Mercurial > repos > xuebing > sharplabtool

comparison tools/sr_assembly/velvetg.xml @ 0:9071e359b9a3

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author xuebing
date Fri, 09 Mar 2012 19:37:19 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:9071e359b9a3
1 <tool id="velvetg" name="velvetg" version="1.0.0">
2 <description>Velvet sequence assembler for very short reads</description>
3 <command interpreter="python">
4 velvetg_wrapper.py
5 '$input.extra_files_path'
6 '$contigs' '$stats' '$LastGraph' '$velvet_asm' '$unused_reads_fasta'
7 #if $generate_amos.afg == "yes":
8 -amos_file $generate_amos.afg
9 #end if
10 #if $unused_reads.generate_unused == "yes":
11 -unused_reads $unused_reads.generate_unused
12 #end if
13 $read_trkg
14 #if $coverage.cutoff == "auto":
15 -cov_cutoff auto
16 #elif $coverage.cutoff == "value":
17 -cov_cutoff $coverage.cov_cutoff
18 #end if
19 #if $expected.coverage == "auto":
20 -exp_cov auto
21 #elif $expected.coverage == "value":
22 -exp_cov $expected.cov_cutoff
23 #end if
24 #if $contig_lgth.use_contig_lgth == "yes":
25 -min_contig_lgth $contig_lgth.min_contig_lgth
26 #end if
27 #if $reads.paired == "yes":
28 #if int($reads.ins_length) > 0:
29 -ins_length $reads.ins_length
30 #end if
31 #if $reads.options.advanced == "yes":
32 #if int($reads.options.ins_length_sd) > 0:
33 -ins_length_sd $reads.options.ins_length_sd
34 #end if
35 #if int($reads.options.ins_length2) > 0:
36 -ins_length2 $reads.options.ins_length2
37 #end if
38 #if int($reads.options.ins_length2_sd) > 0:
39 -ins_length2_sd $reads.options.ins_length2_sd
40 #end if
41 #if int($reads.options.ins_length_long) > 0:
42 -ins_length_long $reads.options.ins_length_long
43 #end if
44 #if int($reads.options.ins_length_long_sd) > 0:
45 -ins_length_long_sd $reads.options.ins_length_long_sd
46 #end if
47 #if int($reads.options.max_branch_length) > 0:
48 -max_branch_length $reads.options.max_branch_length
49 #end if
50 #if int($reads.options.max_divergence) > 0:
51 -max_divergence $reads.options.max_divergence
52 #end if
53 #if int($reads.options.max_gap_count) > 0:
54 -max_gap_count $reads.options.max_gap_count
55 #end if
56 #if int($reads.options.min_pair_count) > 0:
57 -min_pair_count $reads.options.min_pair_count
58 #end if
59 #if int($reads.options.max_coverage) > 0:
60 -max_coverage $reads.options.max_coverage
61 #end if
62 #if int($reads.options.long_mult_cutoff) > 0:
63 -long_mult_cutoff $reads.options.long_mult_cutoff
64 #end if
65 $reads.options.scaffolding
66 #end if
67 #end if
68 </command>
69 <inputs>
70 <param name="input" type="data" format="velvet" label="Velvet Dataset" help="Prepared by velveth."/>
71 <conditional name="generate_amos">
72 <param name="afg" type="select" label="Generate a AMOS.afg file">
73 <option value="no">No</option>
74 <option value="yes">Yes</option>
75 </param>
76 <when value="no"/>
77 <when value="yes"/>
78 </conditional>
79
80 <conditional name="unused_reads">
81 <param name="generate_unused" type="select" label="Generate a UnusedReads fasta file">
82 <option value="no">No</option>
83 <option value="yes">Yes</option>
84 </param>
85 <when value="no"/>
86 <when value="yes"/>
87 </conditional>
88
89 <conditional name="last_graph">
90 <param name="generate_graph" type="select" label="Generate velvet LastGraph file">
91 <option value="no">No</option>
92 <option value="yes">Yes</option>
93 </param>
94 <when value="no"/>
95 <when value="yes"/>
96 </conditional>
97
98 <param name="read_trkg" type="boolean" checked="false" truevalue="-read_trkg yes" falsevalue="-read_trkg no" label="track short read positions" help=" tracking of short read positions in assembly"/>
99
100 <conditional name="coverage">
101 <param name="cutoff" type="select" label="Coverage cutoff" help="">
102 <option value="none">None</option>
103 <option value="auto">Automatically Determined</option>
104 <option value="value">Specify Cutoff Value</option>
105 </param>
106 <when value="none"/>
107 <when value="auto"/>
