Mercurial > repos > edward-kirton > roche454_toolsuite

comparison roche454/runMapping_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 368a6ebebdde
comparison
equal deleted inserted replaced
-1:000000000000 0:f036c7107601
1 <tool id="runMapping_cDNA" name="runMapping cDNA" version="1.0.0">
2 <description>Map Roche/454 reads to a reference using Newbler</description>
3 <command interpreter='perl'>runMapping_cDNA_wrapper.pl
4 $newbler_metrics.extra_files_path
5 $alignment_info
6 $all_contigs_fasta
7 $all_contigs_qual
8 $all_diffs
9 $all_struct_vars
10 $hc_diff
11 $hc_struct_vars
12 $mapping_qc
13 $newbler_metrics
14 $pair_align
15 $read_status
16 $ref_status
17 $tag_pair_align
18 $trim_status
19 $trimmed_reads_fasta
20 $trimmed_reads_qual
21 $contigs_ace
22 $gene_status
23 $isotigs_ace
24 $isotigs_fasta
25 $isotigs_qual
26 $isotigs_agp
27 $isotigs_layout
28 $newbler_exe -o $newbler_metrics.extra_files_path
29 -cpu 8
30 -a $a
31 -e $e
32 -mi $mi
33 -ml $ml
34 -minlen $minlen
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 -rst $rst
49 -hsl $hsl
50 -mcf $mcf
51 -vs $vs
52 -vt $vt
53 -fi $fi
54 -fe $fe
55 -cdna
56 $srv
57 -ig $ig
58 -it $it
59 -icc $icc
60 -icl $icl
61 $ref_type
62 -ref
63 #for $i in $ref_inputs
64 ${i.ref_input}
65 #end for
66 -read
67 #for $i in $sff_paired_inputs
68 -p ${i.sff_paired_input}
69 #end for
70 #for $i in $sanger_paired_inputs
71 -p ${i.sanger_paired_input}
72 #end for
73 #for $i in $sff_inputs
74 ${i.sff_input}
75 #end for
76 #for $i in $sanger_inputs
77 ${i.sanger_input}
78 #end for
79 </command>
80 <inputs>
81 <!-- NEWBLER VERSION -->
82 <param name='newbler_exe' type='select' display='radio' label='Newbler version'>
83 <option value='runMapping' selected='true'>default</option>
84 <!-- OTHER VERSIONS MAY BE INCLUDED HERE; OR SIMPLY EDIT TO REMOVE THIS ENTIRE SECTION
85 <option value='/jgi/tools/454/rig-DataProcessing_2.3/bin/runMapping'>2.3</option>
86 <option value='/jgi/tools/454/rig-DataProcessing_2.4pre-20091204/bin/runMapping'>2.4</option>
87 <option value='/home/copeland/local/x86_64/newbler/v2.5p1-internal-10Jun23-1/runMapping'>2.5</option>
88 -->
89 </param>
90
91 <!-- READSEQ INFILES -->
92 <repeat name="sff_inputs" title="Unpaired Reads Sff Files">
93 <param name="sff_input" type="data" format="sff" label="SE Sff file"/>
94 </repeat>
95 <repeat name="sanger_inputs" title="Unpaired Reads Fasta Files">
96 <param name="sanger_input" type="data" format="fasta" label="SE Fasta file"/>
97 </repeat>
98 <repeat name="sff_paired_inputs" title="Paired Reads Sff Files">
99 <param name="sff_paired_input" type="data" format="sff" label="PE Sff file"/>
100 </repeat>
101 <repeat name="sanger_paired_inputs" title="Paired Reads Fasta Files">
102 <param name="sanger_paired_input" type="data" format="fasta" label="PE Fasta file"/>
103 </repeat>
104 <param name='paired_reads' type='select' display='radio' label='[-paired_reads] If supplying paired reads (above), do you want paired-read info?'>
105 <option value='false'>no</option>
106 <option value='true'>[-paired_reads] yes</option>
107 </param>
108 <param name='pair' type='select' display='radio' label='[-pair] Output pairwise overlaps'>
109 <option value=''>no</option>
110 <option value='-pair'>[-pair] yes</option>
111 </param>
112
113 <!-- SOURCE DNA TYPE -->
114 <param name='it' type='integer' value='100' label='[-it] Specify the maximum number of isotigs in an isogroup. Maximum is 10,000.'/>
115 <param name='ig' type='integer' value='500' label='[-ig] Specify the maximum number of contigs in an isogroup.'/>
116 <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'/>
