annotate tophat2/tophat2_wrapper.xml @ 23:4e7fe3a94ed6 draft

Uploaded
author scottx611x
date Wed, 22 Jun 2016 14:00:45 -0400
parents 2b23bfe315ea
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
1 <tool id="tophat2" name="TopHat" version="2.1.0">
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
2 <!-- Wrapper compatible with Tophat version 2.0.0+ -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
3 <description>Gapped-read mapper for RNA-seq data</description>
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
4 <macros>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
5 <import>tophat_macros.xml</import>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
6 <xml name="paired_parameters">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
7 <param name="mate_inner_distance" type="integer" value="300" label="Mean Inner Distance between Mate Pairs" help="-r/--mate-inner-dist; This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments selected at 300bp, where each end is 50bp, you should set -r to be 200. The default is 50bp."/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
8 <param name="mate_std_dev" type="integer" value="20" label="Std. Dev for Distance between Mate Pairs" help="--mate-std-dev; The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp."/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
9 <!-- Discordant pairs. -->
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
10 <param name="report_discordant_pairs" type="select" label="Report discordant pair alignments?" help="--no-discordant">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
11 <option value="No">No</option>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
12 <option selected="True" value="Yes">Yes</option>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
13 </param>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
14 </xml>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
15 <macro name="dbKeyActions">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
16 <actions>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
17 <conditional name="refGenomeSource.genomeSource">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
18 <when value="indexed">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
19 <action type="metadata" name="dbkey">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
20 <option type="from_data_table" name="tophat2_indexes" column="1" offset="0">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
21 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
22 <filter type="param_value" ref="refGenomeSource.index" column="0"/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
23 </option>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
24 </action>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
25 </when>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
26 <when value="history">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
27 <action type="metadata" name="dbkey">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
28 <option type="from_param" name="refGenomeSource.ownFile" param_attribute="dbkey" />
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
29 </action>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
30 </when>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
31 </conditional>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
32 </actions>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
33 </macro>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
34 </macros>
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
35 <requirements>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
36 <requirement type="package" version="2.2.5">bowtie2</requirement>
18
11a6a9ac5432 Uploaded
scottx611x
parents: 0
diff changeset
37 <requirement type="package" version="2.1.0">tophat</requirement>
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
38 </requirements>
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
39 <stdio>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
40 <regex match="Exception|Error" source="both" level="fatal" description="Tool execution failed"/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
41 <regex match=".*" source="both" level="log" description="tool progress"/>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
42 </stdio>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
43 <version_command>tophat2 --version</version_command>
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
44
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
45 <command>
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
46 ##
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
47 ## Set path to index, building the reference if necessary.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
48 ##
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
49
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
50 #set index_path = ''
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
51 #if $refGenomeSource.genomeSource == "history":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
52 bowtie2-build "$refGenomeSource.ownFile" genome ; ln -s "$refGenomeSource.ownFile" genome.fa ;
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
53 #set index_path = 'genome'
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
54 #else:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
55 #set index_path = $refGenomeSource.index.fields.path
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
56 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
57
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
58 ##
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
59 ## Run tophat.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
60 ##
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
61
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
62 tophat2
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
63
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
64 ## Change this to accommodate the number of threads you have available.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
65 --num-threads \${GALAXY_SLOTS:-4}
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
66
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
67 ## Set params.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
68 #if $params.settingsType == "full":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
69 --read-mismatches $params.read_mismatches
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
70 #if str($params.bowtie_n) == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
71 --bowtie-n
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
72 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
73
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
74 --read-edit-dist $params.read_edit_dist
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
75 --read-realign-edit-dist $params.read_realign_edit_dist
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
76 -a $params.anchor_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
77 -m $params.splice_mismatches
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
78 -i $params.min_intron_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
79 -I $params.max_intron_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
80 -g $params.max_multihits
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
81 --min-segment-intron $params.min_segment_intron
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
82 --max-segment-intron $params.max_segment_intron
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
83 --segment-mismatches $params.seg_mismatches
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
84 --segment-length $params.seg_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
85 --library-type $params.library_type
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
86
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
87 ## Indel search.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
88 #if $params.indel_search.allow_indel_search == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
89 ## --allow-indels
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
90 --max-insertion-length $params.indel_search.max_insertion_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
91 --max-deletion-length $params.indel_search.max_deletion_length
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
92 #else:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
93 --no-novel-indels
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
94 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
95
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
