Mercurial > repos > iuc > tetoolkit_tetranscripts

comparison tetranscript.xml @ 2:bbeab8445490 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/mhammell-laboratory/TEtranscripts commit 52fd61119be10e02b66852d5ccf21f4f1904b8c3"
author iuc
date Sun, 04 Oct 2020 09:53:49 +0000
parents bf4ee2810759
children 313414e9abcf
comparison
equal deleted inserted replaced
1:bf4ee2810759 2:bbeab8445490
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="tetoolkit_tetranscripts" name="TEtranscripts" version="@TOOL_VERSION@+galaxy0"> 2 <tool id="tetoolkit_tetranscripts" name="TEtranscripts" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
3 <description>annotates reads to genes and transposable elements</description> 3 <description>annotates reads to genes and transposable elements</description>
4 <macros> 4 <macros>
5 <token name="@TOOL_VERSION@">2.2.0</token> 5 <token name="@TOOL_VERSION@">2.2.1</token>
6 <token name="@VERSION_SUFFIX@">0</token>
6 </macros> 7 </macros>
7 <requirements> 8 <requirements>
8 <requirement type="package" version="@TOOL_VERSION@">tetranscripts</requirement> 9 <requirement type="package" version="@TOOL_VERSION@">tetranscripts</requirement>
9 </requirements> 10 </requirements>
10 <version_command>TEtranscripts --version</version_command> 11 <version_command>TEtranscripts --version</version_command>
11 <command detect_errors="exit_code"><![CDATA[ 12 <command detect_errors="exit_code"><![CDATA[
12 ## initialize 13 ## initialize
13 ## file extension is required 14 ## file extension is required
14 ln -s '$GTF' 'gene_annotation.gtf' && 15 ln -s '$GTF' 'gene_annotation.gtf' &&
15 ln -s '$TE' 'transposable_annotation.gtf' && 16 ln -s '$TE' 'transposable_annotation.gtf' &&
16 17
17 ## run 18 ## run
18 TEtranscripts 19 TEtranscripts
19 ## required 20 ## required
20 -t 21 -t
21 #for $s in $sample_rep 22 #for $s in $sample_rep
22 '${s.t}' 23 '${s.t}'
23 #end for 24 #end for
24 -c 25 -c
25 #for $s in $sample_rep 26 #for $s in $sample_rep
26 '${s.c}' 27 '${s.c}'
27 #end for 28 #end for
28 --GTF 'gene_annotation.gtf' 29 --GTF 'gene_annotation.gtf'
29 --TE 'transposable_annotation.gtf' 30 --TE 'transposable_annotation.gtf'
30 ## optional 31 ## optional
31 --stranded '$io.stranded' 32 --stranded '$io.stranded'
32 $io.sortByPos 33 $io.sortByPos
33 --project 'result' 34 --project 'result'
34 --mode '$ap.mode' 35 --mode '$ap.mode'
35 --minread $ap.minread 36 --minread $ap.minread
36 #if $ap.fragmentLength 37 #if $ap.fragmentLength
37 --fragmentLength $ap.fragmentLength 38 --fragmentLength $ap.fragmentLength
38 #end if 39 #end if
39 --iteration $ap.iteration 40 --iteration $ap.iteration
40 --padj $ap.padj 41 --padj $ap.padj
41 --foldchange $ap.foldchange 42 --foldchange $ap.foldchange
42 #if 'log' in $ap.out 43 #if 'log' in $oo.out
43 --verbose 3 44 --verbose 3
44 |& tee log.txt 45 |& tee '$out_log'
45 #end if 46 #end if
46 ]]></command> 47 ]]></command>
47 <inputs> 48 <inputs>
48 <repeat name="sample_rep" min="2" title="Select input data"> 49 <repeat name="sample_rep" min="2" title="Select input data">
49 <param argument="-t" type="data" format="bam" label="Treatment sample file"/> 50 <param argument="-t" type="data" format="bam" label="Treatment sample file"/>
50 <param argument="-c" type="data" format="bam" label="Control sample file"/> 51 <param argument="-c" type="data" format="bam" label="Control sample file"/>
51 </repeat> 52 </repeat>
52 <param argument="--GTF" type="data" format="gtf" label="Select GTF file for gene annotations"/> 53 <param argument="--GTF" type="data" format="gtf" label="Select file for gene annotations"/>
