Mercurial > repos > eschen42 > mqppep_preproc

comparison mqppep_preproc.xml @ 23:7560a4e80a1e 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/mqppep commit 0c7ca054e77e042c8a584c9903073da064df7d8b
author eschen42
date Thu, 30 Jun 2022 16:15:57 +0000
parents 43f1fd0ff86b
children 29775869faba
comparison
equal deleted inserted replaced
22:43f1fd0ff86b 23:7560a4e80a1e
1 <tool 1 <tool
2 id="mqppep_preproc" 2 id="mqppep_preproc"
3 name="MaxQuant Phosphopeptide Preprocessing" 3 name="MaxQuant Phosphopeptide Preprocessing"
4 version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" 4 version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"
5 python_template_version="3.5"
6 profile="21.05" 5 profile="21.05"
7 > 6 >
8 <description> 7 <description>
9 Transform the output of MaxQuant for phosphoproteome-enriched samples to prepare it for statistical anlaysis. 8 Prep phosphoproteomic MaxQuant output for statistical anlaysis.
10 </description> 9 </description>
11 <macros> 10 <macros>
12 <import>macros.xml</import> 11 <import>macros.xml</import>
13 </macros> 12 </macros>
13 <edam_topics>
14 <edam_topic>topic_0121</edam_topic><!-- Proteomics -->
15 <edam_topic>topic_3520</edam_topic><!-- Proteomics experiment-->
16 </edam_topics>
17 <edam_operations>
18 <edam_operation>operation_0338</edam_operation><!-- Sequence database search -->
19 <edam_operation>operation_0361</edam_operation><!-- Sequence annotation -->
20 <edam_operation>operation_3434</edam_operation><!-- Conversion -->
21 <edam_operation>operation_3436</edam_operation><!-- Aggregation -->
22 </edam_operations>
14 <expand macro="requirements"/> 23 <expand macro="requirements"/>
15 <command detect_errors="exit_code"><![CDATA[ 24 <command detect_errors="exit_code"><![CDATA[
16 ( 25 echo '--- localization-filter step:'
17 echo '--- localization-filter step:' 26 && (
18 ) && (
19 Rscript '$__tool_directory__/MaxQuantProcessingScript.R' 27 Rscript '$__tool_directory__/MaxQuantProcessingScript.R'
20 -i '$phosphoSites' 28 -i '$phosphoSites'
21 #if $pst_py_selector == "y" 29 #if $pst_py_selector == "y"
22 --enriched Y 30 --enriched Y
23 #else 31 #else
25 #end if 33 #end if
26 --phosphoCol '$phosphocol_script' 34 --phosphoCol '$phosphocol_script'
27 --startCol '$startcol_script' 35 --startCol '$startcol_script'
28 --intervalCol $intervalCol 36 --intervalCol $intervalCol
29 --localProbCutoff $localProbCutoff 37 --localProbCutoff $localProbCutoff
30 --collapse_func $collapseFunc 38 --collapse_func $collapse_func
31 -o '$phosphoPepIntensities' 39 -o '$phosphoPepIntensities'
32 --locProbCutoffGraph $locProbCutoffGraph 40 --locProbCutoffGraph $locProbCutoffGraph
33 --enrichGraph $enrichGraph 41 --enrichGraph $enrichGraph
34 --locProbCutoffGraph_svg $locProbCutoffGraph_svg 42 --locProbCutoffGraph_svg $locProbCutoffGraph_svg
35 --enrichGraph_svg $enrichGraph_svg 43 --enrichGraph_svg $enrichGraph_svg
36 --filtered_data $filteredData_tabular 44 --filtered_data $filteredData_tabular
37 --quant_data $quantData_tabular 45 --quant_data $quantData_tabular
38 ) && ( 46 ) &&
39 echo '... end localization-filter.' 47 echo '... end localization-filter.'
40 ) && ( 48 && (
41 echo '--- kinase-mapping step:' 49 echo '--- kinase-mapping step:'
42 ) && ( 50 ) && (
43 perl '$__tool_directory__/PhosphoPeptide_Upstream_Kinase_Mapping.pl' 51 perl '$__tool_directory__/PhosphoPeptide_Upstream_Kinase_Mapping.pl'
44 -i '$phosphoPepIntensities' 52 -i '$phosphoPepIntensities'
45 -f '$protein_fasta' 53 -f '$protein_fasta'
55 -F $merge_function 63 -F $merge_function
56 -o '$mapped_phophopeptides' 64 -o '$mapped_phophopeptides'
57 -O '$melted_phophopeptide_map' 65 -O '$melted_phophopeptide_map'
58 -D '$mqppep_output_sqlite' 66 -D '$mqppep_output_sqlite'
59 -s '$species' 67 -s '$species'
60 ) && ( 68 ) &&
61 echo '... end kinase-mapping.' 69 echo '... end kinase-mapping.'
