Mercurial > repos > iuc > deseq2

comparison deseq2.xml @ 11:25204a860b79 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/deseq2 commit 0a56599c36b4968095ec5a3cb589f94fb139466c
author iuc
date Sun, 28 Jan 2018 04:04:12 -0500
parents 24a09ca67621
children bd06df00180a
comparison
equal deleted inserted replaced
10:24a09ca67621 11:25204a860b79
1 <tool id="deseq2" name="DESeq2" version="2.11.39"> 1 <tool id="deseq2" name="DESeq2" version="2.11.40">
2 <description>Determines differentially expressed features from count tables</description> 2 <description>Determines differentially expressed features from count tables</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="1.14.1">bioconductor-deseq2</requirement> 4 <requirement type="package" version="1.18.1">bioconductor-deseq2</requirement>
5 <requirement type="package" version="1.20.0">r-getopt</requirement> 5 <requirement type="package" version="1.6.0">bioconductor-tximport</requirement>
6 </requirements> 6 </requirements>
7 <stdio> 7 <stdio>
8 <regex match="Execution halted" 8 <regex match="Execution halted"
9 source="both" 9 source="both"
10 level="fatal" 10 level="fatal"
16 <regex match="Fatal error" 16 <regex match="Fatal error"
17 source="both" 17 source="both"
18 level="fatal" 18 level="fatal"
19 description="An undefined error occurred, please check your input carefully and contact your administrator." /> 19 description="An undefined error occurred, please check your input carefully and contact your administrator." />
20 </stdio> 20 </stdio>
21 <version_command> 21 <version_command><![CDATA[
22 <![CDATA[ 22 echo $(R --version | grep version | grep -v GNU)", DESeq2 version" $(R --vanilla --slave -e "library(DESeq2); cat(sessionInfo()\$otherPkgs\$DESeq2\$Version)" 2> /dev/null | grep -v -i "WARNING: ")
23 echo $(R --version | grep version | grep -v GNU)", DESeq2 version" $(R --vanilla --slave -e "library(DESeq2); cat(sessionInfo()\$otherPkgs\$DESeq2\$Version)" 2> /dev/null | grep -v -i "WARNING: ") 23 ]]></version_command>
24 ]]> 24 <command><![CDATA[
25 </version_command> 25 #if $tximport.tximport_selector == 'tximport':
26 <command> 26 #if $tximport.mapping_format.mapping_format_selector == 'gtf':
27 <![CDATA[ 27 ln -s '$tximport.mapping_format.gtf_file' mapping.gtf &&
28 #if $tximport.tximport_selector == 'tximport': 28 #else:
29 #if $tximport.mapping_format.mapping_format_selector == 'gtf': 29 ln -s '$tximport.mapping_format.tabular_file' mapping.txt &&
30 ln -s '$tximport.mapping_format.gtf_file' mapping.gtf && 30 #end if
31 #else: 31 #end if
32 ln -s '$tximport.mapping_format.tabular_file' mapping.txt && 32
33 #end if 33 #import json
34 Rscript '${__tool_directory__}/deseq2.R'
35 -o '$deseq_out'
36 #if $pdf:
37 -p '$plots'
38 #end if
39 #if $normCounts:
40 -n '$counts_out'
41 #end if
42 #set $temp_factor_names = list()
43 #for $factor in $rep_factorName:
44 #set $temp_factor = list()
45 #for $level in $factor.rep_factorLevel:
46 #set $count_files = list()
47 #for $file in $level.countsFile:
48 $count_files.append(str($file))
49 #end for
50 $temp_factor.append( {str($level.factorLevel): $count_files} )
51 #end for
52 $temp_factor.reverse()
53 $temp_factor_names.append([str($factor.factorName), $temp_factor])
54 #end for
55 -f '#echo json.dumps(temp_factor_names)#'
56 -t $fit_type
57 #if $outlier_replace_off:
58 -a
59 #end if
60 #if $outlier_filter_off:
61 -b
62 #end if
63 #if $auto_mean_filter_off:
64 -c
65 #end if
66 #if $many_contrasts:
67 -m
68 #end if
69 #if $tximport.tximport_selector == 'tximport':
70 -i
71 -y $tximport.txtype
72 #if $tximport.mapping_format.mapping_format_selector == 'gtf':
73 -x mapping.gtf
74 #else:
75 -x mapping.txt
34 #end if 76 #end if
35 77
36 #import json 78 #end if
37 Rscript '${__tool_directory__}/deseq2.R' 79 ]]></command>
38 -o '$deseq_out'
39 #if $pdf:
40 -p '$plots'
41 #end if
42 #if $normCounts:
43 -n '$counts_out'
44 #end if
45 #set $temp_factor_names = list()
46 #for $factor in $rep_factorName:
47 #set $temp_factor = list()
48 #for $level in $factor.rep_factorLevel:
49 #set $count_files = list()
50 #for $file in $level.countsFile:
51 $count_files.append(str($file))
52 #end for
53 $temp_factor.append( {str($level.factorLevel): $count_files} )