108 <when value="value">
109 <param name="cov_cutoff" value = "10.0" label="Remove nodes with coverage below" type="float" />
110 </when>
111 </conditional>
112
113 <conditional name="expected">
114 <param name="coverage" type="select" label="Expected Coverage of Unique Regions" help="">
115 <option value="none">None</option>
116 <option value="auto">Automatically Determined</option>
117 <option value="value">Specify Expected Value</option>
118 </param>
119 <when value="none"/>
120 <when value="auto"/>
121 <when value="value">
122 <param name="exp_cov" value = "10.0" label="Remove nodes with coverage below" type="float" />
123 </when>
124 </conditional>
125
126 <conditional name="contig_lgth">
127 <param name="use_contig_lgth" type="select" label=" Set minimum contig length" help="minimum contig length exported to contigs.fa file (default: hash length * 2).">
128 <option value="no">No</option>
129 <option value="yes">Yes</option>
130 </param>
131 <when value="no"/>
132 <when value="yes">
133 <param name="min_contig_lgth" value = "42" label="minimum contig length" type="integer" help="minimum contig length exported to contigs.fa file (default: hash length * 2)"/>
134 </when>
135 </conditional>
136
137 <conditional name="reads">
138 <param name="paired" type="select" label="Using Paired Reads">
139 <option value="no">No</option>
140 <option value="yes" selected="${input.metadata.paired_end_reads}">Yes</option>
141 </param>
142 <when value="no"/>
143 <when value="yes">
144 <param name="ins_length" value = "-1" label="Insert Length in Paired-End Read dataset (ignored when -1)" type="integer" help="Expected distance between two paired end reads"/>
145 <conditional name="options">
146 <param name="advanced" type="select" label="Velvet Advanced Options">
147 <option value="no">Use Defaults</option>
148 <option value="yes">Set Advanced Option Values</option>
149 </param>
150 <when value="no"/>
151 <when value="yes">
152 <param name="ins_length_sd" value = "-1" label="Estimate of Standard Deviation of Paired-End Read dataset(ignored when -1)" type="integer" help="Estimate of standard deviation of Paired-End Read dataset (default: 10% of corresponding length)"/>
153 <param name="ins_length2" value = "-1" label="Insert Length in 2nd Paired-End Short Read dataset (ignored when -1)" type="integer" help="Expected distance between two paired end reads in the second short-read dataset"/>
154 <param name="ins_length2_sd" value = "-1" label="Estimate of Standard Deviation of 2nd Paired-End Read dataset (ignored when -1)" type="integer" help="Estimate of standard deviation of 2nd Paired-End Read dataset (default: 10% of corresponding length)"/>
155 <param name="ins_length_long" value = "-1" label="Insert Length in Long Paired-End Read dataset (ignored when -1)" type="integer" help="Expected distance between two long paired-end reads"/>
156 <param name="ins_length_long_sd" value = "-1" label="Estimate of Standard Deviation of 2nd Paired-End Read dataset (ignored when -1)" type="integer" help="Estimate of standard deviation of Long Paired-End Read dataset (default: 10% of corresponding length)"/>
157 <param name="max_branch_length" value = "-1" label="Maximum branch length (ignored when -1)" type="integer" help="maximum length in base pair of bubble (default: 100)"/>
158 <param name="max_divergence" value = "-1." label="Maximum max_divergence (between .0 and 1., ignored when -1.)" type="float" help="maximum divergence rate between two branches in a bubble (default: .2)"/>
159 <param name="max_gap_count" value = "-1" label="Maximum gap count (ignored when -1)" type="integer" help="maximum number of gaps allowed in the alignment of the two branches of a bubble (default: 3)"/>
160 <param name="min_pair_count" value = "-1" label="Minimum read-pair count (ignored when -1)" type="integer" help="minimum number of paired end connections to justify the scaffolding of two long contigs (default: 10)"/>
