Commit 03c2142d3fc56550c4c0c61e3ed59f24491a017c - vmatch

New upstream version 2.3.0+dfsg Sascha Steinbiss 4 years ago

20 changed file(s) with 0 addition(s) and 5709 deletion(s). Raw diff Collapse all Expand all

-1

~~src/doc/WWW/.gitignore~~ less more

vmweb.pdf

-660

~~src/doc/WWW/.ispell_american~~ less more

0		EMBL
1		Fasta
2		Genbank
3		Gzipped
4		Kurtz
5		SWISSPROT
6		Vmatch
7		postprocessing
8		pt
9		AtGDB
10		barleypop
11		biophys
12		cDNA
13		dataflow
14		Dataflowfig
15		DJ
16		duesseldorf
17		edu
18		Fernandes
19		Gbp
20		GCB
21		genalyzer
22		GeneChip
23		genomic
24		gif
25		GL
26		html
27		hypa
28		iastate
29		img
30		matchgraph
31		mga
32		oligo
33		patternsearch
34		PatternSearch
35		pdf
36		PDF
37		php
38		PlantGDB
39		possumsearch
40		PossumSearch
41		RescueMu
42		RSA
43		rsat
44		splicenest
45		transposons
46		virtman
47		vmatchlic
48		vmweb
49		vrac
50		Walbot
51		Xenopus
52		zmdb
53		ac
54		AMD
55		Arabidopsis
56		BarleyBase
57		bibiserv
58		bielefeld
59		Bioinformatics
60		biotools
61		cgi
62		commolbio
63		Debian
64		ESTs
65		GenBank
66		hamburg
67		Helden
68		http
69		HyPa
70		KPATH
71		kurtz
72		latexonly
73		mkvtree
74		molgen
75		mpg
76		Multimat
77		oligos
78		org
79		OSX
80		pl
81		plantgdb
82		PowerPC
83		Promide
84		Rahmann
85		Redhat
86		reputer
87		REPuter
88		Sparc
89		SpliceNest
90		src
91		SuSe
92		Sven
93		techfak
94		thaliana
95		ulb
96		vmatch
97		www
98		zbh
99		Zea
100		ASRP
101		GSSanalysis
102		laevis
103		meningioma
104		microarray
105		micromatches
106		miRNA
107		mRNA
108		mutransposon
109		Transposon
110		ABR
111		AKA
112		ALI
113		ALT
114		ALV
115		AME
116		ANG
117		AQU
118		ARN
119		Affymetrix
120		Agave
121		Apr
122		Aureobasidium
123		Azadirachta
124		BAI
125		BAL
126		BEC
127		BEH
128		BEI
129		BEL
130		BER
131		BLA
132		BLI
133		BLO
134		BOD
135		BOH
136		BOR
137		BOU
138		BOV
139		BRE
140		BRI
141		BRO
142		BRU
143		BUC
144		BUE
145		BioExtract
146		Biopieces
147		BlastP
148		CAS
149		CAV
150		CEV
151		CHA
152		CHAU
153		CHE
154		CHI
155		CHO
156		CHOU
157		CHU
158		CLA
159		CLO
160		COH
161		COL
162		CRISPRFinder
163		CRISPRdatabase
164		CRISPRfinder
165		CRISPRs
166		CRO
167		CUL
168		Chlorophyceae
169		Chs
170		CrossLink
171		Cscript
172		CurrentUsage
173		DAR
174		DAS
175		DAV
176		DEA
177		DEE
178		DES
179		DEZ
180		DHA
181		DIBO
182		DIC
183		DIJ
184		DNAVis
185		DOL
186		DOO
187		DOR
188		DUC
189		DUM
190		DUR
191		EBR
192		EIS
193		ELD
194		ELL
195		ENG
196		ERI
197		EST
198		Ecoli
199		FANTOM
200		FAU
201		FER
202		FESCH
203		FIC
204		FIE
205		FLE
206		FOF
207		FOS
208		FRE
209		Floydiella
210		Frankia
211		GAE
212		GAO
213		GAR
214		GAU
215		GEN
216		GEO
217		GER
218		GES
219		GEY
220		GIE
221		GLA
222		GLAE
223		GNF
224		GNI
225		GOL
226		GOM
227		GON
228		GOS
229		GRAE
230		GRE
231		GRI
232		GRO
233		GRU
234		GU
235		GUA
236		Genome
237		GenomeThreader
238		Gepard
239		GmbH
240		Graminella
241		HAA
242		HAB
243		HAC
244		HAK
245		HAN
246		HAR
247		HAU
248		HAZ
249		HEA
250		HED
251		HEL
252		HEP
253		HES
254		HIL
255		HIN
256		HLE
257		HOEH
258		HOF
259		HOL
260		HOM
261		HOR
262		HRI
263		HRV
264		HUL
265		HUR
266		HUS
267		HYS
268		HYT
269		Heliothis
270		IKE
271		IMM
272		Illumina
273		JAC
274		JAI
275		JEN
276		JI
277		JOH
278		JOR
279		JOU
280		KAE
281		KAM
282		KAN
283		KAR
284		KAT
285		KAW
286		KEM
287		KER
288		KEV
289		KHA
290		KLE
291		KNA
292		KOE
293		KOEN
294		KOG
295		KOL
296		KON
297		KOP
298		KOS
299		KOU
300		KOZ
301		KRI
302		KRO
303		KRU
304		KRUE
305		KUB
306		KUC
307		KUD
308		KUG
309		KUM
310		KUR
311		LAL
312		LAM
313		LAR
314		LAU
315		LAZ
316		LBNL
317		LEA
318		LEM
319		LER
320		LI
321		LIA
322		LIN
323		LIU
324		LOEW
325		LOM
326		LOR
327		LScSA
328		LU
329		LUO
330		LUS
331		Leptosira
332		MAA
333		MAL
334		MCC
335		MCL
336		MCM
337		MEH
338		MER
339		MEY
340		MIC
341		MIN
342		MIPSPlantsDB
343		MOC
344		MOE
345		MOH
346		MOL
347		MOR
348		MUL
349		MYE
350		Macronuclear
351		Maize
352		MicroRNAs
353		Mu
354		Myotis
355		NAI
356		NAO
357		NAR
358		NEL
359		NIC
360		NOU
361		NOV
362		NUR
363		NUS
364		NYG
365		Neochloris
366		OHL
367		OKA
368		OSS
369		OTI
370		OTT
371		PAU
372		PAV
373		PEC
374		PEE
375		PEL
376		PFE
377		PLE
378		PLEXdb
379		POB
380		POM
381		POU
382		PRI
383		Piwik
384		PriMUX
385		ProbeMatch
386		QPALMA
387		RAD
388		RAH
389		REE
390		REH
391		REI
392		REN
393		RIN
394		RIS
395		RIV
396		RNA
397		RNAi
398		RNAseq
399		ROS
400		RT
401		RefSeq
402		Rnnotator
403		SAF
404		SAK
405		SAR
406		SCHAA
407		SCHAEF
408		SCHAR
409		SCHAT
410		SCHEL
411		SCHIJ
412		SCHIL
413		SCHLE
414		SCHLU
415		SCHLUE
416		SCHMU
417		SCHNE
418		SCHOE
419		SCHOF
420		SCHOL
421		SCHOO
422		SCHRO
423		SCHUL
424		SCHWA
425		SCHWE
426		SCO
427		SCZ
428		SEG
429		SEI
430		SEK
431		SEV
432		SHA
433		SHI
434		SHU
435		SIE
436		SIM
437		SIMAP
438		SLE
439		SLO
440		SMA
441		SMI
442		SMY
443		SNY
444		SOE
445		SOU
446		SPA
447		SPI
448		STE
449		STEI
450		STEU
451		STO
452		STR
453		STU
454		SU
455		SUL
456		SZY
457		Schwab
458		Seidel
459		Shewanella
460		Silva
461		Slezak
462		Spirodela
463		Stefan
464		Streptococcaceae
465		TAC
466		TAF
467		TAK
468		TAL
469		TAY
470		TEM
471		THA
472		THI
473		TIK
474		TIR
475		TIS
476		TOL
477		TOR
478		TOU
479		TRI
480		TRO
481		TRU
482		TSA
483		TSU
484		TT
485		TUR
486		Tembe
487		Tetrahymena
488		Thellungiella
489		UDE
490		UPA
491		URA
492		UST
493		Univ
494		VAI
495		VAL
496		VAS
497		VAU
498		VEL
499		VER
500		VHA
501		VIN
502		VIT
503		VIV
504		VLA
505		VMatchForArabidopsis
506		VOI
507		VOS
508		VOSS
509		VRA
510		WAL
511		WEI
512		WES
513		WHA
514		WHE
515		WIC
516		WIE
517		WIL
518		WIS
519		WOD
520		WOL
521		WOR
522		WRE
523		WU
524		XU
525		Xanthomonas
526		YAN
527		YU
528		YUN
529		ZAJ
530		ZAL
531		ZAV
532		ZEM
533		ZHA
534		ZHE
535		ZHO
536		ZHU
537		ZIM
538		ZIN
539		aRNH
540		ab
541		al
542		alt
543		articlerender
544		artid
545		biomoby
546		biopieces
547		bp
548		budworm
549		cand
550		chromosomal
551		chromosome
552		chromosomes
553		colorlinks
554		com
555		contigs
556		crispr
557		crosslink
558		daytrial
559		de
560		div
561		dnavis
562		doc
563		enableLinkTracking
564		endophytes
565		epichloid
566		exome
567		exon
568		fcgi
569		fescue
570		fr
571		genmome
572		genome
573		genomes
574		genomethreader
575		getTracker
576		goltsman
577		gov
578		gsf
579		href
580		ht
581		https
582		idsite
583		indels
584		indica
585		informatik
586		interspaced
587		isotigs
588		javascript
589		jgi
590		js
591		li
592		linkcolor
593		llnl
594		lscsa
595		ltr
596		lucifugus
597		mailto
598		maize
599		meliloti
600		mer
601		mers
602		metagenome
603		metagenomes
604		miRNAs
605		microalgae
606		mips
607		mircoRNA
608		mitochondrial
609		ncRNAs
610		nigrifrons
611		nih
612		nl
613		noscript
614		novo
615		oleoabundans
616		oneidensis
617		oryzae
618		parvula
619		pesticidal
620		pigeonpea
621		piwik
622		piwikTracker
623		pkBaseURL
624		plastid
625		polyrhiza
626		preprocess
627		prj
628		probeBase
629		proteome
630		psud
631		pubmedcentral
632		pullulans
633		retroviruses
634		rnafolding
635		seq
636		siRNA
637		simap
638		sp
639		str
640		subfamilies
641		terrestris
642		tex
643		thermophila
644		tigr
645		trackPageView
646		transcriptional
647		transcriptome
648		trialbox
649		tue
650		tuebingen
651		ul
652		unescape
653		uni
654		var
655		virescens
656		weigelworld
657		wiki
658		wmd
659		zenlicensemanager

-19

~~src/doc/WWW/Dataflowfig.tex~~ less more

0		\documentclass[11pt]{article}
1		\usepackage{a4wide}
2		\pagestyle{empty}
3		\begin{document}
4		\input{Dataflow.inc}
5
6		\noindent The dataflow in \emph{Vmatch}.
7		The programs
8		are shown in ellipses. The inputs are the database
9		and the query sequences and the alphabet transformation,
10		represented by rectangles. At the center of all
11		computations the persistent index is shown. All other
12		rectangles represent the different kinds of output.
13
14		\begin{center}
15		\centerline{\box\graph}
16		\end{center}
17
18		\end{document}

-99

~~src/doc/WWW/Makefile~~ less more

0		vmwebfiles=Dataflowfig.pdf\
1		AboKurOhl2004.pdf\
2		AboKurOhl2002.pdf\
3		BreKurWal2002.pdf\
4		ChoSchleKurGie2004.pdf\
5		FitGarKucKurMyeOttSleVitZemMcc2002.pdf\
6		KurChoOhlSchleStoGie2001.pdf\
7		HoehKurOhl2002.pdf\
8		GraeStrKurSte2001.pdf\
9		BecStroHomGieKur2004.pdf\
10		KrueSczKurGie2004.pdf\
11		virtman.pdf
12
13		PAPERS=${WORK}/archive-etc/own-papers
14
15		SERVER=vmatchserver
16		WWWBASEDIR=/var/www/html
17
18		all:vmweb.pdf vmweb.tgz
19
20		vmweb.pdf:vmweb.tex introduction.inc
21		latexmk vmweb
22
23		introduction.inc:../virtman.tex introexclude
24		extractpart.pl introduction ../virtman.tex \|\
25		grep -v -f introexclude \|\
26		sed -e 's/\\subsection\{The parts/\\section{The parts/' \| \
27		perl -pe 's/\\cite{ABO:KUR:OHL:2004}\.\%\%second/(Abouelhoda, Kurtz, Ohlebusch 2004)./' \| \
28		perl -pe 's/\\cite{(.*)}[\.,]?/\n\\bibentry{\1}\n/' > $@
29
30		Dataflow.inc:../Dataflow.pic
31		pic -t ../Dataflow.pic > $@
32
33		index.html:vmweb.tex vmweb.pdf introduction.inc replace-header.rb replace-par.rb
34		htlatex vmweb.tex "xhtml, charset=utf-8" " -cunihtf -utf8"
35		cat vmweb.html \| replace-header.rb \| \
36		replace-par.rb \| \
37		sed -e 's/CONTENT=/content=/' \
38		-e 's/ALT=/alt=/' > $@
39
40		validate:index.html xhtml-lat1.ent xhtml-symbol.ent xhtml-special.ent xhtml1-transitional.dtd
41		cat index.html \| sed -e 's/\"http:\/\/www.w3.org\/TR\/xhtml1\/DTD\//\"/' > .tmp.html
42		xmllint --valid --noout .tmp.html
43		rm -f .tmp.html
44
45		# also run validation on https://validator.w3.org/
46
47		Dataflowfig.dvi:Dataflowfig.tex Dataflow.inc
48		latex Dataflowfig.tex
49
50		Dataflowfig.pdf:Dataflowfig.dvi
51		dvipdf $<
52
53		vmweb.tgz:matchgraph.gif ${vmwebfiles} index.html vmweb.pdf
54		tar -cvzf $@ matchgraph.gif ${vmwebfiles} index.html vmweb.pdf
55
56		virtman.pdf:
57		cp ../virtman.pdf .
58
59		AboKurOhl2004.pdf:
60		cp ${PAPERS}/$@ .
61
62		AboKurOhl2002.pdf:
63		cp ${PAPERS}/$@ .
64
65		BreKurWal2002.pdf:
66		cp ${PAPERS}/$@ .
67
68		ChoSchleKurGie2004.pdf:
69		cp ${PAPERS}/$@ .
70
71		FitGarKucKurMyeOttSleVitZemMcc2002.pdf:
72		cp ${PAPERS}/$@ .
73
74		KurChoOhlSchleStoGie2001.pdf:
75		cp ${PAPERS}/$@ .
76
77		HoehKurOhl2002.pdf:
78		cp ${PAPERS}/$@ .
79
80		GraeStrKurSte2001.pdf:
81		cp ${PAPERS}/$@ .
82
83		KrueSczKurGie2004.pdf:
84		cp ${PAPERS}/$@ .
85
86		BecStroHomGieKur2004.pdf:
87		cp ${PAPERS}/$@ .
88
89		installwww:
90		rsync -rv index.html vmweb.css download.html virtman.pdf vmweb.pdf matchgraph.gif distributions $(SERVER):$(WWWBASEDIR)
91
92		clean:
93		rm -f .toc .ilg .out .idx .ind .dvi .ps .log *.aux
94		rm -f .bbl .blg
95		rm -f vmweb.4ct vmweb.xref vmweb.tmp vmweb.lg vmweb.idv vmweb.html vmweb.4tc vmweb.fls vmweb.fdb_latexmk
96		rm -f comment.cut introduction.inc
97		rm -f Dataflow.inc
98		rm -f ${vmwebfiles}

-1

~~src/doc/WWW/PUSH-cmd.txt~~ less more

git push kurtz@genometools.org:/home/kurtz/lscsa/vstree.git sk

-53

~~src/doc/WWW/download.html~~ less more

0		<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
1		<html>
2
3		<head>
4		<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1">
5		<title>Download Vmatch</title>
6		<link rel="stylesheet" type="text/css" href="vmweb.css">
7		</head>
8
9		<body>
10
11		<h1>Download <i>Vmatch</i></h1>
12
13		<p>
14		By downloading Vmatch you agree to the following:
15		</p>
16
17		<p>
18		<code>
19		Vmatch is provided on an <strong>AS IS</strong> basis. The developers do not warrant its validity
20		of performance, efficiency, or suitability, nor do they warrant that Vmatch is
21		free from errors. All warranties, including without limitation, any warranty or
22		merchantability or fitness for a particular purpose, are hereby excluded.
23		</code>
24		</p>
25
26		<h2>Linux</h2>
27		<a href="distributions/vmatch-2.3.0-Linux_x86_64-64bit.tar.gz">vmatch-2.3.0-Linux_x86_64-64bit.tar.gz</a> (2017-06-12)<br/>
28		<a href="distributions/vmatch-2.3.0-Linux_i386-32bit.tar.gz">vmatch-2.3.0-Linux_i386-32bit.tar.gz</a> (2017-06-12)<br/>
29
30		<h2>Mac OS</h2>
31		<a href="distributions/vmatch-2.3.0-Darwin_i386-64bit.tar.gz">vmatch-2.3.0-Darwin_i386-64bit.tar.gz</a> (2017-06-12)<br/>
32		<a href="distributions/vmatch-2.3.0-Darwin_i386-32bit.tar.gz">vmatch-2.3.0-Darwin_i386-32bit.tar.gz</a> (2017-06-12)<br/>
33
34		<h2>Windows</h2>
35		<a href="distributions/vmatch-2.3.0-Windows_i686-64bit.zip">vmatch-2.3.0-Windows_i686-64bit.zip</a> (2017-06-12)<br/>
36		<a href="distributions/vmatch-2.3.0-Windows_i686-32bit.zip">vmatch-2.3.0-Windows_i686-32bit.zip</a> (2017-06-12)<br/>
37
38		<!-- Piwik -->
39		<script type="text/javascript">
40		var pkBaseURL = "https://zenlicensemanager.com/piwik/";
41		document.write(unescape("%3Cscript src='" + pkBaseURL + "piwik.js' type='text/javascript'%3E%3C/script%3E"));
42		</script><script type="text/javascript">
43		try {
44		var piwikTracker = Piwik.getTracker(pkBaseURL + "piwik.php", 3);
45		piwikTracker.trackPageView();
46		piwikTracker.enableLinkTracking();
47		} catch( err ) {}
48		</script><noscript><p><img src="https://zenlicensemanager.com/piwik/piwik.php?idsite=3" style="border:0" alt="" /></p></noscript>
49		<!-- End Piwik Tracking Tag -->
50
51		</body>
52		</html>

-85

~~src/doc/WWW/extractpart.pl~~ less more

0		#!/usr/bin/env perl
1
2		# select a list of options from a documentation
3
4		use strict;
5		use warnings;
6
7		my $numofargs = scalar @ARGV;
8
9		if($numofargs le 1)
10		{
11		print STDERR "Usage: $0 <tags to be selected> <filename>\n";
12		exit 1;
13		}
14
15		my(%tagtab) = ();
16
17		my $filename = $ARGV[$numofargs-1];
18
19		for(my $i=0; $i<$numofargs-1; $i++)
20		{
21		my $key = $ARGV[$i];
22		$tagtab{$key} = 1;
23		}
24
25		# Get file data
26
27		my @filecontents = get_file_data($filename);
28
29		my $currenttagtext = '';
30		my $currenttag = '';
31		my $intag = 0; # inside an option (which can be multiline)
32
33		for my $line (@filecontents)
34		{
35		if($intag)
36		{
37		if($line =~ /^\%\%\%END{([a-z]+)/)
38		{
39		if($1 ne $currenttag)
40		{
41		print STDERR "$0: BEGIN{$currenttag} ends with END{$1}\n";
42		exit 1;
43		}
44		print STDERR "\%\%\%matched END with \"$currenttag\"\n";
45		$intag = 0;
46		print $currenttagtext, "\n";
47		$currenttagtext = '';
48		$currenttag = '';
49		} else
50		{
51		$currenttagtext .= $line;
52		}
53		} else
54		{
55		if($line =~ /^\%\%\%BEGIN{([a-z]+)}/)
56		{
57		print STDERR "\%\%\%matched BEGIN with \"$1\"\n";
58		if(exists $tagtab{$1})
59		{
60		$intag = 1;
61		$currenttag = $1;
62		}
63		}
64		}
65		}
66
67		exit 0;
68
69		# check if the number of arguments is as expected
70		# get last argument
71
72		sub get_file_data
73		{
74		my($filename) = @_;
75
76		unless(open(GET_FILE_DATA, $filename))
77		{
78		print STDERR "$0: Cannot open file $filename\n";
79		exit 1;
80		}
81		my @filedata = <GET_FILE_DATA>;
82		close GET_FILE_DATA;
83		return @filedata;
84		}

