Mercurial > repos > charles-bernard > alfa

comparison ALFA/alfa_wrapper.xml @ 22:1714165f5df0 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author charles-bernard
date Thu, 27 Oct 2016 04:42:59 -0400
parents a74f6350f32e
children 887c6cb328e9
comparison
equal deleted inserted replaced
21:728294cecd96 22:1714165f5df0
6 <requirement type="package" version="2.24">bedtools</requirement> 6 <requirement type="package" version="2.24">bedtools</requirement>
7 <requirement type="package" version="1.2">samtools</requirement> 7 <requirement type="package" version="1.2">samtools</requirement>
8 <requirement type="package" version="1.4">matplotlib</requirement> 8 <requirement type="package" version="1.4">matplotlib</requirement>
9 </requirements> 9 </requirements>
10 10
11 <command interpreter="bash"> 11 <command interpreter="python">
12 alfa_wrapper.sh $__root_dir__ $__tool_directory__ $ALFA_config $logReport 12 <![CDATA[
13 </command> 13 ALFA_wrapper.py
14 14
15 --project_name "${projectName}"
16
17 ##__INPUT 1__##
18 #if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "index"
19 --index $annotation.annotationSource['strandedIndex'] $annotation.annotationSource['unstrandedIndex']
20 #else if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "built_in_index"
21 --bi_index $annotation.annotationSource.built_in_index_prefix.fields.prefix
22 #else
23 --annotation $annotation.annotationSource['annotationFile']
24 #end if
25
26 ##__INPUT 2__##
27 --reads_format $reads.readsType['readsTypeSelection']
28 --reads
29 #for $i, $r in enumerate ( $reads.readsType['readsList'] )
30 __fname__$r.readsFile
31 __label__$r.readsLabel
32 #end for
33 --strandness $reads['strandness']
34
35 ##__OUTPUT FILES__##
36 #if str ( $outputFiles['plot'] ) == "True"
37 #if str ( $outputOptions['plotFormat'] ) == "pdf"
38 --output_pdf $outputPdf
39 #else if str ( $outputOptions['plotFormat'] ) == "png"
40 --output_png $outputCategoriesPng $outputBiotypesPng
41 #else
42 --output_svg $outputCategoriesSvg $outputBiotypesSvg
43 #end if
44 #end if
45 #if str ( $outputFiles['countFile'] ) == "True"
46 --output_count $outputCountFile
47 #end if
48 #if str ( $outputFiles['index'] ) == "True"
49 --output_index $outputStrandedIndex $outputUnstrandedIndex
50 #end if
51
52 ##__OUTPUT OPTIONS__##
53 --categories_depth $outputOptions['categoriesDepth']
54 #if str ( $outputFiles['plot'] ) == "True"
55 --plot_format $outputOptions['plotFormat']
56 #if str ( $outputOptions.plotThreshold['plotThresholdChoice'] ) == "True"
57 --threshold $outputOptions.plotThreshold.yMin $outputOptions.plotThreshold.yMax
58 #end if
59 #end if
60
61 --log_report $logReport
62 --galaxy_root $__root_dir__
63 --tool_dir $__tool_directory__
64 ]]>
65 </command>
15 <inputs> 66 <inputs>
16 <param name="projectName" value="ALFA" type="text" size="20" label="Project Name"> 67 <param name="projectName" value="ALFA" type="text" size="20" label="Project Name">
17 <validator type="empty_field" message="Please, specify a name for your project."/> 68 <validator type="empty_field" message="Please, specify a name for your project."/>
18 </param> 69 </param>
19 70
27 <when value="personal_gtf"> 78 <when value="personal_gtf">
28 <param name="annotationFile" type="data" format="Gff, Gtf" label="Select your personal annotation file (GTF format)"> 79 <param name="annotationFile" type="data" format="Gff, Gtf" label="Select your personal annotation file (GTF format)">
29 </param> 80 </param>
30 </when> 81 </when>
31 <when value="index"> 82 <when value="index">
32 <param name="strandedIndex" type="data" format="index" label="Select your ALFA stranded index file (index format)"/> 83 <param name="strandedIndex" type="data" format="index" label="Select your ALFA Stranded index file (index format)"/>
33 <param name="unstrandedIndex" type="data" format="index" label="Select your ALFA Unstranded index file (index format)"/> 84 <param name="unstrandedIndex" type="data" format="index" label="Select your ALFA Unstranded index file (index format)"/>
34 </when> 85 </when>
35 <when value="built_in_index"> 86 <when value="built_in_index">
