Mercurial > repos > galaxyp > proteomics_moff

comparison moff.xml @ 2:28b65ce1a091 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/moFF commit ba04453c8ce4bd23a138e3e546ad17064b3ac38c
author galaxyp
date Wed, 14 Feb 2018 07:19:47 -0500
parents 8f0e76ad46ef
children 226287d75d96
comparison
equal deleted inserted replaced
1:8f0e76ad46ef 2:28b65ce1a091
1 <tool id="proteomics_moff" name="moFF" version="@VERSION@"> 1 <tool id="proteomics_moff" name="moFF" version="@VERSION@.1">
2 <description>extracts MS1 intensities from spectrum files</description> 2 <description>extracts MS1 intensities from spectrum files</description>
3 <macros> 3 <macros>
4 <token name="@VERSION@">1.2.1</token> 4 <token name="@VERSION@">1.2.1</token>
5 <!-- xml macros, used for shared Galaxy parameter inputs --> 5 <!-- xml macros, used for shared Galaxy parameter inputs -->
6 <xml name="ident_input_macro" token_allow_multiple="true" token_input_type="data"> 6 <xml name="ident_input_macro" token_allow_multiple="true" token_input_type="data">
75 --inputtsv './ident_inputs/${task.ident_input.ident_input_file.display_name}' 75 --inputtsv './ident_inputs/${task.ident_input.ident_input_file.display_name}'
76 ]]></token> 76 ]]></token>
77 <token name="@WRANGLE_IDENT_INPUT_SINGLE@"><![CDATA[ 77 <token name="@WRANGLE_IDENT_INPUT_SINGLE@"><![CDATA[
78 mkdir ./ident_inputs && 78 mkdir ./ident_inputs &&
79 #if $task.ident_input.input_type_selector == "ps": 79 #if $task.ident_input.input_type_selector == "ps":
80 ln -s '$task.ident_input.ident_input_file' './ident_inputs/$task.ident_input.ident_input_file.display_name' && 80 cp '$task.ident_input.ident_input_file' './ident_inputs/$task.ident_input.ident_input_file.display_name' &&
81 #else 81 #else
82 cp '$task.ident_input.ident_input_file' ./tempfile1.tab &&
82 ## optionally remove first line 83 ## optionally remove first line
83 #if $task.ident_input.remove_header: 84 #if $task.ident_input.remove_header:
84 sed -i '1d' '$task.ident_input.ident_input_file' && 85 sed -i '1d' ./tempfile1.tab &&
85 #end if 86 #end if
86 ## header row with correct names: "peptide", "prot", "mod_peptide", "rt", "mz", "mass", and "charge" 87 ## header row with correct names: "peptide", "prot", "mod_peptide", "rt", "mz", "mass", and "charge"
87 echo -e "peptide\tprot\tmod_peptide\trt\tmz\tmass\tcharge" > tempfile.tab && 88 echo -e "peptide\tprot\tmod_peptide\trt\tmz\tmass\tcharge" > ./tempfile2.tab &&
88 awk 'BEGIN{OFS="\t"; FS="\t"}{print \$pep,\$prot,\$mod,\$rt,\$mz,\$mass,\$charge}' pep="${task.ident_input.peptide}" prot="$task.ident_input.prot" mod="$task.ident_input.mod_peptide" rt="$task.ident_input.rt" mz="$task.ident_input.mz" mass="$task.ident_input.mass" charge="$task.ident_input.charge" '$task.ident_input.ident_input_file' >> tempfile.tab && 89 awk 'BEGIN{OFS="\t"; FS="\t"}{print \$pep,\$prot,\$mod,\$rt,\$mz,\$mass,\$charge}' pep="${task.ident_input.peptide}" prot="$task.ident_input.prot" mod="$task.ident_input.mod_peptide" rt="$task.ident_input.rt" mz="$task.ident_input.mz" mass="$task.ident_input.mass" charge="$task.ident_input.charge" ./tempfile1.tab >> ./tempfile2.tab &&
89 mv tempfile.tab '$task.ident_input.ident_input_file' && 90 mv ./tempfile2.tab './ident_inputs/$task.ident_input.ident_input_file.display_name' &&
90 ln -s '$task.ident_input.ident_input_file' './ident_inputs/$task.ident_input.ident_input_file.display_name' &&
91 #end if 91 #end if
92 ]]></token> 92 ]]></token>
93 <token name="@WRANGLE_IDENT_INPUT_MULTIPLE@"><![CDATA[ 93 <token name="@WRANGLE_IDENT_INPUT_MULTIPLE@"><![CDATA[
94 mkdir ./ident_inputs && 94 mkdir ./ident_inputs &&
95 #if $task.ident_input.input_type_selector == "ps": 95 #if $task.ident_input.input_type_selector == "ps":
96 #for $key in $task.ident_input.ident_input_file.keys(): 96 #for $key in $task.ident_input.ident_input_file.keys():
97 ln -s '${task.ident_input.ident_input_file[$key]}' './ident_inputs/${task.ident_input.ident_input_file[$key].display_name}' && 97 cp '${task.ident_input.ident_input_file[$key]}' './ident_inputs/${task.ident_input.ident_input_file[$key].display_name}' &&
