r only compute reverse complement matches -s show the matching substrings -c report the query-position of a reverse complement match relative to the original query sequence -F force 4 column output format regardless of the number of reference sequence inputs -L show the length of the query sequences on the header line .br .B nuncmer nucmer generates nucleotide alignments between two mutli-FASTA input files. Two output files are generated. The .cluster output file lists clusters of matches between each sequence. The .delta file lists the distance between insertions and deletions that produce maximal scoring alignments between each sequence. .I MANDATORY: Reference Set the input reference multi-FASTA filename Query Set the input query multi-FASTA filename --mum Use anchor matches that are unique in both the reference and query --mumcand Same as --mumreference --mumreference Use anchor matches that are unique in in the reference but not necessarily unique in the query (default behavior) --maxmatch Use all anchor matches regardless of their uniqueness -b|breaklen Set the distance an alignment extension will attempt to extend poor scoring regions before giving up (default 200) -c|mincluster Sets the minimum length of a cluster of matches (default 65) --[no]delta Toggle the creation of the delta file (default --delta) --depend Print the dependency information and exit -d|diagfactor Set the clustering diagonal difference separation factor (default 0.12) --[no]extend Toggle the cluster extension step (default --extend) -f --forward Use only the forward strand of the Query sequences -g|maxgap Set the maximum gap between two adjacent matches in a cluster (default 90) -h --help Display help information and exit -l|minmatch Set the minimum length of a single match (default 20) -o --coords Automatically generate the original NUCmer1.1 coords output file using the 'show-coords' program --[no]optimize Toggle alignment score optimization, i.e. if an alignment extension reaches the end of a sequence, it will backtrack to optimize the alignment score instead of terminating the alignment at the end of the sequence (default --optimize) -p|prefix Set the prefix of the output files (default "out") -r --reverse Use only the reverse complement of the Query sequences --[no]simplify Simplify alignments by removing shadowed clusters. Turn this option off if aligning a sequence to itself to look for repeats (default --simplify) .br .B promer promer generates amino acid alignments between two mutli-FASTA DNA input files. Two output files are generated. The .cluster output file lists clusters of matches between each sequence. The .delta file lists the distance between insertions and deletions that produce maximal scoring alignments between each sequence. The DNA input is translated into all 6 reading frames in order to generate the output, but the output coordinates reference the original DNA input. .I MANDATORY: Reference Set the input reference multi-FASTA DNA file Query Set the input query multi-FASTA DNA file --mum Use anchor matches that are unique in both the reference and query --mumcand Same as --mumreference --mumreference Use anchor matches that are unique in in the reference but not necessarily unique in the query (default behavior) --maxmatch Use all anchor matches regardless of their uniqueness -b|breaklen Set the distance an alignment extension will attempt to extend poor scoring regions before giving up, measured in amino acids (default 60) -c|mincluster Sets the minimum length of a cluster of matches, measured in amino acids (default 20) --[no]delta Toggle the creation of the delta file (default --delta) --depend Print the dependency information and exit -d|diagfactor Set the clustering diagonal difference separation factor (default .11) --[no]extend Toggle the cluster extension step (default --extend) -g|maxgap Set the maximum gap between two adjacent matches in a cluster, measured in amino acids (default 30) -l|minmatch Set the minimum length of a single match, measured in amino acids (default 6) -m|masklen Set the maximum bookend masking lenth, measured in amino acids (default 8) -o --coords Automatically generate the original PROmer1.1 ".coords" output file using the "show-coords" program --[no]optimize Toggle alignment score optimization, i.e. if an alignment extension reaches the end of a sequence, it will backtrack to optimize the alignment score instead of terminating the alignment at the end of the sequence (default --optimize) -p|prefix Set the prefix of the output files (default "out") -x|matrix Set the alignment matrix number to 1 [BLOSUM 45], 2 [BLOSUM 62] or 3 [BLOSUM 80] (default 2) .br .B repeat-match Find all maximal exact matches in -E Use exhaustive (slow) search to find matches -f Forward strand only, don't use reverse complement -n # Set minimum exact match length to # -t Only output tandem repeats -V # Set level of verbose (debugging) printing to # .br .B show-aligns -h Display help information -q Sort alignments by the query start coordinate -r Sort alignments by the reference start coordinate -w int Set the screen width - default is 60 -x int Set the