53 <param argument="--TE" type="data" format="gtf" label="Select GTF file for transposable element annotations"/> 54 <param argument="--TE" type="data" format ="gtf" label="Select file for transposable element annotations"/>
54 <section name="io" title="Input options"> 55 <section name="io" title="Input options" expanded="true">
55 <param argument="--stranded" type="select" label="Select library type"> 56 <param argument="--stranded" type="select" label="Select library type">
56 <option value="no">Library is unstranded (no)</option> 57 <option value="no">Library is unstranded (no)</option>
57 <option value="forward">Second-strand cDNA library e.g. QIAseq stranded (forward)</option> 58 <option value="forward">Second-strand cDNA library e.g. QIAseq stranded (forward)</option>
58 <option value="reverse">First-strand cDNA library e.g. Illumina TruSeq stranded (reverse)</option> 59 <option value="reverse">First-strand cDNA library e.g. Illumina TruSeq stranded (reverse)</option>
59 </param> 60 </param>
67 <param argument="--minread" type="integer" value="1" min="0" label="Set read count cutoff"/> 68 <param argument="--minread" type="integer" value="1" min="0" label="Set read count cutoff"/>
68 <param argument="--fragmentLength" type="integer" min="0" optional="true" label="Set average length of fragment used for single-end sequencing" help="For paired-end, estimated from the input alignment file. For single-end, ignored by default."/> 69 <param argument="--fragmentLength" type="integer" min="0" optional="true" label="Set average length of fragment used for single-end sequencing" help="For paired-end, estimated from the input alignment file. For single-end, ignored by default."/>
69 <param argument="--iteration" type="integer" value="100" min="0" label="Set maximum number of iterations used to optimize multi-reads assignment"/> 70 <param argument="--iteration" type="integer" value="100" min="0" label="Set maximum number of iterations used to optimize multi-reads assignment"/>
70 <param argument="--padj" type="float" value="0.05" min="0.0" max="1.0" label="Set FDR cutoff for significance"/> 71 <param argument="--padj" type="float" value="0.05" min="0.0" max="1.0" label="Set FDR cutoff for significance"/>
71 <param argument="--foldchange" type="float" value="1.0" min="0.0" label="Set fold-change ratio (absolute) cutoff for differential expression"/> 72 <param argument="--foldchange" type="float" value="1.0" min="0.0" label="Set fold-change ratio (absolute) cutoff for differential expression"/>
72 <param name="out" type="select" multiple="true" label="Select output file(s)" help="Result files for gene TE analysis and sigDiff gene TE will be created if more than one dataset is applied."> 73 </section>
74 <section name="oo" title="Output options">
75 <param name="out" type="select" multiple="true" optional="false" label="Select output file(s)" help="Result files for gene TE analysis and sigDiff gene TE will be created if more than one dataset is applied.">
73 <option value="cnttable" selected="true">cntTable</option> 76 <option value="cnttable" selected="true">cntTable</option>
74 <option value="deseq2" selected="true">DESeq2.R</option> 77 <option value="deseq2">DESeq2.R</option>
75 <option value="gta" selected="true">Gene TE Analysis</option> 78 <option value="gta" selected="true">Gene TE Analysis</option>
79 <option value="log">Log</option>