54 #end for
55 $temp_factor.reverse()
56 $temp_factor_names.append([str($factor.factorName), $temp_factor])
57 #end for
58 -f '#echo json.dumps(temp_factor_names)#'
59 -t '$fit_type'
60 #if $outlier_replace_off:
61 -a
62 #end if
63 #if $outlier_filter_off:
64 -b
65 #end if
66 #if $auto_mean_filter_off:
67 -c
68 #end if
69 #if $many_contrasts:
70 -m
71 #end if
72 #if $tximport.tximport_selector == 'tximport':
73 -i
74 #if $tximport.mapping_format.mapping_format_selector == 'gtf':
75 -x mapping.gtf
76 #else:
77 -x mapping.txt
78 #end if
79
80 #end if
81 ]]>
82 </command>
83 <inputs> 80 <inputs>
84 <repeat name="rep_factorName" title="Factor" min="1"> 81 <repeat name="rep_factorName" title="Factor" min="1">
85 <param name="factorName" type="text" value="FactorName" label="Specify a factor name, e.g. effects_drug_x or cancer_markers" 82 <param name="factorName" type="text" value="FactorName" label="Specify a factor name, e.g. effects_drug_x or cancer_markers"
86 help="Only letters, numbers and underscores will be retained in this field"> 83 help="Only letters, numbers and underscores will be retained in this field">
87 <sanitizer> 84 <sanitizer>
99 </repeat> 96 </repeat>
100 </repeat> 97 </repeat>
101 98
102 <conditional name="tximport"> 99 <conditional name="tximport">
103 <param name="tximport_selector" type="select" label="Choice of Input data"> 100 <param name="tximport_selector" type="select" label="Choice of Input data">
104 <option value="count" selected="True">Count data (e.g. from htseq-count or feature-count)</option> 101 <option value="count" selected="True">Count data (e.g. from HTSeq-count or featureCounts)</option>
105 <option value="tximport">TPM values (e.g. from sailfish or salmon)</option> 102 <option value="tximport">TPM values (e.g. from kallisto, sailfish or salmon)</option>
106 </param> 103 </param>
107 <when value="tximport"> 104 <when value="tximport">
105 <param name="txtype" type="select" label="Program used to generate TPMs">
106 <option value="kallisto">kallisto</option>
107 <option value="sailfish">Sailfish</option>
108 <option value="salmon">Salmon</option>
109 </param>
108 <conditional name="mapping_format"> 110 <conditional name="mapping_format">
109 <param name="mapping_format_selector" type="select" label="Gene mapping format"> 111 <param name="mapping_format_selector" type="select" label="Gene mapping format">
110 <option value="gtf" selected="True">GTF</option> 112 <option value="gtf" selected="True">GTF</option>
111 <option value="tabular">Transcript-ID and Gene-ID mapping file</option> 113 <option value="tabular">Transcript-ID and Gene-ID mapping file</option>
112 </param> 114 </param>
113 <when value="gtf"> 115 <when value="gtf">
114 <param name="gtf_file" type="data" format="gtf" label="GTF file with Transcript - Gene mapping"/> 116 <param name="gtf_file" type="data" format="gtf,gff3" label="GTF/GFF3 file with Transcript - Gene mapping"/>
115 </when> 117 </when>
116 <when value="tabular"> 118 <when value="tabular">
117 <param name="tabular_file" type="data" format="tabular" label="Tabular file with Transcript - Gene mapping"/> 119 <param name="tabular_file" type="data" format="tabular" label="Tabular file with Transcript - Gene mapping"/>
118 </when> 120 </when>
119 </conditional> 121 </conditional>
163 <data format="tabular" name="counts_out" label="Normalized counts file on ${on_string}"> 165 <data format="tabular" name="counts_out" label="Normalized counts file on ${on_string}">
164 <filter>normCounts == True</filter> 166 <filter>normCounts == True</filter>
165 </data> 167 </data>
166 </outputs> 168 </outputs>
167 <tests> 169 <tests>
168 <test> 170 <!--Ensure tables output works-->
171 <test expect_num_outputs="2">
169 <repeat name="rep_factorName"> 172 <repeat name="rep_factorName">
170 <param name="factorName" value="Treatment"/> 173 <param name="factorName" value="Treatment"/>
171 <repeat name="rep_factorLevel"> 174 <repeat name="rep_factorLevel">
172 <param name="factorLevel" value="Treated"/> 175 <param name="factorLevel" value="Treated"/>