-1980

~~src/doc/WWW/index.html~~ less more

0		<?xml version="1.0" encoding="utf-8" ?>
1		<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
2		"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
3		<!--http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd-->
4		<html xmlns="http://www.w3.org/1999/xhtml"
5		>
6		<head><title>The Vmatch large scale sequence analysis software</title>
7		<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
8		<meta name="generator" content="TeX4ht (http://www.tug.org/tex4ht/)" />
9		<meta name="originator" content="TeX4ht (http://www.tug.org/tex4ht/)" />
10		<!-- xhtml,charset=utf-8,html -->
11		<meta name="src" content="vmweb.tex" />
12		<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"/>
13		<meta name="description" content="The Vmatch large scale sequence analysis
14		software is a versatile software tool for efficiently solving large scale sequence matching tasks."/>
15		<meta name="keywords" content="sequence analysis, sequence mapping, BLAST, bioinformatics, computational biology"/>
16		<meta http-equiv="Content-Style-Type" content="text/css"/>
17		<link rel="stylesheet" type="text/css" href="vmweb.css" />
18		</head><body
19		>
20		<div class="maketitle">
21
22
23
24
25
26
27
28		<h1 align="center" class="titleHead">The Vmatch large scale sequence analysis
29		software</h1>
30		<div align="center" class="author" ><span
31		class="ptmr7t-x-x-144">Stefan Kurtz</span></div>
32		<br />
33		<div align="center" class="date" ><span
34		class="ptmr7t-x-x-144">June 15, 2017</span></div>
35		</div>
36		<!--l. 61--> <br/> <center> <img src="matchgraph.gif" alt="show matches of different sizes in a matchgraph"/> </center> <div id="downloadbox"> <ul> <li><a href="download.html">Download <i>Vmatch</i>!</a></li> </ul> </div>
37		<!--l. 63--><p class="noindent" >This is the web-site for <span
38		class="ptmri7t-x-x-120">Vmatch</span>, a versatile software tool for eﬃciently solving large
39		scale sequence matching tasks. <span
40		class="ptmri7t-x-x-120">Vmatch </span>subsumes the software tool <a
41		href="http://bibiserv.techfak.uni-bielefeld.de/reputer" >REPuter</a>, but is
42		much more general, with a very ﬂexible user interface, and improved space and time
43		requirements. <a href="vmweb.pdf">Here</a> is a printable version of this HTML-page in PDF.
44		</p>
45		<h3 class="likesectionHead"><a
46		id="x1-1000"></a>Features of <span
47		class="ptmri7t-x-x-120">Vmatch</span></h3>
48		<!--l. 76--><p class="noindent" >The <a
49		href="virtman.pdf" ><span
50		class="ptmri7t-x-x-120">Vmatch</span>-manual</a> gives many examples on how to use <span
51		class="ptmri7t-x-x-120">Vmatch</span>. Here are the
52		program’s most important features.
53		</p><!--l. 3--><p class="noindent" >
54		</p>
55
56
57
58		<h4 class="likesubsectionHead"><a
59		id="x1-2000"></a>Persistent index</h4>
60		<!--l. 4--><p class="noindent" >Usually, in a large scale matching problem, extensive portions of the sequences under
61		consideration are static, i.e. they do not change much over time. Therefore it makes
62		sense to preprocess this static data to extract information from it and to store this in a
63		structured manner, allowing eﬃcient searches. <span
64		class="ptmri7t-x-x-120">Vmatch </span>does exactly this: it
65		preprocesses a set of sequences into an index structure. This is stored as a collection of
66		several ﬁles constituting the persistent index. The index eﬃciently represents all
67		substrings of the preprocessed sequences and, unlike many other sequence
68		comparison tools, allows matching tasks to be solved in time, <span
69		class="ptmri7t-x-x-120">independent </span>of
70		the size of the index. Diﬀerent matching tasks require diﬀerent parts of the
71		index, but only the required parts of the index are accessed during the matching
72		process.
73		</p><!--l. 21--><p class="noindent" >
74		</p>
75		<h4 class="likesubsectionHead"><a
76		id="x1-3000"></a>Alphabet independency</h4>
77		<!--l. 22--><p class="noindent" >Most software tools for sequence analysis are restricted to DNA and/or protein
78		sequences. In contrast, <span
79		class="ptmri7t-x-x-120">Vmatch </span>can process sequences over any user deﬁned alphabet
80		not larger than 250 symbols. <span
81		class="ptmri7t-x-x-120">Vmatch </span>fully implements the concept of <span
82		class="ptmri7t-x-x-120">symbol</span>
83		<span
84		class="ptmri7t-x-x-120">mappings</span>, denoting alphabet transformations. These allow the user to specify that
85		diﬀerent characters in the input sequences should be considered identical in
86		the matching process. This feature is used to group similar amino acids, for
87		example.
88		</p><!--l. 31--><p class="noindent" >
89		</p>
90		<h4 class="likesubsectionHead"><a
91		id="x1-4000"></a>Versatility</h4>
92		<!--l. 32--><p class="noindent" ><span
93		class="ptmri7t-x-x-120">Vmatch </span>allows a multitude of diﬀerent matching tasks to be solved using the
94		persistent index. Every matching task is basically characterized by (1) the <span
95		class="ptmri7t-x-x-120">kind</span>
96		<span
97		class="ptmri7t-x-x-120">of sequences </span>to be matched, (2) the <span
98		class="ptmri7t-x-x-120">kind of matches </span>sought, (3) additional
99		<span
100		class="ptmri7t-x-x-120">constraints </span>on the matches, and (4) the <span
101		class="ptmri7t-x-x-120">kind of postprocessing </span>to be done with the
102		matches.
103
104
105
106		</p><!--l. 39--><p class="noindent" >In the standard case, <span
107		class="ptmri7t-x-x-120">Vmatch </span>matches sequences over the same alphabet. Additionally,
108		DNA sequences can be matched against a protein sequence index in all six reading
109		frames. Finally, DNA sequences can be transformed in all six reading frames and
110		compared against itself.
111		</p><!--l. 44--><p class="noindent" >Where appropriate, <span
112		class="ptmri7t-x-x-120">Vmatch </span>can compute the following kinds of matches, using
113		state-of-the-art algorithms:
114		</p>
115		<ul class="itemize1">
116		<li class="itemize">maximal and supermaximal repeats using the algorithms of <a
117		id="XABO:KUR:OHL:2004"></a>M.I.
118		Abouelhoda, S. Kurtz, and E. Ohlebusch. Replacing suﬃx trees with
119		enhanced suﬃx arrays. <span
120		class="ptmri7t-x-x-120">Journal of Discrete Algorithms</span>, 2:53–86, 2004
121		</li>
122		<li class="itemize">branching tandem repeats using the algorithm of <a
123		id="XABO:KUR:OHL:2002"></a>M.I. Abouelhoda,
124		S. Kurtz, and E. Ohlebusch. The enhanced suﬃx array and its applications
125		to genome analysis. In <span
126		class="ptmri7t-x-x-120">Proceedings of the Second Workshop on Algorithms</span>
127		<span
128		class="ptmri7t-x-x-120">in Bioinformatics</span>, pages 449–463. Lecture Notes in Computer Science
129		2452, Springer-Verlag, 2002
130		</li>
131		<li class="itemize">maximal (unique) substring matches using the algorithms of <a
132		id="XKUR:2002B"></a>S. Kurtz. A
133		Time and Space Eﬃcient Algorithm for the Substring Matching Problem,
134		2002
135		</li>
136		<li class="itemize">complete matches using the algorithms of <a
137		id="XMAN:MYE:1993"></a>U. Manber and E.W. Myers.
138		Suﬃx Arrays: A New Method for On-Line String Searches. <span
139		class="ptmri7t-x-x-120">SIAM Journal</span>
140		<span
141		class="ptmri7t-x-x-120">on Computing</span>, 22(5):935–948, 1993 and [<a
142		href="#XMYE:1999">86</a>]
143		</li></ul>
144		<!--l. 69--><p class="noindent" >To compute degenerate substring matches or degenerate repeats, each kind
145		of match (with the exception of tandem repeats and complete matches) can
146		be taken as an exact seed and extended by either of two diﬀerent strategies:
147		</p>
148		<ul class="itemize1">
149		<li class="itemize">the <span
150		class="ptmri7t-x-x-120">maximum error </span>extension strategy, as described in
151
152
153
154		<!--l. 77--><p class="noindent" ><a
155		id="XKUR:CHO:OHL:SCHLE:STO:GIE:2001"></a>S. Kurtz, J.V. Choudhuri, E. Ohlebusch, C. Schleiermacher, J. Stoye, and
156		R. Giegerich. REPuter: The manifold applications of repeat analysis on
157		a genomic scale. <span
158		class="ptmri7t-x-x-120">Nucleic Acids Res.</span>, 29(22):4633–4642, 2001 for repeat
159		detection,
160		</p></li>
161		<li class="itemize">the <span
162		class="ptmri7t-x-x-120">greedy </span>extension strategy of <a
163		id="XZHA:SCHWA:WAG:MIL:2000"></a>Z. Zhang, S. Schwartz, L. Wagner,
164		and W. Miller. A Greedy Algorithm for Aligning DNA Sequences.
165		<span
166		class="ptmri7t-x-x-120">J.</span><span
167		class="ptmri7t-x-x-120"> Comp.</span><span
168		class="ptmri7t-x-x-120"> Biol.</span>, 7(1/2):203–214, 2000
169		</li></ul>
170		<!--l. 84--><p class="noindent" >Matches can be selected according to their length, their E-value, their identity value, or
171		match score.
172		</p><!--l. 87--><p class="noindent" >In the standard case, a match is displayed as an alignment including positional
173		information. Alternatively, a match can directly be postprocessed in diﬀerent
174		ways:
175		</p>
176		<ul class="itemize1">
177		<li class="itemize"><span
178		class="ptmri7t-x-x-120">inverse output</span>, i.e. reporting of substrings <span
179		class="ptmri7t-x-x-120">not </span>covered by a match.
180		</li>
181		<li class="itemize"><span
182		class="ptmri7t-x-x-120">masking </span>of substrings covered by a match.
183		</li>
184		<li class="itemize"><span
185		class="ptmri7t-x-x-120">clustering </span>of sequences according to the matches found.
186		</li>
187		<li class="itemize"><span
188		class="ptmri7t-x-x-120">chaining </span>of matches, i.e. ﬁnding optimal subsets of matches which do not
189		cross, using the algorithms described in
190		<!--l. 104--><p class="noindent" ><a
191		id="XABO:OHL:2003"></a>M.I. Abouelhoda and E. Ohlebusch. A Local Chaining Algorithm
192		and its Applications in Comparative Genomics. In <span
193		class="ptmri7t-x-x-120">Proc. 3rd Worksh.</span>
194		<span
195		class="ptmri7t-x-x-120">Algorithms in Bioinformatics (WABI 2003)</span>, number 2812 in Lecture Notes
196		in Bioinformatics, pages 1–16. Springer-Verlag, 2003
197		</p></li>
198		<li class="itemize"><span
199		class="ptmri7t-x-x-120">clustering </span>of matches according to pairwise sequence similarities computed
200
201
202
203		by the dynamic programming algorithm of <a
204		id="XUKK:1985A"></a>E. Ukkonen. Algorithms for
205		Approximate String Matching. <span
206		class="ptmri7t-x-x-120">Information and Control</span>, 64:100–118, 1985
207		</li>
208		<li class="itemize"><span
209		class="ptmri7t-x-x-120">clustering </span>of matches according to the positions where they occur, following
210		the approach of
211		<!--l. 115--><p class="noindent" ><a
212		id="XVOL:HAA:SAL:2001"></a>N. Volfovsky,
213		B.J. Haas, and S.L. Salzberg. A Clustering Method for Repeat Analysis in
214		DNA Sequences. <span
215		class="ptmri7t-x-x-120">Genome Biology</span>, 2(8):research0027.1–0027.11, 2001
216		</p>
217		</li></ul>
218		<!--l. 119--><p class="noindent" >
219		</p>
220		<h4 class="likesubsectionHead"><a
221		id="x1-5000"></a>Eﬃcient algorithms and data structures</h4>
222		<!--l. 120--><p class="noindent" ><span
223		class="ptmri7t-x-x-120">Vmatch </span>is based on enhanced suﬃx arrays described Abouelhoda, Kurtz & Ohlebusch,
224		2004. This data structure has been shown to be as powerful as suﬃx trees, with the
225		advantage of a reduced space requirement and reduced processing time. Careful
226		implementation of the algorithms and data structures incorporated in <span
227		class="ptmri7t-x-x-120">Vmatch</span>
228		have led to exceedingly fast and robust software, allowing very large sequence
229		sets to be processed quickly. The 32-bit version of <span
230		class="ptmri7t-x-x-120">Vmatch </span>can process up to
231		400 million symbols, if enough memory is available. For large server class
232		machines (e.g. SUN-Sparc/Solaris, Intel Xeon/Linux, Compaq-Alpha/Tru64)
233		<span
234		class="ptmri7t-x-x-120">Vmatch </span>is available as a 64 bit version, enabling gigabytes of sequences to be
235		processed.
236		</p><!--l. 138--><p class="noindent" >
237		</p>
238		<h4 class="likesubsectionHead"><a
239		id="x1-6000"></a>Flexible input format</h4>
240		<!--l. 139--><p class="noindent" >The most common formats for input sequences (Fasta, Genbank, EMBL, and
241		SWISSPROT) are accepted. The user does not have to specify the input format. It is
242
243
244
245		automatically recognized. All input ﬁles can contain an arbitrary number of sequences.
246		Gzipped compressed inputs are accepted.
247		</p><!--l. 145--><p class="noindent" >
248		</p>
249		<h4 class="likesubsectionHead"><a
250		id="x1-7000"></a>Customized output and match selection</h4>
251		<!--l. 146--><p class="noindent" ><span
252		class="ptmri7t-x-x-120">Vmatch</span>’s output can be parsed by other programs easily. Furthermore, several options
253		allow for its customization. XML output is available and new output formats can easily
254		be incorporated without changing <span
255		class="ptmri7t-x-x-120">Vmatch</span>’s program code. Certain matches can easily
256		be selected by user deﬁned criteria, without intermediate output and subsequent
257		parsing.
258		</p><!--l. 154--><p class="noindent" >
259		</p>
260		<h3 class="likesectionHead"><a
261		id="x1-8000"></a>The parts of Vmatch</h3>
262		<!--l. 155--><p class="noindent" >Up until now we have referred to <span
263		class="ptmri7t-x-x-120">Vmatch </span>as a collection of programs. In the following
264		we use the same name, <span
265		class="cmtt-12">vmatch </span>(in typewriter font), for the most important
266		program in this collection. Besides <span
267		class="cmtt-12">vmatch</span>, there are the following programs
268		available:
269		</p><ol class="enumerate1" >
270		<li
271		class="enumerate" id="x1-8002x1"><span
272		class="cmtt-12">mkvtree </span>constructs the persistent index and stores it on ﬁles.
273		</li>
274		<li
275		class="enumerate" id="x1-8004x2"><span
276		class="cmtt-12">mkdna6idx </span>constructs an index for a DNA sequence after translating this in
277		all six reading frames.
278		</li>
279		<li
280		class="enumerate" id="x1-8006x3"><span
281		class="cmtt-12">vseqinfo </span>delivers information about indexed database sequences.
282		</li>
283		<li
284		class="enumerate" id="x1-8008x4"><span
285		class="cmtt-12">vstree2tex </span>outputs a representation of the index in <span class="LATEX">L<span class="A">A</span><span class="TEX">T<span
286		class="E">E</span>X</span></span>-format. It can
287		be used, for example, for educational or debugging purposes.
288
289
290
291		</li>
292		<li
293		class="enumerate" id="x1-8010x5"><span
294		class="cmtt-12">vseqselect </span>selects indexed sequences satisfying speciﬁc criteria.
295		</li>
296		<li
297		class="enumerate" id="x1-8012x6"><span
298		class="cmtt-12">vsubseqselect </span>selects substrings of a speciﬁed length range from an
299		index.
300		</li>
301		<li
302		class="enumerate" id="x1-8014x7"><span
303		class="cmtt-12">vmigrate.sh </span>converts an index from big endian to little endian
304		architectures, or vice versa.
305		</li>
306		<li
307		class="enumerate" id="x1-8016x8"><span
308		class="cmtt-12">vmatchselect </span>sort and selects matches delivered by <span
309		class="cmtt-12">vmatch</span>.
310		</li>
311		<li
312		class="enumerate" id="x1-8018x9"><span
313		class="cmtt-12">chain2dim </span>computes optimal chains of matches from ﬁles in
314		<span
315		class="ptmri7t-x-x-120">Vmatch</span>-format.
316		</li>
317		<li
318		class="enumerate" id="x1-8020x10"><span
319		class="cmtt-12">matchcluster </span>computes clusters of matches from ﬁles in <span
320		class="ptmri7t-x-x-120">Vmatch</span>-format.</li></ol>
321		<!--l. 85--><p class="noindent" > <a href="Dataflowfig.pdf">Here</a> is an overview of the dataflow in <i>Vmatch</i>.
322		</p><!--l. 87--><p class="noindent" >
323		</p>
324		<h3 class="likesectionHead"><a
325		id="x1-9000"></a>Related tools</h3>
326		<!--l. 88--><p class="noindent" >There are several tools which are based on the persistent index of <span
327		class="ptmri7t-x-x-120">Vmatch</span>:
328		</p><!--l. 91--><p class="noindent" >
329		</p><dl class="description"><dt class="description">
330		<span
331		class="ptmb7t-x-x-120">Genalyzer</span> </dt><dd
332		class="description">is a graphical user interface to visualize the output of <span
333		class="ptmri7t-x-x-120">Vmatch </span>in form
334		of a match graph. For details see
335		<!--l. 97--><p class="noindent" ><a
336		id="XCHO:SCHLE:KUR:GIE:2004"></a>J.V. Choudhuri, C. Schleiermacher, S. Kurtz, and R. Giegerich.
337		Genalyzer: Interactive visualization of sequence similarities between entire
338		genomes. <span
339		class="ptmri7t-x-x-120">Bioinformatics</span>, 20:1964–1965, 2004
340		</p><!--l. 99--><p class="noindent" >Genalyzer is not available any more.
341
342
343
344		</p></dd><dt class="description">
345		<a
346		href="http://bibiserv.techfak.uni-bielefeld.de/mga/" ><span
347		class="ptmb7t-x-x-120">MGA</span></a> </dt><dd
348		class="description">is a program to compute multiple alignments of complete genomes. For
349		details see
350		<!--l. 104--><p class="noindent" ><a
351		id="XHOEH:KUR:OHL:2002"></a>M. Höhl, S. Kurtz, and E. Ohlebusch. Eﬃcient multiple genome
352		alignment. <span
353		class="ptmri7t-x-x-120">Bioinformatics</span>, 18(Suppl. 1):S312–S320, 2002
354		</p></dd><dt class="description">
355		<span
356		class="ptmb7t-x-x-120">Multimat</span> </dt><dd
357		class="description">is a program to compute multiple exact matches between three or more
358		genome size sequences. For details see
359		<!--l. 108--><p class="noindent" ><a
360		id="XOHL:KUR:2008"></a>E. Ohlebusch and S. Kurtz. Space eﬃcient computation of rare
361		maximal exact matches between multiple sequences. <span
362		class="ptmri7t-x-x-120">J.</span><span
363		class="ptmri7t-x-x-120"> Comp.</span><span
364		class="ptmri7t-x-x-120"> Biol.</span>,
365		15(4):357–377, 2008
366		</p><!--l. 110--><p class="noindent" >Please contact <a
367		href="http://www.zbh.uni-hamburg.de/kurtz" >Stefan Kurtz</a> if you are interested in using Multimat.
368		</p></dd><dt class="description">
369		<a
370		href="http://bibiserv.techfak.uni-bielefeld.de/possumsearch/" ><span
371		class="ptmb7t-x-x-120">PossumSearch</span></a> </dt><dd
372		class="description">Is a program to search for position speciﬁc scoring matrices. For
373		details, see
374		<!--l. 118--><p class="noindent" ><a
375		id="XBEC:HOM:GIE:KUR:2006"></a>M. Beckstette, R. Homann, R. Giegerich, and S. Kurtz. Fast index based
376		algorithms and software for matching position speciﬁc scoring matrices.
377		<span
378		class="ptmri7t-x-x-120">BMC Bioinformatics</span>, 7:389, 2006
379		</p></dd><dt class="description">
380		</dt><dd
381		class="description">
382		</dd><dt class="description">
383		<a
384		href="http://www.genomethreader.org/" ><span
385		class="ptmb7t-x-x-120">GenomeThreader</span></a> </dt><dd
386		class="description">is a software tool to compute gene structure predictions. The
387		gene structure predictions are calculated using a similarity-based approach
388		where additional cDNA/EST and/or protein sequences are used to predict
389		gene structures via spliced alignments. <span
390		class="ptmri7t-x-x-120">GenomeThreader </span>uses the matching
391		capabilities of <span
392		class="ptmri7t-x-x-120">Vmatch </span>to eﬃciently map the reference sequence to a
393		genomic sequence. For details, see
394		<!--l. 128--><p class="noindent" ><a
395		id="XGRE:BRE:SPA:KUR:2005"></a>G. Gremme, V. Brendel, M.E. Sparks, and S. Kurtz. Engineering a
396		software tool for gene prediction in higher organisms. <span
397		class="ptmri7t-x-x-120">Information and</span>
398		<span
399		class="ptmri7t-x-x-120">Software Technology</span>, 47(15):965–978, 2005
400		</p></dd><dt class="description">
401		</dt><dd
402		class="description">
403
404
405
406		</dd><dt class="description">
407		<a
408		href="http://www.biopieces.org/" ><span
409		class="ptmb7t-x-x-120">Biopieces</span></a> </dt><dd
410		class="description">is a collection of bioinformatics tools that can be pieced together
411		in a very easy and ﬂexible manner to perform both simple and
412		complex tasks. Some Biopieces depend on <span
413		class="ptmri7t-x-x-120">Vmatch</span>. For details see
414		<a
415		href="http://www.biopieces.org/" class="url" ><span
416		class="cmtt-12">http://www.biopieces.org/</span></a>.</dd></dl>
417		<!--l. 139--><p class="noindent" > <a name="CurrentUsage"/>
418		</p>
419		<h3 class="likesectionHead"><a
420		id="x1-10000"></a>Previous and Current Usages</h3>
421		<!--l. 142--><p class="noindent" >We provide an annotated bibliography listing papers which applied <span
422		class="ptmri7t-x-x-120">Vmatch </span>and shortly
423		describe the tasks for which <span
424		class="ptmri7t-x-x-120">Vmatch </span>was used. We omit our own papers. The references
425		were collected by a <a
426		href="https://scholar.google.de/scholar?q=Vmatch+AND+Kurtz+OR+www.vmatch.de" >search in Google scholar</a> (which, as of Jan 2, 2016 retrieved 397
427		results.)
428		</p><!--l. 149--><p class="noindent" >
429		</p>
430		<h4 class="likesubsectionHead"><a
431		id="x1-11000"></a>Usages in Plant Genome Research</h4>
432		<!--l. 150--><p class="noindent" >
433		</p><ol class="enumerate1" >
434		<li
435		class="enumerate" id="x1-11002x1"><a
436		id="XBRE:KUR:WAL:2002"></a>V. Brendel, S. Kurtz, and V. Walbot. Comparative genomics of
437		Arabidopsis and Maize: Prospects and limitations. <span
438		class="ptmri7t-x-x-120">Genome Biology</span>,
439		3(3):reviews1005.1–1005.6, 2002
440		<!--l. 153--><p class="noindent" >In this work <span
441		class="ptmri7t-x-x-120">Vmatch </span>was used to a compute a non-redundant set from a
442		large collection of protein sequences from Zea-Maize.
443		</p><!--l. 155--><p class="noindent" >Similar applications are described in
444		</p><!--l. 157--><p class="noindent" ><a
445		id="XDON:ROY:FRE:WAL:BRE:2003"></a>Q. Dong, L. Roy, M. Freeling, V. Walbot, and V. Brendel. ZmDB, an
446		integrated Database for Maize Genome Research. <span
447		class="ptmri7t-x-x-120">Nucleic Acids Res.</span>,
448		31:244–247, 2003.
449
450
451
452		</p></li>
453		<li
454		class="enumerate" id="x1-11004x2">PLEXdb is a database for gene expression resources for plants and plant
455		pathogens, see
456		<!--l. 166--><p class="noindent" ><a
457		id="XDAS:VAN:HON:WIS:DIC:2012"></a>S. Dash, J. Van Hemert, L. Hong, R. P. Wise, and J. A. Dickerson.
458		PLEXdb: gene expression resources for plants and plant pathogens. <span
459		class="ptmri7t-x-x-120">Nucleic</span>
460		<span
461		class="ptmri7t-x-x-120">Acids Res.</span>, 40(Database issue):D1194–1201, Jan 2012
462		</p><!--l. 168--><p class="noindent" >PLEXdb provides a <span
463		class="ptmri7t-x-x-120">Vmatch</span>-based <a
464		href="http://www.plantgdb.org/cgi-bin/prj/PLEXdb/ProbeMatch.pl" >web-service</a> to match PLEXdb probes.
465		</p></li>
466		<li
467		class="enumerate" id="x1-11006x3">The assembly of the Arabidopsis thaliana genome from 2004 (GenBank
468		entries of 2/19/04) contained vector sequence contaminations. For example,
469		region 3 617 880 to 3 625 027 of chromosome II contained a cloning vector.
470		<span
471		class="ptmri7t-x-x-120">Vmatch </span>was used to detect the vector contamination, see <a
472		href="http://www.plantgdb.org/AtGDB/Annotation/vector.php" >here</a>
473		</li>
474		<li
475		class="enumerate" id="x1-11008x4"><a
476		id="XDON:LAW:SCHLUE:WIL:KUR:LUS:BRE:2005"></a>Q. Dong, C.J. Lawrence, S.D. Schlueter, M.D. Wilkerson, S. Kurtz,
477		C. Lushbough, and V. Brendel. Comparative Plant Genomics Resources at
478		PlantGDB. <span
479		class="ptmri7t-x-x-120">Plant Physiology, Plant Database Focus Issue</span>, 2005
480		<!--l. 183--><p class="noindent" >This work describes PlantGDB, which provides a service called
481		<a
482		href="http://www.plantgdb.org/PlantGDB-cgi/vmatch/patternsearch.pl" >PatternSearch@PlantGDB</a> for genome wide pattern searches in plant
483		sequences. The service is based on <span
484		class="ptmri7t-x-x-120">Vmatch</span>.
485		</p></li>
486		<li
487		class="enumerate" id="x1-11010x5"><a
488		id="XLIN:KRO:2005"></a>M. Lindow and A. Krogh. Computational evidence for hundreds of
489		non-conserved plant micrornas. <span
490		class="ptmri7t-x-x-120">BMC Genomics</span>, 6(1):119, 2005
491		<!--l. 202--><p class="noindent" >In this work <span
492		class="ptmri7t-x-x-120">Vmatch </span>was used for three diﬀerent tasks: </p>
493		<ul class="itemize1">
494		<li class="itemize">Searching spliced mRNA in the Arabidopsis genome to detect
495		micromatches of length at least 20 with maximum 2 mismatches.
496		</li>
497		<li class="itemize">Finding matches of length at least 15 long with at most one mismatch
498		between predicted mature miRNA-sequences and a set of ESTs as well
499		as sequences from the Arabidopsis Small RNA Project (ASRP).
500		</li>
501		<li class="itemize">Aligning and performing single linkage clustering of the predicted
502		mature miRNA sequences. Candidate pairs aligning over at least 17
503		bases, allowing an edit distance of 1 were grouped in the same family.</li></ul>
504
505
506
507		</li>
508		<li
509		class="enumerate" id="x1-11012x6"><a
510		id="XPOM:LEM:TUR:2006"></a>J.-F. Pombert, C. Lemieux, and M. Turmel. The complete chloroplast DNA
511		sequence of the green alga Oltmannsiellopsis viridis reveals a distinctive
512		quadripartite architecture in the chloroplast genome of early diverging ulvophytes.
513		<span
514		class="ptmri7t-x-x-120">BMC Biology</span>, 4:3, 2006
515		<!--l. 207--><p class="noindent" ><a
516		id="XTUR:OTI:LEM:2006"></a>M. Turmel, C. Otis, and C. Lemieux. The Chloroplast Genome Sequence of
517		Chara vulgaris Sheds New Light into the Closest Green Algal Relatives of Land
518		Plants. <span
519		class="ptmri7t-x-x-120">Molecular Biology and Evolution</span>, 23:1324–1338, 2006
520		</p><!--l. 209--><p class="noindent" >In these papers <span
521		class="ptmri7t-x-x-120">Vmatch </span>was used to search and compare repeated elements in
522		diﬀerent chloroplast DNA.
523		</p></li>
524		<li
525		class="enumerate" id="x1-11014x7"><a
526		id="XSPA:NOU:HAA:YAN:GUN:HIN:KLE:HAB:SCHOO:MAY:2007"></a>M. Spannagl, O. Noubibou, D. Haase, L. Yang, H. Gundlach, T. Hindemitt,
527		K. Klee, G. Haberer, H. Schoof, and K.F.X. Mayer. MIPSPlantsDB–plant
528		database resource for integrative and comparative plant genome research. <span
529		class="ptmri7t-x-x-120">Nucleic</span>
530		<span
531		class="ptmri7t-x-x-120">Acids Res</span>, 35(Database issue):D834–40, 2007 In this work about the
532		<span
533		class="ptmri7t-x-x-120">MIPSPlantsDB </span>database <span
534		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster large sequence
535		sets.
536		</li>
537		<li
538		class="enumerate" id="x1-11016x8"><a
539		id="XSCHIJ:VOS:MAR:JON:ROS:MOL:TIK:ANG:TUN:BOV:2007"></a>E.G.W.M. Schijlen, C.H. Ric de Vos, S. Martens, H.H. Jonker, F.M. Rosin, J.W.
540		Molthoﬀ, Y.M. Tikunov, G.C. Angenent, A.J. van Tunen, and A.G. Bovy. RNA
541		interference silencing of chalcone synthase, the ﬁrst step in the ﬂavonoid
542		biosynthesis pathway, leads to parthenocarpic tomato fruits. <span
543		class="ptmri7t-x-x-120">Plant Physiol</span>,
544		144(3):1520–30, 2007
545		<!--l. 218--><p class="noindent" >In this work <span
546		class="ptmri7t-x-x-120">Vmatch </span>was used to compare target genes of the tomato Chs RNAi
547		to a tomato gene index.
548		</p></li>
549		<li
550		class="enumerate" id="x1-11018x9"><a
551		id="XLIN:JAC:NYG:MAN:KRO:2007"></a>M. Lindow, A. Jacobsen, S. Nygaard, Y. Mang, and A. Krogh. Intragenomic
552		matching reveals a huge potential for mirna-mediated regulation in plants. <span
553		class="ptmri7t-x-x-120">PLOS</span>
554		<span
555		class="ptmri7t-x-x-120">Comput. Biol</span>, 3(11):e238, 2007
556		<!--l. 223--><p class="noindent" >In this work <span
557		class="ptmri7t-x-x-120">Vmatch </span>was used to search diﬀerent plant genomes for matches of
558		length at least 20 with maximum of 2 mismatches. Here the fact that <span
559		class="ptmri7t-x-x-120">Vmatch </span>is an
560		exhaustive search tool is important.
561		</p></li>
562		<li
563		class="enumerate" id="x1-11020x10"><a
564		id="XDEC:OTI:THU:LEM:2007"></a>J.-C. de Cambiaire, C. Otis, M. Turmel, and C. Lemieux. The chloroplast
565
566
567
568		genome sequence of the green alga leptosira terrestris: multiple losses of
569		the inverted repeat and extensive genome rearrangements within the
570		trebouxiophyceae. <span
571		class="ptmri7t-x-x-120">BMC Genomics</span>, 8(1):213, 2007
572		<!--l. 228--><p class="noindent" >In this work <span
573		class="ptmri7t-x-x-120">Vmatch </span>was used to determine the presence of shared repeated
574		elements of minimum length 30, with up to 10% mismatches using in diﬀerent
575		sequence sets from the green alga <span
576		class="ptmri7t-x-x-120">Leptosira terrestris</span>.
577		</p></li>
578		<li
579		class="enumerate" id="x1-11022x11"><a
580		id="XOSS:SCHNE:CLA:LAN:WAR:WEI:2008"></a>S. Ossowski, K. Schneeberger, R.M. Clark, C. Lanz, N. Warthmann, and
581		D. Weigel. Sequencing of natural strains of Arabidopsis thaliana with short
582		reads. <span
583		class="ptmri7t-x-x-120">Genome Res.</span>, 18:2024–2033, 2008
584		<!--l. 235--><p class="noindent" >In this work <span
585		class="ptmri7t-x-x-120">Vmatch </span>was used to map millions of short sequence reads to the
586		<span
587		class="ptmri7t-x-x-120">A.</span><span
588		class="ptmri7t-x-x-120"> Thaliana </span>genome. Up to four mismatches and up to three indels were allowed
589		in the matching process. The seed size was chosen to be 0. The reads were aligned
590		using the best match strategy by iteratively increasing the the allowed number of
591		mismatches and gaps at each round.
592		</p></li>
593		<li
594		class="enumerate" id="x1-11024x12"><a
595		id="XDIBO:OSS:SCHNE:RAT:2008"></a>F. De Bona, S. Ossowski, K. Schneeberger, and G. Ratsch. Optimal spliced
596		alignments of short sequence reads. <span
597		class="ptmri7t-x-x-120">Bioinformatics</span>, 24(16):i174–180,
598		2008
599		<!--l. 242--><p class="noindent" >In this work <span
600		class="ptmri7t-x-x-120">Vmatch </span>was used to map millions of short sequence reads to the
601		<span
602		class="ptmri7t-x-x-120">A.</span><span
603		class="ptmri7t-x-x-120"> Thaliana </span>genome. <span
604		class="ptmri7t-x-x-120">Vmatch </span>was part of a multi-step pipeline, combining a fast
605		matching algorithm (<span
606		class="ptmri7t-x-x-120">Vmatch</span>) for initial read mapping and an optimal alignment
607		algorithm based on dynamic programming (QPALMA) for high quality detection
608		of splice sites.
609		</p></li>
610		<li
611		class="enumerate" id="x1-11026x13"><a
612		id="XASS:HER:LIN:HUE:TAL:SMA:IMM:ELD:FIE:SCHAT:2010"></a>A. G. L. Assunção, E. Herrero, Y-F. Lin, B. Huettel, S. Talukdar,
613		C. Smaczniak, R. GH Immink, M. Van Eldik, M. Fiers, H. Schat, et al.
614		Arabidopsis thaliana transcription factors bzip19 and bzip23 regulate the
615		adaptation to zinc deﬁciency. <span
616		class="ptmri7t-x-x-120">Proceedings of the National Academy of Sciences</span>,
617		107(22):10296–10301, 2010
618		<!--l. 245--><p class="noindent" >In this work <span
619		class="ptmri7t-x-x-120">Vmatch </span>was used for motif searching in diﬀerent plant
620		genomes.
621		</p></li>
622		<li
623		class="enumerate" id="x1-11028x14"><a
624		id="XEVE:SAT:GOL:MEY:BET:SAK:WAR:JAC:2010"></a>Andrea L Eveland, Namiko Satoh-Nagasawa, Alexander Goldshmidt, Sandra
625
626
627
628		Meyer, Mary Beatty, Hajime Sakai, Doreen Ware, and David Jackson. Digital
629		gene expression signatures for maize development. <span
630		class="ptmri7t-x-x-120">Plant physiology</span>,
631		154(3):1024–1039, 2010
632		<!--l. 248--><p class="noindent" >In this work <span
633		class="ptmri7t-x-x-120">Vmatch </span>was used to map unique consensus sequence tags to the
634		maize reference genome.
635		</p></li>
636		<li
637		class="enumerate" id="x1-11030x15"><a
638		id="XBRO:OTI:LEM:TUR:2010"></a>Jean-Simon Brouard, Christian Otis, Claude Lemieux, and Monique Turmel. The
639		exceptionally large chloroplast genome of the green alga ﬂoydiella terrestris
640		illuminates the evolutionary history of the chlorophyceae. <span
641		class="ptmri7t-x-x-120">Genome biology and</span>
642		<span
643		class="ptmri7t-x-x-120">evolution</span>, 2:240, 2010
644		<!--l. 252--><p class="noindent" >In this work <span
645		class="ptmri7t-x-x-120">Vmatch </span>was used to identify and cluster repeated sequences in
646		<span
647		class="ptmri7t-x-x-120">Floydiella </span>chloroplast genome.
648		</p></li>
649		<li
650		class="enumerate" id="x1-11032x16"><a
651		id="XREH:AQU:GRU:HEN:HIL:LAU:NAO:PAT:ROM:SHU:2010"></a>Hubert Rehrauer, Catharine Aquino, Wilhelm Gruissem, Stefan R Henz, Pierre
652		Hilson, Sascha Laubinger, Naira Naouar, Andrea Patrignani, Stephane Rombauts,
653		Huan Shu, et al. Agronomics1: a new resource for arabidopsis transcriptome
654		proﬁling. <span
655		class="ptmri7t-x-x-120">Plant Physiology</span>, 152(2):487–499, 2010
656		<!--l. 257--><p class="noindent" >In this work <span
657		class="ptmri7t-x-x-120">Vmatch </span>was used to calculate direct and reverse complementary
658		matches of length 17 bp or greater with edit distance 1 or less between
659		ﬁve nuclear chromosomes and mitochondrial and chloroplast genome
660		sequences.
661		</p></li>
662		<li
663		class="enumerate" id="x1-11034x17"><a
664		id="XSEK:LIN:CHI:HAN:BUE:LEO:KAE:2011"></a>R. S. Sekhon, H. Lin, K. L. Childs, C. N. Hansey, C. R. Buell, N. de Leon,
665		and S. M. Kaeppler. Genome-wide atlas of transcription during maize
666		development. <span
667		class="ptmri7t-x-x-120">Plant J.</span>, 66(4):553–563, May 2011
668		<!--l. 261--><p class="noindent" >In this work <span
669		class="ptmri7t-x-x-120">Vmatch </span>was used to search probe sequences against the maize
670		genome the cDNA sequences of the oﬃcial maize gene models.
671		</p></li>
672		<li
673		class="enumerate" id="x1-11036x18"><a
674		id="XDAS:OH:HAA:HER:HON:ALI:YUN:BRE:ZHU:BOH:2011"></a>M. Dassanayake, D. H. Oh, J. S. Haas, A. Hernandez, H. Hong, S. Ali, D. J.
675		Yun, R. A. Bressan, J. K. Zhu, H. J. Bohnert, and J. M. Cheeseman. The
