Mercurial > repos > iuc > abyss

comparison abyss-pe.xml @ 0:f048033da666 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/abyss commit 0887009a23d176b21536c9fd8a18c4fecc417d4f
author iuc
date Fri, 19 Jun 2015 09:26:16 -0400
parents
children 0a5c7992b1ac
comparison
equal deleted inserted replaced
-1:000000000000 0:f048033da666
1 <tool id="abyss-pe" name="ABySS" version="1.9.0.0">
2 <description>de novo sequence assembler</description>
3 <macros>
4 <xml name="reads_conditional">
5 <conditional name="reads">
6 <param name="reads_selector" type="select" label="Type of paired-end datasets">
7 <option value="paired">2 separate datasets</option>
8 <option value="paired_collection">1 paired dataset collection</option>
9 <option value="paired_il">1 dataset of interleaved reads</option>
10 </param>
11 <when value="paired">
12 <param name="reads1" type="data" format="fasta,fastq,fastqsanger,fastqillumina" label="Paired-end reads 1" />
13 <param name="reads2" type="data" format="fasta,fastq,fastqsanger,fastqillumina" label="Paired-end reads 2" />
14 </when>
15 <when value="paired_collection">
16 <param name="reads_coll" type="data_collection" collection_type="paired" format="fasta,fastq,fastqsanger,fastqillumina" label="Paired-end reads collection" />
17 </when>
18 <when value="paired_il">
19 <param name="reads_il" type="data" format="fasta,fastq,fastqsanger,fastqillumina" label="Interleaved paired-end reads" />
20 </when>
21 </conditional>
22 </xml>
23 </macros>
24 <requirements>
25 <requirement type="package" version="1.9.0">abyss</requirement>
26 </requirements>
27 <stdio>
28 <!-- Anything other than zero is an error -->
29 <exit_code range="1:" />
30 <!-- In case the return code has not been set propery check stderr too -->
31 <regex match="Error:" />
32 <regex match="Exception:" />
33 </stdio>
34 <version_command>ABYSS --version | head -n 1</version_command>
35 <command>
36 abyss-pe name=abyss j=\${GALAXY_SLOTS:-1} k=$k
37 #if str($K)
38 K=$K
39 #end if
40 #if str($q)
41 q=$q
42 #end if
43 #if str($Q)
44 Q=$Q
45 #end if
46 #if str($e)
47 e=$e
48 #end if
49 #if str($E)
50 E=$E
51 #end if
52 #if str($t)
53 t=$t
54 #end if
55 #if str($c)
56 c=$c
57 #end if
58 #if str($b)
59 b=$b
60 #end if
61 #if $SS
62 SS=--SS
63 #end if
64 #if str($m)
65 m=$m
66 #end if
67 #if str($p)
68 p=$p
69 #end if
70 #if str($a)
71 a=$a
72 #end if
73 #if str($l)
74 l=$l
75 #end if
76 #if str($s)
77 s=$s
78 #end if
79 #if str($n)
80 n=$n
81 #end if
82 #if str($d)
83 d=$d
84 #end if
85 #if str($S)
86 S=$S
87 #end if
88 #if str($N)
89 N=$N
90 #end if
91 #if $lib_repeat
92 lib='
93 #for $i in range(len($lib_repeat))
94 lib$i
95 #end for
96 '
97 #for $i, $v in enumerate($lib_repeat)
98 #if $v.reads.reads_selector == 'paired'
99 lib${i}='${v.reads.reads1} ${v.reads.reads2}'
100 #elif $v.reads.reads_selector == 'paired_collection'
101 lib${i}='${v.reads.reads_coll.forward} ${v.reads.reads_coll.reverse}'
102 #else
103 lib${i}='${v.reads.reads_il}'
104 #end if
105 #end for
106 #end if
107 #if str($se_reads) != 'None'
108 se='
109 #for $v in $se_reads
110 $v
111 #end for
112 '
113 #end if
114 #if $mp_repeat
115 mp='
116 #for $i in range(len($mp_repeat))
117 mp$i
118 #end for
119 '
120 #for $i, $v in enumerate($mp_repeat)
121 #if $v.reads.reads_selector == 'paired'
122 mp${i}='${v.reads.reads1} ${v.reads.reads2}'
123 #elif $v.reads.reads_selector == 'paired_collection'
124 mp${i}='${v.reads.reads_coll.forward} ${v.reads.reads_coll.reverse}'
125 #else
126 mp${i}='${v.reads.reads_il}'
127 #end if
128 #end for
129 #end if
130 #if str($long_seqs) != 'None'
131 long='
132 #for $v in $long_seqs
133 $v
134 #end for
135 '
136 #end if
137 </command>
138
139 <inputs>
140 <repeat name="lib_repeat" title="Paired-end library" help="(lib)">
141 <expand macro="reads_conditional" />
142 </repeat>