62 ) && ( 70 &&
63 echo '--- merge-and-filter step:' 71 echo '--- merge-and-filter step:'
64 ) && ( 72 && (
65 python '$__tool_directory__/mqppep_mrgfltr.py' 73 python '$__tool_directory__/mqppep_mrgfltr.py'
66 --phosphopeptides='$mapped_phophopeptides' 74 --phosphopeptides='$mapped_phophopeptides'
67 --ppep_mapping_db='$mqppep_output_sqlite' 75 --ppep_mapping_db='$mqppep_output_sqlite'
68 --species='$species' 76 --species='$species'
69 --mrgfltr_tab='$preproc_tab' 77 --mrgfltr_tab='$preproc_tab'
70 --mrgfltr_csv='$preproc_csv' 78 --mrgfltr_csv='$preproc_csv'
71 --mrgfltr_sqlite='$preproc_sqlite' 79 --mrgfltr_sqlite='$preproc_sqlite'
72 ) && (
73 echo '... end merge-and-filter.'
74 ) 80 )
81 && echo '... end merge-and-filter.'
75 ]]></command> 82 ]]></command>
76 <configfiles> 83 <configfiles>
77 <configfile name="phosphocol_script">$phosphoCol 84 <configfile name="phosphocol_script">$phosphoCol
78 </configfile> 85 </configfile>
79 <configfile name="startcol_script">$startCol 86 <configfile name="startcol_script">$startCol
80 </configfile> 87 </configfile>
81 </configfiles> 88 </configfiles>
82 <inputs> 89 <inputs>
83 <param name="phosphoSites" type="data" format="tabular" 90 <param name="phosphoSites" type="data" format="tabular"
84 label="Phospho (STY)Sites.txt" 91 label="Phospho (STY)Sites.txt"
85 help="[phosphoSites] Tabular 'Phospho (STY)Sites.txt' produced by MaxQuant" 92 help="Tabular 'Phospho (STY)Sites.txt' produced by MaxQuant"
86 /> 93 />
87 <param name="phosphoCol" type="text" 94 <param name="phosphoCol" type="text"
88 label="pattern for column 'Number of Phospho (STY)'" 95 label="pattern for column 'Number of Phospho (STY)'"
89 help="[phosphoCol] PERL-compatible regular expression matching header of column having number of 'Phospho (STY)'" 96 help="PERL-compatible regular expression matching header of column having number of 'Phospho (STY)'"
90 value="^Number of Phospho [(]STY[)]$"> 97 value="^Number of Phospho [(]STY[)]$">
91 <sanitizer> 98 <sanitizer>
92 <valid initial="string.printable"> 99 <valid initial="string.printable">
93 <remove value="&apos;"/> 100 <remove value="&apos;"/>
94 </valid> 101 </valid>
95 </sanitizer> 102 </sanitizer>
96 </param> 103 </param>
97 <param name="startCol" type="text" 104 <param name="startCol" type="text"
98 label="pattern for first column of intensity values" 105 label="pattern for first column of intensity values"
99 help="[startCol] PERL-compatible regular expression matching column header having first sample intensity" 106 help="PERL-compatible regular expression matching column header having first sample intensity"
100 value="^Intensity[^_]"> 107 value="^Intensity[^_]">
101 <sanitizer> 108 <sanitizer>
102 <valid initial="string.printable"> 109 <valid initial="string.printable">
103 <remove value="&apos;"/> 110 <remove value="&apos;"/>
104 </valid> 111 </valid>
105 </sanitizer> 112 </sanitizer>
106 </param> 113 </param>
107 <param name="intervalCol" type="integer" value="1" min="1" 114 <param name="intervalCol" type="integer" value="1" min="1"
108 label="Interval between the intensity column of samples" 115 label="Interval between the intensity column of samples"
109 help="[intervalCol] E.g., 1 if subsequent column is next sample; 2 if next sample is two columns away, etc."/> 116 help="E.g., 1 if subsequent column is next sample; 2 if next sample is two columns away, etc."/>
110 <param name="pst_py_selector" type="select" 117 <param name="pst_py_selector" type="select"
111 label="Phosphopeptide enrichment type" 118 label="Phosphopeptide enrichment type"
112 help="[enrichment] Were samples enriched for pS and pT, or were they enriched for pY instead?" 119 help="Were samples enriched for pS and pT, or were they enriched for pY instead?"