76 <option value="sgt" selected="true">SigDiff Gene TE</option> 80 <option value="sgt" selected="true">SigDiff Gene TE</option>
77 <option value="log">Log</option>
78 </param> 81 </param>
79 </section> 82 </section>
80 </inputs> 83 </inputs>
81 <outputs> 84 <outputs>
82 <data name="out_cnt" format="tabular" from_work_dir="result.cntTable" label="${tool.name} on ${on_string}: cntTable"> 85 <data name="out_cnt" format="tabular" from_work_dir="result.cntTable" label="${tool.name} on ${on_string}: cntTable">
83 <filter>'cnttable' in ap['out']</filter> 86 <filter>'cnttable' in oo['out']</filter>
84 </data> 87 </data>
85 <data name="out_deseq2" format="txt" from_work_dir="result_DESeq2.R" label="${tool.name} on ${on_string}: DESeq2.R"> 88 <data name="out_deseq2" format="txt" from_work_dir="result_DESeq2.R" label="${tool.name} on ${on_string}: DESeq2.R">
86 <filter>'deseq2' in ap['out']</filter> 89 <filter>'deseq2' in oo['out']</filter>
90 </data>
91 <data name="out_gta" format="tabular" from_work_dir="result_gene_TE_analysis.txt" label="${tool.name} on ${on_string}: Gene TE analysis">
92 <filter>'gta' in oo['out']</filter>
87 </data> 93 </data>
88 <data name="out_log" format="txt" from_work_dir="log.txt" label="${tool.name} on ${on_string}: log"> 94 <data name="out_log" format="txt" from_work_dir="log.txt" label="${tool.name} on ${on_string}: log">
89 <filter>'log' in ap['out']</filter> 95 <filter>'log' in oo['out']</filter>
90 </data> 96 </data>
91 <data name="out_gta" format="txt" from_work_dir="result_gene_TE_analysis.txt" label="${tool.name} on ${on_string}: Gene TE analysis"> 97 <data name="out_sgt" format="tabular" from_work_dir="result_sigdiff_gene_TE.txt" label="${tool.name} on ${on_string}: SigDiff Gene TE">
92 <filter>'gta' in ap['out']</filter> 98 <filter>'sgt' in oo['out']</filter>
93 </data>
94 <data name="out_sgt" format="txt" from_work_dir="result_sigdiff_gene_TE.txt" label="${tool.name} on ${on_string}: SigDiff Gene TE">
95 <filter>'sgt' in ap['out']</filter>
96 </data> 99 </data>
97 </outputs> 100 </outputs>
98 <tests> 101 <tests>
99 <!-- 102 <!--
100 test data sources: 103 test data sources:
101 https://github.com/mhammell-laboratory/tetoolkit-test-data 104 https://github.com/mhammell-laboratory/tetoolkit-test-data
102 https://github.com/mhammell-laboratory/TEtranscripts/issues/66 105 https://github.com/mhammell-laboratory/TEtranscripts/issues/66
103 --> 106 -->
104 107
105 <!-- #1: default --> 108 <!-- #1: default -->
106 <test expect_num_outputs="5"> 109 <test expect_num_outputs="3">
107 <repeat name="sample_rep"> 110 <repeat name="sample_rep">
108 <param name="t" value="treatment1.bam"/> 111 <param name="t" value="treatment1.bam"/>
109 <param name="c" value="control1.bam"/> 112 <param name="c" value="control1.bam"/>
110 </repeat> 113 </repeat>
111 <repeat name="sample_rep"> 114 <repeat name="sample_rep">
112 <param name="t" value="treatment2.bam"/> 115 <param name="t" value="treatment2.bam"/>
113 <param name="c" value="control2.bam"/> 116 <param name="c" value="control2.bam"/>
114 </repeat> 117 </repeat>
115 <param name="GTF" value="gtf.gtf"/> 118 <param name="GTF" value="gtf.gtf"/>
116 <param name="TE" value="te.gtf"/> 119 <param name="TE" value="te.gtf"/>
117 <section name="ap">
118 <param name="out" value="cnttable,deseq2,gta,sgt,log"/>
119 </section>
120 <output name="out_cnt"> 120 <output name="out_cnt">
121 <assert_contents> 121 <assert_contents>
122 <has_n_lines n="295"/> 122 <has_n_lines n="295"/>
123 <!-- depends on sample names -->