96 ## Supplying junctions parameters.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
97 #if $params.own_junctions.use_junctions == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
98 #if $params.own_junctions.gene_model_ann.use_annotations == "indexed"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
99 -G $params.own_junctions.gene_model_ann.gene_annotation_model.fields.path
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
100 #elif $params.own_junctions.gene_model_ann.use_annotations == "history"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
101 -G $params.own_junctions.gene_model_ann.gene_annotation_model
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
102 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
103 #if $params.own_junctions.raw_juncs.use_juncs == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
104 -j $params.own_junctions.raw_juncs.raw_juncs
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
105 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
106 #if str($params.own_junctions.no_novel_juncs) == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
107 --no-novel-juncs
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
108 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
109 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
110
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
111 #if $params.coverage_search.use_search == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
112 --coverage-search
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
113 --min-coverage-intron $params.coverage_search.min_coverage_intron
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
114 --max-coverage-intron $params.coverage_search.max_coverage_intron
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
115 #else:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
116 --no-coverage-search
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
117 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
118
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
119 #if str($params.microexon_search) == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
120 --microexon-search
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
121 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
122
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
123 #if $params.fusion_search.do_search == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
124 --fusion-search
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
125 --fusion-anchor-length $params.fusion_search.anchor_len
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
126 --fusion-min-dist $params.fusion_search.min_dist
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
127 --fusion-read-mismatches $params.fusion_search.read_mismatches
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
128 --fusion-multireads $params.fusion_search.multireads
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
129 --fusion-multipairs $params.fusion_search.multipairs
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
130 --fusion-ignore-chromosomes "$params.fusion_search.ignore_chromosomes"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
131 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
132
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
133 #if $params.bowtie2_settings.b2_settings == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
134 #if $params.bowtie2_settings.preset.b2_preset == "Yes":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
135 --b2-$params.bowtie2_settings.preset.b2_preset_select
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
136 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
137 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
138
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
139 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
140
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
141 ## Read group information.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
142 #if $readGroup.specReadGroup == "yes"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
143 --rg-id "$readGroup.rgid"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
144 --rg-library "$readGroup.rglb"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
145 --rg-platform "$readGroup.rgpl"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
146 --rg-sample "$readGroup.rgsm"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
147 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
148
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
149 ## Set index path, inputs and parameters specific to paired data.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
150 #if $singlePaired.sPaired != "single"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
151 -r $singlePaired.mate_inner_distance
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
152 --mate-std-dev=$singlePaired.mate_std_dev
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
153
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
154 #if str($singlePaired.report_discordant_pairs) == "No":
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
155 --no-discordant
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
156 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
157
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
158 #if $singlePaired.sPaired == "paired"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
159 ${index_path} "$singlePaired.input1" "$singlePaired.input2"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
160 #else
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
161 ${index_path} "$singlePaired.input.forward" "$singlePaired.input.reverse"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
162 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
163 #else
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
164 ${index_path} "$singlePaired.input1"
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
165 #end if
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
166 </command>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
167
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
168 <inputs>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
169 <conditional name="singlePaired">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
170 <param name="sPaired" type="select" label="Is this single-end or paired-end data?">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
171 <option value="single">Single-end</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
172 <option value="paired">Paired-end (as individual datasets)</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
173 <option value="paired_collection">Paired-end (as collection)</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
174 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
175 <when value="single">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
176 <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file" help="Must have Sanger-scaled quality values with ASCII offset 33"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
177 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
178 <when value="paired">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
179 <param format="fastqsanger" name="input1" type="data" label="RNA-Seq FASTQ file, forward reads" help="Must have Sanger-scaled quality values with ASCII offset 33" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
180 <param format="fastqsanger" name="input2" type="data" label="RNA-Seq FASTQ file, reverse reads" help="Must have Sanger-scaled quality values with ASCII offset 33" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
181 <expand macro="paired_parameters" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
182 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
183 <when value="paired_collection">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
184 <param format="fastqsanger" name="input" type="data_collection" collection_type="paired" label="RNA-Seq FASTQ paired reads" help="Must have Sanger-scaled quality values with ASCII offset 33" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
185 <expand macro="paired_parameters" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
186 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
187 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
188 <expand macro="refGenomeSourceConditional">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
189 <options from_data_table="tophat2_indexes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
190 <filter type="sort_by" column="2"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
