Mercurial > repos > edward-kirton > roche454_toolsuite

comparison runMapping.xml @ 2:2d86d5b112e8

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author edward-kirton
date Thu, 14 Jul 2011 22:14:07 -0400
parents
children bf1f8bc4abe6
comparison
equal deleted inserted replaced
1:368a6ebebdde 2:2d86d5b112e8
1 <tool id="runMapping" name="runMapping" version="1.0.0">
2 <description>Map Roche/454 reads to a reference using Newbler</description>
3 <command interpreter='perl'>runMapping_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 $large_contigs_fasta
23 $large_contigs_qual
24 $gene_status
25 $newbler_exe -o $newbler_metrics.extra_files_path
26 -cpu 8
27 -a $a
28 -e $e
29 -mi $mi
30 -ml $ml
31 -minlen $minlen
32 $pair
33 $info
34 $notrim
35 $tr
36 $ace
37 $no
38 $qo
39 $nor
40 $ud
41 -ss $ss
42 -sl $sl
43 -sc $sc
44 -ais $ais
45 -rst $rst
46 -hsl $hsl
47 -mcf $mcf
48 -vs $vs
49 -vt $vt
50 -fi $fi
51 -fe $fe
52 -l $l
53 $ref_type
54 -ref
55 #for $i in $ref_inputs
56 ${i.ref_input}
57 #end for
58 -read
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='/jgi/tools/454/rig-DataProcessing_2.3/bin/runMapping'>2.3</option>
76 <option value='/jgi/tools/454/rig-DataProcessing_2.4pre-20091204/bin/runMapping'>2.4</option>
77 <option value='/home/copeland/local/x86_64/newbler/v2.5p1-internal-10Jun23-1/runMapping' selected='true'>2.5</option>
78 </param>
79
80 <!-- READSEQ INFILES -->
81 <repeat name="sff_inputs" title="Unpaired Reads Sff Files">
82 <param name="sff_input" type="data" format="sff" label="SE Sff file"/>
83 </repeat>
84 <repeat name="sanger_inputs" title="Unpaired Reads Fasta Files">
85 <param name="sanger_input" type="data" format="fasta" label="SE Fasta file"/>
86 </repeat>
87 <repeat name="sff_paired_inputs" title="Paired Reads Sff Files">
88 <param name="sff_paired_input" type="data" format="sff" label="PE Sff file"/>
89 </repeat>
90 <repeat name="sanger_paired_inputs" title="Paired Reads Fasta Files">
91 <param name="sanger_paired_input" type="data" format="fasta" label="PE Fasta file"/>
92 </repeat>
93 <param name='paired_reads' type='select' display='radio' label='[-paired_reads] If supplying paired reads (above), do you want paired-read info?'>
94 <option value='false'>no</option>
95 <option value='true'>[-paired_reads] yes</option>
96 </param>
97 <param name='pair' type='select' display='radio' label='[-pair] Output pairwise overlaps'>
98 <option value=''>no</option>
99 <option value='-pair'>[-pair] yes</option>
100 </param>
101
102 <!-- SOURCE DNA TYPE -->
103 <param name='l' type="integer" value='500' label="[-l] This option sets the minimum length for a contig to appear in the 454LargeContigs.fna file"/>
104
105 <!-- INPUTS SPECIFIC TO MAPPING -->
106 <repeat name='ref_inputs' title='Reference Sequence'>
107 <param name='ref_input' type='data' format='fasta' label='Fasta file'/>
108 </repeat>
109 <param name='ref_type' type='select' display='radio' label='Reference type'>
110 <option value='-gref'>[-gref] Genomic reference sequence</option>
111 <option value='-cref'>[-cref] cDNA reference sequence</option>
112 </param>
113 <param name='rst' type='integer' value='12' label='[-rst] Repeat score threshold parameter. Allowed values: 0 or greater'/>
114 <param name='hsl' type='integer' value='70' label='[-hsl] Hit-per-seed limit parameter'/>
115 <param name='srv' type='boolean' truevalue='-srv' falsevalue='' checked='false' label='[-srv] Single read variant output'/>
116
117 <!-- OPTIONAL ARGUMENTS -->
118 <!-- NYI
119 <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' />
120 <param name='annot' type='data' format='tabular' optional='true' label='[-annot] Supply gene, transcript, and protein information' />
121 -->
122 <param name='mcf' type='data' format='tabular' optional='true' label='[-mcf] Specify non-default MID config file' />
123 <param name='fi' type='data' format='txt' optional='true' label='[-fi] Include filter file to be specified' />
124 <param name='fe' type='data' format='txt' optional='true' label='[-fe] Exclude filter file to be specified' />
125 <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)" />
126 <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" />
127
128
129 <!-- READ TRIMMING -->
130 <param name='minlen' type='integer' value='20' label='[-minlen] Minimum length of reads to use (15-45 allowed)'/>
131 <param name='notrim' type='boolean' truevalue='-notrim' falsevalue='' checked='false' label='[-notrim] Do not perform default quality and primer trimming of input reads'/>
132 <param name='tr' type='select' display='radio' label='[-tr] Output trimmed reads'>
133 <option value=''>no</option>
134 <option value='-tr'>[-tr] yes</option>
135 </param>