161 <param name="max_coverage" value = "-1." label="Maximum coverage exclusion(ignored when -1.)" type="float" help="Exclude data that has coverage more than this maximum coverage value"/>
162 <param name="long_mult_cutoff" value = "-1" label="Minimum number of long reads required to merge contigs (ignored when -1)" type="integer" help="minimum number of long reads required to merge contigs (default: 2)"/>
163 <param name="scaffolding" type="boolean" checked="true" truevalue="-scaffolding yes" falsevalue="-scaffolding no" label="Use Scaffolding" help="Scaffold contigs that it cannot quite be connected (This results in sequences of Ns in the contigs)"/>
164
165 </when>
166 </conditional>
167 </when>
168 </conditional>
169 </inputs>
170 <outputs>
171 <!--
172 <data format="velvet_graph" name="LastGraph" />
173 -->
174 <data format="txt" name="LastGraph" label="${tool.name} on ${on_string}: LastGraph">
175 <filter>last_graph['generate_graph'] == "yes"</filter>
176 </data>
177 <data format="afg" name="velvet_asm" label="${tool.name} on ${on_string}: AMOS.afg">
178 <filter>generate_amos['afg'] == "yes"</filter>
179 </data>
180 <data format="fasta" name="unused_reads_fasta" label="${tool.name} on ${on_string}: Unused Reads">
181 <filter>unused_reads['generate_unused'] == "yes"</filter>
182 </data>
183 <data format="tabular" name="stats" label="${tool.name} on ${on_string}: Stats"/>
184 <data format="fasta" name="contigs" label="${tool.name} on ${on_string}: Contigs"/>
185 </outputs>
186 <requirements>
187 <requirement type="package">velvet</requirement>
188 </requirements>
189 <tests>
190 <test>
191 <param name="input" value="velveth_test1/output.html" ftype="velvet" >
192 <composite_data value='velveth_test1/Sequences' ftype="Sequences"/>
193 <composite_data value='velveth_test1/Roadmaps' ftype="Roadmaps"/>
194 <composite_data value='velveth_test1/Log'/>
195 </param>
196 <param name="afg" value="yes" />
197 <param name="generate_unused" value="yes" />
198 <param name="generate_graph" value="no" />
199 <param name="read_trkg" value="-read_trkg no" />
200 <param name="cutoff" value="auto" />
201 <param name="coverage" value="auto" />
202 <param name="use_contig_lgth" value="no" />
203 <param name="paired" value="no" />
204 <!--
205 <output name="LastGraph" file="velvetg_test1/lastgraph.txt" compare="diff"/>
206 -->
207 <output name="velvet_asm" file="velvetg_test1/amos.afg" compare="diff"/>
208 <output name="unused_reads_fasta" file="velvetg_test1/unusedreads.fa" compare="diff"/>
209 <output name="stats" file="velvetg_test1/stats.csv" compare="diff"/>
210 <output name="contigs" file="velvetg_test1/contigs.fa" compare="diff"/>
211 </test>
212 </tests>
213 <help>
214 **Velvet Overview**
215
216 Velvet_ is a de novo genomic assembler specially designed for short read sequencing technologies, such as Solexa or 454, developed by Daniel Zerbino and Ewan Birney at the European Bioinformatics Institute (EMBL-EBI), near Cambridge, in the United Kingdom.
217
218 Velvet currently takes in short read sequences, removes errors then produces high quality unique contigs. It then uses paired-end read and long read information, when available, to retrieve the repeated areas between contigs.
219
220 Read the Velvet `documentation`__ for details on using the Velvet Assembler.
221
222 .. _Velvet: http://www.ebi.ac.uk/~zerbino/velvet/
223
224 .. __: http://www.ebi.ac.uk/~zerbino/velvet/Manual.pdf
225
226 ------
227
228 **Input formats**
229
230 Velvet can input sequence files in the following formats: fasta fastq fasta.gz fastq.gz eland gerald
231
232 The input files are prepared for the velvet assembler using **velveth**.
233
234 ------
235
236 **Outputs**
237
238 **Contigs**
239
240 The *contigs.fa* file.
241 This fasta file contains the sequences of the contigs longer than 2k, where k is the word-length used in velveth. If you have specified a min contig length threshold, then the contigs shorter than that value are omitted.