191 <validator type="no_options" message="No genomes are available for the selected input dataset"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
192 </options>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
193 </expand>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
194 <conditional name="params">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
195 <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.">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
196 <option value="preSet">Use Defaults</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
197 <option value="full">Full parameter list</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
198 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
199 <when value="preSet" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
200 <!-- Full/advanced params. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
201 <when value="full">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
202 <param name="read_realign_edit_dist" type="integer" value="1000" label="Max realign edit distance" help="--read-realign-edit-dist; 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." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
203
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
204 <param name="read_edit_dist" type="integer" value="2" label="Max edit distance" help="--read-edit-dist; Final read alignments having more than these many edit distance are discarded." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
205
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
206 <param name="library_type" type="select" label="Library Type" help="--library-type; 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.">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
207 <option value="fr-unstranded">FR Unstranded</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
208 <option value="fr-firststrand">FR First Strand</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
209 <option value="fr-secondstrand">FR Second Strand</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
210 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
211 <param name="read_mismatches" type="integer" value="2" label="Final read mismatches" help="--read-mismatches; Final read alignments having more than these many mismatches are discarded." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
212 <param name="bowtie_n" type="select" label="Use bowtie -n mode" help="--bowtie-n; TopHat uses &quot;-v&quot; in Bowtie for initial read mapping (the default), but with this option, &quot;-n&quot; is used instead. Read segments are always mapped using &quot;-v&quot; option.">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
213 <option selected="true" value="No">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
214 <option value="Yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
215 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
216 <param name="anchor_length" type="integer" value="8" label="Anchor length (at least 3)" help="-a/--min-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 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 read with this many bases on each side. This must be at least 3 and the default is 8." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
217 <param name="splice_mismatches" type="integer" value="0" label="Maximum number of mismatches that can appear in the anchor region of spliced alignment" help="-m/--splice-mismatches; The default is 0."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
218 <param name="min_intron_length" type="integer" value="70" label="The minimum intron length" help="-i/--min-intron-length; TopHat will ignore donor/acceptor pairs closer than this many bases apart. The default is 70." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
219 <param name="max_intron_length" type="integer" value="500000" label="The maximum intron length" help="-I/--max-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." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
220
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
221 <expand macro="indel_searchConditional" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
222
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
223 <param name="max_multihits" type="integer" value="20" label="Maximum number of alignments to be allowed" help="-g/--max-multihits; Instructs TopHat to allow up to this many alignments to the reference for a given read, and choose the alignments based on their alignment scores if there are more than this number. The default is 20 for read mapping. Unless you use --report-secondary-alignments, TopHat will report the alignments with the best alignment score. If there are more alignments with the same score than this number, TopHat will randomly report only this many alignments. In case of using --report-secondary-alignments, TopHat will try to report alignments up to this option value, and TopHat may randomly output some of the alignments with the same score to meet this number."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
224 <param name="min_segment_intron" type="integer" value="50" label="Minimum intron length that may be found during split-segment (default) search" help="--min-segment-intron; The minimum intron length that may be found during split-segment search. The default is 50."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
225 <param name="max_segment_intron" type="integer" value="500000" label="Maximum intron length that may be found during split-segment (default) search" help="--max-segment-intron; The maximum intron length that may be found during split-segment search. The default is 500000."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
226 <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" help="--segment-mismatches; Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
227 <param name="seg_length" type="integer" value="25" label="Minimum length of read segments" help="--segment-length; Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
228 <param name="output_unmapped" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output unmapped reads" help="If checked, a BAM with the unmapped reads will be added to the history" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
229 <!-- Options for supplying own junctions. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
230 <expand macro="own_junctionsConditional" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
231 <!-- Coverage search. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
232 <conditional name="coverage_search">
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
233 <param name="use_search" type="select" label="Use coverage-based search for junctions" help="Select 'Auto' to let TopHat decide when to enable coverage search (e.g. disable it for reads 75bp or longer). Select 'Yes' to enforce maximum sensitivity and to specify minimum and maximum intron length">
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
234 <option selected="true" value="auto">Auto</option>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
235 <option value="No">No (--no-coverage-search)</option>
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
236 <option value="Yes">Yes (--coverage-search)</option>
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
237 </param>
23
4e7fe3a94ed6 Uploaded
scottx611x
parents: 20
diff changeset
238 <when value="auto" />
0
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
239 <when value="Yes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
240 <param name="min_coverage_intron" type="integer" value="50" label="Minimum intron length that may be found during coverage search" help="--min-coverage-intron; The minimum intron length that may be found during coverage search. The default is 50."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
241 <param name="max_coverage_intron" type="integer" value="20000" label="Maximum intron length that may be found during coverage search" help="--max-coverage-intron; The maximum intron length that may be found during coverage search. The default is 20000."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
242 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
243 <when value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
244 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
245
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
246 <!-- Microexon search params -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
247 <param name="microexon_search" type="select" label="Use Microexon Search" help="--microexon-search; With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
248 <option value="No">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