117 <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.'/>
118
119 <!-- INPUTS SPECIFIC TO MAPPING -->
120 <repeat name='ref_inputs' title='Reference Sequence'>
121 <param name='ref_input' type='data' format='fasta' label='Fasta file'/>
122 </repeat>
123 <param name='ref_type' type='select' display='radio' label='Reference type'>
124 <option value='-gref'>[-gref] Genomic reference sequence</option>
125 <option value='-cref'>[-cref] cDNA reference sequence</option>
126 </param>
127 <param name='rst' type='integer' value='12' label='[-rst] Repeat score threshold parameter. Allowed values: 0 or greater'/>
128 <param name='hsl' type='integer' value='70' label='[-hsl] Hit-per-seed limit parameter'/>
129 <param name='srv' type='boolean' truevalue='-srv' falsevalue='' checked='false' label='[-srv] Single read variant output'/>
130
131 <!-- OPTIONAL ARGUMENTS -->
132 <!-- NYI
133 <param name='accno' type='data' format='tabular' optional='true' label='[-accno] Specify annotation data. Required only if reference sequence headers do not contain gene=NAME pairs' />
134 <param name='annot' type='data' format='tabular' optional='true' label='[-annot] Supply gene, transcript, and protein information' />
135 -->
136 <param name='mcf' type='data' format='tabular' optional='true' label='[-mcf] Specify non-default MID config file' />
137 <param name='fi' type='data' format='txt' optional='true' label='[-fi] Include filter file to be specified' />
138 <param name='fe' type='data' format='txt' optional='true' label='[-fe] Exclude filter file to be specified' />
139 <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)" />
140 <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" />
141
142 <!-- READ TRIMMING -->
143 <param name='minlen' type='integer' value='20' label='[-minlen] Minimum length of reads to use (15-45 allowed)'/>
144 <param name='notrim' type='boolean' truevalue='-notrim' falsevalue='' checked='false' label='[-notrim] Do not perform default quality and primer trimming of input reads'/>
145 <param name='tr' type='select' display='radio' label='[-tr] Output trimmed reads'>
146 <option value=''>no</option>
147 <option value='-tr'>[-tr] yes</option>
148 </param>
149 <param name='nor' type='boolean' truevalue='-nor' falsevalue='' label='[-nor] Turn off the automatic rescore function for read quality scores'/>
150 <param name='ud' type='boolean' truevalue='-ud' falsevalue='' label='[-ud] Treat each read separately, with no grouping of duplicates'/>
151
152 <!-- ALIGNMENT PARAMETERS -->
153 <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'/>
154 <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'/>
155 <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'/>
156 <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"/>
157 <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"/>
158 <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'/>
159
160 <!-- ASSEMBLY OPTIONS -->
161 <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"/>
162
163 <!-- OUTPUT OPTIONS -->
164 <param name='no' type='select' display='radio' label='[-no] Do complete assembly'>
165 <option value=''>do complete assembly</option>
166 <option value='-no'>[-no] do not assemble; do alignments only</option>
167 </param>
168 <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'/>
169 <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."/>
170 <param name='info' type='select' display='radio' label='Output Alignment Info'>
171 <option value='-info'>[-info] yes</option>
172 <option value='-infoall'>[-infoall] yes, including 0-coverage positions</option>
173 </param>
