-
Notifications
You must be signed in to change notification settings - Fork 6
/
workflow.cwl
394 lines (375 loc) · 14.3 KB
/
workflow.cwl
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
#!/usr/bin/env cwl-runner
cwlVersion: v1.0
class: Workflow
doc: "
CWL workflow for generating Roslin / Argos post pipeline analysis files and cBioPortal data and metadata files
Inputs
------
The following parameters are required:
project_id
project_pi
request_pi
project_short_name
project_name
project_description
cancer_type
cancer_study_identifier
argos_version_string
helix_filter_version
is_impact
extra_pi_groups
The following filenames are required:
analysis_mutations_filename
analysis_gene_cna_filename
analysis_sv_filename
analysis_segment_cna_filename
cbio_segment_data_filename
cbio_meta_cna_segments_filename
The following filenames have default values and are optional:
cbio_mutation_data_filename
cbio_cna_data_filename
cbio_fusion_data_filename
cbio_clinical_patient_data_filename
cbio_clinical_sample_data_filename
cbio_clinical_sample_meta_filename
cbio_clinical_patient_meta_filename
cbio_meta_study_filename
cbio_meta_cna_filename
cbio_meta_fusions_filename
cbio_meta_mutations_filename
cbio_cases_all_filename
cbio_cases_cnaseq_filename
cbio_cases_cna_filename
cbio_cases_sequenced_filename
Output
------
Workflow output should look like this:
output
├── analysis
│ ├── <project_id>.gene.cna.txt
│ ├── <project_id>.muts.maf
│ ├── <project_id>.seg.cna.txt
│ └── <project_id>.svs.maf
└── portal
├── case_list
│ ├── cases_all.txt
│ ├── cases_cnaseq.txt
│ ├── cases_cna.txt
│ └── cases_sequenced.txt
├── data_clinical_patient.txt
├── data_clinical_sample.txt
├── data_CNA.ascna.txt
├── data_CNA.scna.txt
├── data_CNA.txt
├── data_fusions.txt
├── data_mutations_extended.txt
├── meta_clinical_patient.txt
├── meta_clinical_sample.txt
├── meta_CNA.txt
├── meta_fusions.txt
├── meta_mutations_extended.txt
├── meta_study.txt
├── <project_id>_data_cna_hg19.seg
└── <project_id>_meta_cna_hg19_seg.txt
"
requirements:
ScatterFeatureRequirement: {}
StepInputExpressionRequirement: {}
InlineJavascriptRequirement: {}
SubworkflowFeatureRequirement: {}
inputs:
project_id:
type: string
doc: "unique identifier for the project (PROJ_ID)"
project_pi:
type: string
doc: "principle investigator for the project (PROJ_PI)"
request_pi:
type: string
doc: "principle investigator who requested the project (REQUEST_PI)"
project_short_name:
type: string
doc: "a short name for the project in cBioPortal (PROJ_SHORT_NAME)"
project_name:
type: string
doc: "a formal name for the project (PROJ_NAME)"
project_description:
type: string
doc: "a description of the project (PROJ_DESC)"
cancer_type:
type: string
doc: "the type of cancer used in the project (CANCER_TYPE)"
cancer_study_identifier:
type: string
doc: "a study identifier for the project to use in cBioPortal (CANCER_STUDY_IDENTIFIER)"
argos_version_string:
type: string
doc: "the version label of Roslin / Argos used to run the project analysis (ARGOS_VERSION_STRING)"
helix_filter_version:
type: string
doc: "the version label of this helix filter repo (HELIX_FILTER_VERSION; git describe --all --long)"
is_impact:
default: True
type: boolean
doc: "whether or not the project is an IMPACT project; should be the value 'True' if so, otherwise any other value means 'False' (IS_IMPACT)"