98 #end for 98 #end for
99 #else 99 #else
100 #for $key in $task.ident_input.ident_input_file.keys(): 100 #for $key in $task.ident_input.ident_input_file.keys():
101 cp '${task.ident_input.ident_input_file[$key]}' './tempfile${key}_1.tab' &&
101 ## optionally remove first line 102 ## optionally remove first line
102 #if $task.ident_input.remove_header: 103 #if $task.ident_input.remove_header:
103 sed -i '1d' '$task.ident_input.ident_input_file[$key]' && 104 sed -i '1d' './tempfile${key}_1.tab' &&
104 #end if 105 #end if
105 ## header row with correct names: "peptide", "prot", "mod_peptide", "rt", "mz", "mass", and "charge" 106 ## header row with correct names: "peptide", "prot", "mod_peptide", "rt", "mz", "mass", and "charge"
106 echo -e "peptide\tprot\tmod_peptide\trt\tmz\tmass\tcharge" > tempfile.tab && 107 echo -e "peptide\tprot\tmod_peptide\trt\tmz\tmass\tcharge" > './tempfile${key}_2.tab' &&
107 awk 'BEGIN{OFS="\t"; FS="\t"}{print \$pep,\$prot,\$mod,\$rt,\$mz,\$mass,\$charge}' pep="${task.ident_input.peptide}" prot="$task.ident_input.prot" mod="$task.ident_input.mod_peptide" rt="$task.ident_input.rt" mz="$task.ident_input.mz" mass="$task.ident_input.mass" charge="$task.ident_input.charge" '$filename' >> tempfile.tab && 108 awk 'BEGIN{OFS="\t"; FS="\t"}{print \$pep,\$prot,\$mod,\$rt,\$mz,\$mass,\$charge}' pep="${task.ident_input.peptide}" prot="$task.ident_input.prot" mod="$task.ident_input.mod_peptide" rt="$task.ident_input.rt" mz="$task.ident_input.mz" mass="$task.ident_input.mass" charge="$task.ident_input.charge" './tempfile${key}_1.tab' >> './tempfile${key}_2.tab' &&
108 mv tempfile.tab '$task.ident_input.ident_input_file[$key]' && 109 mv './tempfile${key}_2.tab' './ident_inputs/$task.ident_input.ident_input_file[$key].display_name' &&
109 ln -s '$task.ident_input.ident_input_file[$key]' './ident_inputs/$task.ident_input.ident_input_file[$key].display_name' &&
110 #end for 110 #end for
111 #end if 111 #end if
112 ]]></token> 112 ]]></token>
113 <token name="@RAW_INPUT_ARG_SINGLE@"><![CDATA[ 113 <token name="@RAW_INPUT_ARG_SINGLE@"><![CDATA[
114 --inputraw './raws/$task.msms_input.inputraw.display_name' 114 --inputraw './raws/$task.msms_input.inputraw.display_name'
133 ]]></token> 133 ]]></token>
134 </macros> 134 </macros>
135 <requirements> 135 <requirements>
136 <requirement type="package" version="@VERSION@">moff</requirement> 136 <requirement type="package" version="@VERSION@">moff</requirement>
137 </requirements> 137 </requirements>
138 <version_command>echo @VERSION@</version_command>
138 <command detect_errors="aggressive"><![CDATA[ 139 <command detect_errors="aggressive"><![CDATA[
139 mkdir ./out && 140 mkdir ./out &&
140 #if $task.task_selector == "moff": 141 #if $task.task_selector == "moff":
141 @WRANGLE_IDENT_INPUT_SINGLE@ 142 @WRANGLE_IDENT_INPUT_SINGLE@
142 @WRANGLE_RAW_INPUT_SINGLE@ 143 @WRANGLE_RAW_INPUT_SINGLE@
186 #end if 187 #end if
187 ]]></command> 188 ]]></command>
188 <inputs> 189 <inputs>
189 <conditional name="task"> 190 <conditional name="task">
190 <param name="task_selector" type="select" label="Choose which module to run"> 191 <param name="task_selector" type="select" label="Choose which module to run">
191 <option value="moff" selected="true">Apex intensity</option> 192 <option value="moff">Apex intensity</option>
192 <option value="mbr">Match between runs</option> 193 <option value="mbr">Match between runs</option>
193 <option value="all">All (match-between-runs followed by quantitation)</option> 194 <option value="all">All (match-between-runs followed by quantitation)</option>
194 </param> 195 </param>
195 <when value = "moff"> 196 <when value = "moff">
196 <expand macro="ident_input_macro" allow_multiple="false"/> 197 <expand macro="ident_input_macro" allow_multiple="false"/>
199 help="Specify the tolerance parameter in ppm." /> 200 help="Specify the tolerance parameter in ppm." />