249 <option value="Yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
250 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
251
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
252 <!-- Fusion mapping. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
253 <conditional name="fusion_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
254 <param name="do_search" type="select" label="Do Fusion Search" help="Reads can be aligned to potential fusion transcripts if the --fusion-search option is specified. The fusion alignments are reported in SAM format using custom fields XF and XP (see the output format) and some additional information about fusions will be reported (see fusions.out). Once mapping is done, you can run tophat-fusion-post to filter out fusion transcripts (see the TopHat-Fusion website for more details).">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
255 <option selected="true" value="No">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
256 <option value="Yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
257 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
258 <when value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
259 <when value="Yes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
260 <param name="anchor_len" type="integer" value="20" label="Anchor Length" help="--fusion-anchor-length; A 'supporting' read must map to both sides of a fusion by at least this many bases. The default is 20."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
261 <param name="min_dist" type="integer" value="10000000" label="Minimum Distance" help="--fusion-min-dist; For intra-chromosomal fusions, TopHat-Fusion tries to find fusions separated by at least this distance. The default is 10000000."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
262 <param name="read_mismatches" type="integer" value="2" label="Read Mismatches" help="--fusion-read-mismatches; Reads support fusions if they map across fusion with at most this many mismatches. The default is 2."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
263 <param name="multireads" type="integer" value="2" label="Multireads" help="--fusion-multireads; 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. The default is 2."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
264 <param name="multipairs" type="integer" value="2" label="Multipairs" help="--fusion-multipairs; Pairs that map to more than this many places will be ignored. The default is 2."/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
265 <param name="ignore_chromosomes" type="text" value='' label="--fusion-ignore-chromosomes; Ignore some chromosomes such as chrM when detecting fusion break points"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
266 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
267 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
268
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
269 <!-- Bowtie2 settings. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
270 <conditional name="bowtie2_settings">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
271 <param name="b2_settings" type="select" label="Set Bowtie2 settings">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
272 <option selected="true" value="No">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
273 <option value="Yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
274 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
275 <when value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
276 <when value="Yes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
277 <conditional name="preset">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
278 <param name="b2_preset" type="select" label="Use Preset options">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
279 <option selected="true" value="Yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
280 <option value="No">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
281 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
282 <when value="Yes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
283 <param name="b2_preset_select" type="select" label="Preset option">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
284 <option value="very-fast">Very fast</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
285 <option value="fast">Fast</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
286 <option selected="true" value="sensitive">Sensitive</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
287 <option value="very-sensitive">Very sensitive</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
288 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
289 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
290 <!-- TODO: -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
291 <when value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
292 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
293 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
294 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
295 </when> <!-- full -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
296 </conditional> <!-- params -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
297 <conditional name="readGroup">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
298 <param name="specReadGroup" type="select" label="Specify read group?">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
299 <option value="yes">Yes</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
300 <option value="no" selected="True">No</option>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
301 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
302 <when value="yes">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
303 <param name="rgid" type="text" 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." />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
304 <param name="rglb" type="text" label="Library name (LB)" help="Required if RG specified" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
305 <param name="rgpl" type="text" label="Platform/technology used to produce the reads (PL)" help="Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
306 <param name="rgsm" type="text" label="Sample (SM)" help="Required if RG specified. Use pool name where a pool is being sequenced" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
307 </when>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
308 <when value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
309 </conditional> <!-- readGroup -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
310 </inputs>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
311
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
312 <outputs>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
313 <data format="txt" name="align_summary" label="${tool.name} on ${on_string}: align_summary" from_work_dir="tophat_out/align_summary.txt"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
314 <data format="tabular" name="fusions" label="${tool.name} on ${on_string}: fusions" from_work_dir="tophat_out/fusions.out">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
315 <filter>(params['settingsType'] == 'full' and params['fusion_search']['do_search'] == 'Yes')</filter>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
316 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
317 <data format="bed" name="insertions" label="${tool.name} on ${on_string}: insertions" from_work_dir="tophat_out/insertions.bed">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
318 <expand macro="dbKeyActions" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
319 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
320 <data format="bed" name="deletions" label="${tool.name} on ${on_string}: deletions" from_work_dir="tophat_out/deletions.bed">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
321 <expand macro="dbKeyActions" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
322 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
323 <data format="bed" name="junctions" label="${tool.name} on ${on_string}: splice junctions" from_work_dir="tophat_out/junctions.bed">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
324 <expand macro="dbKeyActions" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
325 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
326 <data format="bam" name="accepted_hits" label="${tool.name} on ${on_string}: accepted_hits" from_work_dir="tophat_out/accepted_hits.bam">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
327 <expand macro="dbKeyActions" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