676		genome of the extremophile crucifer Thellungiella parvula. <span
677		class="ptmri7t-x-x-120">Nat. Genet.</span>,
678		43(9):913–918, Sep 2011
679		<!--l. 266--><p class="noindent" >In this work <span
680		class="ptmri7t-x-x-120">Vmatch </span>was used for clustering sequences assembled from 454-reads
681
682
683
684		of <span
685		class="ptmri7t-x-x-120">Thellungiella parvula</span>, a model for the evolution of plant adaptation to extreme
686		environments.
687		</p></li>
688		<li
689		class="enumerate" id="x1-11038x19"><a
690		id="XWIL:HOF:KLE:WEI:2011"></a>E. M. Willing, M. Hoﬀmann, J. D. Klein, D. Weigel, and C. Dreyer.
691		Paired-end RAD-seq for de novo assembly and marker design without available
692		reference. <span
693		class="ptmri7t-x-x-120">Bioinformatics</span>, 27(16):2187–2193, Aug 2011
694		<!--l. 270--><p class="noindent" >In this work <span
695		class="ptmri7t-x-x-120">Vmatch </span>was used for grouping short reads into pools representing
696		the same RAD tag.
697		</p></li>
698		<li
699		class="enumerate" id="x1-11040x20"><a
700		id="XGAO:ZHO:WAN:SU:WAN:2011"></a>L. Gao, Y. Zhou, Z.-W. Wang, Y.-J. Su, and T. Wang. Evolution of the
701		<span
702		class="ptmri7t-x-x-120">rpoB-psbZ </span>region in fern plastid genomes: notable structural rearrangements
703		and highly variable intergenic spacers. <span
704		class="ptmri7t-x-x-120">BMC Plant Biology</span>, 11(1):64,
705		2011
706		<!--l. 274--><p class="noindent" >In this work <span
707		class="ptmri7t-x-x-120">Vmatch </span>was used for detecting and clustering repetitive sequences in
708		diverse fern plastid genomes.
709		</p></li>
710		<li
711		class="enumerate" id="x1-11042x21"><a
712		id="XSLO:ALV:CHU:WU:MCC:PAL:TAY:2012"></a>D. B. Sloan, A. J. Alverson, J. P. Chuckalovcak, M. Wu, D. E. McCauley,
713		J. D. Palmer, and D. R. Taylor. Rapid evolution of enormous, multichromosomal
714		genomes in ﬂowering plant mitochondria with exceptionally high mutation rates.
715		<span
716		class="ptmri7t-x-x-120">PLoS Biol.</span>, 10(1):e1001241, Jan 2012
717		<!--l. 278--><p class="noindent" >In this work <span
718		class="ptmri7t-x-x-120">Vmatch </span>was used to precisely deﬁne the boundaries of all repeats
719		with 100% sequence identity.
720		</p></li>
721		<li
722		class="enumerate" id="x1-11044x22"><a
723		id="XDUB:FAR:SCHLU:CAN:ABE:TUT:WOO:SHA:MUL:KUD:2011"></a>Anuja Dubey, Andrew Farmer, Jessica Schlueter, Steven B Cannon, Brian
724		Abernathy, Reetu Tuteja, Jimmy Woodward, Trushar Shah, Benjamin
725		Mulasmanovic, Himabindu Kudapa, et al. Deﬁning the transcriptome
726		assembly and its use for genome dynamics and transcriptome proﬁling
727		studies in pigeonpea (<span
728		class="ptmri7t-x-x-120">Cajanus cajan </span>l.). <span
729		class="ptmri7t-x-x-120">DNA research</span>, 18(3):153–164,
730		2011
731		<!--l. 281--><p class="noindent" >In this work <span
732		class="ptmri7t-x-x-120">Vmatch </span>was used cluster sequences based on their six-frame
733		translation.
734		</p></li>
735		<li
736		class="enumerate" id="x1-11046x23"><a
737		id="XSAX:PEN:UPA:KUM:CAR:SCHLU:FAR:WHA:SAR:MAY:2012"></a>Rachit K Saxena, R Varma Penmetsa, Hari D Upadhyaya, Ashish Kumar,
738
739
740
741		Noelia Carrasquilla-Garcia, Jessica A Schlueter, Andrew Farmer, Adam M
742		Whaley, Birinchi K Sarma, Gregory D May, et al. Large-scale development of
743		cost-eﬀective single-nucleotide polymorphism marker assays for genetic
744		mapping in pigeonpea and comparative mapping in legumes. <span
745		class="ptmri7t-x-x-120">DNA research</span>,
746		19(6):449–461, 2012
747		<!--l. 285--><p class="noindent" >In this work <span
748		class="ptmri7t-x-x-120">Vmatch </span>was used to identify reciprocal best matches between the
749		pigeonpea sequences and other legume sequences.
750		</p></li>
751		<li
752		class="enumerate" id="x1-11048x24"><a
753		id="XHAZ:REE:RIS:PEC:2012"></a>B. Z. Haznedaroglu, D. Reeves, H. Rismani-Yazdi, and J. Peccia. Optimization
754		of de novo transcriptome assembly from high-throughput short read sequencing
755		data improves functional annotation for non-model organisms. <span
756		class="ptmri7t-x-x-120">BMC</span>
757		<span
758		class="ptmri7t-x-x-120">Bioinformatics</span>, 13:170, 2012
759		<!--l. 290--><p class="noindent" >In this work <span
760		class="ptmri7t-x-x-120">Vmatch </span>was used for assembly clustering and optimization
761		of contigs for <span
762		class="ptmri7t-x-x-120">Neochloris oleoabundans </span>(a Chlorophyceae class green
763		microalgae).
764		</p></li>
765		<li
766		class="enumerate" id="x1-11050x25"><a
767		id="XMAR:KLE:BAN:BLA:MAC:SCHMU:SCHOL:GUN:WIC:SIM:2012"></a>M. M. Martis, S. Klemme, A. M. Banaei-Moghaddam, F. R. Blattner,
768		J. Macas, T. Schmutzer, U. Scholz, H. Gundlach, T. Wicker, H. Šimková,
769		P. Novak, P. Neumann, M. Kubalakova, E. Bauer, G. Haseneyer, J. Fuchs,
770		J. Dolezel, N. Stein, K. F. Mayer, and A. Houben. Selﬁsh supernumerary
771		chromosome reveals its origin as a mosaic of host genome and organellar
772		sequences. <span
773		class="ptmri7t-x-x-120">Proc. Natl. Acad. Sci. U.S.A.</span>, 109(33):13343–13346, Aug
774		2012
775		<!--l. 294--><p class="noindent" >In this work <span
776		class="ptmri7t-x-x-120">Vmatch </span>was used to match reads against a repeat library to identity
777		the content of the repetitive DNA per sequence read.
778		</p></li>
779		<li
780		class="enumerate" id="x1-11052x26"><a
781		id="XCHI:DAV:BUE:2011"></a>K. L. Childs, R. M. Davidson, and C. R. Buell. Gene coexpression network
782		analysis as a source of functional annotation for rice genes. <span
783		class="ptmri7t-x-x-120">PloS one</span>,
784		6(7):e22196, 2011
785		<!--l. 297--><p class="noindent" >In this work <span
786		class="ptmri7t-x-x-120">Vmatch </span>was used to align individual probes to representative gene
787		models.
788		</p></li>
789		<li
790		class="enumerate" id="x1-11054x27"><a
791		id="XSEV:DIJ:HAM:2011"></a>E. I. Severing, A. D. J. van Dijk, and R. C. H. J. van Ham. Assessing the
792		contribution of alternative splicing to proteome diversity in arabidopsis thaliana
793
794
795
796		using proteomics data. <span
797		class="ptmri7t-x-x-120">BMC Plant Biology</span>, 11(1):82, 2011
798		<!--l. 301--><p class="noindent" >In this work <span
799		class="ptmri7t-x-x-120">Vmatch </span>was used for performing exact searches with peptides
800		against the ﬁltered proteome of <span
801		class="ptmri7t-x-x-120">A. thaliana</span>.
802		</p></li>
803		<li
804		class="enumerate" id="x1-11056x28"><a
805		id="XWOL:WEI:SEG:ROS:BEI:DON:SPI:NOR:REH:KOE:2011"></a>P. Wolﬀ, I. Weinhofer, J. Seguin, P. Roszak, C. Beisel, M.T. Donoghue,
806		C. Spillane, M. Nordborg, M. Rehmsmeier, and C. Köhler. High-resolution
807		analysis of parent-of-origin allelic expression in the arabidopsis endosperm. <span
808		class="ptmri7t-x-x-120">PLoS</span>
809		<span
810		class="ptmri7t-x-x-120">Genet</span>, 7(6):e1002126–e1002126, 2011
811		<!--l. 307--><p class="noindent" >In this work <span
812		class="ptmri7t-x-x-120">Vmatch </span>was used to map RNAseq reads, allowing up to two
813		mismatches (option <span
814		class="cmtt-12">-h 2</span>) and generating maximal substring matches that are
815		unique in some reference dataset (option <span
816		class="cmtt-12">-mum cand</span>).
817		</p></li>
818		<li
819		class="enumerate" id="x1-11058x29"><a
820		id="XFLE:KHA:JOH:YOU:MIT:WRE:HES:FOS:SCHAR:SCO:2011"></a>D. J. Fleetwood, A. K. Khan, R. D. Johnson, C. A. Young, S. Mittal, R. E.
821		Wrenn, U. Hesse, S. J. Foster, C. L. Schardl, and B. Scott. Abundant
822		degenerate miniature inverted-repeat transposable elements in genomes of
823		epichloid fungal endophytes of grasses. <span
824		class="ptmri7t-x-x-120">Genome Biol Evol</span>, 3:1253–1264,
825		2011
826		<!--l. 312--><p class="noindent" >In this work <span
827		class="ptmri7t-x-x-120">Vmatch </span>was used to identify terminal inverted repeats of length
828		range 10-65 bp, <span
829		class="zptmcm7y-x-x-120">≥ </span><span
830		class="zptmcm7t-x-x-120">80% </span>identity, maximum inter-TIR distance 650 bp in in
831		genomes of epichloid fungal endophytes of grasses.
832		</p></li>
833		<li
834		class="enumerate" id="x1-11060x30"><a
835		id="XCHI:KON:BUE:2012"></a>K. L. Childs, K. Konganti, and C. R. Buell. The Biofuel Feedstock Genomics
836		Resource: a web-based portal and database to enable functional genomics
837		of plant biofuel feedstock species. <span
838		class="ptmri7t-x-x-120">Database (Oxford)</span>, 2012:bar061,
839		2012
840		<!--l. 315--><p class="noindent" >In this work <span
841		class="ptmri7t-x-x-120">Vmatch </span>was used to match putative unique transcript sequence
842		assemblies.
843		</p></li>
844		<li
845		class="enumerate" id="x1-11062x31"><a
846		id="XCHE:CAS:BAI:RED:MIC:2012"></a>Y. Chen, B. J. Cassone, X. Bai, M. G. Redinbaugh, and A. P. Michel.
847		Transcriptome of the plant virus vector Graminella nigrifrons, and the molecular
848		interactions of maize ﬁne streak rhabdovirus transmission. <span
849		class="ptmri7t-x-x-120">PLoS ONE</span>,
850		7(7):e40613, 2012
851		<!--l. 319--><p class="noindent" >In this work <span
852		class="ptmri7t-x-x-120">Vmatch </span>was used for reﬁning assemblies of Illumina reads in
853
854
855
856		the context of a transcriptome project for plant virus vector <span
857		class="ptmri7t-x-x-120">Graminella</span>
858		<span
859		class="ptmri7t-x-x-120">nigrifrons</span>.
860		</p></li>
861		<li
862		class="enumerate" id="x1-11064x32"><a
863		id="XKRI:PAT:JAI:GAU:CHOU:VAI:DEE:HAR:KRI:NAI:2012"></a>N. M. Krishnan, S. Pattnaik, P. Jain, P. Gaur, R. Choudhary, S. Vaidyanathan,
864		S. Deepak, A. K. Hariharan, P. B. Krishna, J. Nair, L. Varghese, N. K.
865		Valivarthi, K. Dhas, K. Ramaswamy, and B. Panda. A draft of the genome and
866		four transcriptomes of a medicinal and pesticidal angiosperm Azadirachta indica.
867		<span
868		class="ptmri7t-x-x-120">BMC Genomics</span>, 13:464, 2012
869		<!--l. 324--><p class="noindent" >In this work <span
870		class="ptmri7t-x-x-120">Vmatch </span>was used for clustering repeats and for building a consensus
871		repeat library in the context of genome and transcriptome projects for <span
872		class="ptmri7t-x-x-120">Azadirachta</span>
873		<span
874		class="ptmri7t-x-x-120">indica</span>, a medicinal and pesticidal angiosperm.
875		</p></li>
876		<li
877		class="enumerate" id="x1-11066x33"><a
878		id="XLIU:KUM:ZHA:ZHE:WAR:2012"></a>Z. Liu, S. Kumari, L. Zhang, Y. Zheng, and D. Ware. Characterization of
879		mirnas in response to short-term waterlogging in three inbred lines of zea mays.
880		<span
881		class="ptmri7t-x-x-120">PLoS One</span>, 7(6):e39786, 2012
882		<!--l. 328--><p class="noindent" >In this work <span
883		class="ptmri7t-x-x-120">Vmatch </span>was used to map unique consensus sequences tags to the
884		maize reference genome and to predict targets of novel miRNAs.
885		</p></li>
886		<li
887		class="enumerate" id="x1-11068x34"><a
888		id="XBOU:KOU:PAV:MIN:TSA:DAR:2012"></a>A. Bousios, Y. A. I. Kourmpetis, P. Pavlidis, E. Minga, A. Tsaftaris, and
889		N. Darzentas. The turbulent life of sirevirus retrotransposons and the evolution of
890		the maize genome: more than ten thousand elements tell the story. <span
891		class="ptmri7t-x-x-120">The Plant</span>
892		<span
893		class="ptmri7t-x-x-120">Journal</span>, 69(3):475–488, 2012
894		<!--l. 331--><p class="noindent" >In this work <span
895		class="ptmri7t-x-x-120">Vmatch </span>was used for masking Long Terminal Repeats in the Maize
896		Genome Sequence.
897		</p></li>
898		<li
899		class="enumerate" id="x1-11070x35">In the papers
900		<!--l. 335--><p class="noindent" ><a
901		id="XHER:MAR:DOR:PFE:GAL:SCHAA:JOU:SIM:VAL:DOL:2012"></a>P. Hernandez, M. Martis, G. Dorado, M. Pfeifer, S. Galvez, S. Schaaf, N. Jouve,
902		H. Šimková, M. Valarik, J. Dolezel, and K. F. Mayer. Next-generation
903		sequencing and syntenic integration of ﬂow-sorted arms of wheat chromosome
904		4A exposes the chromosome structure and gene content. <span
905		class="ptmri7t-x-x-120">Plant J.</span>, 69(3):377–386,
906		Feb 2012
907		</p><!--l. 337--><p class="noindent" ><a
908		id="XPHI:PAU:BER:SOU:CHO:LAU:SIM:SAF:BEL:VAU:2013"></a>R. Philippe, E. Paux, I. Bertin, P. Sourdille, F. Choulet, C. Laugier,
909		H. Šimková, J. Šafář, A. Bellec, S. Vautrin, et al. A high density physical map
910
911
912
913		of chromosome 1bl supports evolutionary studies, map-based cloning and
914		sequencing in wheat. <span
915		class="ptmri7t-x-x-120">Genome Biol</span>, 14(6):R64, 2013
916		</p><!--l. 339--><p class="noindent" ><span
917		class="ptmri7t-x-x-120">Vmatch </span>was used to mask repetitive DNA.
918		</p></li>
919		<li
920		class="enumerate" id="x1-11072x36"><a
921		id="XHOW:YU:KNA:CRO:KOL:DOL:LOR:DEA:2013"></a>G. T. Howe, J. Yu, B. Knaus, R. Cronn, S. Kolpak, P. Dolan, W. W. Lorenz,
922		and J. F. Dean. A SNP resource for Douglas-ﬁr: de novo transcriptome
923		assembly and SNP detection and validation. <span
924		class="ptmri7t-x-x-120">BMC Genomics</span>, 14:137,
925		2013
926		<!--l. 342--><p class="noindent" >In this work <span
927		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster 40 010 assembled isotigs.
928		</p></li>
929		<li
930		class="enumerate" id="x1-11074x37"><a
931		id="XKAR:HAA:MAL:GEE:BOV:LAM:ANG:MAA:2013"></a>R. Karlova, J. C. van Haarst, C. Maliepaard, H. van de Geest, A. G. Bovy,
932		M. Lammers, G. C. Angenent, and R. A. de Maagd. Identiﬁcation of
933		microRNA targets in tomato fruit development using high-throughput
934		sequencing and degradome analysis. <span
935		class="ptmri7t-x-x-120">J. Exp. Bot.</span>, 64(7):1863–1878, Apr
936		2013
937		<!--l. 346--><p class="noindent" >In this work <span
938		class="ptmri7t-x-x-120">Vmatch </span>was used to preprocess short reads in the context of
939		identifying mircoRNA targets in tomato fruit development.
940		</p></li>
941		<li
942		class="enumerate" id="x1-11076x38"><a
943		id="XGRO:MAR:SIM:ABR:WAN:VIS:2013"></a>S. M. Gross, J. A. Martin, J. Simpson, M. J. Abraham-Juarez, Z. Wang, and
944		A. Visel. De novo transcriptome assembly of drought tolerant CAM
945		plants, Agave deserti and Agave tequilana. <span
946		class="ptmri7t-x-x-120">BMC Genomics</span>, 14:563,
947		2013
948		<!--l. 351--><p class="noindent" >In this work <span
949		class="ptmri7t-x-x-120">Vmatch </span>was used in an all-vs-all comparison to bin contigs into loci
950		based on a minimum of 200 bp sequence overlap in the context of transcriptome
951		assembly for two Agave-species.
952		</p></li>
953		<li
954		class="enumerate" id="x1-11078x39"><a
955		id="XKAN:HEL:DUR:WIN:ENG:BEH:HOL:BRA:HAU:FER:2013"></a>U. Kanter, W. Heller, J. Durner, J. B. Winkler, M. Engel, H. Behrendt,
956		A. Holzinger, P. Braun, M. Hauser, F. Ferreira, K. Mayer, M. Pfeifer, and
957		D. Ernst. Molecular and immunological characterization of ragweed (Ambrosia
958		artemisiifolia L.) pollen after exposure of the plants to elevated ozone over a
959		whole growing season. <span
960		class="ptmri7t-x-x-120">PLoS ONE</span>, 8(4):e61518, 2013
961		<!--l. 354--><p class="noindent" >In this work <span
962		class="ptmri7t-x-x-120">Vmatch </span>was used to align 454-reads to assembled isotigs for
963		Ragweed pollen.
964
965
966
967		</p></li>
968		<li
969		class="enumerate" id="x1-11080x40"><a
970		id="XKUG:SIE:NUS:AME:SPAN:STEI:LEM:MAY:BUE:SCHWE:2013"></a>K. G. Kugler, G. Siegwart, T. Nussbaumer, C. Ametz, M. Spannagl,
971		B. Steiner, M. Lemmens, K. F. X. Mayer, H. Buerstmayr, and W. Schweiger.
972		Quantitative trait loci-dependent analysis of a gene co-expression network
973		associated with fusarium head blight resistance in bread wheat (triticum aestivum
974		l.). <span
975		class="ptmri7t-x-x-120">BMC Genomics</span>, 14(1):728, 2013
976		<!--l. 357--><p class="noindent" >In this work <span
977		class="ptmri7t-x-x-120">Vmatch </span>was used for comparing gene sets.
978		</p></li>
979		<li
980		class="enumerate" id="x1-11082x41"><a
981		id="XMAR:ZHO:HAS:SCHMU:VRA:KUB:KOEN:KUG:SCHOL:HAC:2013"></a>Mihaela M Martis, Ruonan Zhou, Grit Haseneyer, Thomas Schmutzer, Jan
982		Vrána, Marie Kubaláková, Susanne König, Karl G Kugler, Uwe Scholz, Bernd
983		Hackauf, et al. Reticulate evolution of the rye genome. <span
984		class="ptmri7t-x-x-120">The Plant Cell</span>,
985		25(10):3685–3698, 2013
986		<!--l. 361--><p class="noindent" >In this work <span
987		class="ptmri7t-x-x-120">Vmatch </span>was used to detect repetitive DNA content of chromosomal
988		survey sequences from the Rye genome.
989		</p></li>
990		<li
991		class="enumerate" id="x1-11084x42">In the papers
992		<!--l. 366--><p class="noindent" ><a
993		id="XKOP:MAR:VHA:HRV:VRA:BAR:KOP:CAT:STO:NOV:2013"></a>D. Kopeckỳ, M. Martis, J. Číhalíková, E. Hřibová, J. Vrána, J. Bartoš,
994		J. Kopecká, F. Cattonaro, Š. Stočes, Petr Novák, et al. Flow sorting and
995		sequencing meadow fescue chromosome 4f. <span
996		class="ptmri7t-x-x-120">Plant Physiology</span>, 163(3):1323–1337,
997		2013
998		</p><!--l. 368--><p class="noindent" ><a
999		id="XKOP:MAR:CHA:HRI:VRA:BAR:2013"></a>D. Kopeckỳ, M Martis, J Číhalíková, E Hřibová, J Vrána, J Bartoš, et al.
1000		Genomics of meadow fescue chromosome 4f. <span
1001		class="ptmri7t-x-x-120">Plant Physiol</span>, 163:1323–1337,
1002		2013
1003		</p><!--l. 370--><p class="noindent" ><span
1004		class="ptmri7t-x-x-120">Vmatch </span>was used for identifying repetitive DNA content in contigs of meadow
1005		fescue chromosome 4F assembled from Illumina short reads.
1006		</p></li>
1007		<li
1008		class="enumerate" id="x1-11086x43">In the papers
1009		<!--l. 377--><p class="noindent" ><a
1010		id="XJAY:WAN:YU:TAC:PEL:COL:REN:VOI:2011"></a>F. Jay, Y. Wang, A. Yu, L. Taconnat, S. Pelletier, V. Colot, J.-P. Renou, and
1011		O. Voinnet. Misregulation of <span
1012		class="ptmri7t-x-x-120">AUXIN RESPONSE FACTOR 8 </span>underlies the
1013		developmental abnormalities caused by three distinct viral silencing
1014		suppressors in <span
1015		class="ptmri7t-x-x-120">Arabidopsis</span>. <span
1016		class="ptmri7t-x-x-120">PLoS Pathog</span>, 7(5):e1002035–e1002035,
1017		2011
1018		</p><!--l. 379--><p class="noindent" ><a
1019		id="XWAN:WEI:SMI:2013"></a>X. Wang, D. Weigel, and L. M. Smith. Transposon variants and their
1020
1021
1022
1023		eﬀects on gene expression in arabidopsis. <span
1024		class="ptmri7t-x-x-120">PLoS Genet</span>, 9(2):e1003255,
1025		2013
1026		</p><!--l. 381--><p class="noindent" ><span
1027		class="ptmri7t-x-x-120">Vmatch </span>was used for mapping siRNA sequences to the <span
1028		class="ptmri7t-x-x-120">Arabidopsis thaliana</span>
1029		genome.
1030		</p></li>
1031		<li
1032		class="enumerate" id="x1-11088x44"><a
1033		id="XHEN:VIV:DES:CHAU:PAY:GUT:CAS:2014"></a>E. Henaﬀ, C. Vives, B. Desvoyes, A. Chaurasia, J. Payet, C. Gutierrez, and
1034		J. M. Casacuberta. Extensive ampliﬁcation of the E2F transcription factor
1035		binding sites by transposons during evolution of Brassica species. <span
1036		class="ptmri7t-x-x-120">Plant J.</span>,
1037		77(6):852–862, Mar 2014
1038		<!--l. 385--><p class="noindent" >In this work <span
1039		class="ptmri7t-x-x-120">Vmatch </span>was used for the identiﬁcation of binding motifs.
1040		</p></li>
1041		<li
1042		class="enumerate" id="x1-11090x45"><a
1043		id="XWAN:HAB:GUN:GLAE:NUS:LUO:LOM:BOR:KER:SHA:2014"></a>W Wang, G Haberer, H Gundlach, C Gläßer, TCLM Nussbaumer,
1044		MC Luo, A Lomsadze, M Borodovsky, RA Kerstetter, J Shanklin,
1045		et al. The <span
1046		class="ptmri7t-x-x-120">Spirodela polyrhiza </span>genome reveals insights into its neotenous
1047		reduction fast growth and aquatic lifestyle. <span
1048		class="ptmri7t-x-x-120">Nature Communications</span>, 5,
1049		2014
1050		<!--l. 390--><p class="noindent" >In this work <span
1051		class="ptmri7t-x-x-120">Vmatch </span>was used for masking one sequence set with another and for
1052		mapping miRNA sequences of all plant species present in a reference database to
1053		whole-genome assembly of <span
1054		class="ptmri7t-x-x-120">Spirodela polyrhiza</span>.
1055		</p></li>
1056		<li
1057		class="enumerate" id="x1-11092x46"><a
1058		id="XLOG:SCHEL:NUR:SAM:PEN:2014"></a>M. D. Logacheva, M. I. Schelkunov, M. S. Nuraliev, T. H. Samigullin, and
1059		A. A. Penin. The plastid genome of mycoheterotrophic monocot petrosavia
1060		stellaris exhibits both gene losses and multiple rearrangements. <span
1061		class="ptmri7t-x-x-120">Genome biology</span>
1062		<span
1063		class="ptmri7t-x-x-120">and evolution</span>, 6(1):238–246, 2014
1064		<!--l. 393--><p class="noindent" >In this work <span
1065		class="ptmri7t-x-x-120">Vmatch </span>was used for repeat detection.
1066		</p></li>
1067		<li
1068		class="enumerate" id="x1-11094x47"><a
1069		id="XWAN:SHI:RIN:2015"></a>X. Wang, W. Shi, and T. Rinehart. Transcriptomes That Confer to Plant Defense
1070		against Powdery Mildew Disease in Lagerstroemia indica. <span
1071		class="ptmri7t-x-x-120">Int J Genomics</span>,
1072		2015:528395, 2015
1073		<!--l. 397--><p class="noindent" >In this work <span
1074		class="ptmri7t-x-x-120">Vmatch </span>was used to eliminate redundancies in assemblies of
1075		Illumina reads in the context of studying plant defense mechanisms.
1076		</p></li>
1077		<li
1078		class="enumerate" id="x1-11096x48"><a
1079		id="XASH:HUL:WAN:YAN:GUA:JON:MAT:MOC:CHE:STE:2015"></a>H. Ashraﬁ, A. M. Hulse-Kemp, F. Wang, S. S. Yang, X. Guan, D. C. Jones,
1080
1081
1082
1083		M. Matvienko, K. Mockaitis, Z. J. Chen, D. M. Stelly, et al. A long-read
1084		transcriptome assembly of cotton (l.) and intraspeciﬁc single nucleotide
1085		polymorphism discovery. <span
1086		class="ptmri7t-x-x-120">The Plant Genome</span>, 2015
1087		<!--l. 400--><p class="noindent" >In this work <span
1088		class="ptmri7t-x-x-120">Vmatch </span>was used for clustering to determine a non-redundant set of
1089		assembled contigs.
1090		</p></li>
1091		<li
1092		class="enumerate" id="x1-11098x49"><a
1093		id="XUST:NOV:BLI:SMY:2015"></a>K. Ustyantsev, O. Novikova, A. Blinov, and G. Smyshlyaev. Convergent
1094		evolution of ribonuclease h in ltr retrotransposons and retroviruses. <span
1095		class="ptmri7t-x-x-120">Molecular</span>
1096		<span
1097		class="ptmri7t-x-x-120">biology and evolution</span>, 32(5):1197–1207, 2015
1098		<!--l. 403--><p class="noindent" >In this work <span
1099		class="ptmri7t-x-x-120">Vmatch </span>was used for clustering sequences based on their RT and
1100		aRNH domain.
1101		</p></li>
1102		<li
1103		class="enumerate" id="x1-11100x50"><a
1104		id="XHLE:RIV:CLA:MAR:VAN:GON:GAR:LER:SIM:VAL:2015"></a>M. Helguera, M. Rivarola, B. Clavijo, M. M. Martis, L. S. Vanzetti,
1105		S. González, I. Garbus, P. Leroy, H. Šimková, M. Valárik, et al. New insights
1106		into the wheat chromosome 4d structure and virtual gene order, revealed by
1107		survey pyrosequencing. <span
1108		class="ptmri7t-x-x-120">Plant Science</span>, 233:200–212, 2015
1109		<!--l. 406--><p class="noindent" >In this work <span
1110		class="ptmri7t-x-x-120">Vmatch </span>was used for identifying repeats in contigs assembled from
1111		454-reads.
1112		</p></li>
1113		<li
1114		class="enumerate" id="x1-11102x51"><a
1115		id="XSHE:YAN:LU:WAN:SON:2015"></a>Qi Shen, Jun Yang, Chaolong Lu, Bo Wang, and Chi Song. The complete
1116		chloroplast genome sequence of perilla frutescens (l.). <span
1117		class="ptmri7t-x-x-120">Mitochondrial DNA</span>,
1118		preprint:1–2, 2015
1119		<!--l. 409--><p class="noindent" >In this work <span
1120		class="ptmri7t-x-x-120">Vmatch </span>was used for identifying inverted repeats in chloroplast
1121		genomes.
1122		</p></li>
1123		<li
1124		class="enumerate" id="x1-11104x52"><a
1125		id="XPAN:MOH:KHA:MEH:EBR:2015"></a>Bahman Panahi, Seyed Abolghasem Mohammadi, Reyhaneh Ebrahimi
1126		Khakseﬁdi, Jalil Fallah Mehrabadi, and Esmaeil Ebrahimie. Genome-wide
1127		analysis of alternative splicing events in <span
1128		class="ptmri7t-x-x-120">Hordeum vulgare</span>: Highlighting retention
1129		of intron-based splicing and its possible function through network analysis. <span
1130		class="ptmri7t-x-x-120">FEBS</span>
1131		<span
1132		class="ptmri7t-x-x-120">letters</span>, 589(23):3564–3575, 2015
1133		<!--l. 413--><p class="noindent" >In this work <span
1134		class="ptmri7t-x-x-120">Vmatch </span>was used to identify contaminations and repetitive
1135		elements by comparison of mRNA sequences to vector, bacterial and repeat
1136		databases.
1137
1138
1139
1140		</p></li>
1141		<li
1142		class="enumerate" id="x1-11106x53"><a
1143		id="XWOL:TWO:GAD:KNA:GRU:GEN:2015"></a>SN Wolfenbarger, MC Twomey, DM Gadoury, BJ Knaus, NJ Grünwald, and
1144		DH Gent. Identiﬁcation and distribution of mating-type idiomorphs in
1145		populations of podosphaera macularis and development of chasmothecia of the
1146		fungus. <span
1147		class="ptmri7t-x-x-120">Plant Pathology</span>, 2015
1148		<!--l. 416--><p class="noindent" >In this work <span
1149		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster contigs of diﬀerent assemblies into
1150		groups of homologous sequences.
1151		</p></li>
1152		<li
1153		class="enumerate" id="x1-11108x54"><a
1154		id="XYAN:LU:SHE:YAN:XU:SON:2015"></a>Jun Yang, Chaolong Lu, Qi Shen, Yuying Yan, Changjiang Xu, and Chi Song.
1155		The complete chloroplast genome sequence of Fagopyrum cymosum.
1156		<span
1157		class="ptmri7t-x-x-120">Mitochondrial DNA</span>, pages 1–2, 2015
1158		<!--l. 419--><p class="noindent" >In this work <span
1159		class="ptmri7t-x-x-120">Vmatch </span>was used to identify inverted repeats in chloroplast
1160		genomes.
1161		</p>
1162		</li></ol>
1163		<!--l. 424--><p class="noindent" >
1164		</p>
1165		<h4 class="likesubsectionHead"><a
1166		id="x1-12000"></a>Usages in the Microbial Genome Research</h4>
1167		<!--l. 425--><p class="noindent" >
1168		</p><ol class="enumerate1" >
1169		<li
1170		class="enumerate" id="x1-12002x1">The <a
1171		href="http://www.llnl.gov/str/April04/Slezak.html" >KPATH system</a>, developed at the Lawrence Livermore National
1172		Laboratories, and described in
1173		<!--l. 432--><p class="noindent" ><a
1174		id="XFIT:GAR:KUC:KUR:MYE:OTT:SLE:VIT:ZEM:MCC:2002"></a>J.P. Fitch, S.N. Gardner, T.A. Kuczmarski, S. Kurtz, R. Myers, L.L.
1175		Ott, T.R. Slezak, E.A. Vitalis, A.T. Zemla, and P.M. McCready. Rapid
1176		development of nucleic acid diagnostics. <span
1177		class="ptmri7t-x-x-120">Proceedings of the IEEE</span>,
1178		90(11):1708–1721, 2002
1179		</p><!--l. 434--><p class="noindent" ><a
1180		id="XSLE:KUC:OTT:TOR:MED:SMI:TRU:MUL:LAM:VIT:ZEM:ZHO:GAR:2003"></a>T. Slezak, T. Kuczmarski, L. Ott, C. Torres, D. Medeiros, J. Smith,
1181		B. Truitt, N. Mulakken, M. Lam, E. Vitalis, A. Zemla, C.E. Zhou, and
1182		S. Gardner. Comparative Genomics Tools Applied to Bioterrorism
1183		Defense. <span
1184		class="ptmri7t-x-x-120">Brieﬁngs in Bioinformatics</span>, 4(2):133–149, 2003
1185
1186
1187
1188		</p><!--l. 436--><p class="noindent" >used <span
1189		class="ptmri7t-x-x-120">Vmatch </span>to detect unique substrings in large collection of DNA
1190		sequences. These unique substrings serve as signatures allowing for rapid
1191		and accurate diagnostics to identify pathogen bacteria and viruses. A
1192		similar application is reported in <a
1193		id="XGAR:KUC:VIT:SLE:2003"></a>S.N. Gardner, T.A. Kuczmarski, E.A.
1194		Vitalis, and T.R. Slezak. Limitations of TaqMan PCR for Detecting Viral
1195		Pathogens I llustrated by Hepatitis A, B, C, and E Viruses and Human
1196		Immunodeﬁciency Virus. <span
1197		class="ptmri7t-x-x-120">J.</span><span
1198		class="ptmri7t-x-x-120"> of Clinical Microbiology</span>, 41(6):2417–2427,
1199		2003.
1200		</p></li>
1201		<li
1202		class="enumerate" id="x1-12004x2"><a
1203		id="XPOB:WET:SZY:SCHIL:KUR:MEY:NAT:BECK:2006"></a>N. Pobigaylo, D. Wetter, S. Szymczak, U. Schiller, S. Kurtz, F. Meyer,
1204		T.W. Nattkemper, and Becker A. Construction of a large signature-tagged
1205		mini-Tn5 transposon library and its application to mutagenesis of
1206		<span
1207		class="ptmri7t-x-x-120">Sinorhizobium meliloti</span>. <span
1208		class="ptmri7t-x-x-120">Appl Environ Microbiol.</span>, 72(6):4329–4337, 2006
1209		<!--l. 444--><p class="noindent" >In this work <span
1210		class="ptmri7t-x-x-120">Vmatch </span>was used to map signature tags to the genome of
1211		<span
1212		class="ptmri7t-x-x-120">S.</span><span
1213		class="ptmri7t-x-x-120"> meliloti</span>.
1214		</p></li>
1215		<li
1216		class="enumerate" id="x1-12006x3">The <a
1217		href="http://crispr.u-psud.fr/Server/CRISPRfinder.php" >CRISPRFinder</a>-program and the <a
1218		href="http://crispr.u-psud.fr/crispr/CRISPRdatabase.php" >CRISPRdatabase</a>, described in
1219		<!--l. 452--><p class="noindent" ><a
1220		id="XGRI:VER:POU:2007A"></a>I. Grissa, G. Vergnaud, and C. Pourcel. CRISPRFinder: a web tool to
1221		identify clustered regularly interspaced short palindromic repeats. <span
1222		class="ptmri7t-x-x-120">Nucleic</span>
1223		<span
1224		class="ptmri7t-x-x-120">Acids Res</span>, 35(Web Server issue):W52–7, 2007
1225		</p><!--l. 454--><p class="noindent" ><a
1226		id="XGRI:VER:POU:2007B"></a>I. Grissa, G. Vergnaud, and C. Pourcel. The CRISPRdb database and tools
1227		to display CRISPRs and to generate dictionaries of spacers and repeats.
1228		<span
1229		class="ptmri7t-x-x-120">BMC Bioinformatics</span>, 8:172, 2007
1230		</p><!--l. 456--><p class="noindent" >used <span
1231		class="ptmri7t-x-x-120">Vmatch </span>to eﬃciently ﬁnd maximal repeats, as a ﬁrst step in localizing
1232		Clustered regularly interspaced short palindromic repeats (CRISPRs).
1233		</p></li>
1234		<li
1235		class="enumerate" id="x1-12008x4"><a
1236		id="XVOSS:GEO:SCHOE:UDE:HES:2009"></a>B. Voss, J. Georg, V. Schöon, S. Ude, and W. R. Hess. Biocomputational
1237		prediction of non-coding RNAs in model cyanobacteria. <span
1238		class="ptmri7t-x-x-120">BMC Genomics</span>,
1239		10:123, 2009
1240		<!--l. 462--><p class="noindent" >In this work <span
1241		class="ptmri7t-x-x-120">Vmatch </span>was used to map predicted sequences to information
1242		about Rho-independent terminators provided by a speciﬁc database.
1243		</p></li>
1244		<li
1245		class="enumerate" id="x1-12010x5"><a
1246		id="XSCHMU:CAN:SCHLU:MA:MIT:NEL:HYT:SON:THE:CHE:2010"></a>Jeremy Schmutz, Steven B Cannon, Jessica Schlueter, Jianxin Ma, Therese
1247
1248
1249
1250		Mitros, William Nelson, David L Hyten, Qijian Song, Jay J Thelen, Jianlin
1251		Cheng, et al. Genome sequence of the palaeopolyploid soybean. <span
1252		class="ptmri7t-x-x-120">Nature</span>,
1253		463(7278):178–183, 2010
1254		<!--l. 466--><p class="noindent" >In this work <span
1255		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster DNA-sequences into families based
1256		on their six-frame translation.
1257		</p></li>
1258		<li
1259		class="enumerate" id="x1-12012x6"><a
1260		id="XZIM:GES:CHE:LOR:SCHRO:2010"></a>Bob Zimmermann, Tanja Gesell, Doris Chen, Christina Lorenz, Renée
1261		Schroeder, and J Valcarcel. Monitoring genomic sequences during selex
1262		using high-throughput sequencing: neutral selex. <span
1263		class="ptmri7t-x-x-120">PLoS One</span>, 5(2):e9169,
1264		2010
1265		<!--l. 469--><p class="noindent" >In this work <span
1266		class="ptmri7t-x-x-120">Vmatch </span>was used to align 454-sequences to the Ecoli-genome
1267		and to cluster the sequences.
1268		</p></li>
1269		<li
1270		class="enumerate" id="x1-12014x7"><a
1271		id="XTOU:DEN:MED:BAR:ELK:PET:2010"></a>Fabrice Touzain, Erick Denamur, Claudine Médigue, Valérie Barbe,
1272		Meriem El Karoui, Marie-Agnès Petit, et al. Small variable segments
1273		constitute a major type of diversity of bacterial genomes at the species level.
1274		<span
1275		class="ptmri7t-x-x-120">Genome Biol</span>, 11(4):R45, 2010
1276		<!--l. 472--><p class="noindent" >In this work <span
1277		class="ptmri7t-x-x-120">Vmatch </span>was used for detecting repeats in three bacterial
1278		species.
1279		</p></li>
1280		<li
1281		class="enumerate" id="x1-12016x8"><a
1282		id="XMAY:MAR:HED:SIM:LIU:MOR:STEU:TAU:ROE:GUN:2011"></a>Klaus FX Mayer, Mihaela Martis, Pete E Hedley, Hana Šimková, Hui Liu,
1283		Jenny A Morris, Burkhard Steuernagel, Stefan Taudien, Stephan Roessner,
1284		Heidrun Gundlach, et al. Unlocking the barley genome by chromosomal
1285		and comparative genomics. <span
1286		class="ptmri7t-x-x-120">The Plant Cell</span>, 23(4):1249–1263, 2011
1287		<!--l. 475--><p class="noindent" >In this work <span
1288		class="ptmri7t-x-x-120">Vmatch </span>was used for masking repeats in 454-reads.
1289		</p></li>
1290		<li
1291		class="enumerate" id="x1-12018x9"><a
1292		id="XPUS:MAN:JI:LI:EVA:CRA:MOR:MEA:SIN:SAX:2011"></a>Smruti Pushalkar, Shrinivasrao P Mane, Xiaojie Ji, Yihong Li, Clive Evans,
1293		Oswald R Crasta, Douglas Morse, Robert Meagher, Anup Singh, and
1294		Deepak Saxena. Microbial diversity in saliva of oral squamous cell
1295		carcinoma. <span
1296		class="ptmri7t-x-x-120">FEMS Immunology & Medical Microbiology</span>, 61(3):269–277,
1297		2011
1298		<!--l. 478--><p class="noindent" >In this work <span
1299		class="ptmri7t-x-x-120">Vmatch </span>was used to identify distal primers.
1300
1301
1302
1303		</p></li>
1304		<li
1305		class="enumerate" id="x1-12020x10"><a
1306		id="XBRE:SHE:POP:2011"></a>J. E. Breitenbach, K. S. Shelby, and H. JR Popham. Baculovirus induced
1307		transcripts in hemocytes from the larvae of heliothis virescens. <span
1308		class="ptmri7t-x-x-120">Viruses</span>,
1309		3(11):2047–2064, 2011
1310		<!--l. 483--><p class="noindent" >In this work <span
1311		class="ptmri7t-x-x-120">Vmatch </span>was used for removing redundant transcripts
1312		assembled in an RNA-seq study based on Illumina reads for <span
1313		class="ptmri7t-x-x-120">Heliothis</span>
1314		<span
1315		class="ptmri7t-x-x-120">virescens </span>(tobacco budworm), infected with a virus.
1316		</p></li>
1317		<li
1318		class="enumerate" id="x1-12022x11"><a
1319		id="XTRI:HAM:BUE:TIS:VER:ZIN:LEA:2011"></a>LR Triplett, JP Hamilton, CR Buell, NA Tisserat, V. Verdier, F Zink,
1320		and JE Leach. Genomic analysis of xanthomonas oryzae isolates from
1321		rice grown in the united states reveals substantial divergence from
1322		known x. oryzae pathovars. <span
1323		class="ptmri7t-x-x-120">Applied and Environmental Microbiology</span>,
1324		77(12):3930–3937, 2011
1325		<!--l. 488--><p class="noindent" >In this work <span
1326		class="ptmri7t-x-x-120">Vmatch </span>was used to search unassembled Illumina reads of US