113 > 120 >
114 <option value="st" selected="true">pST</option> 121 <option value="st" selected="true">pST</option>
115 <option value="y">pY</option> 122 <option value="y">pY</option>
116 </param> 123 </param>
117 <param name="collapseFunc" type="select" 124 <param name="collapse_func" type="select"
118 label="Intensity merge function" 125 label="Intensity merge function"
119 help="[collapseFunc] When a peptide is multiply phosphorylated, how should intensities be merged? [default: sum]" 126 help="When a peptide is multiply phosphorylated, how should intensities be merged? [default: sum]"
120 > 127 >
121 <option value="sum" selected="true">sum</option> 128 <option value="sum" selected="true">sum</option>
122 <option value="mean">average</option> 129 <option value="mean">average</option>
123 </param> 130 </param>
124 <param name="localProbCutoff" type="float" value="0.75" min="0" max="1.0" 131 <param name="localProbCutoff" type="float" value="0.75" min="0" max="1.0"
125 label="Localization Probability Cutoff" 132 label="Localization Probability Cutoff"
126 help="[localProbCutoff] See help below for an explanation." 133 help="See help below for an explanation."
127 /> 134 />
128 <param name="merge_function" type="select" label="intensity merge-function" 135 <param name="merge_function" type="select" label="intensity merge-function"
129 help="[merge_function] Specifies how intensities for identical phosphosites should be merged"> 136 help="Specifies how intensities for identical phosphosites should be merged">
130 <option value="sum" selected="true">sum</option> 137 <option value="sum" selected="true">sum</option>
131 <option value="average">average</option> 138 <option value="average">average</option>
132 </param> 139 </param>
133 <param name="protein_fasta" type="data" format="fasta" label="UniProtKB/SwissProt FASTA database" 140 <param name="protein_fasta" type="data" format="fasta" label="UniProtKB/SwissProt FASTA database"
134 help="[protein_fasta] Sequence database; supply the same FASTA file as you supplied to by MaxQuant" 141 help="Sequence database; supply the same FASTA file as you supplied to by MaxQuant"
135 /> 142 />
136 <param name="networkin" type="data" format="tabular" label="NetworKIN file" 143 <param name="networkin" type="data" format="tabular" label="NetworKIN file"
137 help="[networkin] NetworKIN file; see help section below"/> 144 help="NetworKIN file; see help section below"/>
138 <param name="p_sty_motifs" type="data" format="tabular" label="pSTY_Motifs file" 145 <param name="p_sty_motifs" type="data" format="tabular" label="pSTY_Motifs file"
139 help="[p_sty_motifs] pS/pT/pY phosphorylation site motifs; see help section below"/> 146 help="pS/pT/pY phosphorylation site motifs; see help section below"/>
140 <param name="psp_kinase_substrate" type="data" format="tabular" label="PSP_Kinase_Substrate_Dataset" 147 <param name="psp_kinase_substrate" type="data" format="tabular" label="PSP_Kinase_Substrate_Dataset"
141 help="[psp_kinase_substrate] 'Kinase-substrate dataset'; see help section below"/> 148 help="'Kinase-substrate dataset'; see help section below"/>
142 <param name="psp_regulatory_sites" type="data" format="tabular" label="PSP_Regulatory_sites" 149 <param name="psp_regulatory_sites" type="data" format="tabular" label="PSP_Regulatory_sites"
143 help="[psp_regulatory_sites] 'Regulatory sites'; see help section below"/> 150 help="'Regulatory sites'; see help section below"/>
144 <param name="species" 151 <param name="species"
145 type="text" 152 type="text"
146 value = "human" 153 value = "human"
147 label="filter to limit PhosphoSitePlus records to indicated species" 154 label="filter to limit PhosphoSitePlus records to indicated species"
148 help="[species] (field may be empty) [default: human]" 155 help="(field may be empty) [default: human]. If you supply this parameter, use the species indentifier seen as a suffix in UniProtKB"