124 <has_text_matching expression="gene.+"/> 123 <has_text_matching expression="gene.+"/>
125 <!-- order changes --> 124 <has_text_matching expression="TIRANT.+"/>
126 <has_text_matching expression="TIRANT.+"/>
127 </assert_contents>
128 </output>
129 <output name="out_deseq2">
130 <assert_contents>
131 <has_n_lines n="14"/>
132 <has_text_matching expression="data.+"/>
133 </assert_contents>
134 </output>
135 <output name="out_log">
136 <assert_contents>
137 <has_text_matching expression="INFO"/>
138 <has_text_matching expression=".+Done"/>
139 </assert_contents> 125 </assert_contents>
140 </output> 126 </output>
141 <output name="out_gta"> 127 <output name="out_gta">
142 <assert_contents> 128 <assert_contents>
143 <has_n_lines n="71"/> 129 <has_n_lines n="71"/>
144 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/> 130 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
145 <!-- order changes --> 131 <has_text_matching expression="TIRANT.+"/>
146 <has_text_matching expression="TIRANT.+"/> 132 </assert_contents>
147 </assert_contents> 133 </output>
148 </output>
149 <!-- no content, test dataset to small -->
150 <output name="out_sgt"> 134 <output name="out_sgt">
151 <assert_contents> 135 <assert_contents>
152 <has_n_lines n="1"/> 136 <has_n_lines n="1"/>
153 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/> 137 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
154 </assert_contents> 138 </assert_contents>
175 <param name="minread" value="2"/> 159 <param name="minread" value="2"/>
176 <param name="fragmentLength" value="10"/> 160 <param name="fragmentLength" value="10"/>
177 <param name="iteration" value="90"/> 161 <param name="iteration" value="90"/>
178 <param name="padj" value="0.06"/> 162 <param name="padj" value="0.06"/>
179 <param name="foldchange" value="2.0"/> 163 <param name="foldchange" value="2.0"/>
164 </section>
165 <section name="oo">
180 <param name="out" value="cnttable,deseq2,gta,sgt,log"/> 166 <param name="out" value="cnttable,deseq2,gta,sgt,log"/>
181 </section> 167 </section>
182 <output name="out_cnt"> 168 <output name="out_cnt">
183 <assert_contents> 169 <assert_contents>
184 <has_n_lines n="295"/> 170 <has_n_lines n="295"/>
185 <!-- depends on sample names -->
186 <has_text_matching expression="gene.+"/> 171 <has_text_matching expression="gene.+"/>
187 <!-- order changes -->
188 <has_text_matching expression="TIRANT.+"/> 172 <has_text_matching expression="TIRANT.+"/>
189 </assert_contents> 173 </assert_contents>
190 </output> 174 </output>
191 <output name="out_deseq2"> 175 <output name="out_deseq2">
192 <assert_contents> 176 <assert_contents>
193 <has_n_lines n="14"/> 177 <has_n_lines n="14"/>
194 <has_text_matching expression="data.+"/> 178 <has_text_matching expression="data.+"/>
195 </assert_contents> 179 </assert_contents>
196 </output> 180 </output>
181 <output name="out_gta">
182 <assert_contents>
183 <has_n_lines n="3"/>
184 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
185 <has_text_matching expression="DNAREP1.+"/>
186 </assert_contents>
187 </output>
197 <output name="out_log"> 188 <output name="out_log">
198 <assert_contents> 189 <assert_contents>
199 <has_text_matching expression="INFO.+"/> 190 <has_text_matching expression="INFO.+"/>
200 </assert_contents> 191 </assert_contents>
201 </output> 192 </output>
202 <output name="out_gta">
203 <assert_contents>
204 <has_n_lines n="3"/>
205 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
206 <!-- order changes -->