1327		and African strains of <span
1328		class="ptmri7t-x-x-120">Xanthomonas oryzae </span>for evidence of transcriptional
1329		activator-like eﬀector sequences.
1330		</p></li>
1331		<li
1332		class="enumerate" id="x1-12024x12"><span
1333		class="ptmri7t-x-x-120">Vmatch </span>is used as an integral part of the PriMUX software package
1334		described in
1335		<!--l. 493--><p class="noindent" ><a
1336		id="XHYS:NAR:ELS:CAR:WIL:GAR:2012"></a>D. A. Hysom, P. Naraghi-Arani, M. Elsheikh, A. C. Carrillo, P. L.
1337		Williams, and S. N. Gardner. Skip the alignment: degenerate, multiplex
1338		primer and probe design using K-mer matching instead of alignments. <span
1339		class="ptmri7t-x-x-120">PLoS</span>
1340		<span
1341		class="ptmri7t-x-x-120">ONE</span>, 7(4):e34560, 2012
1342		</p><!--l. 495--><p class="noindent" >In this context <span
1343		class="ptmri7t-x-x-120">Vmatch </span>used for selecting multiplex compatible, degenerate
1344		primers and probes to detect diverse targets such as viruses.
1345		</p></li>
1346		<li
1347		class="enumerate" id="x1-12026x13"><a
1348		id="XSHE:POP:2012"></a>K. S. Shelby and H. JR Popham. Rna-seq study of microbially
1349		induced hemocyte transcripts from larval heliothis virescens (lepidoptera:
1350		Noctuidae). <span
1351		class="ptmri7t-x-x-120">Insects</span>, 3(3):743–762, 2012
1352		<!--l. 499--><p class="noindent" >In this work <span
1353		class="ptmri7t-x-x-120">Vmatch </span>was used to identify redundant contigs from de novo
1354		exome assemblies.
1355		</p></li>
1356		<li
1357		class="enumerate" id="x1-12028x14"><a
1358		id="XHUR:SUL:2013"></a>B. L. Hurwitz and M. B. Sullivan. The Paciﬁc Ocean virome (POV):
1359
1360
1361
1362		a marine viral metagenomic dataset and associated protein clusters for
1363		quantitative viral ecology. <span
1364		class="ptmri7t-x-x-120">PLoS ONE</span>, 8(2):e57355, 2013
1365		<!--l. 503--><p class="noindent" >In this work <span
1366		class="ptmri7t-x-x-120">Vmatch </span>was used to identify reads which have no common
1367		20-mers with other reads in a context of a marine viral metagenome project.
1368		</p></li>
1369		<li
1370		class="enumerate" id="x1-12030x15"><a
1371		id="XZHU:RHO:FESCH:2013"></a>X. Zhuo, M. Rho, and C. Feschotte. Genome-wide characterization of
1372		endogenous retroviruses in the bat Myotis lucifugus reveals recent and
1373		diverse infections. <span
1374		class="ptmri7t-x-x-120">J. Virol.</span>, 87(15):8493–8501, Aug 2013
1375		<!--l. 507--><p class="noindent" >In this work <span
1376		class="ptmri7t-x-x-120">Vmatch </span>was used for clustering potential complete Endogenous
1377		retroviruses of the bat <span
1378		class="ptmri7t-x-x-120">Myotis lucifugus </span>into subfamilies.
1379		</p></li>
1380		<li
1381		class="enumerate" id="x1-12032x16">In the three papers
1382		<!--l. 511--><p class="noindent" ><a
1383		id="XHUR:WES:BRU:SUL:2014"></a>B. L. Hurwitz, A. H. Westveld, J. R. Brum, and M. B. Sullivan.
1384		Modeling ecological drivers in marine viral communities using comparative
1385		metagenomics and network analyses. <span
1386		class="ptmri7t-x-x-120">Proc. Natl. Acad. Sci. U.S.A.</span>,
1387		111(29):10714–10719, July 2014
1388		</p><!--l. 513--><p class="noindent" ><a
1389		id="XHUR:DEN:POU:SUL:2013"></a>B. L. Hurwitz, L. Deng, B. T. Poulos, and M. B. Sullivan. Evaluation
1390		of methods to concentrate and purify ocean virus communities
1391		through comparative, replicated metagenomics. <span
1392		class="ptmri7t-x-x-120">Environ. Microbiol.</span>,
1393		15(5):1428–1440, May 2013
1394		</p><!--l. 515--><p class="noindent" ><a
1395		id="XBRU:HUR:SCHOF:DUC:SUL:2015"></a>J. R. Brum, B. L. Hurwitz, O. Schoﬁeld, H. W. Ducklow, and M. B.
1396		Sullivan. Seasonal time bombs: dominant temperate viruses aﬀect southern
1397		ocean microbial dynamics. <span
1398		class="ptmri7t-x-x-120">The ISME journal</span>, 2015
1399		</p><!--l. 517--><p class="noindent" ><span
1400		class="ptmri7t-x-x-120">Vmatch </span>was used for <span
1401		class="zptmcm7m-x-x-120">k</span>-mer analysis in the context of diﬀerent marine
1402		metagenome projects.
1403		</p></li>
1404		<li
1405		class="enumerate" id="x1-12034x17"><a
1406		id="XDEC:PAR:2014"></a>C. J. Decker and R. Parker. Analysis of double-stranded rna from
1407		microbial communities identiﬁes double-stranded rna virus-like elements.
1408		<span
1409		class="ptmri7t-x-x-120">Cell reports</span>, 7(3):898–906, 2014
1410		<!--l. 521--><p class="noindent" >In this work <span
1411		class="ptmri7t-x-x-120">Vmatch </span>was used for <span
1412		class="zptmcm7m-x-x-120">k</span>-mer analysis in the context of microbial
1413		communities.
1414		</p></li>
1415		<li
1416		class="enumerate" id="x1-12036x18"><a
1417		id="XBEN:BOU:FIC:KRI:LAR:2014"></a>J. Bengtsson-Palme, F. Boulund, J. Fick, E. Kristiansson, and D. G.
1418
1419
1420
1421		Larsson. Shotgun metagenomics reveals a wide array of antibiotic
1422		resistance genes and mobile elements in a polluted lake in India. <span
1423		class="ptmri7t-x-x-120">Front</span>
1424		<span
1425		class="ptmri7t-x-x-120">Microbiol</span>, 5:648, 2014
1426		<!--l. 525--><p class="noindent" >In this work <span
1427		class="ptmri7t-x-x-120">Vmatch </span>was used in an iterative scheme to construct contigs
1428		from reads associated with resistance genes in the context of a shotgun
1429		metagenome project.
1430		</p></li>
1431		<li
1432		class="enumerate" id="x1-12038x19"><a
1433		id="XNIC:THI:GAR:MCL:FOF:KOS:ELL:BRE:JAC:JAI:2013"></a>A Be Nicholas, James B Thissen, Shea N Gardner, Kevin S McLoughlin,
1434		Viacheslav Y Fofanov, Heather Koshinsky, Sally R Ellingson, Thomas S
1435		Brettin, Paul J Jackson, and Crystal J Jaing. Detection of <span
1436		class="ptmri7t-x-x-120">Bacillus</span>
1437		<span
1438		class="ptmri7t-x-x-120">anthracis </span>DNA in complex soil and air samples using next-generation
1439		sequencing. <span
1440		class="ptmri7t-x-x-120">PloS one</span>, 8(9), 2013
1441		<!--l. 529--><p class="noindent" >In this work <span
1442		class="ptmri7t-x-x-120">Vmatch </span>was used to match probe candidate sequences against
1443		viral sequences and the human genmome sequence.
1444		</p></li>
1445		<li
1446		class="enumerate" id="x1-12040x20"><a
1447		id="XHEN:RUM:SCZ:VEL:DIE:GER:GOM:RAH:STO:BOR:2014"></a>Birgit Henrich, Madis Rumming, Alexander Sczyrba, Eunike Velleuer, Ralf
1448		Dietrich, Wolfgang Gerlach, Michael Gombert, Sebastian Rahn, Jens Stoye,
1449		Arndt Borkhardt, et al. <span
1450		class="ptmri7t-x-x-120">Mycoplasma salivarium </span>as a dominant coloniser of
1451		<span
1452		class="ptmri7t-x-x-120">Fanconi anaemia </span>associated oral carcinoma. <span
1453		class="ptmri7t-x-x-120">PloS one</span>, 9(3), 2014
1454		<!--l. 533--><p class="noindent" >In this work <span
1455		class="ptmri7t-x-x-120">Vmatch </span>was used to identify the species of the
1456		Streptococcaceae by comparing with Silva 115 release 16S reference
1457		sequence database.</p></li></ol>
1458		<!--l. 537--><p class="noindent" >
1459		</p>
1460		<h4 class="likesubsectionHead"><a
1461		id="x1-13000"></a>Usages in General Web-Servers or Sequence Analysis Software</h4>
1462		<!--l. 538--><p class="noindent" >
1463		</p><ol class="enumerate1" >
1464		<li
1465		class="enumerate" id="x1-13002x1">Since 2000, the <a
1466		href="http://rsat.ulb.ac.be/rsat/" >RSA-tools</a>, described in
1467		<!--l. 543--><p class="noindent" ><a
1468		id="XHEL:RIO:COL:2000"></a>J. van Helden, A.F. Rios, and J. Collado-Vides. Discovering Regulatory
1469		Elements in Non-Coding Sequences by Analysis of Spaced Dyads. <span
1470		class="ptmri7t-x-x-120">Nucleic</span>
1471
1472
1473
1474		<span
1475		class="ptmri7t-x-x-120">Acids Res.</span>, 28(8):1808–1818, 2000
1476		</p><!--l. 545--><p class="noindent" >and developed by Jacques van Helden use <span
1477		class="ptmri7t-x-x-120">Vmatch </span>to <a
1478		href="http://rsat.ulb.ac.be/rsat/purge-sequence_form.cgi" >purge</a> sequences
1479		before computing sequence statistics. Similar applications are reported in
1480		the following papers:
1481		</p><!--l. 550--><p class="noindent" ><a
1482		id="XHUL:WEE:CRO:GER:HEP:HEL:2003"></a>R.J.M. Hulzink, H. Weerdesteyn, A.F. Croes, M.M.A. Gerats, T. van
1483		Herpen, and J. van Helden. In Silico Identiﬁcation of Putative Regulatory
1484		Sequence Elements in the 5’-Untranslated Region of Genes That Are
1485		Expressed during Male Gametogenesis Gene Co-regulation. <span
1486		class="ptmri7t-x-x-120">Plant Physiol.</span>,
1487		132:75–83, 2003
1488		</p><!--l. 552--><p class="noindent" ><a
1489		id="XSIM:WOD:COH:HEL:2004"></a>N. Simonis, S.J. Wodak, G.N. Cohen, and
1490		J van Helden. Combining Pattern Discovery and Discriminant Analysis to
1491		Predict Gene Co-regulation. <span
1492		class="ptmri7t-x-x-120">Bioinformatics</span>, 20:2370–2379, 2004
1493		</p><!--l. 554--><p class="noindent" ><a
1494		id="XSIM:HEL:COH:WOD:2004"></a>N. Simonis, J. van Helden, G.N. Cohen, and S.J. Wodak. Transcriptional
1495		regulation of protein complexes in yeast. <span
1496		class="ptmri7t-x-x-120">Genome Biology</span>, 5:R33, 2004.
1497		</p></li>
1498		<li
1499		class="enumerate" id="x1-13004x2">The program <a
1500		href="http://splicenest.molgen.mpg.de/" >SpliceNest</a>, described in
1501		<!--l. 559--><p class="noindent" ><a
1502		id="XCOW:HAA:VIN:2002"></a>E. Coward, S.A. Haas, and M. Vingron. SpliceNest: Visualization of Gene
1503		Structure and Alternative Splicing Based on EST Clusters. <span
1504		class="ptmri7t-x-x-120">Trends Genet.</span>,
1505		18(1):53–55, 2002
1506		</p><!--l. 561--><p class="noindent" >computes gene indices and uses <span
1507		class="ptmri7t-x-x-120">Vmatch </span>to <a
1508		href="http://splicenest.molgen.mpg.de/doc/help.html#mapping" >map</a> clustered sequences to large
1509		genomes.
1510		</p></li>
1511		<li
1512		class="enumerate" id="x1-13006x3"><a
1513		href="http://bibiserv.techfak.uni-bielefeld.de/e2g/" >e2g</a> is a web-based server which eﬃciently maps large EST and cDNA data
1514		sets to genomic DNA. The use of <span
1515		class="ptmri7t-x-x-120">Vmatch </span>allows to signiﬁcantly extend the
1516		size of data that can be mapped in reasonable time. e2g is available as a
1517		web service and hosts large collections of EST sequences (e.g. 4.1 million
1518		mouse ESTs of 1.87 Gbp) in a precomputed persistent index. For details see
1519		<!--l. 579--><p class="noindent" ><a
1520		id="XKRUE:SCZ:KUR:GIE:2004"></a>J. Krüger, A. Sczyrba, S. Kurtz, and R. Giegerich. e2g: An interactive
1521		web-based server for eﬃciently mapping large EST and cDNA sets to
1522		genomic sequences. <span
1523		class="ptmri7t-x-x-120">Nucleic Acids Res.</span>, 32:W301–W304, 2004.
1524		</p></li>
1525		<li
1526		class="enumerate" id="x1-13008x4">The <a
1527		href="http://bibiserv.techfak.uni-bielefeld.de/" >Bielefeld Bioinformatics Server</a> provides the <a
1528		href="http://bibiserv.techfak.uni-bielefeld.de/reputer/" >REPuter</a> web-service to
1529		compute repeats in complete genomes. The service is based on <span
1530		class="ptmri7t-x-x-120">Vmatch</span>.
1531
1532
1533
1534		</li>
1535		<li
1536		class="enumerate" id="x1-13010x5"><a
1537		id="XFER:DON:SCHNE:MOR:NAN:BRE:WAL:2004"></a>J. Fernandes, Q. Dong, B. Schneider, D.J. Morrow,
1538		G.-L. Nan, V. Brendel, and V. Walbot. Genome-wide mutagenesis of Zea
1539		mays L. using RescueMu transposons. <span
1540		class="ptmri7t-x-x-120">Genome Biology</span>, 5(10):R82, 2004
1541		<!--l. 589--><p class="noindent" >In this work <span
1542		class="ptmri7t-x-x-120">Vmatch </span>was used to (1) match 130 861 vector-trimmed
1543		sequences against the maize repeat database, and (2) to cluster
1544		near-identical sequences.
1545		</p></li>
1546		<li
1547		class="enumerate" id="x1-13012x6"><a
1548		href="http://www-ab.informatik.uni-tuebingen.de/software/crosslink/welcome.html" >CrossLink</a>, described in
1549		<!--l. 595--><p class="noindent" ><a
1550		id="XDEZ:SCHAEF:WIE:WEI:HUS:2006"></a>T. Dezulian, M. Schaefer, R. Wiese, D. Weigel, and D.H. Huson.
1551		CrossLink: visualization and exploration of sequence relationships between
1552		(micro) RNAs. <span
1553		class="ptmri7t-x-x-120">Nucleic Acids Res.</span>, 34(Web Server Issue):W400–W404,
1554		200
1555		</p><!--l. 597--><p class="noindent" >is a versatile computational tool which aids in visualizing relationships
1556		between RNA sequences (particularly between ncRNAs and their putative
1557		target transcripts) in an intuitive and accessible way. Besides BLAST,
1558		CrossLink uses <span
1559		class="ptmri7t-x-x-120">Vmatch </span>to reveal the sequence relationships to be visualized.
1560		</p></li>
1561		<li
1562		class="enumerate" id="x1-13014x7">The early version of the web-service <a
1563		href="http://mips.gsf.de/simap/" >Similarity matrix of Proteins (SIMAP)</a>,
1564		see
1565		<!--l. 607--><p class="noindent" ><a
1566		id="XARN:RAT:TIS:TRU:STU:MEW:2005"></a>R. Arnold, T. Rattei, P. Tischler, M.-D. Truong, V. Stümpﬂen, and H.W.
1567		Mewes. SIMAP - The similarity matrix of proteins. <span
1568		class="ptmri7t-x-x-120">Bioinformatics</span>,
1569		21(Suppl. 2):ii42–ii46, 2005
1570		</p><!--l. 609--><p class="noindent" >used <span
1571		class="ptmri7t-x-x-120">Vmatch </span>to locate the sequences in SIMAP which are similar to a given
1572		query. This is much faster than running BLAST.
1573		</p></li>
1574		<li
1575		class="enumerate" id="x1-13016x8"><a
1576		id="XFIE:VAN:PEE:VAN:NAP:2005"></a>Fiers, M.W.E.J. and Van de Wetering, H. and Peeters, T.H.J.M. and van
1577		Wijk, J.J. and Nap, J-P. DNAVis: interactive visualization of comparative
1578		genome annotations. <span
1579		class="ptmri7t-x-x-120">Bioinformatics</span>, 22(3):354–355, 2005
1580		<!--l. 615--><p class="noindent" >In this work <span
1581		class="ptmri7t-x-x-120">Vmatch </span>was used to compute similarities between genomes,
1582		which are then visualized by the program <a
1583		href="http://www.win.tue.nl/dnavis/" >DNAVis</a>.
1584		</p></li>
1585		<li
1586		class="enumerate" id="x1-13018x9">In the paper
1587
1588
1589
1590		<!--l. 619--><p class="noindent" ><a
1591		id="XSEI:KRUE:HAR:SCHWA:LOEW:MER:DAN:GIE:2006"></a>P.N. Seibel, J. Krüger, S. Hartmeier, K. Schwarzer, K. Löwenthal,
1592		H. Mersch, T. Dandekar, and R. Giegerich. XML schemas for common
1593		bioinformatic data types and their application in workﬂow systems. <span
1594		class="ptmri7t-x-x-120">BMC</span>
1595		<span
1596		class="ptmri7t-x-x-120">Bioinformatics</span>, 7:490, 2006
1597		</p><!--l. 621--><p class="noindent" >Seidel et. al. describe methods for creating web-services and give
1598		examples which, among other tools, also integrate <span
1599		class="ptmri7t-x-x-120">Vmatch</span>.
1600		</p></li>
1601		<li
1602		class="enumerate" id="x1-13020x10">The program <span
1603		class="ptmri7t-x-x-120">Gepard</span>
1604		<!--l. 628--><p class="noindent" ><a
1605		id="XKRU:ARN:RAT:2007"></a>J. Krumsiek, R. Arnold, and T. Rattei. Gepard: a rapid and sensitive tool
1606		for creating dotplots on genome scale. <span
1607		class="ptmri7t-x-x-120">Bioinformatics</span>, 23(8):1026–8, 2007
1608		</p><!--l. 630--><p class="noindent" >uses <span
1609		class="ptmri7t-x-x-120">mkvtree </span>to compute enhanced suﬃx arrays.
1610		</p></li>
1611		<li
1612		class="enumerate" id="x1-13022x11"><span
1613		class="ptmri7t-x-x-120">Vmatch </span>is used a part of the transcriptome assembler software Rnnotator,
1614		described in
1615		<!--l. 636--><p class="noindent" ><a
1616		id="XMAR:BRU:FAN:MEN:BLO:ZHA:SHE:SNY:WAN:2010"></a>J. Martin, V. M. Bruno, Z. Fang, X. Meng, M. Blow, T. Zhang,
1617		G. Sherlock, M. Snyder, and Z. Wang. Rnnotator: an automated de novo
1618		transcriptome assembly pipeline from stranded RNA-Seq reads. <span
1619		class="ptmri7t-x-x-120">BMC</span>
1620		<span
1621		class="ptmri7t-x-x-120">Genomics</span>, 11:663, 2010
1622		</p></li>
1623		<li
1624		class="enumerate" id="x1-13024x12">The BioExtract-Server described in
1625		<!--l. 640--><p class="noindent" ><a
1626		id="XLUS:JEN:BRE:2011"></a>C. M. Lushbough, D. M. Jennewein, and V. Brendel. The bioextract
1627		server: a web-based bioinformatic workﬂow platform. <span
1628		class="ptmri7t-x-x-120">Nucleic acids</span>
1629		<span
1630		class="ptmri7t-x-x-120">research</span>, 39(suppl 2):W528–W532, 2011
1631		</p><!--l. 642--><p class="noindent" >uses <span
1632		class="ptmri7t-x-x-120">Vmatch </span>to remove duplicated sequences.
1633		</p></li>
1634		<li
1635		class="enumerate" id="x1-13026x13"><a
1636		id="XLUS:GNI:DOO:2015"></a>C. M. Lushbough, E. Z. Gnimpieba, and R. Dooley. Life science data
1637		analysis workﬂow development using the bioextract server leveraging the
1638		iplant collaborative cyberinfrastructure. <span
1639		class="ptmri7t-x-x-120">Concurrency and Computation:</span>
1640		<span
1641		class="ptmri7t-x-x-120">Practice and Experience</span>, 27(2):408–419, 2015
1642		<!--l. 648--><p class="noindent" >In this work <span
1643		class="ptmri7t-x-x-120">Vmatch </span>was used for removing duplicates in BlastP results.
1644		This use is part of a workﬂow in <a
1645		href="http://www.myexperiment.org/workflows/3131.html" >myexperiment</a>.
1646
1647
1648
1649		</p></li>
1650		<li
1651		class="enumerate" id="x1-13028x14"><a
1652		id="XGRE:LOY:HOR:RAT:2015"></a>Daniel Greuter, Alexander Loy, Matthias Horn, and Thomas Rattei.
1653		ProbeBase-an online resource for rRNA-targeted oligonucleotide probes
1654		and primers: new features 2016. <span
1655		class="ptmri7t-x-x-120">Nucleic acids research</span>, page gkv1232,
1656		2015
1657		<!--l. 651--><p class="noindent" >In this work <span
1658		class="ptmri7t-x-x-120">Vmatch </span>was used for probe/primer search functionality in the
1659		probeBase database.</p></li></ol>
1660		<!--l. 655--><p class="noindent" >
1661		</p>
1662		<h4 class="likesubsectionHead"><a
1663		id="x1-14000"></a>Current Usages in Human Genome Research</h4>
1664		<!--l. 656--><p class="noindent" >
1665		</p><ol class="enumerate1" >
1666		<li
1667		class="enumerate" id="x1-14002x1"><a
1668		id="XBUC:JAR:MEN:MAT:SCO:GRE:LAN:DUM:2005"></a>P.G. Buckley, C. Jarbo, U. Menzel, T. Mathiesen, C. Scott, S.G. Gregory,
1669		C.F. Langford, and J.P. Dumanski. Comprehensive DNA Copy Number
1670		Proﬁling of Meningioma Using a Chromosome 1 Tiling Path Microarray
1671		identiﬁes Novel Candidate Tumor Surpressor Loci. <span
1672		class="ptmri7t-x-x-120">Cancer Res.</span>,
1673		65(7):2653–2661, 2005
1674		<!--l. 659--><p class="noindent" >In this work <span
1675		class="ptmri7t-x-x-120">Vmatch </span>was used to reveal long repeats inside human
1676		chromosome 1 and long similar regions between human chromosome 1 and
1677		all other human chromosomes.
1678		</p></li>
1679		<li
1680		class="enumerate" id="x1-14004x2"><a
1681		id="XLIA:WAN:LIU:JI:LIU:CHE:WEB:REE:DEA:2007"></a>Liang, C. and Wang, G. and Liu, L. and Ji, G. and Liu, Y. and Chen, J. and
1682		Webb, J.S. and Reese, G. and Dean, J.F.D. WebTraceMiner: a web service
1683		for processing and mining EST sequence trace ﬁles. <span
1684		class="ptmri7t-x-x-120">Nucleic Acids Res</span>,
1685		35(Web Server issue):W137–42, 2007
1686		<!--l. 662--><p class="noindent" >In this work <span
1687		class="ptmri7t-x-x-120">Vmatch </span>was used for Vector screening.
1688		</p></li>
1689		<li
1690		class="enumerate" id="x1-14006x3"><a
1691		id="XNYG:JAC:LIN:ERI:BAL:FLY:TOL:MOE:SOE:KRO:LIT:2009"></a>Sanne Nygaard, Anders Jacobsen, Morten Lindow, Jens Eriksen, Eva
1692		Balslev, Henrik Flyger, Niels Tolstrup, Søren Møller, Anders Krogh, and
1693		Thomas Litman. Identiﬁcation and analysis of mirnas in human breast
1694
1695
1696
1697		cancer and teratoma samples using deep sequencing. <span
1698		class="ptmri7t-x-x-120">BMC Medical</span>
1699		<span
1700		class="ptmri7t-x-x-120">Genomics</span>, 2(1):35, 2009
1701		<!--l. 665--><p class="noindent" >In this work <span
1702		class="ptmri7t-x-x-120">Vmatch </span>was used for mapping short reads.
1703		</p></li>
1704		<li
1705		class="enumerate" id="x1-14008x4"><a
1706		id="XCOL:SOB:LU:THA:BOW:BRO:GRE:BAR:HUT:2009"></a>Christian Cole, Andrew Sobala, Cheng Lu, Shawn R Thatcher, Andrew
1707		Bowman, John WS Brown, Pamela J Green, Geoﬀrey J Barton, and
1708		Gyorgy Hutvagner. Filtering of deep sequencing data reveals the
1709		existence of abundant dicer-dependent small rnas derived from trnas. <span
1710		class="ptmri7t-x-x-120">Rna</span>,
1711		15(12):2147–2160, 2009
1712		<!--l. 668--><p class="noindent" >In this work <span
1713		class="ptmri7t-x-x-120">Vmatch </span>was used for matching reads to sets of RNA sequences
1714		and the Human genome.
1715		</p></li>
1716		<li
1717		class="enumerate" id="x1-14010x5"><a
1718		id="XCLO:WAN:XU:GU:LEA:HEA:BAR:STE:MAR:NOU:2011"></a>N. Cloonan, S. Wani, Q. Xu, J. Gu, K. Lea, S. Heater, C. Barbacioru,
1719		A. L. Steptoe, H. C. Martin, E. Nourbakhsh, et al. Micrornas and their
1720		isomirs function cooperatively to target common biological pathways.
1721		<span
1722		class="ptmri7t-x-x-120">Genome Biol</span>, 12(12):R126, 2011
1723		<!--l. 671--><p class="noindent" >In this work <span
1724		class="ptmri7t-x-x-120">Vmatch </span>was used to uniquely map miRNAs against the human
1725		genome.
1726		</p></li>
1727		<li
1728		class="enumerate" id="x1-14012x6"><a
1729		id="XTAK:TSU:KAT:OKA:HOR:IKE:URA:KAW:HAS:IKE:2011"></a>K Takayama, S Tsutsumi, S Katayama, T Okayama, K Horie-Inoue,
1730		K Ikeda, T Urano, C Kawazu, A Hasegawa, K Ikeo, et al. Integration
1731		of cap analysis of gene expression and chromatin immunoprecipitation
1732		analysis on array reveals genome-wide androgen receptor signaling in
1733		prostate cancer cells. <span
1734		class="ptmri7t-x-x-120">Oncogene</span>, 30(5):619–630, 2011
1735		<!--l. 674--><p class="noindent" >In this work <span
1736		class="ptmri7t-x-x-120">Vmatch </span>was used to determine the positions of CAGE tags on
1737		the human genome.
1738		</p></li>
1739		<li
1740		class="enumerate" id="x1-14014x7"><a
1741		id="XKEV:LAL:LI:CAV:NAR:KAM:MIT:HAK:KOZ:GEN:2011"></a>Kevin CH Ha, Emilie Lalonde, Lili Li, Luca Cavallone, Rachael Natrajan,
1742		Maryou B Lambros, Costas Mitsopoulos, Jarle Hakas, Iwanka Kozarewa,
1743		Kerry Fenwick, et al. Identiﬁcation of gene fusion transcripts by
1744		transcriptome sequencing in BRCA1-mutated breast cancers and cell lines.
1745		<span
1746		class="ptmri7t-x-x-120">BMC Medical Genomics</span>, 4(1):75, 2011
1747		<!--l. 677--><p class="noindent" >In this work <span
1748		class="ptmri7t-x-x-120">Vmatch </span>was used to align sections of reads against RefSeq
1749		mRNA exon sequences.
1750
1751
1752
1753		</p></li>
1754		<li
1755		class="enumerate" id="x1-14016x8"><a
1756		id="XKID:CHE:WAN:JAC:ZHA:BOY:FIR:TAN:GAE:COL:2012"></a>Marie J Kidd, Zhiliang Chen, Yan Wang, Katherine J Jackson, Lyndon
1757		Zhang, Scott D Boyd, Andrew Z Fire, Mark M Tanaka, Bruno A Gaëta,
1758		and Andrew M Collins. The inference of phased haplotypes for the
1759		immunoglobulin h chain v region gene loci by analysis of vdj gene
1760		rearrangements. <span
1761		class="ptmri7t-x-x-120">The Journal of Immunology</span>, 188(3):1333–1340, 2012
1762		<!--l. 680--><p class="noindent" >In this work <span
1763		class="ptmri7t-x-x-120">Vmatch </span>was used to align sets of genes.
1764		</p></li>
1765		<li
1766		class="enumerate" id="x1-14018x9"><a
1767		id="XYAM:IKE:BOE:HOR:TAK:URA:KAI:CAR:KAW:HAY:2014"></a>Ryonosuke Yamaga, Kazuhiro Ikeda, Joost Boele, Kuniko Horie-Inoue,
1768		Ken-ichi Takayama, Tomohiko Urano, Kaoru Kaida, Piero Carninci,
1769		Jun Kawai, Yoshihide Hayashizaki, et al. Systemic identiﬁcation of
1770		estrogen-regulated genes in breast cancer cells through cap analysis
1771		of gene expression mapping. <span
1772		class="ptmri7t-x-x-120">Biochemical and biophysical research</span>
1773		<span
1774		class="ptmri7t-x-x-120">communications</span>, 447(3):531–536, 2014
1775		<!--l. 683--><p class="noindent" >In this work <span
1776		class="ptmri7t-x-x-120">Vmatch </span>was used to determine the positions of CAGE tags on
1777		the human genome.
1778		</p>
1779		</li></ol>
1780		<!--l. 688--><p class="noindent" >
1781		</p>
1782		<h4 class="likesubsectionHead"><a
1783		id="x1-15000"></a>Current Usages for diﬀerent Model Organisms</h4>
1784		<!--l. 689--><p class="noindent" >
1785		</p><ol class="enumerate1" >
1786		<li
1787		class="enumerate" id="x1-15002x1"><a
1788		id="XSCZ:BECK:BRI:GIE:ALT:2005"></a>A. Sczyrba, M. Beckstette, A.H. Brivanlou, R. Giegerich, and C.R.
1789		Altmann. Xendb: Full length cDNA prediction and cross species mapping
1790		in <span
1791		class="ptmri7t-x-x-120">xenopus laevis</span>. <span
1792		class="ptmri7t-x-x-120">BMC Genomics</span>, 2005
1793		<!--l. 706--><p class="noindent" >In this work <span
1794		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster 317 242 EST and cDNA sequences
1795		from <span
1796		class="ptmri7t-x-x-120">Xenopus laevis</span>. <span
1797		class="ptmri7t-x-x-120">Vmatch </span>was chosen for the following reasons:
1798		</p>
1799
1800
1801
1802		<ul class="itemize1">
1803		<li class="itemize">At ﬁrst, there was no clustering tool available which could handle large
1804		data sets eﬃciently, and which was documented well enough to allow
1805		a detailed b replication and evaluation of existing clusters.
1806		</li>
1807		<li class="itemize">Second, <span
1808		class="ptmri7t-x-x-120">Vmatch </span>identiﬁes similarities between sequences rapidly, and
1809		it provides additional options to cluster a set of sequences based on
1810		these matches. Furthermore, the <span
1811		class="ptmri7t-x-x-120">Vmatch </span>output provides information
1812		about how the clusters were derived. Due to the eﬃciency of <span
1813		class="ptmri7t-x-x-120">Vmatch</span>, it
1814		was possible to perform the clustering for a wide variety of parameters
1815		on the complete sequence set. This allows to study the eﬀect of the
1816		parameter choice on the clustering.</li></ul>
1817		</li>
1818		<li
1819		class="enumerate" id="x1-15004x2"><a
1820		id="XSPIT:LOR:CUL:SCZ:FUEL:2006"></a>M. Spitzer, S. Lorkowski, P. Cullen, A. Sczyrba, and G. Fuellen. Distinguishing
1821		isoforms and paralogs on the protein level. <span
1822		class="ptmri7t-x-x-120">BMC Bioinformatics</span>, 7:110,
1823		2006
1824		<!--l. 709--><p class="noindent" >In this work <span
1825		class="ptmri7t-x-x-120">Vmatch </span>was used to cluster EST-sequences of <span
1826		class="ptmri7t-x-x-120">Xenopus</span>
1827		<span
1828		class="ptmri7t-x-x-120">laevis</span>.
1829		</p></li>
1830		<li
1831		class="enumerate" id="x1-15006x3"><a
1832		id="XEIS:COY:WU:WU:THI:WOR:BAD:REN:AME:JON:2006"></a>J.A. Eisen, R.S. Coyne, M. Wu, D. Wu, M. Thiagarajan, J.R. Wortman, J.H.
1833		Badger, Q. Ren, P. Amedeo, and K.M. Jones et al. Macronuclear Genome
1834		Sequence of the Ciliate Tetrahymena thermophila, a Model Eukaryote. <span
1835		class="ptmri7t-x-x-120">PLoS</span>
1836		<span
1837		class="ptmri7t-x-x-120">Biology</span>, 4(9):e286, 2006
1838		<!--l. 713--><p class="noindent" >In this work <span
1839		class="ptmri7t-x-x-120">Vmatch </span>was used to search exact repeats in the Macronuclear
1840		Genome Sequence of the Ciliate <span
1841		class="ptmri7t-x-x-120">Tetrahymena thermophila</span>.
1842		</p></li>
1843		<li
1844		class="enumerate" id="x1-15008x4"><a
1845		id="XFAU:FOR:CHA:SCHRO:HAY:CAR:HUM:GRI:2008"></a>G. J. Faulkner, A. R. Forrest, A. M. Chalk, K. Schroder, Y. Hayashizaki,
1846		P. Carninci, D. A. Hume, and S. M. Grimmond. A rescue strategy for
1847		multimapping short sequence tags reﬁnes surveys of transcriptional activity by
1848		CAGE. <span
1849		class="ptmri7t-x-x-120">Genomics</span>, 91(3):281–288, Mar 2008
1850		<!--l. 736--><p class="noindent" >In this work <span
1851		class="ptmri7t-x-x-120">Vmatch </span>was used for mapping </p>
1852		<ul class="itemize1">
1853		<li class="itemize">11 567 973 FANTOM3 mouse CAGE tags to the mouse genome with
1854		minimum match length of 18 bp, a single internal mismatch allowed,
1855
1856
1857
1858		and multiple mismatches allowed at tag ends.
1859		</li>
1860		<li class="itemize">Aﬀymetrix GNF probe sequences to transcripts without allowing for
1861		mismatches.</li></ul>
1862		</li>
1863		<li
1864		class="enumerate" id="x1-15010x5"><a
1865		id="XPRI:JOR:2008"></a>Jittima Piriyapongsa and I King Jordan. Dual coding of sirnas and mirnas by
1866		plant transposable elements. <span
1867		class="ptmri7t-x-x-120">RNA</span>, 14(5):814–821, 2008
1868		<!--l. 741--><p class="noindent" >In this work <span
1869		class="ptmri7t-x-x-120">Vmatch </span>was used to search small RNA signatures in entire miRNA
1870		gene sequences for Arabidopsis and rice.
1871		</p></li>
1872		<li
1873		class="enumerate" id="x1-15012x6"><a
1874		id="XTAF:GLA:LASS:HAY:CAR:MAT:2009"></a>R. J. Taft, E. A. Glazov, T. Lassmann, Y. Hayashizaki, P. Carninci, and J. S.
1875		Mattick. Small RNAs derived from snoRNAs. <span
1876		class="ptmri7t-x-x-120">RNA</span>, 15(7):1233–1240, Jul
1877		2009
1878		<!--l. 745--><p class="noindent" >In this work <span
1879		class="ptmri7t-x-x-120">Vmatch </span>was used to map small RNA data sets onto the
1880		corresponding reference genomes for diﬀerent model organisms.
1881		</p></li>
1882		<li
1883		class="enumerate" id="x1-15014x7"><a
1884		id="XPLE:PAS:BER:AKA:CAR:VAS:LAZ:SEV:VLA:SIM:2012"></a>C. Plessy, G. Pascarella, N. Bertin, A. Akalin, C. Carrieri, A. Vassalli,
1885		D. Lazarevic, J. Severin, C. Vlachouli, R. Simone, et al. Promoter architecture
1886		of mouse olfactory receptor genes. <span
1887		class="ptmri7t-x-x-120">Genome research</span>, 22(3):486–497,
1888		2012
1889		<!--l. 748--><p class="noindent" >In this work <span
1890		class="ptmri7t-x-x-120">Vmatch </span>was used for mapping Illumina reads to the mouse
1891		genome.
1892		</p></li>
1893		<li
1894		class="enumerate" id="x1-15016x8"><a
1895		id="XKEN:SHI:2012"></a>Nathan J Kenny and Sebastian M Shimeld. Additive multiple k-mer
1896		transcriptome of the keelworm <span
1897		class="ptmri7t-x-x-120">Pomatoceros lamarckii </span>(annelida; serpulidae)
1898		reveals annelid trochophore transcription factor cassette. <span
1899		class="ptmri7t-x-x-120">Development genes and</span>
1900		<span
1901		class="ptmri7t-x-x-120">evolution</span>, 222(6):325–339, 2012
1902		<!--l. 752--><p class="noindent" >In this work <span
1903		class="ptmri7t-x-x-120">Vmatch </span>was used for redundancy removal in the context of
1904		transcriptome assembly of a keelworm species.
1905		</p></li>
1906		<li
1907		class="enumerate" id="x1-15018x9"><a
1908		id="XGOS:OHM:KOG:SON:TUR:ZAJ:ZAL:GRU:SUN:HAN:2014"></a>Cene Gostin, Robin A Ohm, Tina Kogej, Silva Sonjak, Martina Turk, Janja Zajc,
1909		Polona Zalar, Martin Grube, Hui Sun, James Han, et al. Genome sequencing of
1910		four aureobasidium pullulans varieties: biotechnological potential, stress
1911
1912
1913
1914		tolerance, and description of new species. <span
1915		class="ptmri7t-x-x-120">BMC Genomics</span>, 15(1):549,
1916		2014
1917		<!--l. 756--><p class="noindent" >In this work <span
1918		class="ptmri7t-x-x-120">Vmatch </span>was used to remove redundant contigs in a genome project
1919		of four <span
1920		class="ptmri7t-x-x-120">Aureobasidium pullulans </span>varieties.
1921		</p></li>
1922		<li
1923		class="enumerate" id="x1-15020x10"><a
1924		id="XMCM:GAR:BAI:KEM:WAR:CEV:ROB:SCHUL:BAL:HOL:2015"></a>M. McMullan, A. Gardiner, K. Bailey, E. Kemen, B. J. Ward, V. Cevik,
1925		A. Robert-Seilaniantz, T. Schultz-Larsen, A. Balmuth, E. Holub, et al.
1926		Evidence for suppression of immunity as a driver for genomic introgressions and
1927		host range expansion in races of albugo candida, a generalist parasite. <span
1928		class="ptmri7t-x-x-120">eLife</span>,
1929		4:e04550, 2015
1930		<!--l. 759--><p class="noindent" >In this work <span
1931		class="ptmri7t-x-x-120">Vmatch </span>was used for merging assemblies of Illumina sequenced
1932		cDNA.
1933		</p></li>
1934		<li
1935		class="enumerate" id="x1-15022x11"><a
1936		id="XMOR:DHA:PAV:TRO:WHE:HEL:2015"></a>C Morandin, K Dhaygude, J Paviala, K Trontti, C Wheat, and H Helanterä.
1937		Caste-biases in gene expression are speciﬁc to developmental stage in the ant
1938		formica exsecta. <span
1939		class="ptmri7t-x-x-120">Journal of evolutionary biology</span>, 28(9):1705–1718,
1940		2015
1941		<!--l. 773--><p class="noindent" >In this work <span
1942		class="ptmri7t-x-x-120">Vmatch </span>was used to combine and scaﬀold contigs.
1943		</p>
1944		</li></ol>
1945		<!--l. 778--><p class="noindent" >Total number of usages: 108
1946		</p><!--l. 780--><p class="noindent" >
1947		</p>
1948		<h3 class="likesectionHead"><a
1949		id="x1-16000"></a>Availability</h3>
1950		<!--l. 781--><p class="noindent" ><span
1951		class="ptmri7t-x-x-120">Vmatch </span>is available for <a
1952		href="http://www.vmatch.de/download.html" >download</a> in executable form for the following platforms:
1953		</p>
1954		<ul class="itemize1">
1955		<li class="itemize">Linux
1956
1957
1958
1959		</li>
1960		<li class="itemize">Mac OS X
1961		</li>
1962		<li class="itemize">MS Windows</li></ul>
1963		<!--l. 794--><p class="noindent" >
1964		</p>
1965		<h3 class="likesectionHead"><a
1966		id="x1-17000"></a>Developer</h3>
1967		<!--l. 795--><p class="noindent" ><span
1968		class="ptmri7t-x-x-120">Vmatch </span>was developed since May 2000 by <a
1969		href="http://www.zbh.uni-hamburg.de/kurtz" >Stefan Kurtz</a>, a professor of Computer
1970		Science at the Center for Bioinformatics, University of Hamburg, Germany.
1971		</p><!--l. 809--> <b>Important Documents</b> <ul> <li> The <a href="virtman.pdf"><i>Vmatch</i>-manual</a> </li> </ul>
1972		<!--l. 817--> <div id="footer"> Copyright © 2000-2017 <a href="mailto:kurtz@zbh.uni-hamburg.de"> Stefan Kurtz</a>. Last update: 2017-06-15 </div>
1973		<!--l. 839--> <!-- Piwik --> <div id="piwik"> <script type="text/javascript"> var pkBaseURL = "https://zenlicensemanager.com/piwik/"; document.write(unescape("</script><script type="text/javascript"> try { var piwikTracker = Piwik.getTracker(pkBaseURL + "piwik.php", 3); piwikTracker.trackPageView(); piwikTracker.enableLinkTracking(); } catch( err ) {} </script> <br/> <noscript> <img src="https://zenlicensemanager.com/piwik/piwik.php?idsite=3" style="border:0" alt=""/> </noscript> <!-- End Piwik Tracking Tag --> </div>
1974
1975		</body></html>
1976
1977
1978
1979