200 <param argument="--rt_w" type="float" value="3.0" label="Retention time window" 201 <param argument="--rt_w" type="float" value="3.0" label="Retention time window"
201 help="Specify rt window for xic in minutes." /> 202 help="Specify rt window for xic in minutes." />
202 <param argument="--rt_p" type="float" value="1" label="Time window for the peak" 203 <param argument="--rt_p" type="float" value="1" label="Time window for the peak"
203 help="Specify the time windows for the peak in minutes." /> 204 help="Specify the time windows for the peak in minutes." />
204 <param argument="--rt_p_match" type="float" value="1.5" label="Time window for the matched peak"
205 help="Specify the time windows for the matched peak in minutes." />
206 <param argument="--peptide_summary" type="boolean" value="true" label="Output the peptide summary?"/> 205 <param argument="--peptide_summary" type="boolean" value="true" label="Output the peptide summary?"/>
207 </when> 206 </when>
208 <when value="mbr"> 207 <when value="mbr">
209 <expand macro="ident_input_macro" allow_multiple="false" input_type="data_collection"/> 208 <expand macro="ident_input_macro" allow_multiple="false" input_type="data_collection"/>
210 <param argument="--ext" type="text" value="tab" label="Provide the extension used in the display file name (without the period)"/> 209 <param argument="--ext" type="text" value="tab" label="Provide the extension used in the display file name (without the period)"/>
223 <param argument="--peptide_summary" type="boolean" value="true" label="Output the peptide summary?"/> 222 <param argument="--peptide_summary" type="boolean" value="true" label="Output the peptide summary?"/>
224 </when> 223 </when>
225 </conditional> 224 </conditional>
226 </inputs> 225 </inputs>
227 <outputs> 226 <outputs>
228 <data format="tabular" name="output_table" label="${tool.name} quantification: ${on_string}"> 227 <data format="tabular" name="output_table" label="${tool.name} on ${on_string}: quantification">
229 <filter>task['task_selector']=='moff'</filter> 228 <filter>task['task_selector']=='moff'</filter>
230 </data> 229 </data>
231 <data format="txt" name="output_logs" label="${tool.name} log: ${on_string}"> 230 <data format="txt" name="output_logs" label="${tool.name} ${on_string}: log">
232 <filter>task['task_selector']=='moff'</filter> 231 <filter>task['task_selector']=='moff'</filter>
233 </data> 232 </data>
234 <collection name="ident_output" type="list" label="${tool.name} quantification: ${on_string}"> 233 <collection name="ident_output" type="list" label="${tool.name} on ${on_string}: quantification">
235 <filter>task['task_selector']=='all' or task['task_selector']=='mbr'</filter> 234 <filter>task['task_selector']=='all'</filter>
236 <!--discover datasets method -->
237 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.txt" directory="out" format="tabular"/> 235 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.txt" directory="out" format="tabular"/>
238 </collection> 236 </collection>
239 <collection name="log_output" type="list" label="${tool.name} logs: ${on_string}"> 237 <collection name="ident_output_mbr" type="list" label="${tool.name} on ${on_string}: matched">
238 <filter>task['task_selector']=='mbr'</filter>
239 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.txt" directory="out" format="tabular"/>
240 </collection>
241 <collection name="log_output" type="list" label="${tool.name} on ${on_string}: logs">
240 <filter>task['task_selector']=='all' or task['task_selector']=='mbr'</filter> 242 <filter>task['task_selector']=='all' or task['task_selector']=='mbr'</filter>
241 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.log" directory="out" format="txt"/> 243 <discover_datasets pattern="(?P&lt;designation&gt;.*)\.log" directory="out" format="txt"/>
242 </collection> 244 </collection>
243 <data format="tabular" name="output_peptide_summary" label="${tool.name} peptide summary: ${on_string}"> 245 <data format="tabular" name="output_peptide_summary" label="${tool.name} on ${on_string}: peptide summary">