328 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
329 <data format="bam" name="unmapped" label="${tool.name} on ${on_string}: unmapped" from_work_dir="tophat_out/unmapped.bam">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
330 <filter>(params['settingsType'] == 'full' and params['output_unmapped'])</filter>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
331 <expand macro="dbKeyActions" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
332 </data>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
333
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
334 </outputs>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
335
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
336 <tests>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
337 <!-- Test base-space single-end reads with pre-built index and preset parameters -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
338 <test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
339 <!-- TopHat commands:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
340 tophat2 -o tmp_dir -p 1 tophat_in1 test-data/tophat_in2.fastqsanger
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
341 Rename the files in tmp_dir appropriately
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
342 -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
343 <param name="sPaired" value="single" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
344 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
345 <param name="genomeSource" value="indexed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
346 <param name="index" value="tophat_test" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
347 <param name="settingsType" value="preSet" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
348 <param name="specReadGroup" value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
349 <output name="junctions" file="tophat2_out1j.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
350 <output name="accepted_hits" file="tophat_out1h.bam" compare="sim_size" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
351 </test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
352 <!-- Test using base-space test data: paired-end reads, index from history. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
353 <test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
354 <!-- TopHat commands:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
355 bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
356 tophat2 -o tmp_dir -p 1 -r 20 tophat_in1 test-data/tophat_in2.fastqsanger test-data/tophat_in3.fastqsanger
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
357 Rename the files in tmp_dir appropriately
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
358 -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
359 <param name="sPaired" value="paired" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
360 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
361 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
362 <param name="genomeSource" value="history" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
363 <param name="ownFile" ftype="fasta" value="tophat_in1.fasta" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
364 <param name="mate_inner_distance" value="20" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
365 <param name="settingsType" value="preSet" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
366 <param name="specReadGroup" value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
367 <output name="junctions" file="tophat2_out2j.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
368 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
369 </test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
370 <test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
371 <!-- Same test as above but with a collection. -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
372 <param name="sPaired" value="paired_collection" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
373 <param name="input">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
374 <collection type="paired">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
375 <element name="forward" value="tophat_in2.fastqsanger" ftype="fastqsanger" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
376 <element name="reverse" value="tophat_in3.fastqsanger" ftype="fastqsanger" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
377 </collection>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
378 </param>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
379 <param name="genomeSource" value="history" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
380 <param name="ownFile" ftype="fasta" value="tophat_in1.fasta" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
381 <param name="mate_inner_distance" value="20" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
382 <param name="settingsType" value="preSet" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
383 <param name="specReadGroup" value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
384 <output name="junctions" file="tophat2_out2j.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
385 <output name="accepted_hits" file="tophat_out2h.bam" compare="sim_size" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
386 </test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
387 <!-- Test base-space single-end reads with user-supplied reference fasta and full parameters -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
388 <test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
389 <!-- TopHat commands:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
390 bowtie2-build -f test-data/tophat_in1.fasta tophat_in1
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
391 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
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
392 Replace the + with double-dash
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
393 Rename the files in tmp_dir appropriately
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
394 -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
395 <conditional name="singlePaired">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
396 <param name="sPaired" value="single"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
397 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
398 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
399 <param name="genomeSource" value="history"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
400 <param name="ownFile" value="tophat_in1.fasta"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
401 <conditional name="params">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
402 <param name="settingsType" value="full"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
403 <param name="library_type" value="FR Unstranded"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
404 <param name="read_mismatches" value="2"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
405 <param name="bowtie_n" value="No"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
406 <param name="anchor_length" value="8"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
407 <param name="splice_mismatches" value="0"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
408 <param name="min_intron_length" value="70"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
409 <param name="max_intron_length" value="500000"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
410 <param name="max_multihits" value="40"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
411 <param name="min_segment_intron" value="50" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
412 <param name="max_segment_intron" value="500000" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
413 <param name="seg_mismatches" value="2"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
414 <param name="seg_length" value="25"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
415 <conditional name="indel_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
416 <param name="allow_indel_search" value="Yes"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
417 <param name="max_insertion_length" value="3"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
418 <param name="max_deletion_length" value="3"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
419 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
420 <conditional name="own_junctions">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
421 <param name="use_junctions" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
422 <conditional name="gene_model_ann">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