-2

~~src/doc/WWW/introexclude~~ less more

0		\\begin{AboutVmatch}
1		\\end{AboutVmatch}

~~src/doc/WWW/matchgraph.gif~~ less more

Binary diff not shown

-12

~~src/doc/WWW/remove-html.rb~~ less more

0		#!/usr/bin/env ruby
1
2		def remove_html_tags(s)
3		re = /<("[^"]"\|'[^']'\|[^'">])*>/
4		return s.gsub(re, "")
5		end
6
7		ARGV.each do \|filename\|
8		file = File.open(filename, "rb")
9		contents = file.read
10		print remove_html_tags(contents)
11		end

-20

~~src/doc/WWW/replace-header.rb~~ less more

0		#!/usr/bin/env ruby
1
2		STDIN.each_line do \|line\|
3		if line.match(/<meta name=\"src\" content="vmweb.tex"/)
4		print "#{line}"
5		puts <<'HEADER'
6		<meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"/>
7		<meta name="description" CONTENT="The Vmatch large scale sequence analysis
8		software is a versatile software tool for efficiently solving large scale sequence matching tasks."/>
9		<meta name="keywords" CONTENT="sequence analysis, sequence mapping, BLAST, bioinformatics, computational biology"/>
10		<meta http-equiv="Content-Style-Type" content="text/css"/>
11		HEADER
12		elsif line.match(/class=\"titleHead\|author\|date\"/)
13		print line.gsub(/class=/,"align=\"center\" class=").gsub(/h2/,"h1")
14		elsif line.match(/\/h2/)
15		print line.gsub(/\/h2/,"\/h1")
16		else
17		print line
18		end
19		end

-3

~~src/doc/WWW/replace-par.rb~~ less more

0		#!/usr/bin/env ruby
1
2		puts STDIN.read.gsub!(/<p class=\"noindent\" > <!--delete paragraph-->(.*)\n?<\/p\>/,"\\1\n")

-44

~~src/doc/WWW/vmweb.css~~ less more

0		body {
1		font-family: Verdana, Geneva, Arial, sans-serif;
2		}
3		h1, h2, h3, h4, h5, h6 {
4		color:black;
5		}
6		#w3checklogo {
7		float: right;
8		clear: right;
9		}
10		#downloadbox {
11		float: right;
12		clear: right;
13		width: 280px;
14		padding-right: 20px;
15		}
16		#downloadbox li {
17		list-style-type: none;
18		}
19		#downloadbox li a {
20		list-style-type: none;
21		border : 1px solid black;
22		display: block;
23		padding: 4px 15px 4px 15px;
24		text-decoration: none;
25		}
26		#downloadbox li a:link {
27		color: black;
28		background: rgb(90%, 90%, 20%);
29		}
30		#downloadbox li a:visited {
31		color: gray;
32		background: rgb(90%, 90%, 20%);
33		}
34		#downloadbox li a:hover {
35		color: white;
36		background: rgb(60%, 60%, 90%);
37		}
38		#footer {
39		font-size: 66%;
40		text-align: center;
41		margin-top: 20px;
42		background-color: #DDDDDD;
43		}

-840

~~src/doc/WWW/vmweb.tex~~ less more

0		\documentclass[12pt]{article}
1		\usepackage{ifpdf}
2		\usepackage{graphicx}
3		\usepackage{mathptmx}
4		\usepackage{natbib}
5		\usepackage{numprint}
6		\usepackage{bibentry}
7		\usepackage{xspace}
8		\usepackage[latin1]{inputenc}
9		\usepackage{hyperref}
10		\hypersetup{%
11		colorlinks=true,
12		linkcolor=blue
13		}
14
15		\newcommand{\Vmatch}[0]{\textit{Vmatch}\xspace}
16		\newcommand{\Mybibentry}[2]{\item \bibentry{#1} \par%
17		In this work \Vmatch was used \xspace #2\xspace}
18		%\newcommand{\href}[2]{#2}
19		%\nobibliography*
20		\newcounter{Allusages}
21		\newcommand{\Updateusages}{\addtocounter{Allusages}{\theenumi}}
22		\newcommand{\PrintVol}[1]{#1}
23		\newcommand{\Includegraphics}[2]{%
24		\includegraphics[#1]{#2.pdf}
25		}
26
27		\makeatletter
28		\edef\texforht{TT\noexpand\fi
29		\@ifpackageloaded{tex4ht}
30		{\noexpand\iftrue}
31		{\noexpand\iffalse}}
32		\makeatother
33		\ifpdf
34		\newcommand{\HCode}[1]{}
35		\fi
36
37		\title{The \Vmatch large scale sequence analysis software}
38		\author{Stefan Kurtz}
39		\date{\today}
40		\parskip5pt
41		\parindent0pt
42		\begin{document}
43		\maketitle
44
45		\bibliographystyle{plain}
46		\nobibliography{defines,ltr,assembly,algorithms,rnafolding,commolbio,biotools,kurtz,genomes,strings,genetics,metagenomes}
47
48		\HCode{
49		<!--delete paragraph-->
50		<br/>
51		<center>
52		<img src="matchgraph.gif"
53		alt="show matches of different sizes in a matchgraph"/>
54		</center>
55		<div id="downloadbox">
56		<ul>
57		<li><a href="download.html">Download <i>Vmatch</i>!</a></li>
58		</ul>
59		</div>
60		}
61
62		This is the web-site for \Vmatch,
63		a versatile software tool for efficiently
64		solving large scale se\-quence matching tasks.
65		\Vmatch subsumes the software tool
66		\href{http://bibiserv.techfak.uni-bielefeld.de/reputer}{REPuter},
67		but is much more general, with a very flexible user interface,
68		and improved space and time requirements.
69		\HCode{
70		<a href="vmweb.pdf">Here</a> is a printable version of this
71		HTML-page in PDF.
72		}
73
74		\section*{Features of \Vmatch}
75		The \href{virtman.pdf}{\Vmatch-manual}
76		gives many examples on how to use \Vmatch. Here are the program's most
77		important features.
78
79		\input{introduction.inc}
80
81		\HCode{
82		<a href="Dataflowfig.pdf">Here</a> is an overview of the dataflow
83		in <i>Vmatch</i>.
84		}
85
86		\section*{Related tools}
87		There are several tools which are
88		based on the persistent index of \Vmatch:
89
90		\begin{description}
91		\item[Genalyzer]
92		is a graphical user interface
93		to visualize the output of \Vmatch in form of a match graph.
94		For details see
95
96		\bibentry{CHO:SCHLE:KUR:GIE:2004}
97
98		Genalyzer is not available any more.
99		\item[\href{http://bibiserv.techfak.uni-bielefeld.de/mga/}{MGA}]
100		is a program to compute multiple alignments of complete
101		genomes. For details see
102
103		\bibentry{HOEH:KUR:OHL:2002}
104		\item[Multimat] is a program to compute multiple exact matches between
105		three or more genome size sequences. For details see
106
107		\bibentry{OHL:KUR:2008}
108
109		Please contact
110		\href{http://www.zbh.uni-hamburg.de/kurtz}{Stefan Kurtz} if you are interested
111		in using Multimat.
112
113		\item[\href{http://bibiserv.techfak.uni-bielefeld.de/possumsearch/}{PossumSearch}]
114		Is a program to search for position specific scoring matrices.
115		For details, see
116
117		\bibentry{BEC:HOM:GIE:KUR:2006}
118		\item
119		\item[\href{http://www.genomethreader.org/}{GenomeThreader}]
120		is a software tool to compute gene structure predictions. The gene structure
121		predictions are calculated using a similarity-based approach where additional
122		cDNA/EST and/or protein sequences are used to predict gene structures via
123		spliced alignments. \textit{GenomeThreader} uses the matching capabilities
124		of \Vmatch to efficiently map the reference sequence to a genomic
125		sequence. For details, see
126
127		\bibentry{GRE:BRE:SPA:KUR:2005}
128		\item
129		\item[\href{http://www.biopieces.org/}{Biopieces}]
130		is a collection of bioinformatics tools that can be pieced together in a
131		very easy and flexible manner to perform both simple and complex tasks.
132		Some Biopieces depend on \Vmatch. For details see
133		\url{http://www.biopieces.org/}.
134		\end{description}
135
136		\HCode{
137		<a name="CurrentUsage"/>
138		}
139		\section*{Previous and Current Usages}
140
141		We provide an annotated bibliography listing papers which applied \Vmatch
142		and shortly describe the tasks for which \Vmatch was used. We omit our own
143		papers. The references were collected by a
144		\href{https://scholar.google.de/scholar?q=Vmatch+AND+Kurtz+OR+www.vmatch.de}%
145		{search in Google scholar}
146		(which, as of Jan 2, 2016 retrieved 397 results.)
147
148		\subsection*{Usages in Plant Genome Research}
149		\begin{enumerate}
150		\Mybibentry{BRE:KUR:WAL:2002}{
151		to a compute a non-redundant set from a large collection of protein sequences
152		from Zea-Maize.}
153
154		Similar applications are described in
155
156		\bibentry{DON:ROY:FRE:WAL:BRE:2003}.
157		%\item
158		%For the development of the
159		%\href{http://barleypop.vrac.iastate.edu/BarleyBase/content.php}{Barley1 GeneChip} \Vmatch is used to search
160		%against probes.
161		\item
162		PLEXdb is a database for gene expression resources for plants and plant
163		pathogens, see
164
165		\bibentry{DAS:VAN:HON:WIS:DIC:2012}
166
167		PLEXdb provides a \Vmatch-based
168		\href{http://www.plantgdb.org/cgi-bin/prj/PLEXdb/ProbeMatch.pl}{web-service}
169		to match PLEXdb probes.
170
171		\item
172		The assembly of the Arabidopsis thaliana genome from 2004
173		(GenBank entries of 2/19/04) contained vector sequence contaminations.
174		For example, region \numprint{3617880} to \numprint{3625027} of
175		chromosome II contained
176		a cloning vector. \Vmatch was used to detect the vector contamination,
177		see \href{http://www.plantgdb.org/AtGDB/Annotation/vector.php}{here}
178
179		\item
180		\bibentry{DON:LAW:SCHLUE:WIL:KUR:LUS:BRE:2005}
181
182		This work describes PlantGDB, which
183		provides a service called
184		\href{http://www.plantgdb.org/PlantGDB-cgi/vmatch/patternsearch.pl}{PatternSearch@PlantGDB}
185		for genome wide pattern searches in plant sequences. The service is based
186		on \Vmatch.
187		\Mybibentry{LIN:KRO:2005}{
188		for three different tasks:
189		\begin{itemize}
190		\item
191		Searching spliced mRNA in the Arabidopsis genome to detect
192		micromatches of length at least 20 with maximum 2 mismatches.
193		\item
194		Finding matches of length at least 15 long with at most one mismatch
195		between predicted mature miRNA-sequences and a set of ESTs as well
196		as sequences from the Arabidopsis Small RNA Project (ASRP).
197		\item
198		Aligning and performing single linkage clustering
199		of the predicted mature miRNA sequences. Candidate pairs aligning over at least
200		17 bases, allowing an edit distance of 1 were grouped in the same family.
201		\end{itemize}}
202
203		\item
204		\bibentry{POM:LEM:TUR:2006}
205
206		\bibentry{TUR:OTI:LEM:2006}
207
208		In these papers \Vmatch was used to search
209		and compare repeated elements in different chloroplast DNA.
210
211		\item
212		\bibentry{SPA:NOU:HAA:YAN:GUN:HIN:KLE:HAB:SCHOO:MAY:2007}
213		In this work about the \textit{MIPSPlantsDB} database
214		\Vmatch was used to cluster large sequence sets.
215
216		\Mybibentry{SCHIJ:VOS:MAR:JON:ROS:MOL:TIK:ANG:TUN:BOV:2007}{
217		to compare target genes of the tomato Chs RNAi to a tomato gene index.}
218
219		\Mybibentry{LIN:JAC:NYG:MAN:KRO:2007}{
220		to search different
221		plant genomes for matches of length at least 20 with maximum of 2 mismatches.
222		Here the fact that \Vmatch is an exhaustive search tool is important.}
223
224		\Mybibentry{DEC:OTI:THU:LEM:2007}{
225		to determine the presence of shared repeated elements of minimum length
226		30, with up to 10\% mismatches using in different sequence sets from
227		the green alga \textit{Leptosira terrestris}.}
228
229		\Mybibentry{OSS:SCHNE:CLA:LAN:WAR:WEI:2008}{
230		to map millions of short sequence reads to the \textit{A.~Thaliana} genome.
231		Up to four mismatches and up to three indels were allowed in the matching
232		process. The seed size was chosen to be 0. The reads were aligned using the
233		best match strategy by iteratively increasing the the allowed number of
234		mismatches and gaps at each round.}
235
236		\Mybibentry{DIBO:OSS:SCHNE:RAT:2008}{
237		to map millions of short sequence reads to the \textit{A.~Thaliana} genome.
238		\Vmatch was part of a multi-step pipeline, combining a fast
239		matching algorithm (\Vmatch) for initial read mapping and
240		an optimal alignment algorithm based on dynamic programming (QPALMA)
241		for high quality detection of splice sites.}
242
243		\Mybibentry{ASS:HER:LIN:HUE:TAL:SMA:IMM:ELD:FIE:SCHAT:2010}{
244		for motif searching in different plant genomes.}
245
246		\Mybibentry{EVE:SAT:GOL:MEY:BET:SAK:WAR:JAC:2010}{
247		to map unique consensus sequence tags to the maize reference genome.}
248
249		\Mybibentry{BRO:OTI:LEM:TUR:2010}{
250		to identify and cluster repeated sequences in \textit{Floydiella} chloroplast
251		genome.}
252
253		\Mybibentry{REH:AQU:GRU:HEN:HIL:LAU:NAO:PAT:ROM:SHU:2010}{
254		to calculate direct and reverse complementary matches of length {17} bp or
255		greater with edit distance {1} or less between five nuclear chromosomes
256		and mitochondrial and chloroplast genome sequences.}
257
258		\Mybibentry{SEK:LIN:CHI:HAN:BUE:LEO:KAE:2011}{
259		to search probe sequences against the maize genome
260		the cDNA sequences of the official maize gene models.}
261
262		\Mybibentry{DAS:OH:HAA:HER:HON:ALI:YUN:BRE:ZHU:BOH:2011}{
263		for clustering sequences assembled from 454-reads of
264		\textit{Thellungiella parvula}, a model for the evolution of plant
265		adaptation to extreme environments.}
266
267		\Mybibentry{WIL:HOF:KLE:WEI:2011}{
268		for grouping short reads into
269		pools representing the same RAD tag.}
270
271		\Mybibentry{GAO:ZHO:WAN:SU:WAN:2011}{
272		for detecting and
273		clustering repetitive sequences in diverse fern plastid genomes.}
274
275		\Mybibentry{SLO:ALV:CHU:WU:MCC:PAL:TAY:2012}{
276		to precisely
277		define the boundaries of all repeats with 100\% sequence identity.}
278
279		\Mybibentry{DUB:FAR:SCHLU:CAN:ABE:TUT:WOO:SHA:MUL:KUD:2011}{
280		cluster sequences based on their six-frame translation.}
281
282		\Mybibentry{SAX:PEN:UPA:KUM:CAR:SCHLU:FAR:WHA:SAR:MAY:2012}{
283		to identify reciprocal best matches between the pigeonpea sequences and
284		other legume sequences.}
285
286		\Mybibentry{HAZ:REE:RIS:PEC:2012}{
287		for assembly clustering and
288		optimization of contigs for
289		\textit{Neochloris oleoabundans} (a Chlorophyceae class green microalgae).}
290
291		\Mybibentry{MAR:KLE:BAN:BLA:MAC:SCHMU:SCHOL:GUN:WIC:SIM:2012}{
292		to match reads against a repeat library to
293		identity the content of the repetitive DNA per sequence read.}
294
295		\Mybibentry{CHI:DAV:BUE:2011}{
296		to align individual probes to representative gene models.}
297
298		\Mybibentry{SEV:DIJ:HAM:2011}{
299		for performing exact searches with
300		peptides against the filtered proteome of \textit{A. thaliana}.}
301
302		\Mybibentry{WOL:WEI:SEG:ROS:BEI:DON:SPI:NOR:REH:KOE:2011}{
303		to map RNAseq reads,
304		allowing up to two mismatches (option \texttt{-h 2})
305		and generating maximal substring matches
306		that are unique in some reference dataset (option \texttt{-mum cand}).}
307
308		\Mybibentry{FLE:KHA:JOH:YOU:MIT:WRE:HES:FOS:SCHAR:SCO:2011}{
309		to identify terminal inverted repeats of length range {10-65} bp,
310		$\geq 80\%$ identity, maximum inter-TIR distance 650~bp in in genomes of
311		epichloid fungal endophytes of grasses.}
312
313		\Mybibentry{CHI:KON:BUE:2012}{
314		to match putative unique transcript sequence assemblies.}
315
316		\Mybibentry{CHE:CAS:BAI:RED:MIC:2012}{
317		for refining assemblies of Illumina reads in the context of a transcriptome
318		project for plant virus vector \textit{Graminella nigrifrons}.}
319
320		\Mybibentry{KRI:PAT:JAI:GAU:CHOU:VAI:DEE:HAR:KRI:NAI:2012}{
321		for clustering repeats and for building a consensus repeat library in the
322		context of genome and transcriptome projects for \textit{Azadirachta indica}, a
323		medicinal and pesticidal angiosperm.}
324
325		\Mybibentry{LIU:KUM:ZHA:ZHE:WAR:2012}{
326		to map unique consensus sequences tags to the maize reference
327		genome and to predict targets of novel miRNAs.}
328
329		\Mybibentry{BOU:KOU:PAV:MIN:TSA:DAR:2012}{
330		for masking Long Terminal Repeats in the Maize Genome Sequence.}
331
332		\item In the papers
333
334		\bibentry{HER:MAR:DOR:PFE:GAL:SCHAA:JOU:SIM:VAL:DOL:2012}
335
336		\bibentry{PHI:PAU:BER:SOU:CHO:LAU:SIM:SAF:BEL:VAU:2013}
337
338		\Vmatch was used to mask repetitive DNA.
339
340		\Mybibentry{HOW:YU:KNA:CRO:KOL:DOL:LOR:DEA:2013}{
341		to cluster \numprint{40010} assembled isotigs.}
342
343		\Mybibentry{KAR:HAA:MAL:GEE:BOV:LAM:ANG:MAA:2013}{
344		to preprocess short reads in the context of identifying mircoRNA targets in
345		tomato fruit development.}
346
347		\Mybibentry{GRO:MAR:SIM:ABR:WAN:VIS:2013}{
348		in an all-vs-all comparison to bin contigs into
349		loci based on a minimum of 200~bp sequence overlap in the context of
350		transcriptome assembly for two Agave-species.}
351
352		\Mybibentry{KAN:HEL:DUR:WIN:ENG:BEH:HOL:BRA:HAU:FER:2013}{
353		to align 454-reads to assembled isotigs for Ragweed pollen.}
354
355		\Mybibentry{KUG:SIE:NUS:AME:SPAN:STEI:LEM:MAY:BUE:SCHWE:2013}{
356		for comparing gene sets.}
357
358		\Mybibentry{MAR:ZHO:HAS:SCHMU:VRA:KUB:KOEN:KUG:SCHOL:HAC:2013}{
359		to detect repetitive DNA content of chromosomal survey
360		sequences from the Rye genome.}
361
362		\item
363		In the papers
364
365		\bibentry{KOP:MAR:VHA:HRV:VRA:BAR:KOP:CAT:STO:NOV:2013}
366
367		\bibentry{KOP:MAR:CHA:HRI:VRA:BAR:2013}
368
369		\Vmatch was used for
370		identifying repetitive DNA content in contigs of meadow fescue chromosome 4F
371		assembled from Illumina short reads.
372
373		\item
374		In the papers
375
376		\bibentry{JAY:WAN:YU:TAC:PEL:COL:REN:VOI:2011}
377
378		\bibentry{WAN:WEI:SMI:2013}
379
380		\Vmatch was used for mapping siRNA sequences to the
381		\textit{Arabidopsis thaliana} genome.
382
383		\Mybibentry{HEN:VIV:DES:CHAU:PAY:GUT:CAS:2014}{
384		for the identification of binding motifs.}
385
386		\Mybibentry{WAN:HAB:GUN:GLAE:NUS:LUO:LOM:BOR:KER:SHA:2014}{
387		for masking one sequence set with another and for
388		mapping miRNA sequences of all plant species present in a reference database
389		to whole-genome assembly of \textit{Spirodela polyrhiza}.}
390
391		\Mybibentry{LOG:SCHEL:NUR:SAM:PEN:2014}{
392		for repeat detection.}
393
394		\Mybibentry{WAN:SHI:RIN:2015}{
395		to eliminate redundancies in assemblies of Illumina reads in
396		the context of studying plant defense mechanisms.}
397
398		\Mybibentry{ASH:HUL:WAN:YAN:GUA:JON:MAT:MOC:CHE:STE:2015}{
399		for clustering to determine a non-redundant set of assembled contigs.}
400
401		\Mybibentry{UST:NOV:BLI:SMY:2015}{
402		for clustering sequences based on their RT and aRNH domain.}
403
404		\Mybibentry{HLE:RIV:CLA:MAR:VAN:GON:GAR:LER:SIM:VAL:2015}{
405		for identifying repeats in contigs assembled from 454-reads.}
406
407		\Mybibentry{SHE:YAN:LU:WAN:SON:2015}{
408		for identifying inverted repeats in chloroplast genomes.}
409
410		\Mybibentry{PAN:MOH:KHA:MEH:EBR:2015}{
411		to identify contaminations and repetitive elements by
412		comparison of mRNA sequences to vector, bacterial and repeat databases.}
413
414		\Mybibentry{WOL:TWO:GAD:KNA:GRU:GEN:2015}{
415		to cluster contigs of different assemblies into groups of homologous sequences.}
416
417		\Mybibentry{YAN:LU:SHE:YAN:XU:SON:2015}{
418		to identify inverted repeats in chloroplast genomes.}
419
420		\Updateusages
421		\end{enumerate}
422
423		\subsection*{Usages in the Microbial Genome Research}
424		\begin{enumerate}
425		\item
426		The
427		\href{http://www.llnl.gov/str/April04/Slezak.html}{KPATH system},
428		developed at the Lawrence Livermore National Laboratories, and
429		described in
430
431		\bibentry{FIT:GAR:KUC:KUR:MYE:OTT:SLE:VIT:ZEM:MCC:2002}
432
433		\bibentry{SLE:KUC:OTT:TOR:MED:SMI:TRU:MUL:LAM:VIT:ZEM:ZHO:GAR:2003}
434
435		used \Vmatch to detect unique substrings in large
436		collection of DNA sequences. These unique substrings serve as
437		signatures allowing for rapid and accurate diagnostics
438		to identify pathogen bacteria and viruses. A similar application
439		is reported in \bibentry{GAR:KUC:VIT:SLE:2003}.
440
441		\Mybibentry{POB:WET:SZY:SCHIL:KUR:MEY:NAT:BECK:2006}{
442		to map signature tags to the genome
443		of \textit{S.~meliloti}.}
444
445		\item
446		The
447		\href{http://crispr.u-psud.fr/Server/CRISPRfinder.php}{CRISPRFinder}-program
448		and the
449		\href{http://crispr.u-psud.fr/crispr/CRISPRdatabase.php}{CRISPRdatabase}, described in
450
451		\bibentry{GRI:VER:POU:2007A}
452
453		\bibentry{GRI:VER:POU:2007B}
454
455		used \Vmatch to
456		efficiently find maximal repeats, as a first step in localizing
457		Clustered regularly interspaced short palindromic repeats (CRISPRs).
458
459		\Mybibentry{VOSS:GEO:SCHOE:UDE:HES:2009}{
460		to map predicted sequences to
461		information about Rho-independent terminators provided by a specific database.}
462
463		\Mybibentry{SCHMU:CAN:SCHLU:MA:MIT:NEL:HYT:SON:THE:CHE:2010}{
464		to cluster DNA-sequences into families based on their
465		six-frame translation.}
466
467		\Mybibentry{ZIM:GES:CHE:LOR:SCHRO:2010}{
468		to align 454-sequences to the Ecoli-genome and to cluster the sequences.}
469
470		\Mybibentry{TOU:DEN:MED:BAR:ELK:PET:2010}{
471		for detecting repeats in three bacterial species.}
472
473		\Mybibentry{MAY:MAR:HED:SIM:LIU:MOR:STEU:TAU:ROE:GUN:2011}{
474		for masking repeats in 454-reads.}
475
476		\Mybibentry{PUS:MAN:JI:LI:EVA:CRA:MOR:MEA:SIN:SAX:2011}{
477		to identify distal primers.}
478
479		\Mybibentry{BRE:SHE:POP:2011}{
480		for removing redundant transcripts assembled in an RNA-seq study based on
481		Illumina reads for \textit{Heliothis virescens} (tobacco budworm), infected
482		with a virus.}
483
484		\Mybibentry{TRI:HAM:BUE:TIS:VER:ZIN:LEA:2011}{
485		to search unassembled Illumina reads of US and African strains of
486		\textit{Xanthomonas oryzae} for evidence of transcriptional activator-like
487		effector sequences.}
488
489		\item
490		\Vmatch is used as an integral part of the PriMUX software package described in
491
492		\bibentry{HYS:NAR:ELS:CAR:WIL:GAR:2012}
493
494		In this context \Vmatch used for selecting multiplex compatible,
495		degenerate primers and probes to detect diverse targets such as viruses.
496
497		\Mybibentry{SHE:POP:2012}{
498		to identify redundant contigs from de novo exome assemblies.}
499
500		\Mybibentry{HUR:SUL:2013}{
501		to identify reads which have no common 20-mers with other
502		reads in a context of a marine viral metagenome project.}
503
504		\Mybibentry{ZHU:RHO:FESCH:2013}{
505		for clustering potential complete
506		Endogenous retroviruses of the bat \textit{Myotis lucifugus} into subfamilies.}
507
508		\item In the three papers
509
510		\bibentry{HUR:WES:BRU:SUL:2014}
511
512		\bibentry{HUR:DEN:POU:SUL:2013}
513
514		\bibentry{BRU:HUR:SCHOF:DUC:SUL:2015}
515
516		\Vmatch was used for $k$-mer analysis in the context of different marine
517		metagenome projects.
518
519		\Mybibentry{DEC:PAR:2014}{
520		for $k$-mer analysis in the context of microbial communities.}
521
522		\Mybibentry{BEN:BOU:FIC:KRI:LAR:2014}{
523		in an iterative scheme to construct contigs from reads associated with
524		resistance genes in the context of a shotgun metagenome project.}
525
526		\Mybibentry{NIC:THI:GAR:MCL:FOF:KOS:ELL:BRE:JAC:JAI:2013}{
527		to match probe candidate sequences against viral sequences and the human
528		genmome sequence.}
529
530		\Mybibentry{HEN:RUM:SCZ:VEL:DIE:GER:GOM:RAH:STO:BOR:2014}{
531		to identify the species of the Streptococcaceae
532		by comparing with Silva 115 release 16S reference sequence database.}
533		\Updateusages
534		\end{enumerate}
535
536		\subsection*{Usages in General Web-Servers or Sequence Analysis Software}
537		\begin{enumerate}
538		\item
539		Since 2000,
540		the \href{http://rsat.ulb.ac.be/rsat/}{RSA-tools}, described in
541
542		\bibentry{HEL:RIO:COL:2000}
543
544		and developed by Jacques van Helden
545		use \Vmatch to \href{http://rsat.ulb.ac.be/rsat/purge-sequence_form.cgi}{purge}
546		sequences before computing sequence statistics. Similar applications are
547		reported in the following papers:
548
549		\bibentry{HUL:WEE:CRO:GER:HEP:HEL:2003}
550
551		\bibentry{SIM:WOD:COH:HEL:2004}
552
553		\bibentry{SIM:HEL:COH:WOD:2004}.
554
555		\item
556		The program \href{http://splicenest.molgen.mpg.de/}{SpliceNest}, described in
557
558		\bibentry{COW:HAA:VIN:2002}
559
560		computes gene indices and uses \Vmatch to
561		\href{http://splicenest.molgen.mpg.de/doc/help.html\#mapping}{map} clustered
562		sequences to large genomes.
563		%\item
564		%The oligo design program
565		%\href{http://oligos.molgen.mpg.de/}{Promide}
566		%\bibentry{RAH:2002} developed by
567		%Sven Rahmann is based on the persistent index structure of \Vmatch.
568		%Promide uses \textit{mkvtree} for generating the index.
569		\item
570		\href{http://bibiserv.techfak.uni-bielefeld.de/e2g/}{e2g}
571		is a web-based server which efficiently maps large
572		EST and cDNA data sets to genomic DNA. The use of \Vmatch
573		allows to significantly extend the size of data that can be mapped in
574		reasonable time. e2g is available as a web service and hosts
575		large collections of EST sequences (e.g.\ 4.1 million mouse ESTs
576		of 1.87 Gbp) in a precomputed persistent index. For details see
577
578		\bibentry{KRUE:SCZ:KUR:GIE:2004}.
579
580		\item
581		The \href{http://bibiserv.techfak.uni-bielefeld.de/}{Bielefeld Bioinformatics Server} provides the
582		\href{http://bibiserv.techfak.uni-bielefeld.de/reputer/}{REPuter}
583		web-service to compute repeats in complete genomes. The service is based on
584		\Vmatch.
585
586		\Mybibentry{FER:DON:SCHNE:MOR:NAN:BRE:WAL:2004}{
587		to (1) match \numprint{130861} vector-trimmed sequences against the maize
588		repeat database, and (2) to cluster near-identical sequences. }
589		%The \href{http://www.mutransposon.org/project/RescueMu/research/GSSanalysis}%
590		%{Mu Transposon Information Resource},
591		\item
592		\href{http://www-ab.informatik.uni-tuebingen.de/software/crosslink/welcome.html}{CrossLink}, described in
593
594		\bibentry{DEZ:SCHAEF:WIE:WEI:HUS:2006}
595
596		is a versatile computational tool which aids in visualizing
597		relationships between RNA sequences (particularly between ncRNAs and
598		their putative target transcripts) in an intuitive and accessible way.
599		Besides BLAST, CrossLink uses \Vmatch to reveal the sequence
600		relationships to be visualized.
601
602		\item
603		The early version of the web-service \href{http://mips.gsf.de/simap/}%
604		{Similarity matrix of Proteins (SIMAP)}, see
605
606		\bibentry{ARN:RAT:TIS:TRU:STU:MEW:2005}
607
608		used \Vmatch to locate
609		the sequences in SIMAP which are similar to a given query. This is much
610		faster than running BLAST.
611
612		\Mybibentry{FIE:VAN:PEE:VAN:NAP:2005}{
613		to compute similarities between genomes, which are then visualized by the
614		program \href{http://www.win.tue.nl/dnavis/}{DNAVis}.}
615
616		\item In the paper
617
618		\bibentry{SEI:KRUE:HAR:SCHWA:LOEW:MER:DAN:GIE:2006}
619
620		Seidel et.\ al.\ describe
621		methods for creating web-services and give examples which, among other tools,
622		also integrate \Vmatch.
623
624		\item
625		The program \textit{Gepard}
626
627		\bibentry{KRU:ARN:RAT:2007}
628
629		uses \textit{mkvtree} to compute enhanced suffix arrays.
630
631		\item
632		\Vmatch is used a part of the transcriptome assembler software Rnnotator,
633		described in
634
635		\bibentry{MAR:BRU:FAN:MEN:BLO:ZHA:SHE:SNY:WAN:2010}
636		\item
637		The BioExtract-Server described in
638
639		\bibentry{LUS:JEN:BRE:2011}
640
641		uses \Vmatch to remove duplicated sequences.
642
643		\Mybibentry{LUS:GNI:DOO:2015}{
644		for removing duplicates in BlastP results. This use is
645		part of a workflow in
646		\href{http://www.myexperiment.org/workflows/3131.html}{myexperiment}.
647		}
648
649		\Mybibentry{GRE:LOY:HOR:RAT:2015}{
650		for probe/primer search functionality in the probeBase database.}
651		\Updateusages
652		\end{enumerate}
653
654		\subsection*{Current Usages in Human Genome Research}
655		\begin{enumerate}
656		\Mybibentry{BUC:JAR:MEN:MAT:SCO:GRE:LAN:DUM:2005}{
657		to reveal long repeats inside human chromosome 1 and long similar regions
658		between human chromosome 1 and all other human chromosomes.}
659
660		\Mybibentry{LIA:WAN:LIU:JI:LIU:CHE:WEB:REE:DEA:2007}{
661		for Vector screening.}
662
663		\Mybibentry{NYG:JAC:LIN:ERI:BAL:FLY:TOL:MOE:SOE:KRO:LIT:2009}{
664		for mapping short reads.}
665
666		\Mybibentry{COL:SOB:LU:THA:BOW:BRO:GRE:BAR:HUT:2009}{
667		for matching reads to sets of RNA sequences and the Human genome.}
668
669		\Mybibentry{CLO:WAN:XU:GU:LEA:HEA:BAR:STE:MAR:NOU:2011}{
670		to uniquely map miRNAs against the human genome.}
671
672		\Mybibentry{TAK:TSU:KAT:OKA:HOR:IKE:URA:KAW:HAS:IKE:2011}{
673		to determine the positions of CAGE tags on the human genome.}
674
675		\Mybibentry{KEV:LAL:LI:CAV:NAR:KAM:MIT:HAK:KOZ:GEN:2011}{
676		to align sections of reads against RefSeq mRNA exon sequences.}
677
678		\Mybibentry{KID:CHE:WAN:JAC:ZHA:BOY:FIR:TAN:GAE:COL:2012}{
679		to align sets of genes.}
680
681		\Mybibentry{YAM:IKE:BOE:HOR:TAK:URA:KAI:CAR:KAW:HAY:2014}{
682		to determine the positions of CAGE tags on the human genome.}
683
684		\Updateusages
685		\end{enumerate}
686
687		\subsection*{Current Usages for different Model Organisms}
688		\begin{enumerate}
689		\Mybibentry{SCZ:BECK:BRI:GIE:ALT:2005}{
690		to cluster \numprint{317242} EST and cDNA sequences from
691		\textit{Xenopus laevis}. \Vmatch was chosen for the following reasons:
692		\begin{itemize}
693		\item
694		At first, there was no clustering tool available which could handle
695		large data sets efficiently, and which was documented well enough to
696		allow a detailed b replication and evaluation of existing clusters.
697		\item
698		Second, \Vmatch identifies similarities between sequences rapidly,
699		and it provides additional options to cluster a set of sequences
700		based on these matches. Furthermore, the \Vmatch output provides
701		information about how the clusters were derived. Due to the
702		efficiency of \Vmatch, it was possible to perform the clustering for a
703		wide variety of parameters on the complete sequence set.
704		This allows to study the effect of the parameter choice on the clustering.
705		\end{itemize}}
706
707		\Mybibentry{SPIT:LOR:CUL:SCZ:FUEL:2006}{
708		to cluster EST-sequences of \textit{Xenopus laevis}.}
709
710		\Mybibentry{EIS:COY:WU:WU:THI:WOR:BAD:REN:AME:JON:2006}{
711		to search exact repeats in the Macronuclear Genome Sequence of the Ciliate
712		\textit{Tetrahymena thermophila}.}
713		%\item
714		%\href{http://www.plantgdb.org/}{PlantGDB} provides a Web Service
715		%named \href{https://biomoby.tigr.org/wiki/index.php/Code_Examples_-_Java}{VMatchForArabidopsis}%
716		%
717		%based on \Vmatch. It allows to search sequences
718		%from \textit{Arabidopsis Thaliana}.
719		%\item
720		%The \href{http://www.jgi.doe.gov/science/posters/LBNL-59860goltsman.pdf}{DOE Joint Genome Institute}%
721		%
722		%used \Vmatch to
723		%identify and mask all continuous non-unique sequence fragments over
724		%500~bp in \textit{Frankia sp.} and \textit{Shewanella oneidensis}.
725
726		\Mybibentry{FAU:FOR:CHA:SCHRO:HAY:CAR:HUM:GRI:2008}{
727		for mapping
728		\begin{itemize}
729		\item
730		\numprint{11567973} FANTOM3 mouse CAGE tags to the mouse genome
731		with minimum match length of {18} bp, a single internal mismatch allowed,
732		and multiple mismatches allowed at tag ends.
733		\item
734		Affymetrix GNF probe sequences to transcripts without allowing for mismatches.
735		\end{itemize}}
736
737
738		\Mybibentry{PRI:JOR:2008}{
739		to search small RNA signatures in entire miRNA gene sequences for
740		Arabidopsis and rice.}
741
742		\Mybibentry{TAF:GLA:LASS:HAY:CAR:MAT:2009}{
743		to map small RNA data sets onto the corresponding reference
744		genomes for different model organisms.}
745
746		\Mybibentry{PLE:PAS:BER:AKA:CAR:VAS:LAZ:SEV:VLA:SIM:2012}{
747		for mapping Illumina reads to the mouse genome.}
748
749		\Mybibentry{KEN:SHI:2012}{
750		for redundancy removal in the context of transcriptome assembly of
751		a keelworm species.}
752
753		\Mybibentry{GOS:OHM:KOG:SON:TUR:ZAJ:ZAL:GRU:SUN:HAN:2014}{
754		to remove redundant contigs in a genome project of four
755		\textit{Aureobasidium pullulans} varieties.}
756
757		\Mybibentry{MCM:GAR:BAI:KEM:WAR:CEV:ROB:SCHUL:BAL:HOL:2015}{
758		for merging assemblies of Illumina sequenced cDNA.}
759
760		% add applications at Bioinformatics Center Copenhagen Univ., see E-mails from
761		% Feb 2007, this may be the Biopieces.
762
763		% the following paper cites \Vmatch, but does not use it.
764		% http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=1868776
765		% \bibentry{TEM:ZAV:BOD:CHA:GEY:WAS:BEN:REI:2007}, Tembe et et.\ al.\
766
767		%Add "Highly Specific Gene Silencing by Artificial MicroRNAs in Arabidopsis"
768		%of Schwab et al, 2006, and implemented on wmd2.weigelworld.org.
769		%refers to Hypa and not really to \Vmatch.
770
771		\Mybibentry{MOR:DHA:PAV:TRO:WHE:HEL:2015}{
772		to combine and scaffold contigs.}
773
774		\Updateusages
775		\end{enumerate}
776
777		Total number of usages: \arabic{Allusages}
778
779		\section*{Availability}
780		\Vmatch is available for
781		\href{http://www.vmatch.de/download.html}{download}
782		in executable form for the following platforms:
783
784		\begin{itemize}
785		\item
786		Linux
787		\item
788		Mac OS X
789		\item
790		MS Windows
791		\end{itemize}
792
793		\section*{Developer}
794		\Vmatch was developed since May 2000 by
795		\href{http://www.zbh.uni-hamburg.de/kurtz}{Stefan Kurtz},
796		a professor of
797		Computer Science at the Center for Bioinformatics, University of Hamburg,
798		Germany.
799
800		\HCode{
801		<!--delete paragraph-->
802		<b>Important Documents</b>
803		<ul>
804		<li>
805		The <a href="virtman.pdf"><i>Vmatch</i>-manual</a>
806		</li>
807		</ul>
808		}
809
810		\HCode{
811		<!--delete paragraph-->
812		<div id="footer">
813		Copyright © 2000-2017 <a href="mailto:kurtz@zbh.uni-hamburg.de">
814		Stefan Kurtz</a>. Last update: 2017-06-15
815		</div>
816		}
817
818		\HCode{
819		<!--delete paragraph-->
820		<!-- Piwik -->
821		<div id="piwik">
822		<script type="text/javascript">
823		var pkBaseURL = "https://zenlicensemanager.com/piwik/";
824		document.write(unescape("%3Cscript src='" + pkBaseURL + "piwik.js' type='text/javascript'%3E%3C/script%3E"));
825		</script><script type="text/javascript">
826		try {
827		var piwikTracker = Piwik.getTracker(pkBaseURL + "piwik.php", 3);
828		piwikTracker.trackPageView();
829		piwikTracker.enableLinkTracking();
830		} catch( err ) {}
831		</script>
832		<br/>
833		<noscript>
834		<img src="https://zenlicensemanager.com/piwik/piwik.php?idsite=3" style="border:0" alt=""/>
835		</noscript>
836		<!-- End Piwik Tracking Tag -->
837		</div>
838		}
839		\end{document}

