Mercurial > repos > edward-kirton > roche454_toolsuite

comparison roche454/runAssembly_cDNA.xml @ 0:f036c7107601

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 1.0.0 from old tool shed archive to new tool shed repository
author edward-kirton
date Tue, 07 Jun 2011 17:50:32 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:f036c7107601
1 <tool id="runAssembly_cDNA" name="runAssembly cDNA" version="1.0.0" force_history_refresh='True'>
2 <description>De novo assembly of Roche/454 cDNA reads using Newbler</description>
3 <command interpreter='perl'>runAssembly_cDNA_wrapper.pl
4 $newbler_metrics.extra_files_path
5 $newbler_metrics
6 $read_status
7 $trimmed_reads_fasta
8 $trimmed_reads_qual
9 $alignment_info
10 $all_contigs_fasta
11 $all_contigs_qual
12 $contigs_ace
13 $contigs_consed_ace
14 $contig_graph
15 $pair_align
16 $pair_status
17 $scaffolds_fasta
18 $scaffolds_qual
19 $scaffolds_agp
20 $tag_pair_align
21 $trim_status
22 $isotigs_ace
23 $isotigs_fasta
24 $isotigs_qual
25 $isotigs_agp
26 $isotigs_layout
27 $newbler_exe -o $newbler_metrics.extra_files_path
28 -cpu 8
29 $rip
30 -e $e
31 -mi $mi
32 -ml $ml
33 -minlen $minlen
34 $large
35 $pair
36 $info
37 $notrim
38 $tr
39 $ace
40 $no
41 $qo
42 $nor
43 $ud
44 -ss $ss
45 -sl $sl
46 -sc $sc
47 -ais $ais
48 -a $a
49 -mcf $mcf
50 -vs $vs
51 -vt $vt
52 -fi $fi
53 -fe $fe
54 -cdna
55 -ig $ig
56 -it $it
57 -icc $icc
58 -icl $icl
59 #for $i in $sff_paired_inputs
60 -p ${i.sff_paired_input}
61 #end for
62 #for $i in $sanger_paired_inputs
63 -p ${i.sanger_paired_input}
64 #end for
65 #for $i in $sff_inputs
66 ${i.sff_input}
67 #end for
68 #for $i in $sanger_inputs
69 ${i.sanger_input}
70 #end for
71 </command>
72 <inputs>
73 <!-- NEWBLER VERSION -->
74 <param name='newbler_exe' type='select' display='radio' label='Newbler version'>
75 <option value='runAssembly' selected='true'>default</option>
76 <!-- OTHER VERSIONS MAY BE INCLUDED HERE; OR SIMPLY EDIT TO REMOVE THIS ENTIRE SECTION
77 <option value='/jgi/tools/454/rig-DataProcessing_2.3/bin/runAssembly'>2.3</option>
78 <option value='/jgi/tools/454/rig-DataProcessing_2.4pre-20091204/bin/runAssembly'>2.4</option>
79 <option value='/home/copeland/local/x86_64/newbler/v2.5p1-internal-10Jun23-1/runAssembly'>2.5</option>
80 -->
81 </param>
82
83 <!-- READSEQ INFILES -->
84 <repeat name="sff_inputs" title="Unpaired Reads Sff Files">
85 <param name="sff_input" type="data" format="sff" label="SE Sff file"/>
86 </repeat>
87 <repeat name="sanger_inputs" title="Unpaired Reads Fasta Files">
88 <param name="sanger_input" type="data" format="fasta" label="SE Fasta file"/>
89 </repeat>
90 <repeat name="sff_paired_inputs" title="Paired Reads Sff Files">
91 <param name="sff_paired_input" type="data" format="sff" label="PE Sff file"/>
92 </repeat>
93 <repeat name="sanger_paired_inputs" title="Paired Reads Fasta Files">
94 <param name="sanger_paired_input" type="data" format="fasta" label="PE Fasta file"/>
95 </repeat>
96 <param name='paired_reads' type='select' display='radio' label='[-paired_reads] If supplying paired reads (above), do you want paired-read info?'>
97 <option value='false'>no</option>
98 <option value='true'>[-paired_reads] yes</option>
99 </param>
100 <param name='pair' type='select' display='radio' label='[-pair] Output pairwise overlaps'>
101 <option value=''>no</option>
102 <option value='-pair'>[-pair] yes</option>
103 </param>
104
105 <param name='it' type='integer' value='100' label='[-it] Specify the maximum number of isotigs in an isogroup. Maximum is 10,000.'/>
106 <param name='ig' type='integer' value='500' label='[-ig] Specify the maximum number of contigs in an isogroup.'/>
107 <param name='icc' type='integer' value='100' label='[-icc] Specify the maximum number of contigs in an isotig. Maximum is 200 and corresponds to the recursion depth during graph traversal'/>
108 <param name='icl' type='integer' value='3' label='[-icl] Specify the minimum length a contig must be to be part of an isotig. Minimum is 3bp.'/>
109
110 <!-- OPTIONAL ARGUMENTS -->
111 <param name='mcf' type='data' format='tabular' optional='true' label='[-mcf] Specify non-default MID config file' />