244 <filter>task['peptide_summary']</filter> 246 <filter>task['peptide_summary'] and (task['task_selector']=='all' or task['task_selector']=='moff')</filter>
245 </data> 247 </data>
246 </outputs> 248 </outputs>
247 <tests> 249 <tests>
248 <!-- test moff_all --> 250 <!-- test moff_all -->
249 <test> 251 <test>
250 <param name="task_selector" value="all"/> 252 <param name="task|task_selector" value="all"/>
251 <param name="ident_input|input_type_selector" value="ps"/> 253 <param name="ident_input|input_type_selector" value="ps"/>
252 <param name="ident_input_file"> 254 <param name="ident_input_file">
253 <collection type="list"> 255 <collection type="list">
254 <element name="mbr_test1" value="input/mbr_test1.tabular"/> 256 <element name="mbr_test1" value="input/mbr_test1.tabular"/>
255 <element name="mbr_test2" value="input/mbr_test2.tabular"/> 257 <element name="mbr_test2" value="input/mbr_test2.tabular"/>
294 </element> 296 </element>
295 </output_collection> 297 </output_collection>
296 </test> 298 </test>
297 <!-- test moff alone --> 299 <!-- test moff alone -->
298 <test> 300 <test>
299 <param name="task_selector" value="moff"/> 301 <param name="task|task_selector" value="moff"/>
300 <param name="ident_input|input_type_selector" value="ps"/> 302 <param name="ident_input|input_type_selector" value="ps"/>
301 <param name="ident_input_file" value="input/test.tabular" ftype="tabular"/> 303 <param name="ident_input_file" value="input/test.tabular" ftype="tabular"/>
302 <param name="msms_input|input_type_selector" value="mzml"/> 304 <param name="msms_input|input_type_selector" value="mzml"/>
303 <param name="inputraw" value="input/test.mzml" ftype="mzml"/> 305 <param name="inputraw" value="input/test.mzml" ftype="mzml"/>
304 <param name="peptide_summary" value="true"/> 306 <param name="peptide_summary" value="true"/>
309 </assert_contents> 311 </assert_contents>
310 </output> 312 </output>
311 </test> 313 </test>
312 <!-- test the generic input --> 314 <!-- test the generic input -->
313 <test> 315 <test>
314 <param name="task_selector" value="moff"/> 316 <param name="task|task_selector" value="moff"/>
315 <param name="ident_input|input_type_selector" value="generic"/> 317 <param name="ident_input|input_type_selector" value="generic"/>
316 <param name="ident_input_file" value="input/test.tabular" ftype="tabular"/> 318 <param name="ident_input_file" value="input/test.tabular" ftype="tabular"/>
317 <param name="remove_header" value="true"/> 319 <param name="remove_header" value="true"/>
318 <param name="msms_input|input_type_selector" value="mzml"/> 320 <param name="msms_input|input_type_selector" value="mzml"/>
319 <param name="inputraw" value="input/test.mzml" ftype="mzml"/> 321 <param name="inputraw" value="input/test.mzml" ftype="mzml"/>
330 <assert_contents> 332 <assert_contents>
331 <has_line line="peptide at line 294 --> MZ: 677.3300 RT: 60.6078"/> 333 <has_line line="peptide at line 294 --> MZ: 677.3300 RT: 60.6078"/>
332 </assert_contents> 334 </assert_contents>
333 </output> 335 </output>
334 </test> 336 </test>
337 <test>
338 <param name="task|task_selector" value="all"/>
339 <param name="ident_input|input_type_selector" value="generic"/>
340 <param name="ident_input_file">
341 <collection type="list">
342 <element name="mbr_test1" value="input/mbr_test1.tabular"/>
343 <element name="mbr_test2" value="input/mbr_test2.tabular"/>
344 </collection>
345 </param>
346 <param name="remove_header" value="true"/>
347 <param name="peptide" value="3"/>
348 <param name="prot" value="2"/>
349 <param name="mod_peptide" value="7"/>
350 <param name="rt" value="13"/>
351 <param name="mz" value="14"/>
352 <param name="mass" value="17"/>
353 <param name="charge" value="15"/>
354 <param name="msms_input|input_type_selector" value="mzml"/>
355 <param name="inputraw">
356 <collection type="list">
357 <element name="mbr_test1" value="input/mbr_test1.mzml"/>
358 <element name="mbr_test2" value="input/mbr_test2.mzml"/>
359 </collection>
360 </param>
361 <param name="peptide_summary" value="true"/>