143 <param name="se_reads" type="data" multiple="true" optional="true" format="fasta,fastq,fastqsanger,fastqillumina" label="Single-end reads" help="(se)" />
144 <repeat name="mp_repeat" title="Mate-pair library" help="The mate-pair libraries are used only for scaffolding and do not contribute towards the consensus sequence (mp)">
145 <expand macro="reads_conditional" />
146 </repeat>
147 <param name="long_seqs" type="data" multiple="true" optional="true" format="fasta,fastq,fastqsanger,fastqillumina" label="Long sequences" help="Long sequence libraries are used only for rescaffolding and do not contribute towards the consensus sequence (long)" />
148 <param name="k" type="integer" value="41" label="K-mer length (in bp)" help="The length of a k-mer (when -K is not set) or the span of a k-mer pair (when K is set) (k)" />
149 <param name="K" type="integer" value="" optional="true" label="The length (in bp) of a single k-mer in a k-mer pair" help="Optional (K)" />
150 <param name="q" type="integer" value="3" max="40" optional="true" label="Minimum base quality when trimming" help="Trim bases from the ends of reads whose quality is less than this value (q)" />
151 <param name="Q" type="integer" value="0" max="40" optional="true" label="Minimum base quality" help="Mask all bases of reads whose quality is less than this value as 'N' (Q)" />
152 <param name="e" type="integer" value="" min="0" optional="true" label="Minimum erosion k-mer coverage" help="Erode bases at the ends of blunt contigs with coverage less than this value. Defaults to round(sqrt(median)) (e)" />
153 <param name="E" type="integer" value="" min="0" optional="true" label="Minimum erosion k-mer coverage per strand" help="Erode bases at the ends of blunt contigs with coverage less than this value on either strand. Defaults to 1 if sqrt(median) &gt; 2 else 0 (E)" />
154 <param name="t" type="integer" value="" optional="true" label="Maximum length of blunt contigs to trim" help="Defaults to the value of k (t)" />
155 <param name="c" type="float" value="" optional="true" label="Minimum mean k-mer coverage of a unitig" help="Defaults to sqrt(median) (c)" />
156 <param name="b" type="integer" value="" optional="true" label="Maximum length of a bubble (in bp)" help="abyss-pe has two bubble popping stages. The default limits are 3*k bp for ABYSS and 10000 bp for PopBubbles (b)" />
157 <param name="SS" type="boolean" label="Assemble in strand-specific mode" help="Requires that all libraries are strand-specific RNA-Seq libraries. Assumes that the first read in a read pair is reveresed with respect to the transcripts sequenced (SS)" />
158 <param name="m" type="integer" value="50" min="0" optional="true" label="Minimum overlap of two unitigs (in bp)" help="(m)" />
159 <param name="p" type="float" value="0.9" optional="true" label="Minimum sequence identity of a bubble" help="(p)" />
160 <param name="a" type="integer" value="2" min="0" optional="true" label="Maximum number of branches of a bubble" help="(a)" />
161 <param name="l" type="integer" value="" min="1" optional="true" label="Minimum alignment length of a read (in bp)" help="Defaults to the value of k (l)" />
162 <param name="s" type="integer" value="200" min="0" optional="true" label="Minimum unitig length required for building contigs (in bp)" help="The seed length should be at least twice the value of k. If more sequence is assembled than the expected genome size, try increasing this value (s)" />
163 <param name="n" type="integer" value="10" min="0" optional="true" label="Minimum number of pairs required for building contigs" help="(n)" />
164 <param name="d" type="integer" value="6" min="0" optional="true" label="Allowable error of a distance estimate (in bp)" help="(d)" />
165 <param name="S" type="integer" value="" min="0" optional="true" label="Minimum contig length required for building scaffolds (in bp)" help="Defaults to the value of s (S)" />