112 <param name='fi' type='data' format='txt' optional='true' label='[-fi] Include filter file to be specified' />
113 <param name='fe' type='data' format='txt' optional='true' label='[-fe] Exclude filter file to be specified' />
114 <param name='vt' type='data' format='fasta' optional='true' label="[-vt] This option specifies a vector trimming database, or FASTA file of sequences to be used to trim the ends of input reads (for cloning vectors, primers, adapters or other end sequences)" />
115 <param name='vs' type='data' format='fasta' optional='true' label="[-vs] This option specifies a vector screening database, or FASTA file of sequences to be used to screen the input reads for contaminants. Reads that completely align against the screening database are trimmed completely (so that it is not used in the computation), but otherwise the read trimpoints are not changed" />
116
117 <!-- READ TRIMMING -->
118 <param name='minlen' type='integer' value='20' label='[-minlen] Minimum length of reads to use (15-45 allowed)'/>
119 <param name='notrim' type='boolean' truevalue='-notrim' falsevalue='' checked='false' label='[-notrim] Do not perform default quality and primer trimming of input reads'/>
120 <param name='tr' type='select' display='radio' label='[-tr] Output trimmed reads'>
121 <option value=''>no</option>
122 <option value='-tr'>[-tr] yes</option>
123 </param>
124 <param name='nor' type='boolean' truevalue='-nor' falsevalue='' label='[-nor] Turn off the automatic rescore function for read quality scores'/>
125 <param name='ud' type='boolean' truevalue='-ud' falsevalue='' label='[-ud] Treat each read separately, with no grouping of duplicates'/>
126
127 <!-- ALIGNMENT PARAMETERS -->
128 <param name='ss' type='integer' value='12' label='[-ss] Seed step parameter - The number of bases between seed generation locations used in the exact k-mer matching part of the overlap detection. Allow values: 1 or greater'/>
129 <param name='sl' type='integer' value='16' label='[-sl] Seed length parameter - The number of bases used for each seed in the exact k-mer matching part of the overlap detection (i.e. the "k" value of the k-mer matching). Allowed values: 6-16'/>
130 <param name='sc' type='integer' value='1' label='[-sc] Seed count parameter - The number of seeds required in a window before an extension is made. Allowed values: 1 or greater'/>
131 <param name='ml' type="text" value='40' label="[-ml] Minimum overlap length - The minimum length of overlaps used for the pairwise alignment step. The value can either be a minimum length in bases or a percentage of read length. In the case of a percentage, simply include '%' immediately following the numeric value. Allowed values: 1 or greater"/>
132 <param name='mi' type="integer" value='90' label="[-mi] Minimum overlap identity - The percent identity of overlaps used for the pairwise alignment step. Allowed values: 0 or greater"/>
133 <param name='ais' type='integer' value='2' label='[-ais] Alignment identity score - When multiple overlaps are found, the per-overlap column identity score used to sort the overlaps for use in the progressive alignment. Allowed values: 0 or greater'/>
134
135 <!-- ASSEMBLY OPTIONS -->
136 <param name='e' type="integer" value='0' label="[-e] This option tells the assembler that the expected depth of the data is at a certain level. The assembler has been optimized for datasets in the 10-50x oversampling size, and this option helps the assembler with datasets that have a higher oversampling level. A value of 0 resets the assembler computation to use its default algorithms"/>
137 <param name='large' type='boolean' truevalue='-large' falsevalue='' checked='false' label='[-large] Check if large or complex genome'/>
138
139 <!-- OUTPUT OPTIONS -->
140 <param name='no' type='select' display='radio' label='[-no] Do complete assembly'>
141 <option value=''>do complete assembly</option>
142 <option value='-no'>[-no] do not assemble; do alignments only</option>
143 </param>