36 <param name="built_in_index_prefix" type="select" label="Select Genome"> 87 <param name="built_in_index_prefix" type="select" label="Select Genome">
37 <options from_data_table="alfa_indexes"> 88 <options from_data_table="alfa_indexes">
72 <param name="plot" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories and Biotypes Histograms" help="Plot the nucleotides distribution of the reads per genomic categories and biotypes"/> 123 <param name="plot" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories and Biotypes Histograms" help="Plot the nucleotides distribution of the reads per genomic categories and biotypes"/>
73 <param name="countFile" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories Count File" help="Edit the exact count of nucleotides in the reads per genomic categories and biotypes"/> 124 <param name="countFile" type="boolean" truevalue="True" falsevalue="False" checked="True" label="Categories Count File" help="Edit the exact count of nucleotides in the reads per genomic categories and biotypes"/>
74 <param name="index" type="boolean" truevalue="True" falsevalue="False" checked="False" label ="Indexes" help="Print the resulting stranded and unstranded indexes from the gtf input file (useful if you plan to run ALFA again with this annotated sequence)"/> 125 <param name="index" type="boolean" truevalue="True" falsevalue="False" checked="False" label ="Indexes" help="Print the resulting stranded and unstranded indexes from the gtf input file (useful if you plan to run ALFA again with this annotated sequence)"/>
75 </section> 126 </section>
76 127
77 <section name="outputOptions" title="ADVANCED OPTIONS" expanded="False"> 128 <section name="outputOptions" title="ADVANCED SETTINGS" expanded="False">
78 <param name="categoriesDepth" type="select" label="Categories to Display"> 129 <param name="categoriesDepth" type="select" label="Categories to Display">
79 <option value="1">gene | intergenic</option> 130 <option value="1">gene | intergenic</option>
80 <option value="2">exon | intron | intergenic</option> 131 <option value="2">exon | intron | intergenic</option>
81 <option value="3" selected="true">5’-UTR | CDS | 3’-UTR | intron | intergenic</option> 132 <option value="3" selected="true">5’-UTR | CDS | 3’-UTR | intron | intergenic</option>
82 <option value="4">5’-UTR | start_codon | CDS | stop_codon | 3’-UTR | intron | intergenic</option> 133 <option value="4">5’-UTR | start_codon | CDS | stop_codon | 3’-UTR | intron | intergenic</option>
90 <param name="plotThresholdChoice" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Plot Options: Modify y axis range of the normalized counts of bio-features" help="Ignore if you did not choose the histograms output file"/> 141 <param name="plotThresholdChoice" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Plot Options: Modify y axis range of the normalized counts of bio-features" help="Ignore if you did not choose the histograms output file"/>
91 <when value="True"> 142 <when value="True">
92 <param name="yMin" type="float" value="-2.0" label="y min"/> 143 <param name="yMin" type="float" value="-2.0" label="y min"/>
93 <param name="yMax" type="float" value="2.0" label="y max"/> 144 <param name="yMax" type="float" value="2.0" label="y max"/>
94 </when> 145 </when>
146 <when value="False"></when>
95 </conditional> 147 </conditional>
96 </section> 148 </section>
97 </inputs> 149 </inputs>
98 150
99 <outputs> 151 <outputs>
121 </data> 173 </data>
122 <data name="outputUnstrandedIndex" format="txt" label="${projectName}-Unstranded Index"> 174 <data name="outputUnstrandedIndex" format="txt" label="${projectName}-Unstranded Index">
123 <filter>outputFiles['index'] is True</filter> 175 <filter>outputFiles['index'] is True</filter>
124 </data> 176 </data>
125 </outputs> 177 </outputs>
126
127 <configfiles>
128 <configfile name="ALFA_config">
129 projectName=$projectName
130
131 ##__INPUT 1__##
132 annotationSource=$annotation.annotationSource['annotationSourceSelection']
133 #if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "index"
134 annotationFile=None
135 strandedIndex=$annotation.annotationSource['strandedIndex']
136 unstrandedIndex=$annotation.annotationSource['unstrandedIndex']
