annotate tophat2_wrapper.xml @ 0:92e9168067b6 default tip

commit
author ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
date Thu, 22 Oct 2015 16:02:19 +0900
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
1 <tool id="tophat2" name="Tophat2" version="0.7">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
2 <!-- Wrapper compatible with Tophat version 2.0.0+ -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
3 <description>Gapped-read mapper for RNA-seq data</description>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
4 <version_command>tophat2 --version</version_command>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
5 <requirements>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
6 <container type="docker">nasuno/tophat2:2.0.9</container>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
7 <!--
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
8 <requirement type="package" version="0.1.18">samtools</requirement>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
9 <requirement type="package" version="2.1.0">bowtie2</requirement>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
10 <requirement type="package" version="2.0.9">tophat2</requirement>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
11 -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
12 </requirements>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
13
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
14 <command>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
15 ##
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
16 ## Set path to index, building the reference if necessary.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
17 ##
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
18
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
19 #set index_path = ''
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
20 #if $refGenomeSource.genomeSource == "history":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
21 bowtie2-build "$refGenomeSource.ownFile" genome ; ln -s "$refGenomeSource.ownFile" genome.fa ;
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
22 #set index_path = 'genome'
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
23 #else:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
24 #set index_path = $refGenomeSource.index.fields.path
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
25 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
26
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
27 ##
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
28 ## Run tophat.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
29 ##
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
30
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
31 tophat2
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
32
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
33 ## Change this to accommodate the number of threads you have available.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
34 --num-threads \${GALAXY_SLOTS:-4}
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
35
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
36 ## Set params.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
37 #if $params.settingsType == "full":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
38 --read-mismatches $params.read_mismatches
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
39 #if str($params.bowtie_n) == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
40 --bowtie-n
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
41 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
42
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
43 --read-edit-dist $params.read_edit_dist
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
44 --read-realign-edit-dist $params.read_realign_edit_dist
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
45 -a $params.anchor_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
46 -m $params.splice_mismatches
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
47 -i $params.min_intron_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
48 -I $params.max_intron_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
49 -g $params.max_multihits
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
50 --min-segment-intron $params.min_segment_intron
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
51 --max-segment-intron $params.max_segment_intron
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
52 --segment-mismatches $params.seg_mismatches
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
53 --segment-length $params.seg_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
54 --library-type $params.library_type
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
55
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
56 ## Indel search.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
57 #if $params.indel_search.allow_indel_search == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
58 ## --allow-indels
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
59 --max-insertion-length $params.indel_search.max_insertion_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
60 --max-deletion-length $params.indel_search.max_deletion_length
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
61 #else:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
62 --no-novel-indels
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
63 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
64
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
65 ## Supplying junctions parameters.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
66 #if $params.own_junctions.use_junctions == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
67 #if $params.own_junctions.gene_model_ann.use_annotations == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
68 -G $params.own_junctions.gene_model_ann.gene_annotation_model
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
69 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
70 #if $params.own_junctions.raw_juncs.use_juncs == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
71 -j $params.own_junctions.raw_juncs.raw_juncs
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
72 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
73 #if str($params.own_junctions.no_novel_juncs) == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
74 --no-novel-juncs
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
75 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
76 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
77
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
78 #if $params.coverage_search.use_search == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
79 --coverage-search
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
80 --min-coverage-intron $params.coverage_search.min_coverage_intron
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
81 --max-coverage-intron $params.coverage_search.max_coverage_intron
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
82 #else:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
83 --no-coverage-search
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
84 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
85
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
86 #if str($params.microexon_search) == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
87 --microexon-search
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
88 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
89
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
90 #if $params.fusion_search.do_search == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
91 --fusion-search
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
92 --fusion-anchor-length $params.fusion_search.anchor_len
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
93 --fusion-min-dist $params.fusion_search.min_dist
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
94 --fusion-read-mismatches $params.fusion_search.read_mismatches
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
95 --fusion-multireads $params.fusion_search.multireads