173 <param name="countsFile" value="GSM461179_treat_single.counts,GSM461180_treat_paired.counts,GSM461181_treat_paired.counts"/> 176 <param name="countsFile" value="GSM461179_treat_single.counts,GSM461180_treat_paired.counts,GSM461181_treat_paired.counts"/>
180 <param name="pdf" value="False"/> 183 <param name="pdf" value="False"/>
181 <param name="normCounts" value="True"/> 184 <param name="normCounts" value="True"/>
182 <output name="counts_out" file="normalized_readcounts.tab"/> 185 <output name="counts_out" file="normalized_readcounts.tab"/>
183 <output name="deseq_out" file="deseq2_out.tab"/> 186 <output name="deseq_out" file="deseq2_out.tab"/>
184 </test> 187 </test>
185 <test> 188 <!--Ensure Sailfish/Salmon input with tx2gene table works-->
189 <test expect_num_outputs="1">
186 <repeat name="rep_factorName"> 190 <repeat name="rep_factorName">
187 <param name="factorName" value="Treatment"/> 191 <param name="factorName" value="Treatment"/>
188 <repeat name="rep_factorLevel"> 192 <repeat name="rep_factorLevel">
189 <param name="factorLevel" value="Treated"/> 193 <param name="factorLevel" value="Treated"/>
190 <param name="countsFile" value="sailfish_quant_result1.tab,sailfish_quant_result2.tab"/> 194 <param name="countsFile" value="sailfish/sailfish_quant.sf1.tab,sailfish/sailfish_quant.sf2.tab,sailfish/sailfish_quant.sf3.tab"/>
191 </repeat> 195 </repeat>
192 <repeat name="rep_factorLevel"> 196 <repeat name="rep_factorLevel">
193 <param name="factorLevel" value="Untreated"/> 197 <param name="factorLevel" value="Untreated"/>
194 <param name="countsFile" value="sailfish_quant_result3.tab,sailfish_quant_result4.tab"/> 198 <param name="countsFile" value="sailfish/sailfish_quant.sf4.tab,sailfish/sailfish_quant.sf5.tab,sailfish/sailfish_quant.sf6.tab"/>
195 </repeat> 199 </repeat>
196 </repeat> 200 </repeat>
197 <param name="pdf" value="False"/> 201 <param name="pdf" value="False"/>
198 <param name="tximport_selector" value="tximport"/> 202 <param name="tximport_selector" value="tximport"/>
199 <param name="mapping_format_selector" value="gtf"/> 203 <param name="txtype" value="sailfish"/>
200 <param name="gtf_file" value="genes_sub.gtf"/> 204 <param name="mapping_format_selector" value="tabular"/>
201 <output name="deseq_out" file="deseq2_tximport_out.tab"/> 205 <param name="tabular_file" value="tx2gene.tab"/>
202 </test> 206 <output name="deseq_out" file="sailfish/out_deseq2_sailfish.tab"/>
207 </test>
203 </tests> 208 </tests>
204 <help> 209 <help><![CDATA[
205 <![CDATA[
206 .. class:: infomark 210 .. class:: infomark
207 211
208 **What it does** 212 **What it does**
209 213
210 Estimate variance-mean dependence in count data from high-throughput sequencing assays and test for differential expression based on a model using the negative binomial distribution 214 Estimate variance-mean dependence in count data from high-throughput sequencing assays and test for differential expression based on a model using the negative binomial distribution
211 215
216 -----
217
212 **Inputs** 218 **Inputs**
213 219
214 DESeq2_ takes count tables that generated from the htseq-count as input. Count tables must be generated for each sample individually. DESeq2 is capable of handling multiple factors that effect your experiment. The first factor you input is considered as the primary factor that affects gene expressions. You also input several secondary factors that might influence your experiment. But the final output will be changes in genes due to primary factor in presence of secondary factors. Each factor has two levels/states. You need to select appropriate count table from your history for each factor level. 220 **Count Files**
221
222 DESeq2_ takes count tables generated from **featureCounts** or **HTSeq-count** as input. Count tables must be generated for each sample individually. DESeq2 is capable of handling multiple factors that affect your experiment. The first factor you input is considered as the primary factor that affects gene expressions. Optionally, you can input one or more secondary factors that might influence your experiment. But the final output will be changes in genes due to primary factor in presence of secondary factors. Each factor has two levels/states. You need to select appropriate count table from your history for each factor level.