137 #else if str ( $annotation.annotationSource['annotationSourceSelection'] ) == "built_in_index"
138 annotationFile=None
139 built_in_index_prefix=$annotation.annotationSource.built_in_index_prefix.fields.prefix
140 #else
141 annotationFile=$annotation.annotationSource['annotationFile']
142 strandedIndex=None
143 unstrandedIndex=None
144 #end if
145
146 ##__INPUT 2__##
147 readsType=$reads.readsType['readsTypeSelection']
148 #for $i, $r in enumerate ( $reads.readsType['readsList'] )
149 readsFile[$i]=$r.readsFile
150 readsLabel[$i]=$r.readsLabel
151 #end for
152 strandness=$reads['strandness']
153
154 ##__OUTPUT FILES__##
155 plotChoice=$outputFiles['plot']
156 countFileChoice=$outputFiles['countFile']
157 indexChoice=$outputFiles['index']
158
159 outputPdf=$outputPdf
160 outputCategoriesPng=$outputCategoriesPng
161 outputBiotypesPng=$outputBiotypesPng
162 outputCategoriesSvg=$outputCategoriesSvg
163 outputBiotypesSvg=$outputBiotypesSvg
164 outputCountFile=$outputCountFile
165 outputStrandedIndex=$outputStrandedIndex
166 outputUnstrandedIndex=$outputUnstrandedIndex
167
168 ##__OUTPUT OPTIONS__##
169 categoriesDepth=$outputOptions['categoriesDepth']
170 plotFormat=$outputOptions['plotFormat']
171 plotThresholdChoice=$outputOptions.plotThreshold['plotThresholdChoice']
172 #if str ( $outputOptions.plotThreshold['plotThresholdChoice'] ) == "True"
173 yMin=$outputOptions.plotThreshold.yMin
174 yMax=$outputOptions.plotThreshold.yMax
175 #else
176 yMin=None
177 yMax=None
178 #end if
179 </configfile>
180 </configfiles>
181 178
182 <tests> 179 <tests>
183 <test> 180 <test>
184 <param name="alfa_toy" /> 181 <param name="alfa_toy" />
185 <section name="annotation"> 182 <section name="annotation">
219 </assert_stdout> 216 </assert_stdout>
220 </test> 217 </test>
221 </tests> 218 </tests>
222 219
223 <help> 220 <help>
221 <![CDATA[
222 **What it does**
223
224
225 | ALFA provides a global overview of features distribution composing New Generation Sequencing dataset(s).
226 |
227 | Given a set of aligned reads (BAM files) and an annotation file (GTF format), the tool produces plots of the raw and normalized distributions of those reads among genomic categories (stop codon, 5'-UTR, CDS, intergenic, etc.) and biotypes (protein coding genes, miRNA, tRNA, etc.). Whatever the sequencing technique, whatever the organism.
228
229 ----
230
224 **ALFA acronym** 231 **ALFA acronym**
225 232
226 - Annotation.Landscape.For.Aligned reads 233 - Annotation.Landscape.For.Aligned reads
227 234
228 ---- 235 ----
229 236
230 **What it does**
231
232 | ALFA provides a global overview of features distribution composing New Generation Sequencing dataset(s).
233 |
234 | Given a set of aligned reads (BAM files) and an annotation file (GTF format), the tool produces plots of the raw and normalized distributions of those reads among genomic categories (stop codon, 5'-UTR, CDS, intergenic, etc.) and biotypes (protein coding genes, miRNA, tRNA, etc.). Whatever the sequencing technique, whatever the organism.
235
236 ----
237
238 **Official documentation of the tool** 237 **Official documentation of the tool**
239 238
240 239
241 - https://github.com/biocompibens/ALFA 240 - https://github.com/biocompibens/ALFA
242 241
248 247
249 ---- 248 ----
250 249
251 **Nota Bene** 250 **Nota Bene**
252 251
253 1. **Input 1: Annotation File** 252 * **Input 1: Annotation File**
254 253
255 254
256 | ALFA requires as first input an annotation file (sequence, genome...) in gtf format in order to generate indexes that will be used in a 2nd step of the program. 255 | ALFA requires as first input an annotation file (sequence, genome...) in gtf format in order to generate alfa indexes needed in a second round of the program.
257 | Indexes are files which list all the coordinates of all categories (stop codon, 5'-UTR, CDS, intergenic...) and biotypes (protein coding genes, miRNA, tRNA, ...) encountered in the annotated sequence. 256 | Indexes are files which list all the coordinates of the categories (stop codon, 5'-UTR, CDS, intergenic...) and biotypes (protein coding genes, miRNA, tRNA, ...) encountered in the annotated sequence.