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
96 --fusion-multipairs $params.fusion_search.multipairs
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
97 --fusion-ignore-chromosomes "$params.fusion_search.ignore_chromosomes"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
98 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
99
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
100 #if $params.bowtie2_settings.b2_settings == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
101 #if $params.bowtie2_settings.preset.b2_preset == "Yes":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
102 --b2-$params.bowtie2_settings.preset.b2_preset_select
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
103 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
104 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
105
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
106 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
107
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
108 ## Read group information.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
109 #if $readGroup.specReadGroup == "yes"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
110 --rg-id "$readGroup.rgid"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
111 --rg-library "$readGroup.rglb"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
112 --rg-platform "$readGroup.rgpl"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
113 --rg-sample "$readGroup.rgsm"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
114 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
115
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
116 ## Set index path, inputs and parameters specific to paired data.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
117 #if $singlePaired.sPaired != "single"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
118 -r $singlePaired.mate_inner_distance
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
119 --mate-std-dev=$singlePaired.mate_std_dev
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
120
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
121 #if str($singlePaired.report_discordant_pairs) == "No":
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
122 --no-discordant
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
123 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
124
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
125 #if $singlePaired.sPaired == "paired"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
126 ${index_path} "$singlePaired.input1" "$singlePaired.input2"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
127 #else
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
128 ${index_path} "$singlePaired.input.forward" "$singlePaired.input.reverse"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
129 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
130 #else
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
131 ${index_path} "$singlePaired.input1"
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
132 #end if
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
133 </command>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
134
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
135 <inputs>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
136 <conditional name="singlePaired">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
137 <param name="sPaired" type="select" label="Is this library mate-paired?">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
138 <option value="single">Single-end</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
139 <option value="paired">Paired-end (as individual datasets)</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
140 <option value="paired_collection">Paired-end (as collection)</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
141 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
142 <when value="single">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
143 <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
144 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
145 <when value="paired">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
146 <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
147 <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
148 <expand macro="paired_parameters" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
149 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
150 <when value="paired_collection">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
151 <param format="fastqsanger" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ paired reads" help="Nucleotide-space: Must have Sanger-scaled quality values with ASCII offset 33" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
152 <expand macro="paired_parameters" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
153 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
154 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
155 <expand macro="refGenomeSourceConditional">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
156 <options from_data_table="tophat2_indexes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
157 <filter type="sort_by" column="2"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
158 <validator type="no_options" message="No genomes are available for the selected input dataset"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
159 </options>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
160 </expand>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
161 <conditional name="params">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
162 <param name="settingsType" type="select" label="TopHat settings to use" help="You can use the default settings or set custom values for any of Tophat's parameters.">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
163 <option value="preSet">Use Defaults</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
164 <option value="full">Full parameter list</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
165 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
166 <when value="preSet" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
167 <!-- Full/advanced params. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
168 <when value="full">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
169 <param name="read_realign_edit_dist" type="integer" value="1000" label="Max realign edit distance" help="Some of the reads spanning multiple exons may be mapped incorrectly as a contiguous alignment to the genome even though the correct alignment should be a spliced one - this can happen in the presence of processed pseudogenes that are rarely (if at all) transcribed or expressed. This option can direct TopHat to re-align reads for which the edit distance of an alignment obtained in a previous mapping step is above or equal to this option value. If you set this option to 0, TopHat will map every read in all the mapping steps (transcriptome if you provided gene annotations, genome, and finally splice variants detected by TopHat), reporting the best possible alignment found in any of these mapping steps. This may greatly increase the mapping accuracy at the expense of an increase in running time. The default value for this option is set such that TopHat will not try to realign reads already mapped in earlier steps." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
170
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
171 <param name="read_edit_dist" type="integer" value="2" label="Max edit distance" help="Final read alignments having more than these many edit distance are discarded." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
172
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
173 <param name="library_type" type="select" label="Library Type" help="TopHat will treat the reads as strand specific. Every read alignment will have an XS attribute tag. Consider supplying library type options below to select the correct RNA-seq protocol.">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
174 <option value="fr-unstranded">FR Unstranded</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