149 /> 156 />
150 </inputs> 157 </inputs>
151 <outputs> 158 <outputs>
152 <!-- localization filter --> 159 <!-- localization filter -->
153 <data name="phosphoPepIntensities" format="tabular" label="${phosphoSites.name}.ppep_intensities" /> 160 <data name="phosphoPepIntensities" format="tabular" label="${phosphoSites.name}.ppep_intensities" />
178 <param name="merge_function" value="sum"/> 185 <param name="merge_function" value="sum"/>
179 186
180 <param name="phosphoCol" value="^Number of Phospho [(][STY][STY]*[)]$"/> 187 <param name="phosphoCol" value="^Number of Phospho [(][STY][STY]*[)]$"/>
181 <param name="startCol" value="^Intensity[^_]"/> 188 <param name="startCol" value="^Intensity[^_]"/>
182 <param name="intervalCol" value="1"/> 189 <param name="intervalCol" value="1"/>
183 <param name="collapseFunc" value="sum"/> 190 <param name="collapse_func" value="sum"/>
184 <param name="localProbCutoff" value="0.75"/> 191 <param name="localProbCutoff" value="0.75"/>
185 <param name="species" value="human"/> 192 <param name="species" value="human"/>
186 193
187 <output name="phosphoPepIntensities"> 194 <output name="phosphoPepIntensities">
188 <assert_contents> 195 <assert_contents>
198 <has_text text="AEBP2_HUMAN Isoform 2 of Zinc finger protein AEBP2" /> 205 <has_text text="AEBP2_HUMAN Isoform 2 of Zinc finger protein AEBP2" />
199 <has_text text="molecular association, regulation" /> 206 <has_text text="molecular association, regulation" />
200 <has_text text="cell cycle regulation" /> 207 <has_text text="cell cycle regulation" />
201 <has_text text="PPP2CA(INDUCES)" /> 208 <has_text text="PPP2CA(INDUCES)" />
202 <has_text text="SNCA(DISRUPTS)" /> 209 <has_text text="SNCA(DISRUPTS)" />
203 <has_text text="Casein Kinase II substrate" />
204 <has_text text="PKC kinase substrate" />
205 <has_text text="PKCiota" />
206 <has_text text="Csnk2a1" />
207 <has_text text="CDK7" /> 210 <has_text text="CDK7" />
208 <has_text text="CK1alpha" /> 211 <has_text text="CK1alpha" />
209 <has_text text="CK2a2" />
210 <has_text text="CK2alpha" /> 212 <has_text text="CK2alpha" />
211 <has_text text="DNAPK" /> 213 <has_text text="DNAPK" />
212 <has_text text="HIPK2" /> 214 <has_text text="HIPK2" />
213 <has_text text="IKKalpha" /> 215 <has_text text="IKKalpha" />
214 <has_text text="PKCalpha" /> 216 <has_text text="PKCalpha" />
215 <has_text text="PKCbeta" /> 217 <has_text text="PKCbeta" />
218 <has_text text="PKC" />
219 <has_text text="CK2a2" />
220 <has_text text="CK2alpha" />
221 <has_text text="Csnk2a1" />
216 </assert_contents> 222 </assert_contents>
217 </output> 223 </output>
218 224
219 <output name="melted_phophopeptide_map"> 225 <output name="melted_phophopeptide_map">
220 <assert_contents> 226 <assert_contents>
221 <has_text text="CDK7_NetworKIN" /> 227 <has_text text="CDK7" />
222 <has_text text="CK1alpha_NetworKIN" /> 228 <has_text text="CK1alpha" />
223 <has_text text="CK2a2_NetworKIN" /> 229 <has_text text="CK2alpha" />
224 <has_text text="CK2alpha_NetworKIN" /> 230 <has_text text="DNAPK" />
225 <has_text text="DNAPK_NetworKIN" /> 231 <has_text text="HIPK2" />
226 <has_text text="HIPK2_NetworKIN" /> 232 <has_text text="IKKalpha" />
227 <has_text text="IKKalpha_NetworKIN" /> 233 <has_text text="PKCalpha" />
228 <has_text text="PKCalpha_NetworKIN" /> 234 <has_text text="PKCbeta" />
229 <has_text text="PKCbeta_NetworKIN" /> 235 <has_text text="PKC" />
230 <has_text text="PKC kinase substrate motif" /> 236 <has_text text="CK2a2" />
231 <has_text text="Casein Kinase II substrate motif" /> 237 <has_text text="CK2alpha" />
232 <has_text text="Csnk2a1_PhosphoSite" /> 238 <has_text text="Csnk2a1" />
233 </assert_contents> 239 </assert_contents>
234 </output> 240 </output>
235 </test> 241 </test>
236 <test> 242 <test>