423 <param name="use_annotations" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
424 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
425 <conditional name="raw_juncs">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
426 <param name="use_juncs" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
427 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
428 <conditional name="no_novel_juncs">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
429 <param name="no_novel_juncs" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
430 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
431 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
432 <conditional name="coverage_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
433 <param name="use_search" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
434 <param name="min_coverage_intron" value="50" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
435 <param name="max_coverage_intron" value="20000" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
436 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
437 <param name="microexon_search" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
438 <conditional name="bowtie2_settings">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
439 <param name="b2_settings" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
440 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
441 <!-- Fusion search params -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
442 <conditional name="fusion_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
443 <param name="do_search" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
444 <param name="anchor_len" value="21" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
445 <param name="min_dist" value="10000021" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
446 <param name="read_mismatches" value="3" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
447 <param name="multireads" value="4" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
448 <param name="multipairs" value="5" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
449 <param name="ignore_chromosomes" value="chrM"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
450 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
451 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
452 <conditional name="readGroup">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
453 <param name="specReadGroup" value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
454 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
455 <output name="insertions" file="tophat_out3i.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
456 <output name="deletions" file="tophat_out3d.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
457 <output name="junctions" file="tophat2_out3j.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
458 <output name="accepted_hits" file="tophat_out3h.bam" compare="sim_size" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
459 </test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
460 <!-- Test base-space paired-end reads with user-supplied reference fasta and full parameters -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
461 <test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
462 <!-- TopHat commands:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
463 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
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
464 Replace the + with double-dash
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
465 Rename the files in tmp_dir appropriately
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
466 -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
467 <conditional name="singlePaired">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
468 <param name="sPaired" value="paired"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
469 <param name="input1" ftype="fastqsanger" value="tophat_in2.fastqsanger"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
470 <param name="input2" ftype="fastqsanger" value="tophat_in3.fastqsanger"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
471 <param name="mate_inner_distance" value="20"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
472 <param name="report_discordant_pairs" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
473 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
474 <param name="genomeSource" value="indexed"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
475 <param name="index" value="tophat_test"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
476 <conditional name="params">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
477 <param name="settingsType" value="full"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
478 <param name="library_type" value="FR Unstranded"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
479 <param name="read_mismatches" value="5"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
480 <!-- Error: the read mismatches (5) and the read gap length (2) should be less than or equal to the read edit dist (2) -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
481 <param name="read_edit_dist" value="5" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
482 <param name="bowtie_n" value="Yes"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
483 <param name="mate_std_dev" value="20"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
484 <param name="anchor_length" value="8"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
485 <param name="splice_mismatches" value="0"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
486 <param name="min_intron_length" value="70"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
487 <param name="max_intron_length" value="500000"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
488 <param name="max_multihits" value="40"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
489 <param name="min_segment_intron" value="50" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
490 <param name="max_segment_intron" value="500000" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
491 <param name="seg_mismatches" value="2"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
492 <param name="seg_length" value="25"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
493 <conditional name="indel_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
494 <param name="allow_indel_search" value="No"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
495 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
496 <conditional name="own_junctions">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
497 <param name="use_junctions" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
498 <conditional name="gene_model_ann">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
499 <param name="use_annotations" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
500 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
501 <conditional name="raw_juncs">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
502 <param name="use_juncs" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
503 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
504 <conditional name="no_novel_juncs">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
505 <param name="no_novel_juncs" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
506 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
507 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
508 <conditional name="coverage_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
509 <param name="use_search" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
510 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
511 <param name="microexon_search" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
512 <conditional name="bowtie2_settings">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
513 <param name="b2_settings" value="No" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
514 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
515 <!-- Fusion search params -->
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
516 <conditional name="fusion_search">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
517 <param name="do_search" value="Yes" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
518 <param name="anchor_len" value="21" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
519 <param name="min_dist" value="10000021" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
520 <param name="read_mismatches" value="3" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