175 <option value="fr-firststrand">FR First Strand</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
176 <option value="fr-secondstrand">FR Second Strand</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
177 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
178 <param name="read_mismatches" type="integer" value="2" label="Final read mismatches" help="Final read alignments having more than these many mismatches are discarded." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
179 <param name="bowtie_n" type="select" label="Use bowtie -n mode">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
180 <option selected="true" value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
181 <option value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
182 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
183 <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="Report junctions spanned by reads with at least this many bases on each side of the junction." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
184 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
185 <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="TopHat will ignore donor/acceptor pairs closer than this many bases apart." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
186 <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
187 <expand macro="indel_searchConditional" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
188 alignments (number of reads divided by average depth of coverage)" help="0.0 to 1.0 (0 to turn off)" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
189 <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
190 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
191 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
192 <param name="seg_mismatches" type="integer" min="0" max="3" value="2" label="Number of mismatches allowed in each segment alignment for reads mapped independently" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
193 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
194
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
195 <!-- Options for supplying own junctions. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
196 <expand macro="own_junctionsConditional" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
197 <!-- Coverage search. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
198 <conditional name="coverage_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
199 <param name="use_search" type="select" label="Use Coverage Search" help="Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
200 <option selected="true" value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
201 <option value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
202 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
203 <when value="Yes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
204 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
205 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
206 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
207 <when value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
208 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
209
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
210 <!-- Microexon search params -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
211 <param name="microexon_search" type="select" label="Use Microexon Search" help="With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
212 <option value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
213 <option value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
214 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
215
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
216 <!-- Fusion mapping. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
217 <conditional name="fusion_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
218 <param name="do_search" type="select" label="Do Fusion Search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
219 <option selected="true" value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
220 <option value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
221 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
222 <when value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
223 <when value="Yes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
224 <param name="anchor_len" type="integer" value="20" label="Anchor Length" help="A 'supporting' read must map to both sides of a fusion by at least this many bases."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
225 <param name="min_dist" type="integer" value="10000000" label="Minimum Distance" help="For intra-chromosomal fusions, TopHat-Fusion tries to find fusions separated by at least this distance."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
226 <param name="read_mismatches" type="integer" value="2" label="Read Mismatches" help="Reads support fusions if they map across fusion with at most this many mismatches."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
227 <param name="multireads" type="integer" value="2" label="Multireads" help="Reads that map to more than this many places will be ignored. It may be possible that a fusion is supported by reads (or pairs) that map to multiple places."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
228 <param name="multipairs" type="integer" value="2" label="Multipairs" help="Pairs that map to more than this many places will be ignored."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
229 <param name="ignore_chromosomes" type="text" value='' label="Ignore some chromosomes such as chrM when detecting fusion break points"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
230 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
231 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
232
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
233 <!-- Bowtie2 settings. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
234 <conditional name="bowtie2_settings">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
235 <param name="b2_settings" type="select" label="Set Bowtie2 settings">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
236 <option selected="true" value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
237 <option value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
238 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
239 <when value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
240 <when value="Yes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
241 <conditional name="preset">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
242 <param name="b2_preset" type="select" label="Use Preset options">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
243 <option selected="true" value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
244 <option value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
245 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
246 <when value="Yes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
247 <param name="b2_preset_select" type="select" label="Preset option">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
248 <option value="very-fast">Very fast</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
249 <option value="fast">Fast</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
250 <option selected="true" value="sensitive">Sensitive</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
251 <option value="very-sensitive">Very sensitive</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
252 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
253 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
254 <!-- TODO: -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
255 <when value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
256 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
257 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
258 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
259 </when> <!-- full -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
260 </conditional> <!-- params -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