-196

~~src/doc/WWW/xhtml-lat1.ent~~ less more

0		<!-- Portions (C) International Organization for Standardization 1986
1		Permission to copy in any form is granted for use with
2		conforming SGML systems and applications as defined in
3		ISO 8879, provided this notice is included in all copies.
4		-->
5		<!-- Character entity set. Typical invocation:
6		<!ENTITY % HTMLlat1 PUBLIC
7		"-//W3C//ENTITIES Latin 1 for XHTML//EN"
8		"http://www.w3.org/TR/xhtml1/DTD/xhtml-lat1.ent">
9		%HTMLlat1;
10		-->
11
12		<!ENTITY nbsp " "> <!-- no-break space = non-breaking space,
13		U+00A0 ISOnum -->
14		<!ENTITY iexcl "¡"> <!-- inverted exclamation mark, U+00A1 ISOnum -->
15		<!ENTITY cent "¢"> <!-- cent sign, U+00A2 ISOnum -->
16		<!ENTITY pound "£"> <!-- pound sign, U+00A3 ISOnum -->
17		<!ENTITY curren "¤"> <!-- currency sign, U+00A4 ISOnum -->
18		<!ENTITY yen "¥"> <!-- yen sign = yuan sign, U+00A5 ISOnum -->
19		<!ENTITY brvbar "¦"> <!-- broken bar = broken vertical bar,
20		U+00A6 ISOnum -->
21		<!ENTITY sect "§"> <!-- section sign, U+00A7 ISOnum -->
22		<!ENTITY uml "¨"> <!-- diaeresis = spacing diaeresis,
23		U+00A8 ISOdia -->
24		<!ENTITY copy "©"> <!-- copyright sign, U+00A9 ISOnum -->
25		<!ENTITY ordf "ª"> <!-- feminine ordinal indicator, U+00AA ISOnum -->
26		<!ENTITY laquo "«"> <!-- left-pointing double angle quotation mark
27		= left pointing guillemet, U+00AB ISOnum -->
28		<!ENTITY not "¬"> <!-- not sign = angled dash,
29		U+00AC ISOnum -->
30		<!ENTITY shy ""> <!-- soft hyphen = discretionary hyphen,
31		U+00AD ISOnum -->
32		<!ENTITY reg "®"> <!-- registered sign = registered trade mark sign,
33		U+00AE ISOnum -->
34		<!ENTITY macr "¯"> <!-- macron = spacing macron = overline
35		= APL overbar, U+00AF ISOdia -->
36		<!ENTITY deg "°"> <!-- degree sign, U+00B0 ISOnum -->
37		<!ENTITY plusmn "±"> <!-- plus-minus sign = plus-or-minus sign,
38		U+00B1 ISOnum -->
39		<!ENTITY sup2 "²"> <!-- superscript two = superscript digit two
40		= squared, U+00B2 ISOnum -->
41		<!ENTITY sup3 "³"> <!-- superscript three = superscript digit three
42		= cubed, U+00B3 ISOnum -->
43		<!ENTITY acute "´"> <!-- acute accent = spacing acute,
44		U+00B4 ISOdia -->
45		<!ENTITY micro "µ"> <!-- micro sign, U+00B5 ISOnum -->
46		<!ENTITY para "¶"> <!-- pilcrow sign = paragraph sign,
47		U+00B6 ISOnum -->
48		<!ENTITY middot "·"> <!-- middle dot = Georgian comma
49		= Greek middle dot, U+00B7 ISOnum -->
50		<!ENTITY cedil "¸"> <!-- cedilla = spacing cedilla, U+00B8 ISOdia -->
51		<!ENTITY sup1 "¹"> <!-- superscript one = superscript digit one,
52		U+00B9 ISOnum -->
53		<!ENTITY ordm "º"> <!-- masculine ordinal indicator,
54		U+00BA ISOnum -->
55		<!ENTITY raquo "»"> <!-- right-pointing double angle quotation mark
56		= right pointing guillemet, U+00BB ISOnum -->
57		<!ENTITY frac14 "¼"> <!-- vulgar fraction one quarter
58		= fraction one quarter, U+00BC ISOnum -->
59		<!ENTITY frac12 "½"> <!-- vulgar fraction one half
60		= fraction one half, U+00BD ISOnum -->
61		<!ENTITY frac34 "¾"> <!-- vulgar fraction three quarters
62		= fraction three quarters, U+00BE ISOnum -->
63		<!ENTITY iquest "¿"> <!-- inverted question mark
64		= turned question mark, U+00BF ISOnum -->
65		<!ENTITY Agrave "À"> <!-- latin capital letter A with grave
66		= latin capital letter A grave,
67		U+00C0 ISOlat1 -->
68		<!ENTITY Aacute "Á"> <!-- latin capital letter A with acute,
69		U+00C1 ISOlat1 -->
70		<!ENTITY Acirc "Â"> <!-- latin capital letter A with circumflex,
71		U+00C2 ISOlat1 -->
72		<!ENTITY Atilde "Ã"> <!-- latin capital letter A with tilde,
73		U+00C3 ISOlat1 -->
74		<!ENTITY Auml "Ä"> <!-- latin capital letter A with diaeresis,
75		U+00C4 ISOlat1 -->
76		<!ENTITY Aring "Å"> <!-- latin capital letter A with ring above
77		= latin capital letter A ring,
78		U+00C5 ISOlat1 -->
79		<!ENTITY AElig "Æ"> <!-- latin capital letter AE
80		= latin capital ligature AE,
81		U+00C6 ISOlat1 -->
82		<!ENTITY Ccedil "Ç"> <!-- latin capital letter C with cedilla,
83		U+00C7 ISOlat1 -->
84		<!ENTITY Egrave "È"> <!-- latin capital letter E with grave,
85		U+00C8 ISOlat1 -->
86		<!ENTITY Eacute "É"> <!-- latin capital letter E with acute,
87		U+00C9 ISOlat1 -->
88		<!ENTITY Ecirc "Ê"> <!-- latin capital letter E with circumflex,
89		U+00CA ISOlat1 -->
90		<!ENTITY Euml "Ë"> <!-- latin capital letter E with diaeresis,
91		U+00CB ISOlat1 -->
92		<!ENTITY Igrave "Ì"> <!-- latin capital letter I with grave,
93		U+00CC ISOlat1 -->
94		<!ENTITY Iacute "Í"> <!-- latin capital letter I with acute,
95		U+00CD ISOlat1 -->
96		<!ENTITY Icirc "Î"> <!-- latin capital letter I with circumflex,
97		U+00CE ISOlat1 -->
98		<!ENTITY Iuml "Ï"> <!-- latin capital letter I with diaeresis,
99		U+00CF ISOlat1 -->
100		<!ENTITY ETH "Ð"> <!-- latin capital letter ETH, U+00D0 ISOlat1 -->
101		<!ENTITY Ntilde "Ñ"> <!-- latin capital letter N with tilde,
102		U+00D1 ISOlat1 -->
103		<!ENTITY Ograve "Ò"> <!-- latin capital letter O with grave,
104		U+00D2 ISOlat1 -->
105		<!ENTITY Oacute "Ó"> <!-- latin capital letter O with acute,
106		U+00D3 ISOlat1 -->
107		<!ENTITY Ocirc "Ô"> <!-- latin capital letter O with circumflex,
108		U+00D4 ISOlat1 -->
109		<!ENTITY Otilde "Õ"> <!-- latin capital letter O with tilde,
110		U+00D5 ISOlat1 -->
111		<!ENTITY Ouml "Ö"> <!-- latin capital letter O with diaeresis,
112		U+00D6 ISOlat1 -->
113		<!ENTITY times "×"> <!-- multiplication sign, U+00D7 ISOnum -->
114		<!ENTITY Oslash "Ø"> <!-- latin capital letter O with stroke
115		= latin capital letter O slash,
116		U+00D8 ISOlat1 -->
117		<!ENTITY Ugrave "Ù"> <!-- latin capital letter U with grave,
118		U+00D9 ISOlat1 -->
119		<!ENTITY Uacute "Ú"> <!-- latin capital letter U with acute,
120		U+00DA ISOlat1 -->
121		<!ENTITY Ucirc "Û"> <!-- latin capital letter U with circumflex,
122		U+00DB ISOlat1 -->
123		<!ENTITY Uuml "Ü"> <!-- latin capital letter U with diaeresis,
124		U+00DC ISOlat1 -->
125		<!ENTITY Yacute "Ý"> <!-- latin capital letter Y with acute,
126		U+00DD ISOlat1 -->
127		<!ENTITY THORN "Þ"> <!-- latin capital letter THORN,
128		U+00DE ISOlat1 -->
129		<!ENTITY szlig "ß"> <!-- latin small letter sharp s = ess-zed,
130		U+00DF ISOlat1 -->
131		<!ENTITY agrave "à"> <!-- latin small letter a with grave
132		= latin small letter a grave,
133		U+00E0 ISOlat1 -->
134		<!ENTITY aacute "á"> <!-- latin small letter a with acute,
135		U+00E1 ISOlat1 -->
136		<!ENTITY acirc "â"> <!-- latin small letter a with circumflex,
137		U+00E2 ISOlat1 -->
138		<!ENTITY atilde "ã"> <!-- latin small letter a with tilde,
139		U+00E3 ISOlat1 -->
140		<!ENTITY auml "ä"> <!-- latin small letter a with diaeresis,
141		U+00E4 ISOlat1 -->
142		<!ENTITY aring "å"> <!-- latin small letter a with ring above
143		= latin small letter a ring,
144		U+00E5 ISOlat1 -->
145		<!ENTITY aelig "æ"> <!-- latin small letter ae
146		= latin small ligature ae, U+00E6 ISOlat1 -->
147		<!ENTITY ccedil "ç"> <!-- latin small letter c with cedilla,
148		U+00E7 ISOlat1 -->
149		<!ENTITY egrave "è"> <!-- latin small letter e with grave,
150		U+00E8 ISOlat1 -->
151		<!ENTITY eacute "é"> <!-- latin small letter e with acute,
152		U+00E9 ISOlat1 -->
153		<!ENTITY ecirc "ê"> <!-- latin small letter e with circumflex,
154		U+00EA ISOlat1 -->
155		<!ENTITY euml "ë"> <!-- latin small letter e with diaeresis,
156		U+00EB ISOlat1 -->
157		<!ENTITY igrave "ì"> <!-- latin small letter i with grave,
158		U+00EC ISOlat1 -->
159		<!ENTITY iacute "í"> <!-- latin small letter i with acute,
160		U+00ED ISOlat1 -->
161		<!ENTITY icirc "î"> <!-- latin small letter i with circumflex,
162		U+00EE ISOlat1 -->
163		<!ENTITY iuml "ï"> <!-- latin small letter i with diaeresis,
164		U+00EF ISOlat1 -->
165		<!ENTITY eth "ð"> <!-- latin small letter eth, U+00F0 ISOlat1 -->
166		<!ENTITY ntilde "ñ"> <!-- latin small letter n with tilde,
167		U+00F1 ISOlat1 -->
168		<!ENTITY ograve "ò"> <!-- latin small letter o with grave,
169		U+00F2 ISOlat1 -->
170		<!ENTITY oacute "ó"> <!-- latin small letter o with acute,
171		U+00F3 ISOlat1 -->
172		<!ENTITY ocirc "ô"> <!-- latin small letter o with circumflex,
173		U+00F4 ISOlat1 -->
174		<!ENTITY otilde "õ"> <!-- latin small letter o with tilde,
175		U+00F5 ISOlat1 -->
176		<!ENTITY ouml "ö"> <!-- latin small letter o with diaeresis,
177		U+00F6 ISOlat1 -->
178		<!ENTITY divide "÷"> <!-- division sign, U+00F7 ISOnum -->
179		<!ENTITY oslash "ø"> <!-- latin small letter o with stroke,
180		= latin small letter o slash,
181		U+00F8 ISOlat1 -->
182		<!ENTITY ugrave "ù"> <!-- latin small letter u with grave,
183		U+00F9 ISOlat1 -->
184		<!ENTITY uacute "ú"> <!-- latin small letter u with acute,
185		U+00FA ISOlat1 -->
186		<!ENTITY ucirc "û"> <!-- latin small letter u with circumflex,
187		U+00FB ISOlat1 -->
188		<!ENTITY uuml "ü"> <!-- latin small letter u with diaeresis,
189		U+00FC ISOlat1 -->
190		<!ENTITY yacute "ý"> <!-- latin small letter y with acute,
191		U+00FD ISOlat1 -->
192		<!ENTITY thorn "þ"> <!-- latin small letter thorn,
193		U+00FE ISOlat1 -->
194		<!ENTITY yuml "ÿ"> <!-- latin small letter y with diaeresis,
195		U+00FF ISOlat1 -->

-80

~~src/doc/WWW/xhtml-special.ent~~ less more

0		<!-- Special characters for XHTML -->
1
2		<!-- Character entity set. Typical invocation:
3		<!ENTITY % HTMLspecial PUBLIC
4		"-//W3C//ENTITIES Special for XHTML//EN"
5		"http://www.w3.org/TR/xhtml1/DTD/xhtml-special.ent">
6		%HTMLspecial;
7		-->
8
9		<!-- Portions (C) International Organization for Standardization 1986:
10		Permission to copy in any form is granted for use with
11		conforming SGML systems and applications as defined in
12		ISO 8879, provided this notice is included in all copies.
13		-->
14
15		<!-- Relevant ISO entity set is given unless names are newly introduced.
16		New names (i.e., not in ISO 8879 list) do not clash with any
17		existing ISO 8879 entity names. ISO 10646 character numbers
18		are given for each character, in hex. values are decimal
19		conversions of the ISO 10646 values and refer to the document
20		character set. Names are Unicode names.
21		-->
22
23		<!-- C0 Controls and Basic Latin -->
24		<!ENTITY quot """> <!-- quotation mark, U+0022 ISOnum -->
25		<!ENTITY amp "&#38;"> <!-- ampersand, U+0026 ISOnum -->
26		<!ENTITY lt "&#60;"> <!-- less-than sign, U+003C ISOnum -->
27		<!ENTITY gt ">"> <!-- greater-than sign, U+003E ISOnum -->
28		<!ENTITY apos "'"> <!-- apostrophe = APL quote, U+0027 ISOnum -->
29
30		<!-- Latin Extended-A -->
31		<!ENTITY OElig "Œ"> <!-- latin capital ligature OE,
32		U+0152 ISOlat2 -->
33		<!ENTITY oelig "œ"> <!-- latin small ligature oe, U+0153 ISOlat2 -->
34		<!-- ligature is a misnomer, this is a separate character in some languages -->
35		<!ENTITY Scaron "Š"> <!-- latin capital letter S with caron,
36		U+0160 ISOlat2 -->
37		<!ENTITY scaron "š"> <!-- latin small letter s with caron,
38		U+0161 ISOlat2 -->
39		<!ENTITY Yuml "Ÿ"> <!-- latin capital letter Y with diaeresis,
40		U+0178 ISOlat2 -->
41
42		<!-- Spacing Modifier Letters -->
43		<!ENTITY circ "ˆ"> <!-- modifier letter circumflex accent,
44		U+02C6 ISOpub -->
45		<!ENTITY tilde "˜"> <!-- small tilde, U+02DC ISOdia -->
46
47		<!-- General Punctuation -->
48		<!ENTITY ensp " "> <!-- en space, U+2002 ISOpub -->
49		<!ENTITY emsp " "> <!-- em space, U+2003 ISOpub -->
50		<!ENTITY thinsp " "> <!-- thin space, U+2009 ISOpub -->
51		<!ENTITY zwnj "‌"> <!-- zero width non-joiner,
52		U+200C NEW RFC 2070 -->
53		<!ENTITY zwj "‍"> <!-- zero width joiner, U+200D NEW RFC 2070 -->
54		<!ENTITY lrm "‎"> <!-- left-to-right mark, U+200E NEW RFC 2070 -->
55		<!ENTITY rlm "‏"> <!-- right-to-left mark, U+200F NEW RFC 2070 -->
56		<!ENTITY ndash "–"> <!-- en dash, U+2013 ISOpub -->
57		<!ENTITY mdash "—"> <!-- em dash, U+2014 ISOpub -->
58		<!ENTITY lsquo "‘"> <!-- left single quotation mark,
59		U+2018 ISOnum -->
60		<!ENTITY rsquo "’"> <!-- right single quotation mark,
61		U+2019 ISOnum -->
62		<!ENTITY sbquo "‚"> <!-- single low-9 quotation mark, U+201A NEW -->
63		<!ENTITY ldquo "“"> <!-- left double quotation mark,
64		U+201C ISOnum -->
65		<!ENTITY rdquo "”"> <!-- right double quotation mark,
66		U+201D ISOnum -->
67		<!ENTITY bdquo "„"> <!-- double low-9 quotation mark, U+201E NEW -->
68		<!ENTITY dagger "†"> <!-- dagger, U+2020 ISOpub -->
69		<!ENTITY Dagger "‡"> <!-- double dagger, U+2021 ISOpub -->
70		<!ENTITY permil "‰"> <!-- per mille sign, U+2030 ISOtech -->
71		<!ENTITY lsaquo "‹"> <!-- single left-pointing angle quotation mark,
72		U+2039 ISO proposed -->
73		<!-- lsaquo is proposed but not yet ISO standardized -->
74		<!ENTITY rsaquo "›"> <!-- single right-pointing angle quotation mark,
75		U+203A ISO proposed -->
76		<!-- rsaquo is proposed but not yet ISO standardized -->
77
78		<!-- Currency Symbols -->
79		<!ENTITY euro "€"> <!-- euro sign, U+20AC NEW -->