166 <param name="N" type="integer" value="" min="0" optional="true" label="Minimum number of pairs required for building scaffolds" help="Defaults to the value of n (N)" />
167 </inputs>
168
169 <outputs>
170 <data name="unitigs" format="fasta" label="${tool.name} on ${on_string}: unitigs" from_work_dir="abyss-unitigs.fa" />
171 <data name="contigs_outfile" format="fasta" label="${tool.name} on ${on_string}: contigs" from_work_dir="abyss-contigs.fa">
172 <filter>lib_repeat</filter>
173 </data>
174 <data name="scaffolds" format="fasta" label="${tool.name} on ${on_string}: scaffolds" from_work_dir="abyss-scaffolds.fa">
175 <filter>lib_repeat or mp_repeat</filter>
176 </data>
177 <data name="bubbles" format="fasta" label="${tool.name} on ${on_string}: bubbles" from_work_dir="abyss-bubbles.fa" />
178 <data name="indels" format="fasta" label="${tool.name} on ${on_string}: indels" from_work_dir="abyss-indel.fa" />
179 <data name="coverage_histogram_outfile" format="tabular" label="${tool.name} on ${on_string}: coverage histogram" from_work_dir="coverage.hist" />
180 <data name="stats" format="tabular" label="${tool.name} on ${on_string}: stats" from_work_dir="abyss-stats.tab" />
181 </outputs>
182
183 <tests>
184 <test>
185 <repeat name="lib_repeat">
186 <conditional name="reads">
187 <param name="reads_selector" value="paired" />
188 <param name="reads1" ftype="fastqsanger" value="assembly_sample-R1.fastq" />
189 <param name="reads2" ftype="fastqsanger" value="assembly_sample-R2.fastq" />
190 </conditional>
191 </repeat>
192 <param name="k" value="50" />
193 <output name="unitigs" file="abyss-unitigs1.fa" />
194 <output name="contigs_outfile" file="abyss-contigs1.fa" />
195 <output name="scaffolds" file="abyss-scaffolds1.fa" />
196 <output name="bubbles" file="empty_file.fasta" />
197 <output name="indels" file="empty_file.fasta" />
198 <output name="coverage_histogram_outfile" file="coverage1.hist" />
199 <output name="stats" file="abyss-stats1.tab" />
200 </test>
201 <test>
202 <param name="se_reads" ftype="fastqsanger" value="assembly_sample-R1.fastq,assembly_sample-R2.fastq" />
203 <param name="k" value="50" />
204 <output name="unitigs" file="abyss-unitigs2.fa" />
205 <output name="bubbles" file="empty_file.fasta" />
206 <output name="indels" file="empty_file.fasta" />
207 <output name="coverage_histogram_outfile" file="coverage2.hist" />
208 <output name="stats" file="abyss-stats2.tab" />
209 </test>
210 </tests>
211 <help>
212 **What it does**
213
214 `ABySS`_ is a de novo sequence assembler intended for short paired-end reads and large genomes.
215
216 **Input**
217
218 Input files should be FASTA or FASTQ files.
219
220 For paired reads, a pair of reads must be named with the suffixes /1 and /2 to identify the first and second read, or the reads may be named identically. The paired reads may be in separate files or interleaved in a single file.
221
222 At least a paired-end library or a single-end library must be provided.
223
224 Contigs are generated only if at least a paired-end library is provided. Scaffolds are generated only if at least a paired-end library or a mate-pair library is provided.
225
226 **Description**
227
228 This tool performs the complete ABySS pipeline using abyss-pe, described in https://github.com/bcgsc/abyss/blob/master/doc/flowchart.pdf .
229
230 **License and citation**
231
232 This Galaxy tool is Copyright © 2015 `The Genome Analysis Centre (TGAC)`_ and is released under the `MIT license`_.
233
234 .. _The Genome Analysis Centre (TGAC): http://www.tgac.ac.uk/
235 .. _MIT license: http://opensource.org/licenses/MIT
236
237 You can use this tool only if you agree to the license terms of: `ABySS`_.
238
239 .. _ABySS: http://www.bcgsc.ca/platform/bioinfo/software/abyss
240 </help>
241 <citations>
242 <citation type="doi">10.1101/gr.089532.108</citation>
243 </citations>
244 </tool>