242 Note that the length and coverage information provided in the header of each contig should therefore be understood in k-mers and in k-mer coverage (cf. 5.1) respectively.
243 The N's in the sequence correspond to gaps between scaffolded contigs. The number of N's corresponds to the estimated length of the gap. For reasons of compatibility with the archives, any gap shorter than 10bp is represented by a sequence of 10 N's.
244
245 **Stats**
246
247 The *stats.txt* file.
248 This file is a simple tabbed-delimited description of the nodes. The column names are pretty much self-explanatory. Note however that node lengths are given in k-mers. To obtain the length in nucleotides of each node you simply need to add k - 1, where k is the word-length used in velveth.
249 The in and out columns correspond to the number of arcs on the 5' and 3' ends of the contig respectively.
250 The coverages in columns short1 cov, short1 Ocov, short2 cov, and short2 Ocov are provided in k-mer coverage (5.1).
251 Also, the difference between # cov and # Ocov is the way these values are computed. In the first count, slightly divergent sequences are added to the coverage tally. However, in the second, stricter count, only the sequences which map perfectly onto the consensus sequence are taken into account.
252
253 **LastGraph**
254
255 The *LastGraph* file.
256 This file describes in its entirety the graph produced by Velvet.
257
258 **AMOS.afg**
259
260 The *velvet_asm.afg* file.
261 This file is mainly designed to be read by the open-source AMOS genome assembly package. Nonetheless, a number of programs are available to transform this kind of file into other assembly file formats (namely ACE, TIGR, Arachne and Celera). See http://amos.sourceforge.net/ for more information.
262 The file describes all the contigs contained in the contigs.fa file (cf 4.2.1).
263
264 ------
265
266 **Velvet parameter list**
267
268 This is a list of implemented Velvetg options::
269
270 Standard options:
271 -cov_cutoff floating-point|auto : removal of low coverage nodes AFTER tour bus or allow the system to infer it
272 (default: no removal)
273 -ins_length integer : expected distance between two paired end reads (default: no read pairing)
274 -read_trkg yes|no : tracking of short read positions in assembly (default: no tracking)
275 -min_contig_lgth integer : minimum contig length exported to contigs.fa file (default: hash length * 2)
276 -amos_file yes|no : export assembly to AMOS file (default: no export)
277 -exp_cov floating point|auto : expected coverage of unique regions or allow the system to infer it
278 (default: no long or paired-end read resolution)
279
280 Advanced options:
281 -ins_length2 integer : expected distance between two paired-end reads in the second short-read dataset (default: no read pairing)
282 -ins_length_long integer : expected distance between two long paired-end reads (default: no read pairing)
283 -ins_length*_sd integer : est. standard deviation of respective dataset (default: 10% of corresponding length)
284 [replace '*' by nothing, '2' or '_long' as necessary]
285 -scaffolding yes|no : scaffolding of contigs used paired end information (default: on)
286 -max_branch_length integer : maximum length in base pair of bubble (default: 100)
287 -max_divergence floating-point : maximum divergence rate between two branches in a bubble (default: 0.2)
288 -max_gap_count integer : maximum number of gaps allowed in the alignment of the two branches of a bubble (default: 3)
289 -min_pair_count integer : minimum number of paired end connections to justify the scaffolding of two long contigs (default: 10)
290 -max_coverage floating point : removal of high coverage nodes AFTER tour bus (default: no removal)
291 -long_mult_cutoff int : minimum number of long reads required to merge contigs (default: 2)
292 -unused_reads yes|no : export unused reads in UnusedReads.fa file (default: no)
293
294 Output:
295 directory/contigs.fa : fasta file of contigs longer than twice hash length
296 directory/stats.txt : stats file (tab-spaced) useful for determining appropriate coverage cutoff
297 directory/LastGraph : special formatted file with all the information on the final graph
298 directory/velvet_asm.afg : (if requested) AMOS compatible assembly file
299
300 </help>
301 </tool>