144 <param name='qo' type='boolean' truevalue='' falsevalue='-qo' checked='false' label='[-qo] Generate quick output for mapping and assembly. Disables signal distribution computation for calling consensus sequences and can decrease accuracy'/>
145 <param name='a' type="integer" value='100' label="[-a] This option sets the minimum length for a contig to appear in the 454AllContigs.fna file."/>
146 <param name='rip' type='boolean' truevalue='' falsevalue='-rip' checked='false' label='[-rip] Output each read in only one contig'/>
147 <param name='info' type='select' display='radio' label='Output Alignment Info'>
148 <option value='-info'>[-info] yes</option>
149 <option value='-infoall'>[-infoall] yes, including 0-coverage positions</option>
150 </param>
151 <param name='ace' type='select' display='radio' label='Produce Ace assembly file'>
152 <option value=''>no</option>
153 <option value='-ace'>[-ace] yes</option>
154 <option value='-ace -consed'>[-consed] yes, in consed dir</option>
155 </param>
156 </inputs>
157
158 <outputs>
159 <data name='newbler_metrics' format='txt' />
160 <data name='read_status' format='tabular' label='Read Status'/>
161 <data name='trimmed_reads_fasta' format='fasta' label='Trimmed Reads (Fasta)'>
162 <filter>tr == '-tr'</filter>
163 </data>
164 <data name='trimmed_reads_qual' format='qual454' label='Trimmed Reads (Qual)'>
165 <filter>tr == '-tr'</filter>
166 </data>
167 <!-- the following produced only if no != '-no' -->
168 <data name='alignment_info' format='tabular' label='Alignment Info'>
169 <filter>no != '-no'</filter>
170 </data>
171 <data name='all_contigs_fasta' format='fasta' label='All Contigs (Fasta)'>
172 <filter>no != '-no'</filter>
173 </data>
174 <data name='all_contigs_qual' format='qual454' label='All Contigs (Qual454)'>
175 <filter>no != '-no'</filter>
176 </data>
177 <data name='contigs_ace' format='ace' label='Contigs (Ace)'>
178 <filter>ace == '-ace' and no != '-no'</filter>
179 </data>
180 <data name='contigs_consed_ace' format='ace' label='Contigs (Consed/Ace)'>
181 <filter>ace == '-ace -consed' and no != '-no'</filter>
182 </data>
183
184 <data name='contig_graph' format='txt' label='Contig Graph'/>
185 <data name='pair_align' format='txt' label='Pairwise Alignments'>
186 <filter>pair == '-pair' and no != '-no'</filter>
187 </data>
188 <data name='pair_status' format='tabular' label='Paired-End Read Status'>
189 <filter>paired_reads == 'true' and no != '-no'</filter>
190 </data>
191 <data name='scaffolds_fasta' format='fasta' label='Scaffolds (Fasta)'>
192 <filter>paired_reads == 'true' and no != '-no'</filter>
193 </data>
194 <data name='scaffolds_qual' format='qual454' label='Scaffolds (Qual454)'>
195 <filter>paired_reads == 'true' and no != '-no'</filter>
196 </data>
197 <data name='scaffolds_agp' format='tabular' label='Scaffolds (Agp)'>
198 <filter>paired_reads == 'true' and no != '-no'</filter>
199 </data>
200 <data name='tag_pair_align' format='txt' label='Tag Pair Alignments'>
201 <filter>pair == '-pair' and paired_reads == 'true' and no != '-no'</filter>
202 </data>
203 <data name='trim_status' format='tabular' label='Trim Status'/>
204
205 <data name='isotigs_ace' format='ace' label='Isotigs (Ace)'>
206 <filter>ace != '' and no != '-no'</filter>
207 </data>
208 <data name='isotigs_fasta' format='fasta' label='Isotigs (Fasta)'>
209 <filter>no != '-no'</filter>
210 </data>
211 <data name='isotigs_qual' format='qual454' label='Isotigs (Qual454)'>
212 <filter>no != '-no'</filter>
213 </data>
214 <data name='isotigs_agp' format='tabular' label='Isotigs (Agp)'>
215 <filter>no != '-no'</filter>
216 </data>
217 <data name='isotigs_layout' format='txt' label='Isotig Layout'>
218 <filter>no != '-no'</filter>
219 </data>
220
221 </outputs>
222 <help>
223
224 **What it does**
225
226 Assemble (Roche/454) reads using Newbler.
227
228 Download the manual here: http://galaxy.jgi-psf.org/static/manuals/GSFLXSystemSoftwareManual_PartC_Assembler-Mapper-SFFTools.pdf
229
230 .. class:: warningmark
231
232 **Fasta Header Format** Fasta input must provide any pairing information in the header using the expected key=value format. Use the 'Sanger tab to Newbler Fasta' tool.
233
234 </help>
235 </tool>