261 <conditional name="readGroup">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
262 <param name="specReadGroup" type="select" label="Specify read group?">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
263 <option value="yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
264 <option value="no" selected="True">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
265 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
266 <when value="yes">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
267 <param name="rgid" type="text" size="25" label="Read group identifier (ID). Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section." help="Required if RG specified. Read group IDs may be modified when merging SAM files in order to handle collisions." />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
268 <param name="rglb" type="text" size="25" label="Library name (LB)" help="Required if RG specified" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
269 <param name="rgpl" type="text" size="25" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
270 <param name="rgsm" type="text" size="25" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
271 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
272 <when value="no" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
273 </conditional> <!-- readGroup -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
274 </inputs>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
275
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
276 <stdio>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
277 <regex match="Exception|Error" source="both" level="fatal" description="Tool execution failed"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
278 <regex match=".*" source="both" level="log" description="tool progress"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
279 </stdio>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
280
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
281 <outputs>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
282 <data format="txt" name="align_summary" label="${tool.name} on ${on_string}: align_summary" from_work_dir="tophat_out/align_summary.txt"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
283 <data format="tabular" name="fusions" label="${tool.name} on ${on_string}: fusions" from_work_dir="tophat_out/fusions.out">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
284 <filter>(params['settingsType'] == 'full' and params['fusion_search']['do_search'] == 'Yes')</filter>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
285 </data>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
286 <data format="bed" name="insertions" label="${tool.name} on ${on_string}: insertions" from_work_dir="tophat_out/insertions.bed">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
287 <expand macro="dbKeyActions" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
288 </data>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
289 <data format="bed" name="deletions" label="${tool.name} on ${on_string}: deletions" from_work_dir="tophat_out/deletions.bed">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
290 <expand macro="dbKeyActions" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
291 </data>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
292 <data format="bed" name="junctions" label="${tool.name} on ${on_string}: splice junctions" from_work_dir="tophat_out/junctions.bed">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
293 <expand macro="dbKeyActions" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
294 </data>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
295 <data format="bam" name="accepted_hits" label="${tool.name} on ${on_string}: accepted_hits" from_work_dir="tophat_out/accepted_hits.bam">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
296 <expand macro="dbKeyActions" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
297 </data>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
298 </outputs>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
299
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
300 <macros>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
301 <import>tophat_macros.xml</import>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
302 <xml name="paired_parameters">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
303 <param name="mate_inner_distance" type="integer" value="300" label="Mean Inner Distance between Mate Pairs" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
304 <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="The standard deviation for the distribution on inner distances between mate pairs."/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
305 <!-- Discordant pairs. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
306 <param name="report_discordant_pairs" type="select" label="Report discordant pair alignments?">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
307 <option value="No">No</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
308 <option selected="True" value="Yes">Yes</option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
309 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
310 </xml>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
311 <macro name="dbKeyActions">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
312 <actions>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
313 <conditional name="refGenomeSource.genomeSource">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
314 <when value="indexed">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
315 <action type="metadata" name="dbkey">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
316 <option type="from_data_table" name="tophat2_indexes" column="1" offset="0">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
317 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
318 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
319 </option>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
320 </action>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
321 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
322 <when value="history">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
323 <action type="metadata" name="dbkey">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
324 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
325 </action>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
326 </when>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
327 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
328 </actions>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
329 </macro>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
330 </macros>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
331
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
332 <tests>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
333 <!-- Test base-space single-end reads with pre-built index and preset parameters -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
334 <test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
335 <!-- TopHat commands:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
336 tophat2 -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
337 Rename the files in tmp_dir appropriately
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
338 -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
339 <param name="sPaired" value="single" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
340 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
341 <param name="genomeSource" value="indexed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
342 <param name="index" value="tophat_test" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
343 <param name="settingsType" value="preSet" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
344 <param name="specReadGroup" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
345 <output name="junctions" file="tophat2_out1j.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
346 <output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
347 </test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
