Mercurial > repos > eschen42 > mqppep_anova

comparison workflow/ppenrich_suite_wf.ga @ 13:b41a077af3aa 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 040e4945da00a279cb60daae799fce9489f99c50"
author eschen42
date Tue, 22 Mar 2022 20:47:40 +0000
parents
children 6679616d0c18
comparison
equal deleted inserted replaced
12:4deacfee76ef 13:b41a077af3aa
1 {
2 "a_galaxy_workflow": "true",
3 "annotation": "phoshpoproteomic enrichment data pre-processing and ANOVA",
4 "creator": [
5 {
6 "class": "Person",
7 "identifier": "0000-0002-2882-0508",
8 "name": "Art Eschenlauer"
9 }
10 ],
11 "format-version": "0.1",
12 "license": "MIT",
13 "name": "ppenrich_suite_wf",
14 "steps": {
15 "0": {
16 "annotation": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).",
17 "content_id": null,
18 "errors": null,
19 "id": 0,
20 "input_connections": {},
21 "inputs": [
22 {
23 "description": "The Phospho (STY)Sites.txt file produced by MaxQuant (found in the txt folder).",
24 "name": "Phospho (STY)Sites.txt"
25 }
26 ],
27 "label": "Phospho (STY)Sites.txt",
28 "name": "Input dataset",
29 "outputs": [],
30 "position": {
31 "bottom": 346.3999938964844,
32 "height": 81.89999389648438,
33 "left": 495,
34 "right": 695,
35 "top": 264.5,
36 "width": 200,
37 "x": 495,
38 "y": 264.5
39 },
40 "tool_id": null,
41 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
42 "tool_version": null,
43 "type": "data_input",
44 "uuid": "21c3c29d-9e8c-4ece-b585-9e68fed7a93f",
45 "workflow_outputs": []
46 },
47 "1": {
48 "annotation": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)",
49 "content_id": null,
50 "errors": null,
51 "id": 1,
52 "input_connections": {},
53 "inputs": [
54 {
55 "description": "FASTA file of all human canonical isoforms, derived from Swiss-Prot (e.g., merge of https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot_varsplic.fasta.gz and https://ftp.uniprot.org/pub/databases/uniprot/current_release/knowledgebase/complete/uniprot_sprot.fasta.gz)",
56 "name": "SwissProt_Human_Canonical_Isoform.fasta"
57 }
58 ],
59 "label": "SwissProt_Human_Canonical_Isoform.fasta",
60 "name": "Input dataset",
61 "outputs": [],
62 "position": {
63 "bottom": 708.8000030517578,
64 "height": 102.30000305175781,
65 "left": 685,
66 "right": 885,
67 "top": 606.5,
68 "width": 200,
69 "x": 685,
70 "y": 606.5
71 },
72 "tool_id": null,
73 "tool_state": "{\"optional\": false, \"format\": [\"fasta\"]}",
74 "tool_version": null,
75 "type": "data_input",
76 "uuid": "5da7317c-4def-48f3-8eac-af95bd18b290",
77 "workflow_outputs": []
78 },
79 "2": {
80 "annotation": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)",
81 "content_id": null,
82 "errors": null,
83 "id": 2,
84 "input_connections": {},
85 "inputs": [
86 {
87 "description": "Derived from https://networkin.info/download/networkin_human_predictions_3.1.tsv.xz (which is free for non-commercial use - for required citation, see https://networkin.info/)",
88 "name": "NetworKIN_cutoffscore2.0.tabular"
89 }
90 ],
91 "label": "NetworKIN_cutoffscore2.0.tabular",
92 "name": "Input dataset",
93 "outputs": [],
94 "position": {
95 "bottom": 853.8000030517578,
96 "height": 102.30000305175781,
97 "left": 696,