215 223
216 The following table gives some examples of factors and their levels: 224 The following table gives some examples of factors and their levels:
217 225
218 ========= ============== =============== 226 ========= ============== ===============
219 Factor Factor level 1 Factor level 2 227 Factor Factor level 1 Factor level 2
228 --------- -------------- --------------- 236 --------- -------------- ---------------
229 Gender Female Male 237 Gender Female Male
230 ========= ============== =============== 238 ========= ============== ===============
231 239
232 *Note*: Output log2 fold changes are based on primary factor level 1 vs. factor level2. Here the order of factor levels is important. For example, for the factor 'Treatment' given in above table, DESeq2 computes fold changes of 'Treated' samples against 'Untreated', i.e. the values correspond to up or down regulations of genes in Treated samples. 240 *Note*: Output log2 fold changes are based on primary factor level 1 vs. factor level2. Here the order of factor levels is important. For example, for the factor 'Treatment' given in above table, DESeq2 computes fold changes of 'Treated' samples against 'Untreated', i.e. the values correspond to up or down regulations of genes in Treated samples.
241
242 DESeq2_ can also take transcript-level counts from quantification tools such as, **kallisto**, **Salmon** and **Sailfish**, and this Galaxy wrapper incorporates the Bioconductor tximport_ package to process the transcript counts for DESeq2.
243
244 **Salmon or Sailfish Files**
245
246 Salmon or Sailfish ``quant.sf`` files can be imported by setting type to *Salmon* or *Sailfish* respectively above. Note: for previous version of Salmon or Sailfish, in which the quant.sf files start with comment lines you will need to remove the comment lines before inputting here. An example of the format is shown below.
247
248 Example:
249
250 ============ ========== =============== =========== ===========
251 Name Length EffectiveLength TPM NumReads
252 ------------ ---------- --------------- ----------- -----------
253 NR_001526 164 20.4518 0 0
254 NR_001526_1 164 20.4518 0 0
255 NR_001526_2 164 20.4518 0 0
256 NM_130786 1764 1956.04 2.47415 109.165
257 NR_015380 2129 2139.53 1.77331 85.5821
258 NM_001198818 9360 7796.58 2.38616e-07 4.19648e-05
259 NM_001198819 9527 7964.62 0 0
260 NM_001198820 9410 7855.78 0 0
261 NM_014576 9267 7714.88 0.0481114 8.37255
262 ============ ========== =============== =========== ===========
263
264 **kallisto Files**
265
266 kallisto ``abundance.tsv`` files can be imported by setting type to *kallisto* above. An example of the format is shown below.
267
268 Example:
269
270 ============ ========== =============== =========== ===========
271 target_id length eff_length est_counts tpm
272 ------------ ---------- --------------- ----------- -----------
273 NR_001526 164 20.4518 0 0
274 NR_001526_1 164 20.4518 0 0
275 NR_001526_2 164 20.4518 0 0
276 NM_130786 1764 1956.04 109.165 2.47415
277 NR_015380 2129 2139.53 85.5821 1.77331
278 NM_001198818 9360 7796.58 4.19648e-05 2.38616e-07
279 NM_001198819 9527 7964.62 0 0
280 NM_001198820 9410 7855.78 0 0
281 NM_014576 9267 7714.88 8.37255 0.0481114
282 ============ ========== =============== =========== ===========
283
284 -----
233 285
234 **Output** 286 **Output**
235 287
236 DESeq2_ generates a tabular file containing the different columns and optional visualized results as PDF. 288 DESeq2_ generates a tabular file containing the different columns and optional visualized results as PDF.
237 289
247 7 p value adjusted for multiple testing with the Benjamini-Hochberg procedure 299 7 p value adjusted for multiple testing with the Benjamini-Hochberg procedure
248 which controls false discovery rate (FDR) 300 which controls false discovery rate (FDR)
249 ====== ========================================================== 301 ====== ==========================================================
250 302
251 .. _DESeq2: http://master.bioconductor.org/packages/release/bioc/html/DESeq2.html 303 .. _DESeq2: http://master.bioconductor.org/packages/release/bioc/html/DESeq2.html
252 ]]> 304 .. _tximport: https://bioconductor.org/packages/devel/bioc/vignettes/tximport/inst/doc/tximport.html
253 </help> 305 ]]></help>
254 <citations> 306 <citations>
255 <citation type="doi">10.1186/s13059-014-0550-8</citation> 307 <citation type="doi">10.1186/s13059-014-0550-8</citation>
256 </citations> 308 </citations>
257 </tool> 309 </tool>