136 <param name='nor' type='boolean' truevalue='-nor' falsevalue='' label='[-nor] Turn off the automatic rescore function for read quality scores'/>
137 <param name='ud' type='boolean' truevalue='-ud' falsevalue='' label='[-ud] Treat each read separately, with no grouping of duplicates'/>
138
139 <!-- ALIGNMENT PARAMETERS -->
140 <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'/>
141 <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'/>
142 <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'/>
143 <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"/>
144 <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"/>
145 <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'/>
146
147 <!-- ASSEMBLY OPTIONS -->
148 <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"/>
149
150 <!-- OUTPUT OPTIONS -->
151 <param name='no' type='select' display='radio' label='[-no] Do complete assembly'>
152 <option value=''>do complete assembly</option>
153 <option value='-no'>[-no] do not assemble; do alignments only</option>
154 </param>
155 <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'/>
156 <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."/>
157 <param name='info' type='select' display='radio' label='Output Alignment Info'>
158 <option value='-info'>[-info] yes</option>
159 <option value='-infoall'>[-infoall] yes, including 0-coverage positions</option>
160 </param>
161 <param name='ace' type='select' display='radio' label='Produce Ace assembly file'>
162 <option value=''>no</option>
163 <option value='-ace'>[-ace] yes</option>
164 </param>
165 </inputs>
166
167 <outputs>
168 <!-- the following are common to runMapping and runAssembly -->
169 <data name='newbler_metrics' format='txt' />
170 <data name='read_status' format='tabular' label='Read Status'/>
171 <data name='trimmed_reads_fasta' format='fasta' label='Trimmed Reads (Fasta)'>
172 <filter>tr == '-tr'</filter>
173 </data>
174 <data name='trimmed_reads_qual' format='qual454' label='Trimmed Reads (Qual)'>
175 <filter>tr == '-tr'</filter>
176 </data>
177 <!-- the following produced only if no != '-no' -->
178 <data name='alignment_info' format='tabular' label='Alignment Info'/>
179 <data name='all_contigs_fasta' format='fasta' label='All Contigs (Fasta)'>
180 <filter>no != '-no'</filter>
181 </data>
182 <data name='all_contigs_qual' format='qual454' label='All Contigs (Qual454)'>
183 <filter>no != '-no'</filter>
184 </data>
185 <data name='contigs_ace' format='ace' label='Contigs (Ace)'>
186 <filter>ace == '-ace' and no != '-no'</filter>
187 </data>
188 <data name='large_contigs_fasta' format='fasta' label='Large Contigs (Fasta)'>
189 <filter>no != '-no'</filter>
190 </data>
191 <data name='large_contigs_qual' format='qual454' label='Large Contigs (Qual454)'>
192 <filter>no != '-no'</filter>
193 </data>
194 <data name='pair_align' format='txt' label='Pairwise Alignments'>
195 <filter>pair == '-pair' and no != '-no'</filter>
196 </data>
197 <data name='pair_status' format='tabular' label='Paired-End Read Status'>
198 <filter>paired_reads == 'true' and no != '-no'</filter>
199 </data>
200 <data name='scaffolds_fasta' format='fasta' label='Scaffolds (Fasta)'>
201 <filter>paired_reads == 'true' and no != '-no'</filter>
202 </data>
203 <data name='scaffolds_qual' format='qual454' label='Scaffolds (Qual454)'>
204 <filter>paired_reads == 'true' and no != '-no'</filter>
205 </data>
206 <data name='scaffolds_agp' format='tabular' label='Scaffolds (Agp)'>
207 <filter>paired_reads == 'true' and no != '-no'</filter>
208 </data>
209 <data name='tag_pair_align' format='txt' label='Tag Pair Alignments'>
210 <filter>pair == '-pair' and paired_reads == 'true' and no != '-no'</filter>
211 </data>
212 <data name='trim_status' format='tabular' label='Trim Status'/>
213
214 <!-- THE FOLLOWING ARE LIMITED TO MAPPING -->
215 <data name='all_diffs' format='tabular' label='All Diffs'/>
216 <data name='all_struct_vars' format='tabular' label='All Struct Vars'/>
217 <data name='hc_diff' format='tabular' label='High Confidence Diff'/>
218 <data name='hc_struct_vars' format='tabular' label='High Confidence Struct Vars'/>
219 <data name='gene_status' format='tabular' label='Gene Status'/>
220 <data name='mapping_qc' format='xls' label='Mapping QC (Excel)'/>
221 <data name='ref_status' format='tabular' label='Ref Status'/>
222
223 </outputs>
224 <help>
225
226 **What it does**
227
228 Map (Roche/454) reads to a reference using Newbler.
229
230 Download the manual here: http://galaxy.jgi-psf.org/static/manuals/GSFLXSystemSoftwareManual_PartC_Assembler-Mapper-SFFTools.pdf
231
232 .. class:: warningmark
233
234 **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.
235
236 </help>
237 </tool>