98 "right": 896,
99 "top": 751.5,
100 "width": 200,
101 "x": 696,
102 "y": 751.5
103 },
104 "tool_id": null,
105 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
106 "tool_version": null,
107 "type": "data_input",
108 "uuid": "2edff8de-4379-45e2-b6b9-6ed4706bbf00",
109 "workflow_outputs": []
110 },
111 "3": {
112 "annotation": "Derived from http://hprd.org/serine_motifs, http://hprd.org/tyrosine_motifs, and http://pegasus.biochem.mpg.de/phosida/help/motifs.aspx",
113 "content_id": null,
114 "errors": null,
115 "id": 3,
116 "input_connections": {},
117 "inputs": [
118 {
119 "description": "Derived from http://hprd.org/serine_motifs, http://hprd.org/tyrosine_motifs, and http://pegasus.biochem.mpg.de/phosida/help/motifs.aspx",
120 "name": "pSTY_Motifs.tabular"
121 }
122 ],
123 "label": "pSTY_Motifs.tabular",
124 "name": "Input dataset",
125 "outputs": [],
126 "position": {
127 "bottom": 977.3999938964844,
128 "height": 81.89999389648438,
129 "left": 708,
130 "right": 908,
131 "top": 895.5,
132 "width": 200,
133 "x": 708,
134 "y": 895.5
135 },
136 "tool_id": null,
137 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
138 "tool_version": null,
139 "type": "data_input",
140 "uuid": "86ebaaf2-b050-4eca-a88b-23a4c1af39f5",
141 "workflow_outputs": []
142 },
143 "4": {
144 "annotation": "Derived from Kinase_Substrate_Dataset.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)",
145 "content_id": null,
146 "errors": null,
147 "id": 4,
148 "input_connections": {},
149 "inputs": [
150 {
151 "description": "Derived from Kinase_Substrate_Dataset.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)",
152 "name": "PSP_Kinase_Substrate_Dataset.tabular"
153 }
154 ],
155 "label": "PSP_Kinase_Substrate_Dataset.tabular",
156 "name": "Input dataset",
157 "outputs": [],
158 "position": {
159 "bottom": 1126.8000030517578,
160 "height": 102.30000305175781,
161 "left": 729,
162 "right": 929,
163 "top": 1024.5,
164 "width": 200,
165 "x": 729,
166 "y": 1024.5
167 },
168 "tool_id": null,
169 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
170 "tool_version": null,
171 "type": "data_input",
172 "uuid": "92f16705-a19c-4fb9-b278-3ae8e11f09d8",
173 "workflow_outputs": []
174 },
175 "5": {
176 "annotation": "Derived from Regulatory_sites.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)",
177 "content_id": null,
178 "errors": null,
179 "id": 5,
180 "input_connections": {},
181 "inputs": [
182 {
183 "description": "Derived from Regulatory_sites.gz found at https://www.phosphosite.org/staticDownloads (free for non-commercial use - see that link for citation.)",
184 "name": "PSP_Regulatory_sites.tabular"
185 }
186 ],
187 "label": "PSP_Regulatory_sites.tabular",
188 "name": "Input dataset",
189 "outputs": [],
190 "position": {
191 "bottom": 1251.3999938964844,
192 "height": 81.89999389648438,
193 "left": 745,
194 "right": 945,
195 "top": 1169.5,
196 "width": 200,
197 "x": 745,
198 "y": 1169.5
199 },
200 "tool_id": null,
201 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
202 "tool_version": null,
203 "type": "data_input",
204 "uuid": "5ab49d93-11e4-4e91-b30b-92269b319879",
205 "workflow_outputs": []
206 },
207 "6": {