-237

~~src/doc/WWW/xhtml-symbol.ent~~ less more

0		<!-- Mathematical, Greek and Symbolic characters for XHTML -->
1
2		<!-- Character entity set. Typical invocation:
3		<!ENTITY % HTMLsymbol PUBLIC
4		"-//W3C//ENTITIES Symbols for XHTML//EN"
5		"http://www.w3.org/TR/xhtml1/DTD/xhtml-symbol.ent">
6		%HTMLsymbol;
7		-->
8
9		<!-- Portions (C) International Organization for Standardization 1986:
10		Permission to copy in any form is granted for use with
11		conforming SGML systems and applications as defined in
12		ISO 8879, provided this notice is included in all copies.
13		-->
14
15		<!-- Relevant ISO entity set is given unless names are newly introduced.
16		New names (i.e., not in ISO 8879 list) do not clash with any
17		existing ISO 8879 entity names. ISO 10646 character numbers
18		are given for each character, in hex. values are decimal
19		conversions of the ISO 10646 values and refer to the document
20		character set. Names are Unicode names.
21		-->
22
23		<!-- Latin Extended-B -->
24		<!ENTITY fnof "ƒ"> <!-- latin small letter f with hook = function
25		= florin, U+0192 ISOtech -->
26
27		<!-- Greek -->
28		<!ENTITY Alpha "Α"> <!-- greek capital letter alpha, U+0391 -->
29		<!ENTITY Beta "Β"> <!-- greek capital letter beta, U+0392 -->
30		<!ENTITY Gamma "Γ"> <!-- greek capital letter gamma,
31		U+0393 ISOgrk3 -->
32		<!ENTITY Delta "Δ"> <!-- greek capital letter delta,
33		U+0394 ISOgrk3 -->
34		<!ENTITY Epsilon "Ε"> <!-- greek capital letter epsilon, U+0395 -->
35		<!ENTITY Zeta "Ζ"> <!-- greek capital letter zeta, U+0396 -->
36		<!ENTITY Eta "Η"> <!-- greek capital letter eta, U+0397 -->
37		<!ENTITY Theta "Θ"> <!-- greek capital letter theta,
38		U+0398 ISOgrk3 -->
39		<!ENTITY Iota "Ι"> <!-- greek capital letter iota, U+0399 -->
40		<!ENTITY Kappa "Κ"> <!-- greek capital letter kappa, U+039A -->
41		<!ENTITY Lambda "Λ"> <!-- greek capital letter lamda,
42		U+039B ISOgrk3 -->
43		<!ENTITY Mu "Μ"> <!-- greek capital letter mu, U+039C -->
44		<!ENTITY Nu "Ν"> <!-- greek capital letter nu, U+039D -->
45		<!ENTITY Xi "Ξ"> <!-- greek capital letter xi, U+039E ISOgrk3 -->
46		<!ENTITY Omicron "Ο"> <!-- greek capital letter omicron, U+039F -->
47		<!ENTITY Pi "Π"> <!-- greek capital letter pi, U+03A0 ISOgrk3 -->
48		<!ENTITY Rho "Ρ"> <!-- greek capital letter rho, U+03A1 -->
49		<!-- there is no Sigmaf, and no U+03A2 character either -->
50		<!ENTITY Sigma "Σ"> <!-- greek capital letter sigma,
51		U+03A3 ISOgrk3 -->
52		<!ENTITY Tau "Τ"> <!-- greek capital letter tau, U+03A4 -->
53		<!ENTITY Upsilon "Υ"> <!-- greek capital letter upsilon,
54		U+03A5 ISOgrk3 -->
55		<!ENTITY Phi "Φ"> <!-- greek capital letter phi,
56		U+03A6 ISOgrk3 -->
57		<!ENTITY Chi "Χ"> <!-- greek capital letter chi, U+03A7 -->
58		<!ENTITY Psi "Ψ"> <!-- greek capital letter psi,
59		U+03A8 ISOgrk3 -->
60		<!ENTITY Omega "Ω"> <!-- greek capital letter omega,
61		U+03A9 ISOgrk3 -->
62
63		<!ENTITY alpha "α"> <!-- greek small letter alpha,
64		U+03B1 ISOgrk3 -->
65		<!ENTITY beta "β"> <!-- greek small letter beta, U+03B2 ISOgrk3 -->
66		<!ENTITY gamma "γ"> <!-- greek small letter gamma,
67		U+03B3 ISOgrk3 -->
68		<!ENTITY delta "δ"> <!-- greek small letter delta,
69		U+03B4 ISOgrk3 -->
70		<!ENTITY epsilon "ε"> <!-- greek small letter epsilon,
71		U+03B5 ISOgrk3 -->
72		<!ENTITY zeta "ζ"> <!-- greek small letter zeta, U+03B6 ISOgrk3 -->
73		<!ENTITY eta "η"> <!-- greek small letter eta, U+03B7 ISOgrk3 -->
74		<!ENTITY theta "θ"> <!-- greek small letter theta,
75		U+03B8 ISOgrk3 -->
76		<!ENTITY iota "ι"> <!-- greek small letter iota, U+03B9 ISOgrk3 -->
77		<!ENTITY kappa "κ"> <!-- greek small letter kappa,
78		U+03BA ISOgrk3 -->
79		<!ENTITY lambda "λ"> <!-- greek small letter lamda,
80		U+03BB ISOgrk3 -->
81		<!ENTITY mu "μ"> <!-- greek small letter mu, U+03BC ISOgrk3 -->
82		<!ENTITY nu "ν"> <!-- greek small letter nu, U+03BD ISOgrk3 -->
83		<!ENTITY xi "ξ"> <!-- greek small letter xi, U+03BE ISOgrk3 -->
84		<!ENTITY omicron "ο"> <!-- greek small letter omicron, U+03BF NEW -->
85		<!ENTITY pi "π"> <!-- greek small letter pi, U+03C0 ISOgrk3 -->
86		<!ENTITY rho "ρ"> <!-- greek small letter rho, U+03C1 ISOgrk3 -->
87		<!ENTITY sigmaf "ς"> <!-- greek small letter final sigma,
88		U+03C2 ISOgrk3 -->
89		<!ENTITY sigma "σ"> <!-- greek small letter sigma,
90		U+03C3 ISOgrk3 -->
91		<!ENTITY tau "τ"> <!-- greek small letter tau, U+03C4 ISOgrk3 -->
92		<!ENTITY upsilon "υ"> <!-- greek small letter upsilon,
93		U+03C5 ISOgrk3 -->
94		<!ENTITY phi "φ"> <!-- greek small letter phi, U+03C6 ISOgrk3 -->
95		<!ENTITY chi "χ"> <!-- greek small letter chi, U+03C7 ISOgrk3 -->
96		<!ENTITY psi "ψ"> <!-- greek small letter psi, U+03C8 ISOgrk3 -->
97		<!ENTITY omega "ω"> <!-- greek small letter omega,
98		U+03C9 ISOgrk3 -->
99		<!ENTITY thetasym "ϑ"> <!-- greek theta symbol,
100		U+03D1 NEW -->
101		<!ENTITY upsih "ϒ"> <!-- greek upsilon with hook symbol,
102		U+03D2 NEW -->
103		<!ENTITY piv "ϖ"> <!-- greek pi symbol, U+03D6 ISOgrk3 -->
104
105		<!-- General Punctuation -->
106		<!ENTITY bull "•"> <!-- bullet = black small circle,
107		U+2022 ISOpub -->
108		<!-- bullet is NOT the same as bullet operator, U+2219 -->
109		<!ENTITY hellip "…"> <!-- horizontal ellipsis = three dot leader,
110		U+2026 ISOpub -->
111		<!ENTITY prime "′"> <!-- prime = minutes = feet, U+2032 ISOtech -->
112		<!ENTITY Prime "″"> <!-- double prime = seconds = inches,
113		U+2033 ISOtech -->
114		<!ENTITY oline "‾"> <!-- overline = spacing overscore,
115		U+203E NEW -->
116		<!ENTITY frasl "⁄"> <!-- fraction slash, U+2044 NEW -->
117
118		<!-- Letterlike Symbols -->
119		<!ENTITY weierp "℘"> <!-- script capital P = power set
120		= Weierstrass p, U+2118 ISOamso -->
121		<!ENTITY image "ℑ"> <!-- black-letter capital I = imaginary part,
122		U+2111 ISOamso -->
123		<!ENTITY real "ℜ"> <!-- black-letter capital R = real part symbol,
124		U+211C ISOamso -->
125		<!ENTITY trade "™"> <!-- trade mark sign, U+2122 ISOnum -->
126		<!ENTITY alefsym "ℵ"> <!-- alef symbol = first transfinite cardinal,
127		U+2135 NEW -->
128		<!-- alef symbol is NOT the same as hebrew letter alef,
129		U+05D0 although the same glyph could be used to depict both characters -->
130
131		<!-- Arrows -->
132		<!ENTITY larr "←"> <!-- leftwards arrow, U+2190 ISOnum -->
133		<!ENTITY uarr "↑"> <!-- upwards arrow, U+2191 ISOnum-->
134		<!ENTITY rarr "→"> <!-- rightwards arrow, U+2192 ISOnum -->
135		<!ENTITY darr "↓"> <!-- downwards arrow, U+2193 ISOnum -->
136		<!ENTITY harr "↔"> <!-- left right arrow, U+2194 ISOamsa -->
137		<!ENTITY crarr "↵"> <!-- downwards arrow with corner leftwards
138		= carriage return, U+21B5 NEW -->
139		<!ENTITY lArr "⇐"> <!-- leftwards double arrow, U+21D0 ISOtech -->
140		<!-- Unicode does not say that lArr is the same as the 'is implied by' arrow
141		but also does not have any other character for that function. So lArr can
142		be used for 'is implied by' as ISOtech suggests -->
143		<!ENTITY uArr "⇑"> <!-- upwards double arrow, U+21D1 ISOamsa -->
144		<!ENTITY rArr "⇒"> <!-- rightwards double arrow,
145		U+21D2 ISOtech -->
146		<!-- Unicode does not say this is the 'implies' character but does not have
147		another character with this function so rArr can be used for 'implies'
148		as ISOtech suggests -->
149		<!ENTITY dArr "⇓"> <!-- downwards double arrow, U+21D3 ISOamsa -->
150		<!ENTITY hArr "⇔"> <!-- left right double arrow,
151		U+21D4 ISOamsa -->
152
153		<!-- Mathematical Operators -->
154		<!ENTITY forall "∀"> <!-- for all, U+2200 ISOtech -->
155		<!ENTITY part "∂"> <!-- partial differential, U+2202 ISOtech -->
156		<!ENTITY exist "∃"> <!-- there exists, U+2203 ISOtech -->
157		<!ENTITY empty "∅"> <!-- empty set = null set, U+2205 ISOamso -->
158		<!ENTITY nabla "∇"> <!-- nabla = backward difference,
159		U+2207 ISOtech -->
160		<!ENTITY isin "∈"> <!-- element of, U+2208 ISOtech -->
161		<!ENTITY notin "∉"> <!-- not an element of, U+2209 ISOtech -->
162		<!ENTITY ni "∋"> <!-- contains as member, U+220B ISOtech -->
163		<!ENTITY prod "∏"> <!-- n-ary product = product sign,
164		U+220F ISOamsb -->
165		<!-- prod is NOT the same character as U+03A0 'greek capital letter pi' though
166		the same glyph might be used for both -->
167		<!ENTITY sum "∑"> <!-- n-ary summation, U+2211 ISOamsb -->
168		<!-- sum is NOT the same character as U+03A3 'greek capital letter sigma'
169		though the same glyph might be used for both -->
170		<!ENTITY minus "−"> <!-- minus sign, U+2212 ISOtech -->
171		<!ENTITY lowast "∗"> <!-- asterisk operator, U+2217 ISOtech -->
172		<!ENTITY radic "√"> <!-- square root = radical sign,
173		U+221A ISOtech -->
174		<!ENTITY prop "∝"> <!-- proportional to, U+221D ISOtech -->
175		<!ENTITY infin "∞"> <!-- infinity, U+221E ISOtech -->
176		<!ENTITY ang "∠"> <!-- angle, U+2220 ISOamso -->
177		<!ENTITY and "∧"> <!-- logical and = wedge, U+2227 ISOtech -->
178		<!ENTITY or "∨"> <!-- logical or = vee, U+2228 ISOtech -->
179		<!ENTITY cap "∩"> <!-- intersection = cap, U+2229 ISOtech -->
180		<!ENTITY cup "∪"> <!-- union = cup, U+222A ISOtech -->
181		<!ENTITY int "∫"> <!-- integral, U+222B ISOtech -->
182		<!ENTITY there4 "∴"> <!-- therefore, U+2234 ISOtech -->
183		<!ENTITY sim "∼"> <!-- tilde operator = varies with = similar to,
184		U+223C ISOtech -->
185		<!-- tilde operator is NOT the same character as the tilde, U+007E,
186		although the same glyph might be used to represent both -->
187		<!ENTITY cong "≅"> <!-- approximately equal to, U+2245 ISOtech -->
188		<!ENTITY asymp "≈"> <!-- almost equal to = asymptotic to,
189		U+2248 ISOamsr -->
190		<!ENTITY ne "≠"> <!-- not equal to, U+2260 ISOtech -->
191		<!ENTITY equiv "≡"> <!-- identical to, U+2261 ISOtech -->
192		<!ENTITY le "≤"> <!-- less-than or equal to, U+2264 ISOtech -->
193		<!ENTITY ge "≥"> <!-- greater-than or equal to,
194		U+2265 ISOtech -->
195		<!ENTITY sub "⊂"> <!-- subset of, U+2282 ISOtech -->
196		<!ENTITY sup "⊃"> <!-- superset of, U+2283 ISOtech -->
197		<!ENTITY nsub "⊄"> <!-- not a subset of, U+2284 ISOamsn -->
198		<!ENTITY sube "⊆"> <!-- subset of or equal to, U+2286 ISOtech -->
199		<!ENTITY supe "⊇"> <!-- superset of or equal to,
200		U+2287 ISOtech -->
201		<!ENTITY oplus "⊕"> <!-- circled plus = direct sum,
202		U+2295 ISOamsb -->
203		<!ENTITY otimes "⊗"> <!-- circled times = vector product,
204		U+2297 ISOamsb -->
205		<!ENTITY perp "⊥"> <!-- up tack = orthogonal to = perpendicular,
206		U+22A5 ISOtech -->
207		<!ENTITY sdot "⋅"> <!-- dot operator, U+22C5 ISOamsb -->
208		<!-- dot operator is NOT the same character as U+00B7 middle dot -->
209
210		<!-- Miscellaneous Technical -->
211		<!ENTITY lceil "⌈"> <!-- left ceiling = APL upstile,
212		U+2308 ISOamsc -->
213		<!ENTITY rceil "⌉"> <!-- right ceiling, U+2309 ISOamsc -->
214		<!ENTITY lfloor "⌊"> <!-- left floor = APL downstile,
215		U+230A ISOamsc -->
216		<!ENTITY rfloor "⌋"> <!-- right floor, U+230B ISOamsc -->
217		<!ENTITY lang "〈"> <!-- left-pointing angle bracket = bra,
218		U+2329 ISOtech -->
219		<!-- lang is NOT the same character as U+003C 'less than sign'
220		or U+2039 'single left-pointing angle quotation mark' -->
221		<!ENTITY rang "〉"> <!-- right-pointing angle bracket = ket,
222		U+232A ISOtech -->
223		<!-- rang is NOT the same character as U+003E 'greater than sign'
224		or U+203A 'single right-pointing angle quotation mark' -->
225
226		<!-- Geometric Shapes -->
227		<!ENTITY loz "◊"> <!-- lozenge, U+25CA ISOpub -->
228
229		<!-- Miscellaneous Symbols -->
230		<!ENTITY spades "♠"> <!-- black spade suit, U+2660 ISOpub -->
231		<!-- black here seems to mean filled as opposed to hollow -->
232		<!ENTITY clubs "♣"> <!-- black club suit = shamrock,
233		U+2663 ISOpub -->
234		<!ENTITY hearts "♥"> <!-- black heart suit = valentine,
235		U+2665 ISOpub -->
236		<!ENTITY diams "♦"> <!-- black diamond suit, U+2666 ISOpub -->