matrix type - default is 2 (BLOSUM 62), other options include 1 (BLOSUM 45) and 3 (BLOSUM 80) note: only has effect on amino acid alignments .br .B show-coords -b Merges overlapping alignments regardless of match dir or frame and does not display any idenitity information. -B Switch output to btab format -c Include percent coverage information in the output -d Display the alignment direction in the additional FRM columns (default for promer) -g Deprecated option. Please use 'delta-filter' instead -h Display help information -H Do not print the output header -I float Set minimum percent identity to display -k Knockout (do not display) alignments that overlap another alignment in a different frame by more than 50% of their length, AND have a smaller percent similarity or are less than 75% of the size of the other alignment (promer only) -l Include the sequence length information in the output -L long Set minimum alignment length to display -o Annotate maximal alignments between two sequences, i.e. overlaps between reference and query sequences -q Sort output lines by query IDs and coordinates -r Sort output lines by reference IDs and coordinates -T Switch output to tab-delimited format Input is the .delta output of either the "nucmer" or the "promer" program passed on the command line. .PP Output is to stdout, and consists of a list of coordinates, percent identity, and other useful information regarding the alignment data contained in the .delta file used as input. .PP NOTE: No sorting is done by default, therefore the alignments will be ordered as found in the input. .br .B show-snps -C Do not report SNPs from alignments with an ambiguous mapping, i.e. only report SNPs where the [R] and [Q] columns equal 0 and do not output these columns -h Display help information -H Do not print the output header -I Do not report indels -l Include sequence length information in the output -q Sort output lines by query IDs and SNP positions -r Sort output lines by reference IDs and SNP positions -S Specify which alignments to report by passing 'show-coords' lines to stdin -T Switch to tab-delimited format -x int Include x characters of surrounding SNP context in the output, default 0 Input is the .delta output of either the nucmer or promer program passed on the command line. .PP Output is to stdout, and consists of a list of SNPs (or amino acid substitutions for promer) with positions and other useful info. Output will be sorted with -r by default and the [BUFF] column will always refer to the sequence whose positions have been sorted. This value specifies the distance from this SNP to the nearest mismatch (end of alignment, indel, SNP, etc) in the same alignment, while the [DIST] column specifies the distance from this SNP to the nearest sequence end. SNPs for which the [R] and [Q] columns are greater than 0 should be evaluated with caution, as these columns specify the number of other alignments which overlap this position. Use -C to assure SNPs are only reported from unique alignment regions. .B show-tiling -a Describe the tiling path by printing the tab-delimited alignment region coordinates to stdout -c Assume the reference sequences are circular, and allow tiled contigs to span the origin -g int Set maximum gap between clustered alignments [-1, INT_MAX] A value of -1 will represent infinity (nucmer default = 1000) (promer default = -1) -i float Set minimum percent identity to tile [0.0, 100.0] (nucmer default = 90.0) (promer default = 55.0) -l int Set minimum length contig to report [-1, INT_MAX] A value of -1 will represent infinity (common default = 1) -p file Output a pseudo molecule of the query contigs to 'file' -R Deal with repetitive contigs by randomly placing them in one of their copy locations (implies -V 0) -t file Output a TIGR style contig list of each query sequence that sufficiently matches the reference (non-circular) -u file Output the tab-delimited alignment region coordinates of the unusable contigs to 'file' -v float Set minimum contig coverage to tile [0.0, 100.0] (nucmer default = 95.0) sum of individual alignments (promer default = 50.0) extent of syntenic region -V float Set minimum contig coverage difference [0.0, 100.0] i.e. the difference needed to determine one alignment is 'better' than another alignment (nucmer default = 10.0) sum of individual alignments (promer default = 30.0) extent of syntenic region -x Describe the tiling path by printing the XML contig linking information to stdout Input is the .delta output of the nucmer program, run on very similar sequence data, or the .delta output of the promer program, run on divergent sequence data. .PP Output is to stdout, and consists of the predicted location of each aligning query contig as mapped to the reference sequences. These coordinates reference the extent of the entire query contig, even when only a certain percentage of the contig was actually aligned (unless the -a option is used). Columns are, start in ref, end in ref, distance to next contig, length of this contig, alignment coverage, identity, orientation, and ID respectively. .SH SEE ALSO .BR http://mummer.sourceforge.net/ .br .PP Open source MUMmer 3.0 is described in .br .I "Versatile and open software for comparing large genomes." S. Kurtz, A. Phillippy, A.L. Delcher, M. Smoot, M. Shumway, C. Antonescu, and S.L. Salzberg, Genome Biology (2004), 5:R12. .SH AUTHOR mummer was written by S. Kurtz, A. Phillippy, A.L. Delcher, M. Smoot, M. Shumway, C. Antonescu, and S.L. Salzberg. debian/sh-replacement-scripts/0000755000000000000000000000000011714137124013563 5ustar debian/sh-replacement-scripts/run-mummer30000644000000000000000000000213311352502570015673 0ustar #!