208 "annotation": "List of alpha cutoff values for significance testing; text file having no header and a single line for each cutoff value.",
209 "content_id": null,
210 "errors": null,
211 "id": 6,
212 "input_connections": {},
213 "inputs": [
214 {
215 "description": "List of alpha cutoff values for significance testing; text file having no header and a single line for each cutoff value.",
216 "name": "alpha_levels.tabular"
217 }
218 ],
219 "label": "alpha_levels.tabular",
220 "name": "Input dataset",
221 "outputs": [],
222 "position": {
223 "bottom": 1501.8999938964844,
224 "height": 81.89999389648438,
225 "left": 727,
226 "right": 927,
227 "top": 1420,
228 "width": 200,
229 "x": 727,
230 "y": 1420
231 },
232 "tool_id": null,
233 "tool_state": "{\"optional\": false, \"format\": [\"tabular\"]}",
234 "tool_version": null,
235 "type": "data_input",
236 "uuid": "481c627c-a4ce-45d7-b659-4f54692aafc7",
237 "workflow_outputs": []
238 },
239 "7": {
240 "annotation": "",
241 "content_id": "mqppep_preproc",
242 "errors": null,
243 "id": 7,
244 "input_connections": {
245 "networkin": {
246 "id": 2,
247 "output_name": "output"
248 },
249 "p_sty_motifs": {
250 "id": 3,
251 "output_name": "output"
252 },
253 "phosphoSites": {
254 "id": 0,
255 "output_name": "output"
256 },
257 "protein_fasta": {
258 "id": 1,
259 "output_name": "output"
260 },
261 "psp_kinase_substrate": {
262 "id": 4,
263 "output_name": "output"
264 },
265 "psp_regulatory_sites": {
266 "id": 5,
267 "output_name": "output"
268 }
269 },
270 "inputs": [],
271 "label": null,
272 "name": "MaxQuant Phosphopeptide Preprocessing",
273 "outputs": [
274 {
275 "name": "phosphoPepIntensities",
276 "type": "tabular"
277 },
278 {
279 "name": "enrichGraph",
280 "type": "pdf"
281 },
282 {
283 "name": "locProbCutoffGraph",
284 "type": "pdf"
285 },
286 {
287 "name": "enrichGraph_svg",
288 "type": "svg"
289 },
290 {
291 "name": "locProbCutoffGraph_svg",
292 "type": "svg"
293 },
294 {
295 "name": "filteredData_tabular",
296 "type": "tabular"
297 },
298 {
299 "name": "quantData_tabular",
300 "type": "tabular"
301 },
302 {
303 "name": "mapped_phophopeptides",
304 "type": "tabular"
305 },
306 {
307 "name": "melted_phophopeptide_map",
308 "type": "tabular"
309 },
310 {
311 "name": "mqppep_output_sqlite",
312 "type": "sqlite"
313 },
314 {
315 "name": "preproc_tab",
316 "type": "tabular"
317 },
318 {
319 "name": "preproc_csv",
320 "type": "csv"
321 },
322 {
323 "name": "preproc_sqlite",
324 "type": "sqlite"
325 }
326 ],
327 "position": {
328 "bottom": 1408.7000122070312,
329 "height": 793.2000122070312,
330 "left": 1138.5,
331 "right": 1338.5,
332 "top": 615.5,
333 "width": 200,
334 "x": 1138.5,
335 "y": 615.5
336 },
337 "post_job_actions": {
338 "RenameDatasetActionenrichGraph": {
339 "action_arguments": {
340 "newname": "#{phosphoSites}.enrichGraph_pdf"
341 },
342 "action_type": "RenameDatasetAction",
343 "output_name": "enrichGraph"
344 },
345 "RenameDatasetActionenrichGraph_svg": {
346 "action_arguments": {
347 "newname": "#{phosphoSites}.enrichGraph_svg"
348 },
349 "action_type": "RenameDatasetAction",
350 "output_name": "enrichGraph_svg"
351 },
352 "RenameDatasetActionfilteredData_tabular": {