348 <!-- Test using base-space test data: paired-end reads, index from history. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
349 <test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
350 <!-- TopHat commands:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
351 bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
352 tophat2 -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
353 Rename the files in tmp_dir appropriately
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
354 -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
355 <param name="sPaired" value="paired" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
356 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
357 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
358 <param name="genomeSource" value="history" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
359 <param name="ownFile" ftype="fasta" value="tophat_in1.fasta" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
360 <param name="mate_inner_distance" value="20" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
361 <param name="settingsType" value="preSet" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
362 <param name="specReadGroup" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
363 <output name="junctions" file="tophat2_out2j.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
364 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
365 </test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
366 <test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
367 <!-- Same test as above but with a collection. -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
368 <param name="sPaired" value="paired_collection" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
369 <param name="input">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
370 <collection type="paired">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
371 <element name="forward" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
372 <element name="reverse" value="tophat_in3.fastqsanger" ftype="fastqsanger" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
373 </collection>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
374 </param>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
375 <param name="genomeSource" value="history" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
376 <param name="ownFile" ftype="fasta" value="tophat_in1.fasta" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
377 <param name="mate_inner_distance" value="20" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
378 <param name="settingsType" value="preSet" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
379 <param name="specReadGroup" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
380 <output name="junctions" file="tophat2_out2j.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
381 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
382 </test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
383 <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
384 <test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
385 <!-- Tophat commands:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
386 bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
387 tophat2 -o tmp_dir -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search tophat_in1 test-data/tophat_in2.fastqsanger
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
388 Replace the + with double-dash
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
389 Rename the files in tmp_dir appropriately
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
390 -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
391 <conditional name="singlePaired">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
392 <param name="sPaired" value="single"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
393 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
394 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
395 <param name="genomeSource" value="history"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
396 <param name="ownFile" value="tophat_in1.fasta"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
397 <conditional name="params">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
398 <param name="settingsType" value="full"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
399 <param name="library_type" value="FR Unstranded"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
400 <param name="read_mismatches" value="2"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
401 <param name="bowtie_n" value="No"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
402 <param name="anchor_length" value="8"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
403 <param name="splice_mismatches" value="0"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
404 <param name="min_intron_length" value="70"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
405 <param name="max_intron_length" value="500000"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
406 <param name="max_multihits" value="40"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
407 <param name="min_segment_intron" value="50" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
408 <param name="max_segment_intron" value="500000" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
409 <param name="seg_mismatches" value="2"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
410 <param name="seg_length" value="25"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
411 <conditional name="indel_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
412 <param name="allow_indel_search" value="Yes"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
413 <param name="max_insertion_length" value="3"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
414 <param name="max_deletion_length" value="3"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
415 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
416 <conditional name="own_junctions">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
417 <param name="use_junctions" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
418 <conditional name="gene_model_ann">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
419 <param name="use_annotations" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
420 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
421 <conditional name="raw_juncs">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
422 <param name="use_juncs" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
423 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
424 <conditional name="no_novel_juncs">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
425 <param name="no_novel_juncs" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
426 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
427 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
428 <conditional name="coverage_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
429 <param name="use_search" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
430 <param name="min_coverage_intron" value="50" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
431 <param name="max_coverage_intron" value="20000" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
432 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
433 <param name="microexon_search" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
434 <conditional name="bowtie2_settings">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
435 <param name="b2_settings" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
436 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
437 <!-- Fusion search params -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
438 <conditional name="fusion_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
439 <param name="do_search" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
440 <param name="anchor_len" value="21" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
441 <param name="min_dist" value="10000021" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
442 <param name="read_mismatches" value="3" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