207 <has_text_matching expression="DNAREP1.+"/>
208 </assert_contents>
209 </output>
210 <!-- no content, test dataset to small -->
211 <output name="out_sgt"> 193 <output name="out_sgt">
212 <assert_contents> 194 <assert_contents>
213 <has_n_lines n="1"/> 195 <has_n_lines n="1"/>
214 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/> 196 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
215 </assert_contents> 197 </assert_contents>
228 <param name="GTF" value="gtf.gtf"/> 210 <param name="GTF" value="gtf.gtf"/>
229 <param name="TE" value="te.gtf"/> 211 <param name="TE" value="te.gtf"/>
230 <section name="io"> 212 <section name="io">
231 <param name="stranded" value="reverse"/> 213 <param name="stranded" value="reverse"/>
232 </section> 214 </section>
233 <section name="ap"> 215 <section name="oo">
234 <param name="out" value="cnttable,deseq2,gta,sgt,log"/> 216 <param name="out" value="cnttable,deseq2,gta,sgt,log"/>
235 </section> 217 </section>
236 <output name="out_cnt"> 218 <output name="out_cnt">
237 <assert_contents> 219 <assert_contents>
238 <has_n_lines n="295"/> 220 <has_n_lines n="295"/>
239 <!-- depends on sample names -->
240 <has_text_matching expression="gene.+"/> 221 <has_text_matching expression="gene.+"/>
241 <!-- order changes -->
242 <has_text_matching expression="TIRANT.+"/> 222 <has_text_matching expression="TIRANT.+"/>
243 </assert_contents> 223 </assert_contents>
244 </output> 224 </output>
245 <output name="out_deseq2"> 225 <output name="out_deseq2">
246 <assert_contents> 226 <assert_contents>
247 <has_n_lines n="14"/> 227 <has_n_lines n="14"/>
248 <has_text_matching expression="data.+"/> 228 <has_text_matching expression="data.+"/>
249 </assert_contents> 229 </assert_contents>
250 </output> 230 </output>
231 <output name="out_gta">
232 <assert_contents>
233 <has_n_lines n="23"/>
234 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
235 <has_text_matching expression="TART.+"/>
236 </assert_contents>
237 </output>
251 <output name="out_log"> 238 <output name="out_log">
252 <assert_contents> 239 <assert_contents>
253 <has_text_matching expression="INFO.+"/> 240 <has_text_matching expression="INFO.+"/>
254 </assert_contents>
255 </output>
256 <output name="out_gta">
257 <assert_contents>
258 <has_n_lines n="23"/>
259 <has_line line="baseMean&#009;log2FoldChange&#009;lfcSE&#009;stat&#009;pvalue&#009;padj"/>
260 <!-- order changes -->
261 <has_text_matching expression="TART.+"/>
262 </assert_contents> 241 </assert_contents>
263 </output> 242 </output>
264 <output name="out_sgt"> 243 <output name="out_sgt">
265 <assert_contents> 244 <assert_contents>
266 <has_n_lines n="2"/> 245 <has_n_lines n="2"/>
287 266
288 .. class:: infomark 267 .. class:: infomark
289 268
290 **References** 269 **References**
291 270
292 More information are available on the `project website <http://hammelllab.labsites.cshl.edu/software/#TEtranscripts>`_ and `github <https://github.com/mhammell-laboratory/TEtranscripts>`_. 271 More information are available on the `project website <http://hammelllab.labsites.cshl.edu/software/#TEtranscripts>`_ and `GitHub <https://github.com/mhammell-laboratory/TEtranscripts>`_.
293 ]]></help> 272 ]]></help>
294 <citations> 273 <citations>
295 <citation type="doi">10.1093/bioinformatics/btv422</citation> 274 <citation type="doi">10.1093/bioinformatics/btv422</citation>
296 <citation type="doi">10.1007/978-1-4939-7710-9_11</citation> 275 <citation type="doi">10.1007/978-1-4939-7710-9_11</citation>
297 </citations> 276 </citations>