353 "action_arguments": {
354 "newname": "#{phosphoSites}.filteredData"
355 },
356 "action_type": "RenameDatasetAction",
357 "output_name": "filteredData_tabular"
358 },
359 "RenameDatasetActionlocProbCutoffGraph": {
360 "action_arguments": {
361 "newname": "#{phosphoSites}.locProbCutoffGraph_pdf"
362 },
363 "action_type": "RenameDatasetAction",
364 "output_name": "locProbCutoffGraph"
365 },
366 "RenameDatasetActionlocProbCutoffGraph_svg": {
367 "action_arguments": {
368 "newname": "#{phosphoSites}.locProbCutoffGraph_svg"
369 },
370 "action_type": "RenameDatasetAction",
371 "output_name": "locProbCutoffGraph_svg"
372 },
373 "RenameDatasetActionmapped_phophopeptides": {
374 "action_arguments": {
375 "newname": "#{phosphoSites}.ppep_map"
376 },
377 "action_type": "RenameDatasetAction",
378 "output_name": "mapped_phophopeptides"
379 },
380 "RenameDatasetActionmelted_phophopeptide_map": {
381 "action_arguments": {
382 "newname": "#{phosphoSites}.melted"
383 },
384 "action_type": "RenameDatasetAction",
385 "output_name": "melted_phophopeptide_map"
386 },
387 "RenameDatasetActionmqppep_output_sqlite": {
388 "action_arguments": {
389 "newname": "#{phosphoSites}.ppep_mapping_sqlite"
390 },
391 "action_type": "RenameDatasetAction",
392 "output_name": "mqppep_output_sqlite"
393 },
394 "RenameDatasetActionphosphoPepIntensities": {
395 "action_arguments": {
396 "newname": "#{phosphoSites}.ppep_intensities"
397 },
398 "action_type": "RenameDatasetAction",
399 "output_name": "phosphoPepIntensities"
400 },
401 "RenameDatasetActionpreproc_csv": {
402 "action_arguments": {
403 "newname": "#{phosphoSites}.preproc_csv"
404 },
405 "action_type": "RenameDatasetAction",
406 "output_name": "preproc_csv"
407 },
408 "RenameDatasetActionpreproc_sqlite": {
409 "action_arguments": {
410 "newname": "#{phosphoSites}.preproc_sqlite"
411 },
412 "action_type": "RenameDatasetAction",
413 "output_name": "preproc_sqlite"
414 },
415 "RenameDatasetActionpreproc_tab": {
416 "action_arguments": {
417 "newname": "#{phosphoSites}.preproc_tab"
418 },
419 "action_type": "RenameDatasetAction",
420 "output_name": "preproc_tab"
421 },
422 "RenameDatasetActionquantData_tabular": {
423 "action_arguments": {
424 "newname": "#{phosphoSites}.quantData"
425 },
426 "action_type": "RenameDatasetAction",
427 "output_name": "quantData_tabular"
428 }
429 },
430 "tool_id": "mqppep_preproc",
431 "tool_state": "{\"collapseFunc\": \"sum\", \"intervalCol\": \"1\", \"localProbCutoff\": \"0.75\", \"merge_function\": \"sum\", \"networkin\": {\"__class__\": \"ConnectedValue\"}, \"p_sty_motifs\": {\"__class__\": \"ConnectedValue\"}, \"phosphoCol\": \"^Number of Phospho [(]STY[)]$\", \"phosphoSites\": {\"__class__\": \"ConnectedValue\"}, \"protein_fasta\": {\"__class__\": \"ConnectedValue\"}, \"psp_kinase_substrate\": {\"__class__\": \"ConnectedValue\"}, \"psp_regulatory_sites\": {\"__class__\": \"ConnectedValue\"}, \"pst_not_py\": \"true\", \"species\": \"human\", \"startCol\": \"^Intensity[^_]\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
432 "tool_version": null,
433 "type": "tool",
434 "uuid": "1e983dba-edca-4aed-a589-49b1651b4a85",
435 "workflow_outputs": [