257 |
258 258
259 .. class:: warningmark 259 .. class:: warningmark
260 260
261 Gtf File must be sorted. 261 | Gtf File must be sorted.
262 262 |
263 .. class:: infomark 263
264 264 .. class:: infomark
265 Generation of indexes from an annotation file may be time consuming (i.e ~10min for the human genome). Thus, ALFA allows the user to submit directly indexes generated in previous runs. 265
266 266 | Generation of indexes from an annotation file might be time consuming (i.e ~10min for the human genome). Thus, ALFA allows the user to submit directly indexes generated in previous runs.
267 2. **Input 2: Reads** 267 |
268 268
269 | ALFA requires as second input a single or a set of mapped reads file(s) in either bam or bedgraph format. These files are required to intersect the coordinates of the mapped reads with the associated categories and biotypes on the annotated sequence. 269 .. class:: infomark
270
271 | ALFA also allows to use built-in indexes to save even more computational time. In order to generate these built-in indexes, install the data manager tool 'data_manager_build_alfa_indexes' available on the toolshed.
272
273 * **Input 2: Reads**
274
275 | ALFA requires as second input a single or a set of mapped reads file(s) in either bam or bedgraph format. The coordinates of the mapped reads will be intersected with the according categories and biotypes mentioned in the indexes.
270 | The strandness option determines which strand of the annotated sequence will be taken into account during this intersection. 276 | The strandness option determines which strand of the annotated sequence will be taken into account during this intersection.
271 277 |
272 .. class:: warningmark 278
273 279 .. class:: warningmark
274 Bam or Bedgraph file(s) must be sorted. 280
275 281 | Bam or Bedgraph file(s) must be sorted.
276 <!-- 282 |
277 .. class:: warningmark 283
278 284 .. class:: warningmark
279 For oriented reads (either matching the forward strand or the reverse strand), 'forward' or 'reverse' strandness must be selected. 285
280 286 | Chromosome names in reads and in annotation file (gtf or indexes) must be the same for the intersection to occur
281 .. class:: warningmark 287 |
282 288
283 For paired-end or non-oriented reads, 'unstranded' strandness must be selected. 289 * **Output files**
284 -->
285
286 3. **Output files**
287 290
288 | The result of the intersection is a count file displaying the count of nucleotides in the reads for each genomic categories and biotypes. From this count file, plots of the raw and normalized distributions of the reads among these categories are generated. 291 | The result of the intersection is a count file displaying the count of nucleotides in the reads for each genomic categories and biotypes. From this count file, plots of the raw and normalized distributions of the reads among these categories are generated.
289 | In the output files section, the user can choose what kind of files he desires as ALFA output. Categories Count File and Plots are proposed by default. 292 | In the output files section, the user can choose what kind of files he desires as ALFA output. Categories Count File and Plots are proposed by default.
290 293 |
291 .. class:: infomark 294
292 295 .. class:: infomark
293 The user can also select the 'indexes' option as output. This option is interesting if you plan to run ALFA again with the same submitted annotation file. *See Nota Bene/Input 1: Annotation File for more information.* 296
294 297 | The user can also select the 'indexes' option as output. This option is interesting if you plan to run ALFA again with the same submitted annotation file. *See Nota Bene/Input 1: Annotation File for more information.*
295 298 |
296 - `How the plots look like`_ 299
297 300 - `How the plots look like`_
298 .. _How the plots look like: https://github.com/biocompibens/ALFA#plots 301
299 302 .. _How the plots look like: https://github.com/biocompibens/ALFA#plots
300 - `How they are generated`_ 303
301 304 |
302 .. _How they are generated: https://github.com/biocompibens/ALFA#detailed-example 305
306 - `How they are generated`_
307
308 .. _How they are generated: https://github.com/biocompibens/ALFA#detailed-example
303 309
304 ---- 310 ----
305 311
306 **ALFA Developpers** 312 **ALFA Developpers**
307 313
308 | Benoît Noël and Mathieu Bahin: *compbio team, Institut de Biologie de l'Ecole Normale Supérieure de Paris* 314 | Benoît Noël and Mathieu Bahin: *compbio team, Institut de Biologie de l'Ecole Normale Supérieure de Paris*
309 315
310 316 ]]>
311 </help> 317 </help>
312 318
313 <citations> 319 <citations>
314 <citation type="bibtex">@MISC{ 320 <citation type="bibtex">@MISC{
315 author="Benoît Noël and Mathieu Bahin" 321 author="Benoît Noël and Mathieu Bahin"