237 <param name="phosphoSites" ftype="tabular" value="test_input_for_preproc.tabular" /> 243 <param name="phosphoSites" ftype="tabular" value="test_input_for_preproc.tabular" />
244 <param name="merge_function" value="sum"/> 250 <param name="merge_function" value="sum"/>
245 251
246 <param name="phosphoCol" value="^Number of Phospho [(][STY][STY]*[)]$"/> 252 <param name="phosphoCol" value="^Number of Phospho [(][STY][STY]*[)]$"/>
247 <param name="startCol" value="^Intensity[^_]"/> 253 <param name="startCol" value="^Intensity[^_]"/>
248 <param name="intervalCol" value="1"/> 254 <param name="intervalCol" value="1"/>
249 <param name="collapseFunc" value="sum"/> 255 <param name="collapse_func" value="sum"/>
250 <param name="localProbCutoff" value="0.75"/> 256 <param name="localProbCutoff" value="0.75"/>
251 <param name="species" value="human"/> 257 <param name="species" value="human"/>
252 258
253 <output name="phosphoPepIntensities"> 259 <output name="phosphoPepIntensities">
254 <assert_contents> 260 <assert_contents>
272 </assert_contents> 278 </assert_contents>
273 </output> 279 </output>
274 280
275 <output name="melted_phophopeptide_map"> 281 <output name="melted_phophopeptide_map">
276 <assert_contents> 282 <assert_contents>
277 <has_text text="Casein Kinase II substrate motif (HPRD)" /> 283 <has_text text="EphA6" />
278 <has_text text="EPHA4_PhosphoSite" /> 284 <has_text text="EPHA4" />
279 <has_text text="EphA4_NetworKIN" /> 285 <has_text text="EphA4" />
280 </assert_contents> 286 </assert_contents>
281 </output> 287 </output>
282 </test> 288 </test>
283 </tests> 289 </tests>
284 <help><![CDATA[ 290 <help><![CDATA[
353 ``quantData`` 359 ``quantData``
354 Data table (in tabular format) comprising rows of the ``filteredData`` file whose localization probability exceeds the **Localization Probability Cutoff** parameter. 360 Data table (in tabular format) comprising rows of the ``filteredData`` file whose localization probability exceeds the **Localization Probability Cutoff** parameter.
355 361
356 **Authors** 362 **Authors**
357 363
364 ``Nicholas A. Graham``
365 (`ORCiD 0000-0002-6811-1941 <https://orcid.org/0000-0002-6811-1941>`_) initiated the original script.
366
358 ``Larry C. Cheng`` 367 ``Larry C. Cheng``
359 (`ORCiD 0000-0002-6922-6433 <https://orcid.org/0000-0002-6922-6433>`_) wrote the original script. 368 (`ORCiD 0000-0002-6922-6433 <https://orcid.org/0000-0002-6922-6433>`_) updated the original script.
360 369
361 ``Arthur C. Eschenlauer`` 370 ``Arthur C. Eschenlauer``
362 (`ORCiD 0000-0002-2882-0508 <https://orcid.org/0000-0002-2882-0508>`_) adapted the script to run in Galaxy. 371 (`ORCiD 0000-0002-2882-0508 <https://orcid.org/0000-0002-2882-0508>`_) adapted the script to run in Galaxy.
363 372
364 ``James E. Johnson`` 373 ``James E. Johnson``
480 ``ppep_mapping_sqlite`` updated with annotations, in SQLite format. 489 ``ppep_mapping_sqlite`` updated with annotations, in SQLite format.
481 490
482 **Authors** 491 **Authors**
483 492
484 ``Nicholas A. Graham`` 493 ``Nicholas A. Graham``
485 (`ORCiD 0000-0002-6811-1941 <https://orcid.org/0000-0002-6811-1941>`_) may have initiated the original script. 494 (`ORCiD 0000-0002-6811-1941 <https://orcid.org/0000-0002-6811-1941>`_) initiated the original script.
486 495
487 ``Larry C. Cheng`` 496 ``Larry C. Cheng``
488 (`ORCiD 0000-0002-6922-6433 <https://orcid.org/0000-0002-6922-6433>`_) may have updated the original script. 497 (`ORCiD 0000-0002-6922-6433 <https://orcid.org/0000-0002-6922-6433>`_) updated the original script.
489 498
490 ``Arthur C. Eschenlauer`` 499 ``Arthur C. Eschenlauer``
491 (`ORCiD 0000-0002-2882-0508 <https://orcid.org/0000-0002-2882-0508>`_) adapted the script to run in Galaxy. 500 (`ORCiD 0000-0002-2882-0508 <https://orcid.org/0000-0002-2882-0508>`_) adapted the script to run in Galaxy.
492 501
493 .. |reg| unicode:: U+000AE .. REGISTERED SIGN 502 .. |reg| unicode:: U+000AE .. REGISTERED SIGN