436 {
437 "label": "preproc_csv",
438 "output_name": "preproc_csv",
439 "uuid": "8cba5367-b25c-40e0-a324-552225b1aa1d"
440 },
441 {
442 "label": "locProbCutoffGraph_pdf",
443 "output_name": "locProbCutoffGraph",
444 "uuid": "641c5959-dab4-42d1-986d-8e6aaeb74ef6"
445 },
446 {
447 "label": "melted_phosphopeptide_map",
448 "output_name": "melted_phophopeptide_map",
449 "uuid": "878dc817-26a3-4061-9dd4-56e737b3c4f7"
450 },
451 {
452 "label": "enrichGraph_svg",
453 "output_name": "enrichGraph_svg",
454 "uuid": "4492366c-945e-492f-8381-1c97c4da2264"
455 },
456 {
457 "label": "locProbCutoffGraph_svg",
458 "output_name": "locProbCutoffGraph_svg",
459 "uuid": "06faf93c-5f04-4cb3-9e41-58e465f6180e"
460 },
461 {
462 "label": "filteredData",
463 "output_name": "filteredData_tabular",
464 "uuid": "76e2e268-f728-45f0-9973-793fbde0dd0a"
465 },
466 {
467 "label": "ppep_map",
468 "output_name": "mapped_phophopeptides",
469 "uuid": "d0fea028-2ea5-4862-8a92-c2088edfcbe1"
470 },
471 {
472 "label": "ppep_mapping_sqlite",
473 "output_name": "mqppep_output_sqlite",
474 "uuid": "eb996931-c548-4f3b-aaaa-39cc711df516"
475 },
476 {
477 "label": "preproc_tab",
478 "output_name": "preproc_tab",
479 "uuid": "c9410cf1-44a2-4aa6-b3df-06cef74f3a45"
480 },
481 {
482 "label": "preproc_sqlite",
483 "output_name": "preproc_sqlite",
484 "uuid": "4eb22cc3-5879-4625-89c0-e0fddb01a197"
485 },
486 {
487 "label": "ppep_intensities",
488 "output_name": "phosphoPepIntensities",
489 "uuid": "c704fd66-5ac3-4779-ad40-536955cd81e3"
490 },
491 {
492 "label": "enrichGraph_pdf",
493 "output_name": "enrichGraph",
494 "uuid": "5bf2a478-0431-4d32-84a9-7d46aad80ec5"
495 },
496 {
497 "label": "quantData",
498 "output_name": "quantData_tabular",
499 "uuid": "cc922a75-6e72-4e60-add2-4b6ed8f73cdb"
500 }
501 ]
502 },
503 "8": {
504 "annotation": "Perform ANOVA. For imputing missing values, use median of non-missing values from the same treatment group.",
505 "content_id": "mqppep_anova",
506 "errors": null,
507 "id": 8,
508 "input_connections": {
509 "alpha_file": {
510 "id": 6,
511 "output_name": "output"
512 },
513 "input_file": {
514 "id": 7,
515 "output_name": "preproc_tab"
516 }
517 },
518 "inputs": [],
519 "label": "MaxQuant Phosphopeptide ANOVA group-median imputed",
520 "name": "MaxQuant Phosphopeptide ANOVA",
521 "outputs": [
522 {
523 "name": "imputed_data_file",
524 "type": "tabular"
525 },
526 {
527 "name": "report_file",
528 "type": "pdf"
529 }
530 ],
531 "position": {
532 "bottom": 1775.6000061035156,
533 "height": 255.60000610351562,
534 "left": 1370,
535 "right": 1570,
536 "top": 1520,
537 "width": 200,
538 "x": 1370,
539 "y": 1520
540 },
541 "post_job_actions": {
542 "RenameDatasetActionimputed_data_file": {
543 "action_arguments": {
544 "newname": "#{input_file}.intensities_group-mean-imputed_QN_LT"
545 },
546 "action_type": "RenameDatasetAction",
547 "output_name": "imputed_data_file"
548 },
549 "RenameDatasetActionreport_file": {
550 "action_arguments": {
551 "newname": "#{input_file}.intensities_group-mean-imputed_report (download/unzip to view)"
552 },
553 "action_type": "RenameDatasetAction",
554 "output_name": "report_file"
555 }
556 },