/bin/sh -e # # for running the basic mummer 3 suite, should use nucmer instead when possible # to avoid the confusing reverse coordinate system of the raw programs. # # NOTE: be warned that all reverse matches will then # be relative to the reverse complement of the query sequence. # # Edit this script as necessary to alter the matching and clustering values # usage () { echo "Usage: `basename $0` " return 67 # EX_USAGE } if [ $# -ne 3 ] ; then echo "You provided $# arguments." usage fi ref="$1" qry="$2" pfx="$3" bindir=/usr/bin if [ ! -e "$ref" ] ; then echo "File for fasta reference $ref does not exist." usage fi if [ ! -e "$qry" ] ; then echo "File for fasta query $qry does not exist." usage fi if [ "$pfx" = "" ] ; then usage fi echo "Find MUMs" $bindir/mummer -mumreference -b -l 20 "$ref" "$qry" > "$pfx".out echo "Determine gaps" $bindir/mgaps -l 100 -f .12 -s 600 < "$pfx".out > "$pfx".gaps echo "Align gaps" $bindir/combineMUMs -x -e .10 -W "$pfx".errorsgaps "$ref" "$qry" "$pfx".gaps > "$pfx".align debian/sh-replacement-scripts/exact-tandems0000644000000000000000000000137611352502570016251 0ustar #!/bin/sh -e # # Find exact tandem repeats in specified file involving an # exact duplicate of at least the specified length usage () { echo "Usage: `basename $0` " return 67 # EX_USAGE } if [ $# -ne 2 ] ; then echo "You provided $# arguments instead of 2." usage fi filename="$1" matchlen="$2" bindir=/usr/bin scriptdir=/usr/lib/mummer if [ ! -e "$filename" ] ; then echo "File $filename does not exist." usage fi echo "Finding matches" $bindir/repeat-match -t -n $matchlen "$filename" | tail +3 > $$.tmp.matches # This is default behavior when shell started with -e # if ($status != 0) exit -1 echo "Tandem repeats" sort -k1n -k2n $$.tmp.matches | awk -f $ $scriptdir/tandem-repeat.awk rm -f $$.tmp.matches debian/sh-replacement-scripts/run-mummer10000644000000000000000000000172511352502570015677 0ustar #!/bin/sh -e # # **SEVERELY** antiquated script for running the mummer 1 suite # -r option reverse complements the query sequence, coordinates of the reverse # matches will be relative to the reversed sequence # usage () { echo "Usage: `basename $0` [-r]" return 67 # EX_USAGE } if [ $# -ne 3 -a $# -ne 4 ] ; then echo "You provided $# arguments." usage fi ref="$1" qry="$2" pfx="$3" rev="$4" bindir=/usr/bin if [ ! -e "$ref" ] ; then echo "File for fasta reference $ref does not exist." usage fi if [ ! -e "$qry" ] ; then echo "File for fasta query $qry does not exist." usage fi if [ "$pfx" = "" ] ; then usage fi echo "Find MUMs" $bindir/mummer -mum -l 20 "$rev" "$ref" "$qry" | tail +2 > "$pfx".out echo "Determine gaps" $bindir/gaps "$ref" "$rev" < "$pfx".out > "$pfx".gaps echo "Align gaps" $bindir/mummer-annotate "$pfx".gaps "$qry" > "$pfx".align mv witherrors.gaps "$pfx".errorsgaps debian/mummer.docs0000644000000000000000000000003010714420714011333 0ustar README ACKNOWLEDGEMENTS debian/compat0000644000000000000000000000000211744617153010375 0ustar 9 debian/control0000644000000000000000000000322111744620204010567 0ustar Source: mummer Section: science Priority: optional Maintainer: Debian Med Packaging Team DM-Upload-Allowed: yes Uploaders: Steffen Moeller , Andreas Tille , Charles Plessy Build-Depends: debhelper (>= 9), texlive-latex-base, texlive-latex-recommended, texlive-fonts-recommended Standards-Version: 3.9.3 Homepage: http://mummer.sourceforge.net/ Vcs-Browser: http://svn.debian.org/wsvn/debian-med/trunk/packages/mummer/trunk/ Vcs-Svn: svn://svn.debian.org/debian-med/trunk/packages/mummer/trunk/ Package: mummer Architecture: any Depends: ${shlibs:Depends}, ${misc:Depends}, perl, gawk Description: Efficient sequence alignment of full genomes MUMmer is a system for rapidly aligning entire genomes, whether in complete or draft form. For example, MUMmer 3.0 can find all 20-basepair or longer exact matches between a pair of 5-megabase genomes in 13.7 seconds, using 78 MB of memory, on a 2.4 GHz Linux desktop computer. MUMmer can also align incomplete genomes; it handles the 100s or 1000s of contigs from a shotgun sequencing project with ease, and will align them to another set of contigs or a genome using the NUCmer program included with the system. If the species are too divergent for DNA sequence alignment to detect similarity, then the PROmer program can generate alignments based upon the six-frame translations of both input sequences. Package: mummer-doc Architecture: all Section: doc Depends: ${misc:Depends} Description: Documentation for MUMmer This package contains the documentation for MUMmer, a system for rapidly aligning entire genomes.