443 <param name="multireads" value="4" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
444 <param name="multipairs" value="5" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
445 <param name="ignore_chromosomes" value="chrM"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
446 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
447 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
448 <conditional name="readGroup">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
449 <param name="specReadGroup" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
450 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
451 <output name="insertions" file="tophat_out3i.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
452 <output name="deletions" file="tophat_out3d.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
453 <output name="junctions" file="tophat2_out3j.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
454 <output name="accepted_hits" file="tophat_out3h.bam" compare="sim_size" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
455 </test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
456 <!-- Test base-space paired-end reads with user-supplied reference fasta and full parameters -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
457 <test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
458 <!-- TopHat commands:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
459 tophat2 -o tmp_dir -r 20 -p 1 -a 8 -m 0 -i 70 -I 500000 -g 40 +coverage-search +min-coverage-intron 50 +max-coverage-intro 20000 +segment-mismatches 2 +segment-length 25 +microexon-search +report_discordant_pairs tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
460 Replace the + with double-dash
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
461 Rename the files in tmp_dir appropriately
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
462 -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
463 <conditional name="singlePaired">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
464 <param name="sPaired" value="paired"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
465 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
466 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
467 <param name="mate_inner_distance" value="20"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
468 <param name="report_discordant_pairs" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
469 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
470 <param name="genomeSource" value="indexed"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
471 <param name="index" value="tophat_test"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
472 <conditional name="params">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
473 <param name="settingsType" value="full"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
474 <param name="library_type" value="FR Unstranded"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
475 <param name="read_mismatches" value="5"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
476 <!-- Error: the read mismatches (5) and the read gap length (2) should be less than or equal to the read edit dist (2) -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
477 <param name="read_edit_dist" value="5" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
478 <param name="bowtie_n" value="Yes"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
479 <param name="mate_std_dev" value="20"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
480 <param name="anchor_length" value="8"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
481 <param name="splice_mismatches" value="0"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
482 <param name="min_intron_length" value="70"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
483 <param name="max_intron_length" value="500000"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
484 <param name="max_multihits" value="40"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
485 <param name="min_segment_intron" value="50" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
486 <param name="max_segment_intron" value="500000" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
487 <param name="seg_mismatches" value="2"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
488 <param name="seg_length" value="25"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
489 <conditional name="indel_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
490 <param name="allow_indel_search" value="No"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
491 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
492 <conditional name="own_junctions">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
493 <param name="use_junctions" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
494 <conditional name="gene_model_ann">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
495 <param name="use_annotations" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
496 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
497 <conditional name="raw_juncs">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
498 <param name="use_juncs" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
499 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
500 <conditional name="no_novel_juncs">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
501 <param name="no_novel_juncs" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
502 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
503 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
504 <conditional name="coverage_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
505 <param name="use_search" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
506 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
507 <param name="microexon_search" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
508 <conditional name="bowtie2_settings">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
509 <param name="b2_settings" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
510 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
511 <!-- Fusion search params -->
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
512 <conditional name="fusion_search">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
513 <param name="do_search" value="Yes" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
514 <param name="anchor_len" value="21" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
515 <param name="min_dist" value="10000021" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
516 <param name="read_mismatches" value="3" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
517 <param name="multireads" value="4" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
518 <param name="multipairs" value="5" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
519 <param name="ignore_chromosomes" value="chrM"/>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
520 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
521 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
522 <conditional name="readGroup">
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
523 <param name="specReadGroup" value="No" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
524 </conditional>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
525 <output name="junctions" file="tophat2_out4j.bed" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
526 <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
527 </test>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
528 </tests>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
529 <help>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
530 **Tophat Overview**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
531
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
532 TopHat_ is a fast splice junction mapper for RNA-Seq reads. It aligns RNA-Seq reads to mammalian-sized genomes using the ultra high-throughput short read aligner Bowtie(2), and then analyzes the mapping results to identify splice junctions between exons. Please cite: Kim D, Pertea G, Trapnell C, Pimentel H, Kelley R, and Salzberg SL. TopHat2: accurate alignment