557 "tool_id": "mqppep_anova",
558 "tool_state": "{\"alpha_file\": {\"__class__\": \"ConnectedValue\"}, \"first_data_column\": \"Intensity\", \"imputation\": {\"imputation_method\": \"group-median\", \"__current_case__\": 0}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"sample_grouping_regex\": \"(\\\\d+)\", \"sample_names_regex\": \"\\\\.(\\\\d+)[A-Z]$\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
559 "tool_version": null,
560 "type": "tool",
561 "uuid": "ffa771c3-c52d-42a4-b78f-a60a39678792",
562 "workflow_outputs": [
563 {
564 "label": "intensities_group-mean-imputed_QN_LT",
565 "output_name": "imputed_data_file",
566 "uuid": "169d677f-0acb-4c56-b057-21f4aaf2b920"
567 },
568 {
569 "label": "intensities_group-mean-imputed_report",
570 "output_name": "report_file",
571 "uuid": "25edae88-3bb6-4ec9-8b98-686fded7ed79"
572 }
573 ]
574 },
575 "9": {
576 "annotation": "Perform ANOVA. For imputing missing values, create random values.",
577 "content_id": "mqppep_anova",
578 "errors": null,
579 "id": 9,
580 "input_connections": {
581 "alpha_file": {
582 "id": 6,
583 "output_name": "output"
584 },
585 "input_file": {
586 "id": 7,
587 "output_name": "preproc_tab"
588 }
589 },
590 "inputs": [],
591 "label": "MaxQuant Phosphopeptide ANOVA randomly imputed",
592 "name": "MaxQuant Phosphopeptide ANOVA",
593 "outputs": [
594 {
595 "name": "imputed_data_file",
596 "type": "tabular"
597 },
598 {
599 "name": "report_file",
600 "type": "pdf"
601 }
602 ],
603 "position": {
604 "bottom": 1609.6000061035156,
605 "height": 255.60000610351562,
606 "left": 1617,
607 "right": 1817,
608 "top": 1354,
609 "width": 200,
610 "x": 1617,
611 "y": 1354
612 },
613 "post_job_actions": {
614 "RenameDatasetActionimputed_data_file": {
615 "action_arguments": {
616 "newname": "#{input_file}.intensities_randomly-imputed_QN_LT"
617 },
618 "action_type": "RenameDatasetAction",
619 "output_name": "imputed_data_file"
620 },
621 "RenameDatasetActionreport_file": {
622 "action_arguments": {
623 "newname": "#{input_file}.intensities_randomly-imputed_report (download/unzip to view)"
624 },
625 "action_type": "RenameDatasetAction",
626 "output_name": "report_file"
627 }
628 },
629 "tool_id": "mqppep_anova",
630 "tool_state": "{\"alpha_file\": {\"__class__\": \"ConnectedValue\"}, \"first_data_column\": \"Intensity\", \"imputation\": {\"imputation_method\": \"random\", \"__current_case__\": 3, \"meanPercentile\": \"1\", \"sdPercentile\": \"0.2\"}, \"input_file\": {\"__class__\": \"ConnectedValue\"}, \"sample_grouping_regex\": \"(\\\\d+)\", \"sample_names_regex\": \"\\\\.(\\\\d+)[A-Z]$\", \"__page__\": null, \"__rerun_remap_job_id__\": null}",
631 "type": "tool",
632 "uuid": "f1f2bdf9-fbc0-4205-b834-9a8af5814dc9",
633 "workflow_outputs": [
634 {
635 "label": "intensities_randomly-imputed_QN_LT",
636 "output_name": "imputed_data_file",
637 "uuid": "d70a3476-fb42-4533-831b-4fcb2bda74fc"
638 },
639 {
640 "label": "intensities_randomly-imputed_report",
641 "output_name": "report_file",
642 "uuid": "d6701a61-357b-4a27-8154-ca41eb16d8a6"
643 }
644 ]
645 }
646 },
647 "tags": [
648 "ppenrich"
649 ],
650 "uuid": "445a0eb0-25c7-44c0-8259-a3346b01cbf3",
651 "version": 3
652 }