362 <output name="output_peptide_summary" ftype="tabular">
363 <assert_contents>
364 <has_text text="sumIntensity_mbr_test1"/>
365 <has_text text="sumIntensity_mbr_test2"/>
366 </assert_contents>
367 </output>
368 <output_collection name="ident_output" type="list">
369 <element name="mbr_test1_match_moff_result">
370 <assert_contents>
371 <has_text text="NH2-QVEEAVQSDDK-COOH"/>
372 </assert_contents>
373 </element>
374 <element name="mbr_test2_match_moff_result">
375 <assert_contents>
376 <has_text text="NH2-RDVGINNTVK-COOH"/>
377 </assert_contents>
378 </element>
379 </output_collection>
380 <output_collection name="log_output" type="list">
381 <element name="mbr_test1_match__moff">
382 <assert_contents>
383 <has_line line="peptide at line 200 --> MZ: 783.4200 RT: 134.6997 matched (yes=1/no=0): 0"/>
384 </assert_contents>
385 </element>
386 <element name="mbr_test2_match__moff">
387 <assert_contents>
388 <has_line line="peptide at line 132 --> MZ: 767.8700 RT: 98.1975 matched (yes=1/no=0): 0"/>
389 </assert_contents>
390 </element>
391 </output_collection>
392 </test>
335 <!-- test mbr --> 393 <!-- test mbr -->
336 <test> 394 <test>
337 <param name="task_selector" value="mbr"/> 395 <param name="task|task_selector" value="mbr"/>
338 <param name="ident_input|input_type_selector" value="ps"/> 396 <param name="ident_input|input_type_selector" value="ps"/>
339 <param name="ident_input_file"> 397 <param name="ident_input_file">
340 <collection type="list"> 398 <collection type="list">
341 <element name="mbr_test1" value="input/mbr_test1.tabular"/> 399 <element name="mbr_test1" value="input/mbr_test1.tabular"/>
342 <element name="mbr_test2" value="input/mbr_test2.tabular"/> 400 <element name="mbr_test2" value="input/mbr_test2.tabular"/>
343 </collection> 401 </collection>
344 </param> 402 </param>
345 <param name="ext" value="tabular"/> 403 <param name="ext" value="tabular"/>
346 <output_collection name="ident_output" type="list" count="2"> 404 <output_collection name="ident_output_mbr" type="list" count="2">
347 <element name="mbr_test1_match"> 405 <element name="mbr_test1_match">
348 <assert_contents> 406 <assert_contents>
349 <has_text text="NH2-QVEEAVQSDDK-COOH"/> 407 <has_text text="NH2-QVEEAVQSDDK-COOH"/>
350 </assert_contents> 408 </assert_contents>
351 </element> 409 </element>
376 3. All (match between runs followed by apex intensity): this is used for more than one pair of identification and spectrum files. 434 3. All (match between runs followed by apex intensity): this is used for more than one pair of identification and spectrum files.
377 435
378 If both match between runs and apex intensity are desired, it is best to run them both at once (i.e., run the 'All' module). 436 If both match between runs and apex intensity are desired, it is best to run them both at once (i.e., run the 'All' module).
379 The MBR module is mainly useful for observing the intermediate steps of the algorithm - its outputs are not able to be used as inputs in moFF or in other tools. 437 The MBR module is mainly useful for observing the intermediate steps of the algorithm - its outputs are not able to be used as inputs in moFF or in other tools.
380 438
439 If quantification of multiple files without MBR is desired, the apex intensity module may be run with multiple files or a dataset collection in batch mode.
440 In either case, moFF must be given the paired files at the same time - thus the best method is to construct a dataset collection in which the raw and identification files are in the same order.
441
381 442
382 *Inputs:* 443 *Inputs:*
383 444
384 - Identification file: this can either be a generic tabular file or the standard PSM report from PeptideShaker. 445 - Identification file: this can either be a generic tabular file or the standard PSM report from PeptideShaker.
385 If it is a generic tabular file, please select the columns corresponding to the required information. 446 If it is a generic tabular file, please select the columns corresponding to the required information.