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
533 of transcriptomes in the presence of insertions, deletions and gene fusions. Genome Biol 14:R36, 2013.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
534
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
535 .. _Tophat: http://ccb.jhu.edu/software/tophat/
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
536
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
537 ------
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
538
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
539 **Know what you are doing**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
540
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
541 .. class:: warningmark
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
542
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
543 There is no such thing (yet) as an automated gearshift in splice junction identification. It is all like stick-shift driving in San Francisco. In other words, running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
544
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
545 .. __: http://ccb.jhu.edu/software/tophat/manual.shtml
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
546
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
547 ------
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
548
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
549 **Input formats**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
550
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
551 Tophat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
552
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
553 ------
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
554
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
555 **Outputs**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
556
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
557 Tophat produces two output files:
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
558
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
559 - junctions -- A UCSC BED_ track of junctions reported by TopHat. Each junction consists of two connected BED blocks, where each block is as long as the maximal overhang of any read spanning the junction. The score is the number of alignments spanning the junction.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
560 - accepted_hits -- A list of read alignments in BAM_ format.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
561
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
562 .. _BED: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
563 .. _BAM: http://samtools.sourceforge.net/
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
564
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
565 Two other possible outputs, depending on the options you choose, are insertions and deletions, both of which are in BED format.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
566
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
567 -------
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
568
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
569 **Tophat settings**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
570
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
571 All of the options have a default value. You can change any of them. Some of the options in Tophat have been implemented here.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
572
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
573 ------
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
574
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
575 **Tophat parameter list**
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
576
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
577 This is a list of implemented Tophat options::
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
578
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
579 -r This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
580 selected at 300bp, where each end is 50bp, you should set -r to be 200. There is no default, and this parameter
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
581 is required for paired end runs.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
582 --mate-std-dev INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
583 -a/--min-anchor-length INT The "anchor length". TopHat will report junctions spanned by reads with at least this many bases on each side of the junction. Note that individual spliced
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
584 alignments may span a junction with fewer than this many bases on one side. However, every junction involved in spliced alignments is supported by at least one
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
585 read with this many bases on each side. This must be at least 3 and the default is 8.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
586 -m/--splice-mismatches INT The maximum number of mismatches that may appear in the "anchor" region of a spliced alignment. The default is 0.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
587 -i/--min-intron-length INT The minimum intron length. TopHat will ignore donor/acceptor pairs closer than this many bases apart. The default is 70.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
588 -I/--max-intron-length INT The maximum intron length. When searching for junctions ab initio, TopHat will ignore donor/acceptor pairs farther than this many bases apart, except when such a pair is supported by a split segment alignment of a long read. The default is 500000.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
589 -g/--max-multihits INT Instructs TopHat to allow up to this many alignments to the reference for a given read, and suppresses all alignments for reads with more than this many
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
590 alignments. The default is 40.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
591 -G/--GTF [GTF 2.2 file] Supply TopHat with a list of gene model annotations. TopHat will use the exon records in this file to build a set of known splice junctions for each gene, and will attempt to align reads to these junctions even if they would not normally be covered by the initial mapping.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
592 -j/--raw-juncs [juncs file] Supply TopHat with a list of raw junctions. Junctions are specified one per line, in a tab-delimited format. Records look like: [chrom] [left] [right] [+/-], left and right are zero-based coordinates, and specify the last character of the left sequenced to be spliced to the first character of the right sequence, inclusive.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
593 -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G)
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
594 --no-coverage-search Disables the coverage based search for junctions.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
595 --coverage-search Enables the coverage based search for junctions. Use when coverage search is disabled by default (such as for reads 75bp or longer), for maximum sensitivity.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
596 --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
597 --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
598 --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
599 --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
600 --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
601 --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
602 --max-segment-intron The maximum intron length that may be found during split-segment search. The default is 500000.
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
603 </help>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
604 <citations>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
605 <citation type="doi">10.1186/gb-2013-14-4-r36</citation>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
606 </citations>
ryotas <yamanaka@genome.rcast.u-tokyo.ac.jp>
parents:
diff changeset
607 </tool>