-1201

~~src/doc/WWW/xhtml1-transitional.dtd~~ less more

0		<!--
1		Extensible HTML version 1.0 Transitional DTD
2
3		This is the same as HTML 4 Transitional except for
4		changes due to the differences between XML and SGML.
5
6		Namespace = http://www.w3.org/1999/xhtml
7
8		For further information, see: http://www.w3.org/TR/xhtml1
9
10		Copyright (c) 1998-2002 W3C (MIT, INRIA, Keio),
11		All Rights Reserved.
12
13		This DTD module is identified by the PUBLIC and SYSTEM identifiers:
14
15		PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
16		SYSTEM "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd"
17
18		$Revision: 1.2 $
19		$Date: 2002/08/01 18:37:55 $
20
21		-->
22
23		<!--================ Character mnemonic entities =========================-->
24
25		<!ENTITY % HTMLlat1 PUBLIC
26		"-//W3C//ENTITIES Latin 1 for XHTML//EN"
27		"xhtml-lat1.ent">
28		%HTMLlat1;
29
30		<!ENTITY % HTMLsymbol PUBLIC
31		"-//W3C//ENTITIES Symbols for XHTML//EN"
32		"xhtml-symbol.ent">
33		%HTMLsymbol;
34
35		<!ENTITY % HTMLspecial PUBLIC
36		"-//W3C//ENTITIES Special for XHTML//EN"
37		"xhtml-special.ent">
38		%HTMLspecial;
39
40		<!--================== Imported Names ====================================-->
41
42		<!ENTITY % ContentType "CDATA">
43		<!-- media type, as per [RFC2045] -->
44
45		<!ENTITY % ContentTypes "CDATA">
46		<!-- comma-separated list of media types, as per [RFC2045] -->
47
48		<!ENTITY % Charset "CDATA">
49		<!-- a character encoding, as per [RFC2045] -->
50
51		<!ENTITY % Charsets "CDATA">
52		<!-- a space separated list of character encodings, as per [RFC2045] -->
53
54		<!ENTITY % LanguageCode "NMTOKEN">
55		<!-- a language code, as per [RFC3066] -->
56
57		<!ENTITY % Character "CDATA">
58		<!-- a single character, as per section 2.2 of [XML] -->
59
60		<!ENTITY % Number "CDATA">
61		<!-- one or more digits -->
62
63		<!ENTITY % LinkTypes "CDATA">
64		<!-- space-separated list of link types -->
65
66		<!ENTITY % MediaDesc "CDATA">
67		<!-- single or comma-separated list of media descriptors -->
68
69		<!ENTITY % URI "CDATA">
70		<!-- a Uniform Resource Identifier, see [RFC2396] -->
71
72		<!ENTITY % UriList "CDATA">
73		<!-- a space separated list of Uniform Resource Identifiers -->
74
75		<!ENTITY % Datetime "CDATA">
76		<!-- date and time information. ISO date format -->
77
78		<!ENTITY % Script "CDATA">
79		<!-- script expression -->
80
81		<!ENTITY % StyleSheet "CDATA">
82		<!-- style sheet data -->
83
84		<!ENTITY % Text "CDATA">
85		<!-- used for titles etc. -->
86
87		<!ENTITY % FrameTarget "NMTOKEN">
88		<!-- render in this frame -->
89
90		<!ENTITY % Length "CDATA">
91		<!-- nn for pixels or nn% for percentage length -->
92
93		<!ENTITY % MultiLength "CDATA">
94		<!-- pixel, percentage, or relative -->
95
96		<!ENTITY % Pixels "CDATA">
97		<!-- integer representing length in pixels -->
98
99		<!-- these are used for image maps -->
100
101		<!ENTITY % Shape "(rect\|circle\|poly\|default)">
102
103		<!ENTITY % Coords "CDATA">
104		<!-- comma separated list of lengths -->
105
106		<!-- used for object, applet, img, input and iframe -->
107		<!ENTITY % ImgAlign "(top\|middle\|bottom\|left\|right)">
108
109		<!-- a color using sRGB: #RRGGBB as Hex values -->
110		<!ENTITY % Color "CDATA">
111
112		<!-- There are also 16 widely known color names with their sRGB values:
113
114		Black = #000000 Green = #008000
115		Silver = #C0C0C0 Lime = #00FF00
116		Gray = #808080 Olive = #808000
117		White = #FFFFFF Yellow = #FFFF00
118		Maroon = #800000 Navy = #000080
119		Red = #FF0000 Blue = #0000FF
120		Purple = #800080 Teal = #008080
121		Fuchsia= #FF00FF Aqua = #00FFFF
122		-->
123
124		<!--=================== Generic Attributes ===============================-->
125
126		<!-- core attributes common to most elements
127		id document-wide unique id
128		class space separated list of classes
129		style associated style info
130		title advisory title/amplification
131		-->
132		<!ENTITY % coreattrs
133		"id ID #IMPLIED
134		class CDATA #IMPLIED
135		style %StyleSheet; #IMPLIED
136		title %Text; #IMPLIED"
137		>
138
139		<!-- internationalization attributes
140		lang language code (backwards compatible)
141		xml:lang language code (as per XML 1.0 spec)
142		dir direction for weak/neutral text
143		-->
144		<!ENTITY % i18n
145		"lang %LanguageCode; #IMPLIED
146		xml:lang %LanguageCode; #IMPLIED
147		dir (ltr\|rtl) #IMPLIED"
148		>
149
150		<!-- attributes for common UI events
151		onclick a pointer button was clicked
152		ondblclick a pointer button was double clicked
153		onmousedown a pointer button was pressed down
154		onmouseup a pointer button was released
155		onmousemove a pointer was moved onto the element
156		onmouseout a pointer was moved away from the element
157		onkeypress a key was pressed and released
158		onkeydown a key was pressed down
159		onkeyup a key was released
160		-->
161		<!ENTITY % events
162		"onclick %Script; #IMPLIED
163		ondblclick %Script; #IMPLIED
164		onmousedown %Script; #IMPLIED
165		onmouseup %Script; #IMPLIED
166		onmouseover %Script; #IMPLIED
167		onmousemove %Script; #IMPLIED
168		onmouseout %Script; #IMPLIED
169		onkeypress %Script; #IMPLIED
170		onkeydown %Script; #IMPLIED
171		onkeyup %Script; #IMPLIED"
172		>
173
174		<!-- attributes for elements that can get the focus
175		accesskey accessibility key character
176		tabindex position in tabbing order
177		onfocus the element got the focus
178		onblur the element lost the focus
179		-->
180		<!ENTITY % focus
181		"accesskey %Character; #IMPLIED
182		tabindex %Number; #IMPLIED
183		onfocus %Script; #IMPLIED
184		onblur %Script; #IMPLIED"
185		>
186
187		<!ENTITY % attrs "%coreattrs; %i18n; %events;">
188
189		<!-- text alignment for p, div, h1-h6. The default is
190		align="left" for ltr headings, "right" for rtl -->
191
192		<!ENTITY % TextAlign "align (left\|center\|right\|justify) #IMPLIED">
193
194		<!--=================== Text Elements ====================================-->
195
196		<!ENTITY % special.extra
197		"object \| applet \| img \| map \| iframe">
198
199		<!ENTITY % special.basic
200		"br \| span \| bdo">
201
202		<!ENTITY % special
203		"%special.basic; \| %special.extra;">
204
205		<!ENTITY % fontstyle.extra "big \| small \| font \| basefont">
206
207		<!ENTITY % fontstyle.basic "tt \| i \| b \| u
208		\| s \| strike ">
209
210		<!ENTITY % fontstyle "%fontstyle.basic; \| %fontstyle.extra;">
211
212		<!ENTITY % phrase.extra "sub \| sup">
213		<!ENTITY % phrase.basic "em \| strong \| dfn \| code \| q \|
214		samp \| kbd \| var \| cite \| abbr \| acronym">
215
216		<!ENTITY % phrase "%phrase.basic; \| %phrase.extra;">
217
218		<!ENTITY % inline.forms "input \| select \| textarea \| label \| button">
219
220		<!-- these can occur at block or inline level -->
221		<!ENTITY % misc.inline "ins \| del \| script">
222
223		<!-- these can only occur at block level -->
224		<!ENTITY % misc "noscript \| %misc.inline;">
225
226		<!ENTITY % inline "a \| %special; \| %fontstyle; \| %phrase; \| %inline.forms;">
227
228		<!-- %Inline; covers inline or "text-level" elements -->
229		<!ENTITY % Inline "(#PCDATA \| %inline; \| %misc.inline;)*">
230
231		<!--================== Block level elements ==============================-->
232
233		<!ENTITY % heading "h1\|h2\|h3\|h4\|h5\|h6">
234		<!ENTITY % lists "ul \| ol \| dl \| menu \| dir">
235		<!ENTITY % blocktext "pre \| hr \| blockquote \| address \| center \| noframes">
236
237		<!ENTITY % block
238		"p \| %heading; \| div \| %lists; \| %blocktext; \| isindex \|fieldset \| table">
239
240		<!-- %Flow; mixes block and inline and is used for list items etc. -->
241		<!ENTITY % Flow "(#PCDATA \| %block; \| form \| %inline; \| %misc;)*">
242
243		<!--================== Content models for exclusions =====================-->
244
245		<!-- a elements use %Inline; excluding a -->
246
247		<!ENTITY % a.content
248		"(#PCDATA \| %special; \| %fontstyle; \| %phrase; \| %inline.forms; \| %misc.inline;)*">
249
250		<!-- pre uses %Inline excluding img, object, applet, big, small,
251		font, or basefont -->
252
253		<!ENTITY % pre.content
254		"(#PCDATA \| a \| %special.basic; \| %fontstyle.basic; \| %phrase.basic; \|
255		%inline.forms; \| %misc.inline;)*">
256
257		<!-- form uses %Flow; excluding form -->
258
259		<!ENTITY % form.content "(#PCDATA \| %block; \| %inline; \| %misc;)*">
260
261		<!-- button uses %Flow; but excludes a, form, form controls, iframe -->
262
263		<!ENTITY % button.content
264		"(#PCDATA \| p \| %heading; \| div \| %lists; \| %blocktext; \|
265		table \| br \| span \| bdo \| object \| applet \| img \| map \|
266		%fontstyle; \| %phrase; \| %misc;)*">
267
268		<!--================ Document Structure ==================================-->
269
270		<!-- the namespace URI designates the document profile -->
271
272		<!ELEMENT html (head, body)>
273		<!ATTLIST html
274		%i18n;
275		id ID #IMPLIED
276		xmlns %URI; #FIXED 'http://www.w3.org/1999/xhtml'
277		>
278
279		<!--================ Document Head =======================================-->
280
281		<!ENTITY % head.misc "(script\|style\|meta\|link\|object\|isindex)*">
282
283		<!-- content model is %head.misc; combined with a single
284		title and an optional base element in any order -->
285
286		<!ELEMENT head (%head.misc;,
287		((title, %head.misc;, (base, %head.misc;)?) \|
288		(base, %head.misc;, (title, %head.misc;))))>
289
290		<!ATTLIST head
291		%i18n;
292		id ID #IMPLIED
293		profile %URI; #IMPLIED
294		>
295
296		<!-- The title element is not considered part of the flow of text.
297		It should be displayed, for example as the page header or
298		window title. Exactly one title is required per document.
299		-->
300		<!ELEMENT title (#PCDATA)>
301		<!ATTLIST title
302		%i18n;
303		id ID #IMPLIED
304		>
305
306		<!-- document base URI -->
307
308		<!ELEMENT base EMPTY>
309		<!ATTLIST base
310		id ID #IMPLIED
311		href %URI; #IMPLIED
312		target %FrameTarget; #IMPLIED
313		>
314
315		<!-- generic metainformation -->
316		<!ELEMENT meta EMPTY>
317		<!ATTLIST meta
318		%i18n;
319		id ID #IMPLIED
320		http-equiv CDATA #IMPLIED
321		name CDATA #IMPLIED
322		content CDATA #REQUIRED
323		scheme CDATA #IMPLIED
324		>
325
326		<!--
327		Relationship values can be used in principle:
328
329		a) for document specific toolbars/menus when used
330		with the link element in document head e.g.
331		start, contents, previous, next, index, end, help
332		b) to link to a separate style sheet (rel="stylesheet")
333		c) to make a link to a script (rel="script")
334		d) by stylesheets to control how collections of
335		html nodes are rendered into printed documents
336		e) to make a link to a printable version of this document
337		e.g. a PostScript or PDF version (rel="alternate" media="print")
338		-->
339
340		<!ELEMENT link EMPTY>
341		<!ATTLIST link
342		%attrs;
343		charset %Charset; #IMPLIED
344		href %URI; #IMPLIED
345		hreflang %LanguageCode; #IMPLIED
346		type %ContentType; #IMPLIED
347		rel %LinkTypes; #IMPLIED
348		rev %LinkTypes; #IMPLIED
349		media %MediaDesc; #IMPLIED
350		target %FrameTarget; #IMPLIED
351		>
352
353		<!-- style info, which may include CDATA sections -->
354		<!ELEMENT style (#PCDATA)>
355		<!ATTLIST style
356		%i18n;
357		id ID #IMPLIED
358		type %ContentType; #REQUIRED
359		media %MediaDesc; #IMPLIED
360		title %Text; #IMPLIED
361		xml:space (preserve) #FIXED 'preserve'
362		>
363
364		<!-- script statements, which may include CDATA sections -->
365		<!ELEMENT script (#PCDATA)>
366		<!ATTLIST script
367		id ID #IMPLIED
368		charset %Charset; #IMPLIED
369		type %ContentType; #REQUIRED
370		language CDATA #IMPLIED
371		src %URI; #IMPLIED
372		defer (defer) #IMPLIED
373		xml:space (preserve) #FIXED 'preserve'
374		>
375
376		<!-- alternate content container for non script-based rendering -->
377
378		<!ELEMENT noscript %Flow;>
379		<!ATTLIST noscript
380		%attrs;
381		>
382
383		<!--======================= Frames =======================================-->
384
385		<!-- inline subwindow -->
386
387		<!ELEMENT iframe %Flow;>
388		<!ATTLIST iframe
389		%coreattrs;
390		longdesc %URI; #IMPLIED
391		name NMTOKEN #IMPLIED
392		src %URI; #IMPLIED
393		frameborder (1\|0) "1"
394		marginwidth %Pixels; #IMPLIED
395		marginheight %Pixels; #IMPLIED
396		scrolling (yes\|no\|auto) "auto"
397		align %ImgAlign; #IMPLIED
398		height %Length; #IMPLIED
399		width %Length; #IMPLIED
400		>
401
402		<!-- alternate content container for non frame-based rendering -->
403
404		<!ELEMENT noframes %Flow;>
405		<!ATTLIST noframes
406		%attrs;
407		>
408
409		<!--=================== Document Body ====================================-->
410
411		<!ELEMENT body %Flow;>
412		<!ATTLIST body
413		%attrs;
414		onload %Script; #IMPLIED
415		onunload %Script; #IMPLIED
416		background %URI; #IMPLIED
417		bgcolor %Color; #IMPLIED
418		text %Color; #IMPLIED
419		link %Color; #IMPLIED
420		vlink %Color; #IMPLIED
421		alink %Color; #IMPLIED
422		>
423
424		<!ELEMENT div %Flow;> <!-- generic language/style container -->
425		<!ATTLIST div
426		%attrs;
427		%TextAlign;
428		>
429
430		<!--=================== Paragraphs =======================================-->
431
432		<!ELEMENT p %Inline;>
433		<!ATTLIST p
434		%attrs;
435		%TextAlign;
436		>
437
438		<!--=================== Headings =========================================-->
439
440		<!--
441		There are six levels of headings from h1 (the most important)
442		to h6 (the least important).
443		-->
444
445		<!ELEMENT h1 %Inline;>
446		<!ATTLIST h1
447		%attrs;
448		%TextAlign;
449		>
450
451		<!ELEMENT h2 %Inline;>
452		<!ATTLIST h2
453		%attrs;
454		%TextAlign;
455		>
456
457		<!ELEMENT h3 %Inline;>
458		<!ATTLIST h3
459		%attrs;
460		%TextAlign;
461		>
462
463		<!ELEMENT h4 %Inline;>
464		<!ATTLIST h4
465		%attrs;
466		%TextAlign;
467		>
468
469		<!ELEMENT h5 %Inline;>
470		<!ATTLIST h5
471		%attrs;
472		%TextAlign;
473		>
474
475		<!ELEMENT h6 %Inline;>
476		<!ATTLIST h6
477		%attrs;
478		%TextAlign;
479		>
480
481		<!--=================== Lists ============================================-->
482
483		<!-- Unordered list bullet styles -->
484
485		<!ENTITY % ULStyle "(disc\|square\|circle)">
486
487		<!-- Unordered list -->
488
489		<!ELEMENT ul (li)+>
490		<!ATTLIST ul
491		%attrs;
492		type %ULStyle; #IMPLIED
493		compact (compact) #IMPLIED
494		>
495
496		<!-- Ordered list numbering style
497
498		1 arabic numbers 1, 2, 3, ...
499		a lower alpha a, b, c, ...
500		A upper alpha A, B, C, ...
501		i lower roman i, ii, iii, ...
502		I upper roman I, II, III, ...
503
504		The style is applied to the sequence number which by default
505		is reset to 1 for the first list item in an ordered list.
506		-->
507		<!ENTITY % OLStyle "CDATA">
508
509		<!-- Ordered (numbered) list -->
510
511		<!ELEMENT ol (li)+>
512		<!ATTLIST ol
513		%attrs;
514		type %OLStyle; #IMPLIED
515		compact (compact) #IMPLIED
516		start %Number; #IMPLIED
517		>
518
519		<!-- single column list (DEPRECATED) -->
520		<!ELEMENT menu (li)+>
521		<!ATTLIST menu
522		%attrs;
523		compact (compact) #IMPLIED
524		>
525
526		<!-- multiple column list (DEPRECATED) -->
527		<!ELEMENT dir (li)+>
528		<!ATTLIST dir
529		%attrs;
530		compact (compact) #IMPLIED
531		>
532
533		<!-- LIStyle is constrained to: "(%ULStyle;\|%OLStyle;)" -->
534		<!ENTITY % LIStyle "CDATA">
535
536		<!-- list item -->
537
538		<!ELEMENT li %Flow;>
539		<!ATTLIST li
540		%attrs;
541		type %LIStyle; #IMPLIED
542		value %Number; #IMPLIED
543		>
544
545		<!-- definition lists - dt for term, dd for its definition -->
546
547		<!ELEMENT dl (dt\|dd)+>
548		<!ATTLIST dl
549		%attrs;
550		compact (compact) #IMPLIED
551		>
552
553		<!ELEMENT dt %Inline;>
554		<!ATTLIST dt
555		%attrs;
556		>
557
558		<!ELEMENT dd %Flow;>
559		<!ATTLIST dd
560		%attrs;
561		>
562
563		<!--=================== Address ==========================================-->
564
565		<!-- information on author -->
566
567		<!ELEMENT address (#PCDATA \| %inline; \| %misc.inline; \| p)*>
568		<!ATTLIST address
569		%attrs;
570		>
571
572		<!--=================== Horizontal Rule ==================================-->
573
574		<!ELEMENT hr EMPTY>
575		<!ATTLIST hr
576		%attrs;
577		align (left\|center\|right) #IMPLIED
578		noshade (noshade) #IMPLIED
579		size %Pixels; #IMPLIED
580		width %Length; #IMPLIED
581		>
582
583		<!--=================== Preformatted Text ================================-->
584
585		<!-- content is %Inline; excluding
586		"img\|object\|applet\|big\|small\|sub\|sup\|font\|basefont" -->
587
588		<!ELEMENT pre %pre.content;>
589		<!ATTLIST pre
590		%attrs;
591		width %Number; #IMPLIED
592		xml:space (preserve) #FIXED 'preserve'
593		>
594
595		<!--=================== Block-like Quotes ================================-->
596
597		<!ELEMENT blockquote %Flow;>
598		<!ATTLIST blockquote
599		%attrs;
600		cite %URI; #IMPLIED
601		>
602
603		<!--=================== Text alignment ===================================-->
604
605		<!-- center content -->
606		<!ELEMENT center %Flow;>
607		<!ATTLIST center
608		%attrs;
609		>
610
611		<!--=================== Inserted/Deleted Text ============================-->
612
613		<!--
614		ins/del are allowed in block and inline content, but its
615		inappropriate to include block content within an ins element
616		occurring in inline content.
617		-->
618		<!ELEMENT ins %Flow;>
619		<!ATTLIST ins
620		%attrs;
621		cite %URI; #IMPLIED
622		datetime %Datetime; #IMPLIED
623		>
624
625		<!ELEMENT del %Flow;>
626		<!ATTLIST del
627		%attrs;
628		cite %URI; #IMPLIED
629		datetime %Datetime; #IMPLIED
630		>
631
632		<!--================== The Anchor Element ================================-->
633
634		<!-- content is %Inline; except that anchors shouldn't be nested -->
635
636		<!ELEMENT a %a.content;>
637		<!ATTLIST a
638		%attrs;
639		%focus;
640		charset %Charset; #IMPLIED
641		type %ContentType; #IMPLIED
642		name NMTOKEN #IMPLIED
643		href %URI; #IMPLIED
644		hreflang %LanguageCode; #IMPLIED
645		rel %LinkTypes; #IMPLIED
646		rev %LinkTypes; #IMPLIED
647		shape %Shape; "rect"
648		coords %Coords; #IMPLIED
649		target %FrameTarget; #IMPLIED
650		>
651
652		<!--===================== Inline Elements ================================-->
653
654		<!ELEMENT span %Inline;> <!-- generic language/style container -->
655		<!ATTLIST span
656		%attrs;
657		>
658
659		<!ELEMENT bdo %Inline;> <!-- I18N BiDi over-ride -->
660		<!ATTLIST bdo
661		%coreattrs;
662		%events;
663		lang %LanguageCode; #IMPLIED
664		xml:lang %LanguageCode; #IMPLIED
665		dir (ltr\|rtl) #REQUIRED
666		>
667
668		<!ELEMENT br EMPTY> <!-- forced line break -->
669		<!ATTLIST br
670		%coreattrs;
671		clear (left\|all\|right\|none) "none"
672		>
673
674		<!ELEMENT em %Inline;> <!-- emphasis -->
675		<!ATTLIST em %attrs;>
676
677		<!ELEMENT strong %Inline;> <!-- strong emphasis -->
678		<!ATTLIST strong %attrs;>
679
680		<!ELEMENT dfn %Inline;> <!-- definitional -->
681		<!ATTLIST dfn %attrs;>
682
683		<!ELEMENT code %Inline;> <!-- program code -->
684		<!ATTLIST code %attrs;>
685
686		<!ELEMENT samp %Inline;> <!-- sample -->
687		<!ATTLIST samp %attrs;>
688
689		<!ELEMENT kbd %Inline;> <!-- something user would type -->
690		<!ATTLIST kbd %attrs;>
691
692		<!ELEMENT var %Inline;> <!-- variable -->
693		<!ATTLIST var %attrs;>
694
695		<!ELEMENT cite %Inline;> <!-- citation -->
696		<!ATTLIST cite %attrs;>
697
698		<!ELEMENT abbr %Inline;> <!-- abbreviation -->
699		<!ATTLIST abbr %attrs;>
700
701		<!ELEMENT acronym %Inline;> <!-- acronym -->
702		<!ATTLIST acronym %attrs;>
703
704		<!ELEMENT q %Inline;> <!-- inlined quote -->
705		<!ATTLIST q
706		%attrs;
707		cite %URI; #IMPLIED
708		>
709
710		<!ELEMENT sub %Inline;> <!-- subscript -->
711		<!ATTLIST sub %attrs;>
712
713		<!ELEMENT sup %Inline;> <!-- superscript -->
714		<!ATTLIST sup %attrs;>
715
716		<!ELEMENT tt %Inline;> <!-- fixed pitch font -->
717		<!ATTLIST tt %attrs;>
718
719		<!ELEMENT i %Inline;> <!-- italic font -->
720		<!ATTLIST i %attrs;>
721
722		<!ELEMENT b %Inline;> <!-- bold font -->
723		<!ATTLIST b %attrs;>
724
725		<!ELEMENT big %Inline;> <!-- bigger font -->
726		<!ATTLIST big %attrs;>
727
728		<!ELEMENT small %Inline;> <!-- smaller font -->
729		<!ATTLIST small %attrs;>
730
731		<!ELEMENT u %Inline;> <!-- underline -->
732		<!ATTLIST u %attrs;>
733
734		<!ELEMENT s %Inline;> <!-- strike-through -->
735		<!ATTLIST s %attrs;>
736
737		<!ELEMENT strike %Inline;> <!-- strike-through -->
738		<!ATTLIST strike %attrs;>
739
740		<!ELEMENT basefont EMPTY> <!-- base font size -->
741		<!ATTLIST basefont
742		id ID #IMPLIED
743		size CDATA #REQUIRED
744		color %Color; #IMPLIED
745		face CDATA #IMPLIED
746		>
747
748		<!ELEMENT font %Inline;> <!-- local change to font -->
749		<!ATTLIST font
750		%coreattrs;
751		%i18n;
752		size CDATA #IMPLIED
753		color %Color; #IMPLIED
754		face CDATA #IMPLIED
755		>
756
757		<!--==================== Object ======================================-->
758		<!--
759		object is used to embed objects as part of HTML pages.
760		param elements should precede other content. Parameters
761		can also be expressed as attribute/value pairs on the
762		object element itself when brevity is desired.
763		-->
764
765		<!ELEMENT object (#PCDATA \| param \| %block; \| form \| %inline; \| %misc;)*>
766		<!ATTLIST object
767		%attrs;
768		declare (declare) #IMPLIED
769		classid %URI; #IMPLIED
770		codebase %URI; #IMPLIED
771		data %URI; #IMPLIED
772		type %ContentType; #IMPLIED
773		codetype %ContentType; #IMPLIED
774		archive %UriList; #IMPLIED
775		standby %Text; #IMPLIED
776		height %Length; #IMPLIED
777		width %Length; #IMPLIED
778		usemap %URI; #IMPLIED
779		name NMTOKEN #IMPLIED
780		tabindex %Number; #IMPLIED
781		align %ImgAlign; #IMPLIED
782		border %Pixels; #IMPLIED
783		hspace %Pixels; #IMPLIED
784		vspace %Pixels; #IMPLIED
785		>
786
787		<!--
788		param is used to supply a named property value.
789		In XML it would seem natural to follow RDF and support an
790		abbreviated syntax where the param elements are replaced
791		by attribute value pairs on the object start tag.
792		-->
793		<!ELEMENT param EMPTY>
794		<!ATTLIST param
795		id ID #IMPLIED
796		name CDATA #REQUIRED
797		value CDATA #IMPLIED
798		valuetype (data\|ref\|object) "data"
799		type %ContentType; #IMPLIED
800		>
801
802		<!--=================== Java applet ==================================-->
803		<!--
804		One of code or object attributes must be present.
805		Place param elements before other content.
806		-->
807		<!ELEMENT applet (#PCDATA \| param \| %block; \| form \| %inline; \| %misc;)*>
808		<!ATTLIST applet
809		%coreattrs;
810		codebase %URI; #IMPLIED
811		archive CDATA #IMPLIED
812		code CDATA #IMPLIED
813		object CDATA #IMPLIED
814		alt %Text; #IMPLIED
815		name NMTOKEN #IMPLIED
816		width %Length; #REQUIRED
817		height %Length; #REQUIRED
818		align %ImgAlign; #IMPLIED
819		hspace %Pixels; #IMPLIED
820		vspace %Pixels; #IMPLIED
821		>
822
823		<!--=================== Images ===========================================-->
824
825		<!--
826		To avoid accessibility problems for people who aren't
827		able to see the image, you should provide a text
828		description using the alt and longdesc attributes.
829		In addition, avoid the use of server-side image maps.
830		-->
831
832		<!ELEMENT img EMPTY>
833		<!ATTLIST img
834		%attrs;
835		src %URI; #REQUIRED
836		alt %Text; #REQUIRED
837		name NMTOKEN #IMPLIED
838		longdesc %URI; #IMPLIED
839		height %Length; #IMPLIED
840		width %Length; #IMPLIED
841		usemap %URI; #IMPLIED
842		ismap (ismap) #IMPLIED
843		align %ImgAlign; #IMPLIED
844		border %Length; #IMPLIED
845		hspace %Pixels; #IMPLIED
846		vspace %Pixels; #IMPLIED
847		>
848
849		<!-- usemap points to a map element which may be in this document
850		or an external document, although the latter is not widely supported -->
851
852		<!--================== Client-side image maps ============================-->
853
854		<!-- These can be placed in the same document or grouped in a
855		separate document although this isn't yet widely supported -->
856
857		<!ELEMENT map ((%block; \| form \| %misc;)+ \| area+)>
858		<!ATTLIST map
859		%i18n;
860		%events;
861		id ID #REQUIRED
862		class CDATA #IMPLIED
863		style %StyleSheet; #IMPLIED
864		title %Text; #IMPLIED
865		name CDATA #IMPLIED
866		>
867
868		<!ELEMENT area EMPTY>
869		<!ATTLIST area
870		%attrs;
871		%focus;
872		shape %Shape; "rect"
873		coords %Coords; #IMPLIED
874		href %URI; #IMPLIED
875		nohref (nohref) #IMPLIED
876		alt %Text; #REQUIRED
877		target %FrameTarget; #IMPLIED
878		>
879
880		<!--================ Forms ===============================================-->
881
882		<!ELEMENT form %form.content;> <!-- forms shouldn't be nested -->
883
884		<!ATTLIST form
885		%attrs;
886		action %URI; #REQUIRED
887		method (get\|post) "get"
888		name NMTOKEN #IMPLIED
889		enctype %ContentType; "application/x-www-form-urlencoded"
890		onsubmit %Script; #IMPLIED
891		onreset %Script; #IMPLIED
892		accept %ContentTypes; #IMPLIED
893		accept-charset %Charsets; #IMPLIED
894		target %FrameTarget; #IMPLIED
895		>
896
897		<!--
898		Each label must not contain more than ONE field
899		Label elements shouldn't be nested.
900		-->
901		<!ELEMENT label %Inline;>
902		<!ATTLIST label
903		%attrs;
904		for IDREF #IMPLIED
905		accesskey %Character; #IMPLIED
906		onfocus %Script; #IMPLIED
907		onblur %Script; #IMPLIED
908		>
909
910		<!ENTITY % InputType
911		"(text \| password \| checkbox \|
912		radio \| submit \| reset \|
913		file \| hidden \| image \| button)"
914		>
915
916		<!-- the name attribute is required for all but submit & reset -->
917
918		<!ELEMENT input EMPTY> <!-- form control -->
919		<!ATTLIST input
920		%attrs;
921		%focus;
922		type %InputType; "text"
923		name CDATA #IMPLIED
924		value CDATA #IMPLIED
925		checked (checked) #IMPLIED
926		disabled (disabled) #IMPLIED
927		readonly (readonly) #IMPLIED
928		size CDATA #IMPLIED
929		maxlength %Number; #IMPLIED
930		src %URI; #IMPLIED
931		alt CDATA #IMPLIED
932		usemap %URI; #IMPLIED
933		onselect %Script; #IMPLIED
934		onchange %Script; #IMPLIED
935		accept %ContentTypes; #IMPLIED
936		align %ImgAlign; #IMPLIED
937		>
938
939		<!ELEMENT select (optgroup\|option)+> <!-- option selector -->
940		<!ATTLIST select
941		%attrs;
942		name CDATA #IMPLIED
943		size %Number; #IMPLIED
944		multiple (multiple) #IMPLIED
945		disabled (disabled) #IMPLIED
946		tabindex %Number; #IMPLIED
947		onfocus %Script; #IMPLIED
948		onblur %Script; #IMPLIED
949		onchange %Script; #IMPLIED
950		>
951
952		<!ELEMENT optgroup (option)+> <!-- option group -->
953		<!ATTLIST optgroup
954		%attrs;
955		disabled (disabled) #IMPLIED
956		label %Text; #REQUIRED
957		>
958
959		<!ELEMENT option (#PCDATA)> <!-- selectable choice -->
960		<!ATTLIST option
961		%attrs;
962		selected (selected) #IMPLIED
963		disabled (disabled) #IMPLIED
964		label %Text; #IMPLIED
965		value CDATA #IMPLIED
966		>
967
968		<!ELEMENT textarea (#PCDATA)> <!-- multi-line text field -->
969		<!ATTLIST textarea
970		%attrs;
971		%focus;
972		name CDATA #IMPLIED
973		rows %Number; #REQUIRED
974		cols %Number; #REQUIRED
975		disabled (disabled) #IMPLIED
976		readonly (readonly) #IMPLIED
977		onselect %Script; #IMPLIED
978		onchange %Script; #IMPLIED
979		>
980
981		<!--
982		The fieldset element is used to group form fields.
983		Only one legend element should occur in the content
984		and if present should only be preceded by whitespace.
985		-->
986		<!ELEMENT fieldset (#PCDATA \| legend \| %block; \| form \| %inline; \| %misc;)*>
987		<!ATTLIST fieldset
988		%attrs;
989		>
990
991		<!ENTITY % LAlign "(top\|bottom\|left\|right)">
992
993		<!ELEMENT legend %Inline;> <!-- fieldset label -->
994		<!ATTLIST legend
995		%attrs;
996		accesskey %Character; #IMPLIED
997		align %LAlign; #IMPLIED
998		>
999
1000		<!--
1001		Content is %Flow; excluding a, form, form controls, iframe
1002		-->
1003		<!ELEMENT button %button.content;> <!-- push button -->
1004		<!ATTLIST button
1005		%attrs;
1006		%focus;
1007		name CDATA #IMPLIED
1008		value CDATA #IMPLIED
1009		type (button\|submit\|reset) "submit"
1010		disabled (disabled) #IMPLIED
1011		>
1012
1013		<!-- single-line text input control (DEPRECATED) -->
1014		<!ELEMENT isindex EMPTY>
1015		<!ATTLIST isindex
1016		%coreattrs;
1017		%i18n;
1018		prompt %Text; #IMPLIED
1019		>
1020
1021		<!--======================= Tables =======================================-->
1022
1023		<!-- Derived from IETF HTML table standard, see [RFC1942] -->
1024
1025		<!--
1026		The border attribute sets the thickness of the frame around the
1027		table. The default units are screen pixels.
1028
1029		The frame attribute specifies which parts of the frame around
1030		the table should be rendered. The values are not the same as
1031		CALS to avoid a name clash with the valign attribute.
1032		-->
1033		<!ENTITY % TFrame "(void\|above\|below\|hsides\|lhs\|rhs\|vsides\|box\|border)">
1034
1035		<!--
1036		The rules attribute defines which rules to draw between cells:
1037
1038		If rules is absent then assume:
1039		"none" if border is absent or border="0" otherwise "all"
1040		-->
1041
1042		<!ENTITY % TRules "(none \| groups \| rows \| cols \| all)">
1043
1044		<!-- horizontal placement of table relative to document -->
1045		<!ENTITY % TAlign "(left\|center\|right)">
1046
1047		<!-- horizontal alignment attributes for cell contents
1048
1049		char alignment char, e.g. char=':'
1050		charoff offset for alignment char
1051		-->
1052		<!ENTITY % cellhalign
1053		"align (left\|center\|right\|justify\|char) #IMPLIED
1054		char %Character; #IMPLIED
1055		charoff %Length; #IMPLIED"
1056		>
1057
1058		<!-- vertical alignment attributes for cell contents -->
1059		<!ENTITY % cellvalign
1060		"valign (top\|middle\|bottom\|baseline) #IMPLIED"
1061		>
1062
1063		<!ELEMENT table
1064		(caption?, (col\|colgroup), thead?, tfoot?, (tbody+\|tr+))>
1065		<!ELEMENT caption %Inline;>
1066		<!ELEMENT thead (tr)+>
1067		<!ELEMENT tfoot (tr)+>
1068		<!ELEMENT tbody (tr)+>
1069		<!ELEMENT colgroup (col)*>
1070		<!ELEMENT col EMPTY>
1071		<!ELEMENT tr (th\|td)+>
1072		<!ELEMENT th %Flow;>
1073		<!ELEMENT td %Flow;>
1074
1075		<!ATTLIST table
1076		%attrs;
1077		summary %Text; #IMPLIED
1078		width %Length; #IMPLIED
1079		border %Pixels; #IMPLIED
1080		frame %TFrame; #IMPLIED
1081		rules %TRules; #IMPLIED
1082		cellspacing %Length; #IMPLIED
1083		cellpadding %Length; #IMPLIED
1084		align %TAlign; #IMPLIED
1085		bgcolor %Color; #IMPLIED
1086		>
1087
1088		<!ENTITY % CAlign "(top\|bottom\|left\|right)">
1089
1090		<!ATTLIST caption
1091		%attrs;
1092		align %CAlign; #IMPLIED
1093		>
1094
1095		<!--
1096		colgroup groups a set of col elements. It allows you to group
1097		several semantically related columns together.
1098		-->
1099		<!ATTLIST colgroup
1100		%attrs;
1101		span %Number; "1"
1102		width %MultiLength; #IMPLIED
1103		%cellhalign;
1104		%cellvalign;
1105		>
1106
1107		<!--
1108		col elements define the alignment properties for cells in
1109		one or more columns.
1110
1111		The width attribute specifies the width of the columns, e.g.
1112
1113		width=64 width in screen pixels
1114		width=0.5* relative width of 0.5
1115
1116		The span attribute causes the attributes of one
1117		col element to apply to more than one column.
1118		-->
1119		<!ATTLIST col
1120		%attrs;
1121		span %Number; "1"
1122		width %MultiLength; #IMPLIED
1123		%cellhalign;
1124		%cellvalign;
1125		>
1126
1127		<!--
1128		Use thead to duplicate headers when breaking table
1129		across page boundaries, or for static headers when
1130		tbody sections are rendered in scrolling panel.
1131
1132		Use tfoot to duplicate footers when breaking table
1133		across page boundaries, or for static footers when
1134		tbody sections are rendered in scrolling panel.
1135
1136		Use multiple tbody sections when rules are needed
1137		between groups of table rows.
1138		-->
1139		<!ATTLIST thead
1140		%attrs;
1141		%cellhalign;
1142		%cellvalign;
1143		>
1144
1145		<!ATTLIST tfoot
1146		%attrs;
1147		%cellhalign;
1148		%cellvalign;
1149		>
1150
1151		<!ATTLIST tbody
1152		%attrs;
1153		%cellhalign;
1154		%cellvalign;
1155		>
1156
1157		<!ATTLIST tr
1158		%attrs;
1159		%cellhalign;
1160		%cellvalign;
1161		bgcolor %Color; #IMPLIED
1162		>
1163
1164		<!-- Scope is simpler than headers attribute for common tables -->
1165		<!ENTITY % Scope "(row\|col\|rowgroup\|colgroup)">
1166
1167		<!-- th is for headers, td for data and for cells acting as both -->
1168
1169		<!ATTLIST th
1170		%attrs;
1171		abbr %Text; #IMPLIED
1172		axis CDATA #IMPLIED
1173		headers IDREFS #IMPLIED
1174		scope %Scope; #IMPLIED
1175		rowspan %Number; "1"
1176		colspan %Number; "1"
1177		%cellhalign;
1178		%cellvalign;
1179		nowrap (nowrap) #IMPLIED
1180		bgcolor %Color; #IMPLIED
1181		width %Length; #IMPLIED
1182		height %Length; #IMPLIED
1183		>
1184
1185		<!ATTLIST td
1186		%attrs;
1187		abbr %Text; #IMPLIED
1188		axis CDATA #IMPLIED
1189		headers IDREFS #IMPLIED
1190		scope %Scope; #IMPLIED
1191		rowspan %Number; "1"
1192		colspan %Number; "1"
1193		%cellhalign;
1194		%cellvalign;
1195		nowrap (nowrap) #IMPLIED
1196		bgcolor %Color; #IMPLIED
1197		width %Length; #IMPLIED
1198		height %Length; #IMPLIED
1199		>
1200

-176

~~src/testdata/swissSmall~~ less more

0		ID 100K_RAT STANDARD; PRT; 889 AA.
1		AC Q62671;
2		DT 01-NOV-1997 (Rel. 35, Created)
3		DT 01-NOV-1997 (Rel. 35, Last sequence update)
4		DT 15-JUL-1999 (Rel. 38, Last annotation update)
5		DE 100 KD PROTEIN (EC 6.3.2.-).
6		OS Rattus norvegicus (Rat).
7		OC Eukaryota; Metazoa; Chordata; Craniata; Vertebrata; Mammalia;
8		OC Eutheria; Rodentia; Sciurognathi; Muridae; Murinae; Rattus.
9		RN [1]
10		RP SEQUENCE FROM N.A.
11		RC STRAIN=WISTAR; TISSUE=TESTIS;
12		RX MEDLINE; 92253337.
13		RA MUELLER D., REHBEIN M., BAUMEISTER H., RICHTER D.;
14		RT "Molecular characterization of a novel rat protein structurally
15		RT related to poly(A) binding proteins and the 70K protein of the U1
16		RT small nuclear ribonucleoprotein particle (snRNP).";
17		RL Nucleic Acids Res. 20:1471-1475(1992).
18		RN [2]
19		RP ERRATUM.
20		RA MUELLER D., REHBEIN M., BAUMEISTER H., RICHTER D.;
21		RL Nucleic Acids Res. 20:2624-2624(1992).
22		CC -!- FUNCTION: E3 UBIQUITIN-PROTEIN LIGASE WHICH ACCEPTS UBIQUITIN FROM
23		CC AN E2 UBIQUITIN-CONJUGATING ENZYME IN THE FORM OF A THIOESTER AND
24		CC THEN DIRECTLY TRANSFERS THE UBIQUITIN TO TARGETED SUBSTRATES (BY
25		CC SIMILARITY). THIS PROTEIN MAY BE INVOLVED IN MATURATION AND/OR
26		CC POST-TRANSCRIPTIONAL REGULATION OF MRNA.
27		CC -!- TISSUE SPECIFICITY: HIGHEST LEVELS FOUND IN TESTIS. ALSO PRESENT
28		CC IN LIVER, KIDNEY, LUNG AND BRAIN.
29		CC -!- DEVELOPMENTAL STAGE: IN EARLY POST-NATAL LIFE, EXPRESSION IN
30		CC THE TESTIS INCREASES TO REACH A MAXIMUM AROUND DAY 28.
31		CC -!- MISCELLANEOUS: A CYSTEINE RESIDUE IS REQUIRED FOR
32		CC UBIQUITIN-THIOLESTER FORMATION.
33		CC -!- SIMILARITY: CONTAINS AN HECT-TYPE E3 UBIQUITIN-PROTEIN LIGASE
34		CC DOMAIN.
35		CC -!- SIMILARITY: A CENTRAL REGION (AA 485-514) IS SIMILAR TO THE
36		CC C-TERMINAL DOMAINS OF MAMMALIAN AND YEAST POLY (A) RNA BINDING
37		CC PROTEINS (PABP).
38		CC -!- SIMILARITY: THE C-TERMINAL HALF SHOWS HIGH SIMILARITY TO
39		CC DROSOPHILA HYPERPLASMIC DISC PROTEIN AND SOME, TO HUMAN E6-AP.
40		CC -!- SIMILARITY: CONTAINS MIXED-CHARGE DOMAINS SIMILAR TO RNA-BINDING
41		CC PROTEINS.
42		CC --------------------------------------------------------------------------
43		CC This SWISS-PROT entry is copyright. It is produced through a collaboration
44		CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
45		CC the European Bioinformatics Institute. There are no restrictions on its
46		CC use by non-profit institutions as long as its content is in no way
47		CC modified and this statement is not removed. Usage by and for commercial
48		CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
49		CC or send an email to license@isb-sib.ch).
50		CC --------------------------------------------------------------------------
51		DR EMBL; X64411; CAA45756.1; -.
52		DR PFAM; PF00632; HECT; 1.
53		DR PFAM; PF00658; PABP; 1.
54		KW Ubiquitin conjugation; Ligase.
55		FT DOMAIN 77 88 ASP/GLU-RICH (ACIDIC).
56		FT DOMAIN 127 150 PRO-RICH.
57		FT DOMAIN 420 439 ARG/GLU-RICH (MIXED CHARGE).
58		FT DOMAIN 448 457 ARG/ASP-RICH (MIXED CHARGE).
59		FT DOMAIN 485 514 PABP-LIKE.
60		FT DOMAIN 579 590 ASP/GLU-RICH (ACIDIC).
61		FT DOMAIN 786 889 HECT DOMAIN.
62		FT DOMAIN 827 847 PRO-RICH.
63		FT BINDING 858 858 UBIQUITIN (BY SIMILARITY).
64		SQ SEQUENCE 889 AA; 100368 MW; DD7E6C7A CRC32;
65		MMSARGDFLN YALSLMRSHN DEHSDVLPVL DVCSLKHVAY VFQALIYWIK AMNQQTTLDT
66		PQLERKRTRE LLELGIDNED SEHENDDDTS QSATLNDKDD ESLPAETGQN HPFFRRSDSM
67		TFLGCIPPNP FEVPLAEAIP LADQPHLLQP NARKEDLFGR PSQGLYSSSA GSGKCLVEVT
68		MDRNCLEVLP TKMSYAANLK NVMNMQNRQK KAGEDQSMLA EEADSSKPGP SAHDVAAQLK
69		SSLLAEIGLT ESEGPPLTSF RPQCSFMGMV ISHDMLLGRW RLSLELFGRV FMEDVGAEPG
70		SILTELGGFE VKESKFRREM EKLRNQQSRD LSLEVDRDRD LLIQQTMRQL NNHFGRRCAT
71		TPMAVHRVKV TFKDEPGEGS GVARSFYTAI AQAFLSNEKL PNLDCIQNAN KGTHTSLMQR
72		LRNRGERDRE REREREMRRS SGLRAGSRRD RDRDFRRQLS IDTRPFRPAS EGNPSDDPDP
73		LPAHRQALGE RLYPRVQAMQ PAFASKITGM LLELSPAQLL LLLASEDSLR ARVEEAMELI
74		VAHGRENGAD SILDLGLLDS SEKVQENRKR HGSSRSVVDM DLDDTDDGDD NAPLFYQPGK
75		RGFYTPRPGK NTEARLNCFR NIGRILGLCL LQNELCPITL NRHVIKVLLG RKVNWHDFAF
76		FDPVMYESLR QLILASQSSD ADAVFSAMDL AFAVDLCKEE GGGQVELIPN GVNIPVTPQN
77		VYEYVRKYAE HRMLVVAEQP LHAMRKGLLD VLPKNSLEDL TAEDFRLLVN GCGEVNVQML
78		ISFTSFNDES GENAEKLLQF KRWFWSIVER MSMTERQDLV YFWTSSPSLP ASEEGFQPMP
79		SITIRPPDDQ HLPTANTCIS RLYVPLYSSK QILKQKLLLA IKTKNFGFV
80		//
81		ID 104K_THEPA STANDARD; PRT; 924 AA.
82		AC P15711;
83		DT 01-APR-1990 (Rel. 14, Created)
84		DT 01-APR-1990 (Rel. 14, Last sequence update)
85		DT 01-AUG-1992 (Rel. 23, Last annotation update)
86		DE 104 KD MICRONEME-RHOPTRY ANTIGEN.
87		OS Theileria parva.
88		OC Eukaryota; Alveolata; Apicomplexa; Piroplasmida; Theileriidae;
89		OC Theileria.
90		RN [1]
91		RP SEQUENCE FROM N.A.
92		RC STRAIN=MUGUGA;
93		RX MEDLINE; 90158697.
94		RA IAMS K.P., YOUNG J.R., NENE V., DESAI J., WEBSTER P.,
95		RA OLE-MOIYOI O.K., MUSOKE A.J.;
96		RT "Characterisation of the gene encoding a 104-kilodalton microneme-
97		RT rhoptry protein of Theileria parva.";
98		RL Mol. Biochem. Parasitol. 39:47-60(1990).
99		CC -!- SUBCELLULAR LOCATION: IN MICRONEME/RHOPTRY COMPLEXES.
100		CC -!- DEVELOPMENTAL STAGE: SPOROZOITE ANTIGEN.
101		CC --------------------------------------------------------------------------
102		CC This SWISS-PROT entry is copyright. It is produced through a collaboration
103		CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
104		CC the European Bioinformatics Institute. There are no restrictions on its
105		CC use by non-profit institutions as long as its content is in no way
106		CC modified and this statement is not removed. Usage by and for commercial
107		CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
108		CC or send an email to license@isb-sib.ch).
109		CC --------------------------------------------------------------------------
110		DR EMBL; M29954; AAA18217.1; -.
111		DR PIR; A44945; A44945.
112		KW Antigen; Sporozoite; Repeat.
113		FT DOMAIN 1 19 HYDROPHOBIC.
114		FT DOMAIN 905 924 HYDROPHOBIC.
115		SQ SEQUENCE 924 AA; 103625 MW; 4563AAA0 CRC32;
116		MKFLILLFNI LCLFPVLAAD NHGVGPQGAS GVDPITFDIN SNQTGPAFLT AVEMAGVKYL
117		QVQHGSNVNI HRLVEGNVVI WENASTPLYT GAIVTNNDGP YMAYVEVLGD PNLQFFIKSG
118		DAWVTLSEHE YLAKLQEIRQ AVHIESVFSL NMAFQLENNK YEVETHAKNG ANMVTFIPRN
119		GHICKMVYHK NVRIYKATGN DTVTSVVGFF RGLRLLLINV FSIDDNGMMS NRYFQHVDDK
120		YVPISQKNYE TGIVKLKDYK HAYHPVDLDI KDIDYTMFHL ADATYHEPCF KIIPNTGFCI
121		TKLFDGDQVL YESFNPLIHC INEVHIYDRN NGSIICLHLN YSPPSYKAYL VLKDTGWEAT
122		THPLLEEKIE ELQDQRACEL DVNFISDKDL YVAALTNADL NYTMVTPRPH RDVIRVSDGS
123		EVLWYYEGLD NFLVCAWIYV SDGVASLVHL RIKDRIPANN DIYVLKGDLY WTRITKIQFT
124		QEIKRLVKKS KKKLAPITEE DSDKHDEPPE GPGASGLPPK APGDKEGSEG HKGPSKGSDS
125		SKEGKKPGSG KKPGPAREHK PSKIPTLSKK PSGPKDPKHP RDPKEPRKSK SPRTASPTRR
126		PSPKLPQLSK LPKSTSPRSP PPPTRPSSPE RPEGTKIIKT SKPPSPKPPF DPSFKEKFYD
127		DYSKAASRSK ETKTTVVLDE SFESILKETL PETPGTPFTT PRPVPPKRPR TPESPFEPPK
128		DPDSPSTSPS EFFTPPESKR TRFHETPADT PLPDVTAELF KEPDVTAETK SPDEAMKRPR
129		SPSEYEDTSP GDYPSLPMKR HRLERLRLTT TEMETDPGRM AKDASGKPVK LKRSKSFDDL
130		TTVELAPEPK ASRIVVDDEG TEADDEETHP PEERQKTEVR RRRPPKKPSK SPRPSKPKKP
131		KKPDSAYIPS ILAILVVSLI VGIL
132		//
133		ID 108_LYCES STANDARD; PRT; 102 AA.
134		AC Q43495;
135		DT 15-JUL-1999 (Rel. 38, Created)
136		DT 15-JUL-1999 (Rel. 38, Last sequence update)
137		DT 15-JUL-1999 (Rel. 38, Last annotation update)
138		DE PROTEIN 108 PRECURSOR.
139		OS Lycopersicon esculentum (Tomato).
140		OC Eukaryota; Viridiplantae; Streptophyta; Embryophyta; Tracheophyta;
141		OC euphyllophytes; Spermatophyta; Magnoliophyta; eudicotyledons;
142		OC core eudicots; Asteridae; euasterids I; Solanales; Solanaceae;
143		OC Solanum.
144		RN [1]
145		RP SEQUENCE FROM N.A.
146		RC STRAIN=CV. VF36; TISSUE=ANTHER;
147		RX MEDLINE; 94143497.
148		RA CHEN R., SMITH A.G.;
149		RT "Nucleotide sequence of a stamen- and tapetum-specific gene from
150		RT Lycopersicon esculentum.";
151		RL Plant Physiol. 101:1413-1413(1993).
152		CC -!- TISSUE SPECIFICITY: STAMEN- AND TAPETUM-SPECIFIC.
153		CC -!- SIMILARITY: BELONGS TO THE A9 / FIL1 FAMILY.
154		CC --------------------------------------------------------------------------
155		CC This SWISS-PROT entry is copyright. It is produced through a collaboration
156		CC between the Swiss Institute of Bioinformatics and the EMBL outstation -
157		CC the European Bioinformatics Institute. There are no restrictions on its
158		CC use by non-profit institutions as long as its content is in no way
159		CC modified and this statement is not removed. Usage by and for commercial
160		CC entities requires a license agreement (See http://www.isb-sib.ch/announce/
161		CC or send an email to license@isb-sib.ch).
162		CC --------------------------------------------------------------------------
163		DR EMBL; Z14088; CAA78466.1; -.
164		DR MENDEL; 8853; LYCes;1133;1.
165		KW Signal.
166		FT SIGNAL 1 30 POTENTIAL.
167		FT CHAIN 31 102 PROTEIN 108.
168		FT DISULFID 41 77 BY SIMILARITY.
169		FT DISULFID 51 66 BY SIMILARITY.
170		FT DISULFID 67 92 BY SIMILARITY.
171		FT DISULFID 79 99 BY SIMILARITY.
172		SQ SEQUENCE 102 AA; 10576 MW; AFA4875A CRC32;
173		MASVKSSSSS SSSSFISLLL LILLVIVLQS QVIECQPQQS CTASLTGLNV CAPFLVPGSP
174		TASTECCNAV QSINHDCMCN TMRIAAQIPA QCNLPPLSCS AN
175		//