521 <param name="multireads" value="4" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
522 <param name="multipairs" value="5" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
523 <param name="ignore_chromosomes" value="chrM"/>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
524 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
525 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
526 <conditional name="readGroup">
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
527 <param name="specReadGroup" value="no" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
528 </conditional>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
529 <output name="junctions" file="tophat2_out4j.bed" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
530 <output name="accepted_hits" file="tophat_out4h.bam" compare="sim_size" />
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
531 </test>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
532 </tests>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
533 <help>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
534 **TopHat Overview**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
535
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
536 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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
537
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
538 .. _TopHat: http://ccb.jhu.edu/software/tophat/
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
539
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
540 ------
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
541
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
542 **Know what you are doing**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
543
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
544 .. class:: warningmark
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
545
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
546 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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
547
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
548 .. __: http://ccb.jhu.edu/software/tophat/manual.shtml
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
549
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
550 ------
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
551
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
552 **Input formats**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
553
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
554 TopHat accepts files in Sanger FASTQ format. Use the FASTQ Groomer to prepare your files.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
555
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
556 ------
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
557
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
558 **Outputs**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
559
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
560 TopHat produces two output files:
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
561
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
562 - 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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
563 - accepted_hits -- A list of read alignments in BAM_ format.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
564
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
565 .. _BED: http://genome.ucsc.edu/FAQ/FAQformat.html#format1
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
566 .. _BAM: http://samtools.sourceforge.net/
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
567
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
568 Two other possible outputs, depending on the options you choose, are insertions and deletions, both of which are in BED format.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
569
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
570 -------
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
571
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
572 **TopHat settings**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
573
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
574 All of the options have a default value. You can change any of them. Some of the options in TopHat have been implemented here.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
575
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
576 ------
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
577
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
578 **TopHat parameter list**
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
579
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
580 This is a list of implemented TopHat options::
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
581
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
582 -r This is the expected (mean) inner distance between mate pairs. For, example, for paired end runs with fragments
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
583 selected at 300bp, where each end is 50bp, you should set -r to be 200. There is no default, and this parameter
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
584 is required for paired end runs.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
585 --mate-std-dev INT The standard deviation for the distribution on inner distances between mate pairs. The default is 20bp.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
586 -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
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
587 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
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
588 read with this many bases on each side. This must be at least 3 and the default is 8.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
589 -m/--splice-mismatches INT The maximum number of mismatches that may appear in the "anchor" region of a spliced alignment. The default is 0.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
590 -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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
591 -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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
592 -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
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
593 alignments. The default is 40.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
594 -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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
595 -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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
596 -no-novel-juncs Only look for junctions indicated in the supplied GFF file. (ignored without -G)
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
597 --no-coverage-search Disables the coverage based search for junctions.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
598 --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.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
599 --microexon-search With this option, the pipeline will attempt to find alignments incident to microexons. Works only for reads 50bp or longer.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
600 --segment-mismatches Read segments are mapped independently, allowing up to this many mismatches in each segment alignment. The default is 2.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
601 --segment-length Each read is cut up into segments, each at least this long. These segments are mapped independently. The default is 25.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
602 --min-coverage-intron The minimum intron length that may be found during coverage search. The default is 50.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
603 --max-coverage-intron The maximum intron length that may be found during coverage search. The default is 20000.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
604 --min-segment-intron The minimum intron length that may be found during split-segment search. The default is 50.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
605 --max-segment-intron The maximum intron length that may be found during split-segment search. The default is 500000.
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
606 </help>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
607 <citations>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
608 <citation type="doi">10.1186/gb-2013-14-4-r36</citation>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
609 </citations>
620cb7a7ef60 Uploaded
scottx611x
parents:
diff changeset
610 </tool>