174 <param name='ace' type='select' display='radio' label='Produce Ace assembly file'>
175 <option value=''>no</option>
176 <option value='-ace'>[-ace] yes</option>
177 </param>
178 </inputs>
179
180 <outputs>
181 <!-- the following are common to runMapping and runAssembly -->
182 <data name='newbler_metrics' format='txt' />
183 <data name='read_status' format='tabular' label='Read Status'/>
184 <data name='trimmed_reads_fasta' format='fasta' label='Trimmed Reads (Fasta)'>
185 <filter>tr == '-tr'</filter>
186 </data>
187 <data name='trimmed_reads_qual' format='qual454' label='Trimmed Reads (Qual)'>
188 <filter>tr == '-tr'</filter>
189 </data>
190 <!-- the following produced only if no != '-no' -->
191 <data name='alignment_info' format='tabular' label='Alignment Info'/>
192 <data name='all_contigs_fasta' format='fasta' label='All Contigs (Fasta)'>
193 <filter>no != '-no'</filter>
194 </data>
195 <data name='all_contigs_qual' format='qual454' label='All Contigs (Qual454)'>
196 <filter>no != '-no'</filter>
197 </data>
198 <data name='contigs_ace' format='ace' label='Contigs (Ace)'>
199 <filter>ace == '-ace' and no != '-no'</filter>
200 </data>
201 <data name='pair_align' format='txt' label='Pairwise Alignments'>
202 <filter>pair == '-pair' and no != '-no'</filter>
203 </data>
204 <data name='pair_status' format='tabular' label='Paired-End Read Status'>
205 <filter>paired_reads == 'true' and no != '-no'</filter>
206 </data>
207 <data name='scaffolds_fasta' format='fasta' label='Scaffolds (Fasta)'>
208 <filter>paired_reads == 'true' and no != '-no'</filter>
209 </data>
210 <data name='scaffolds_qual' format='qual454' label='Scaffolds (Qual454)'>
211 <filter>paired_reads == 'true' and no != '-no'</filter>
212 </data>
213 <data name='scaffolds_agp' format='tabular' label='Scaffolds (Agp)'>
214 <filter>paired_reads == 'true' and no != '-no'</filter>
215 </data>
216 <data name='tag_pair_align' format='txt' label='Tag Pair Alignments'>
217 <filter>pair == '-pair' and paired_reads == 'true' and no != '-no'</filter>
218 </data>
219 <data name='trim_status' format='tabular' label='Trim Status'/>
220
221 <!-- THE FOLLOWING ARE LIMITED TO MAPPING -->
222 <data name='all_diffs' format='tabular' label='All Diffs'/>
223 <data name='all_struct_vars' format='tabular' label='All Struct Vars'/>
224 <data name='hc_diff' format='tabular' label='High Confidence Diff'/>
225 <data name='hc_struct_vars' format='tabular' label='High Confidence Struct Vars'/>
226 <data name='gene_status' format='tabular' label='Gene Status'/>
227 <data name='mapping_qc' format='xls' label='Mapping QC (Excel)'/>
228 <data name='ref_status' format='tabular' label='Ref Status'/>
229
230 <!-- ISOTIGS -->
231 <data name='isotigs_ace' format='ace' label='Isotigs (Ace)'>
232 <filter>ace != '' and no != '-no'</filter>
233 </data>
234 <data name='isotigs_fasta' format='fasta' label='Isotigs (Fasta)'>
235 <filter>no != '-no'</filter>
236 </data>
237 <data name='isotigs_qual' format='qual454' label='Isotigs (Qual454)'>
238 <filter>no != '-no'</filter>
239 </data>
240 <data name='isotigs_agp' format='tabular' label='Isotigs (Agp)'>
241 <filter>no != '-no'</filter>
242 </data>
243 <data name='isotigs_layout' format='txt' label='Isotig Layout'>
244 <filter>no != '-no'</filter>
245 </data>
246
247 </outputs>
248 <help>
249
250 **What it does**
251
252 Map (Roche/454) reads to a reference using Newbler.
253
254 Download the manual here: http://galaxy.jgi-psf.org/static/manuals/GSFLXSystemSoftwareManual_PartC_Assembler-Mapper-SFFTools.pdf
255
256 .. class:: warningmark
257
258 **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.
259
260 </help>
261 </tool>