# TODO: this shouild actually be type: string[]
extra_pi_groups:
type: [ "null", string]
default: null
doc: "a list of other groups to be associated with the project in cBioPortal (EXTRA_PI_GROUPS)"
analysis_segment_cna_filename:
type: string
doc: "(ANALYSIS_SEGMENT_CNA_FILE; <project_id>.seg.cna.txt)"
analysis_sv_filename:
type: string
doc: "(ANALYSIS_SV_FILE; <project_id>.svs.maf)"
analysis_gene_cna_filename:
type: string
doc: "(ANALYSIS_GENE_CNA_FILENAME; <project_id>.gene.cna.txt)"
analysis_mutations_filename:
type: string
doc: "(ANALYSIS_MUTATIONS_FILENAME; <project_id>.muts.maf)"
analysis_mutations_share_filename:
type: string
doc: "<project_id>.muts.share.maf)"
cbio_segment_data_filename:
type: string
doc: "(CBIO_SEGMENT_DATA_FILENAME; <project_id>_data_cna_hg19.seg)"
cbio_meta_cna_segments_filename:
type: string
doc: "(cbio_meta_cna_segments_filename; <project_id>_meta_cna_hg19_seg.txt)"
cbio_cases_sequenced_filename:
type: string
doc: "(CBIO_CASES_SEQUENCED_FILE)"
default: cases_sequenced.txt
cbio_cases_cna_filename:
type: string
default: cases_cna.txt
doc: "(CBIO_CASES_CNA_FILE)"
cbio_cases_cnaseq_filename:
type: string
default: cases_cnaseq.txt
doc: "(CBIO_CASES_CNASEQ_FILE)"
cbio_cases_all_filename:
type: string
default: cases_all.txt
doc: "(CBIO_CASES_ALL_FILE)"
cbio_meta_mutations_filename:
type: string
default: meta_mutations_extended.txt
doc: "(CBIO_META_MUTATIONS_FILE)"
cbio_meta_fusions_filename:
type: string
default: meta_fusions.txt
doc: "(CBIO_META_FUSIONS_FILE)"
cbio_meta_cna_filename:
type: string
default: meta_CNA.txt
doc: "(CBIO_META_CNA_FILE)"
cbio_meta_study_filename:
type: string
default: meta_study.txt
doc: "(CBIO_META_STUDY_FILE)"
cbio_clinical_patient_meta_filename:
type: string
default: meta_clinical_patient.txt
doc: "(CBIO_CLINCAL_PATIENT_META_FILE)"
cbio_clinical_sample_meta_filename:
type: string
default: meta_clinical_sample.txt
doc: "(CBIO_CLINICAL_SAMPLE_META_FILE)"
cbio_clinical_sample_data_filename:
type: string
default: data_clinical_sample.txt
doc: "(CBIO_CLINICAL_SAMPLE_DATA_FILENAME)"
cbio_clinical_patient_data_filename:
type: string
default: data_clinical_patient.txt
doc: "(CBIO_CLINCIAL_PATIENT_DATA_FILENAME)"
cbio_fusion_data_filename:
type: string
default: data_fusions.txt
doc: "(CBIO_FUSION_DATA_FILENAME)"
cbio_mutation_data_filename:
type: string
default: data_mutations_extended.txt
doc: "(CBIO_MUTATION_DATA_FILENAME)"
cbio_cna_data_filename:
type: string
default: data_CNA.txt
doc: "(CBIO_CNA_DATA_FILENAME)"
cbio_cna_ascna_data_filename:
type: string
default: data_CNA.ascna.txt
doc: "(CBIO_CNA_ASCNA_DATA_FILE)"
cbio_cna_scna_data_filename:
type: string
default: data_CNA.scna.txt
doc: "(CBIO_CNA_SCNA_DATA_FILE)"
mutation_maf_files:
type: File[]
doc: "analysis_mutations_filename (ANALYSIS_MUTATIONS_FILENAME) cbio_mutation_data_filename (CBIO_MUTATION_DATA_FILENAME): (MAF_DIR)/*.muts.maf"
facets_hisens_seg_files:
type: File[]
doc: "cbio_segment_data_filename (CBIO_SEGMENT_DATA_FILENAME; <project_id>_data_cna_hg19.seg) analysis_segment_cna_filename (ANALYSIS_SEGMENT_CNA_FILE; <project_id>.seg.cna.txt): (FACETS_DIR)/*_hisens.seg"
facets_hisens_cncf_files:
type: File[]
doc: "cbio_cna_data_filename (CBIO_CNA_DATA_FILENAME; data_CNA.txt) analysis_gene_cna_filename (ANALYSIS_GENE_CNA_FILENAME; <project_id>.gene.cna.txt): (FACETS_DIR)/*_hisens.cncf.txt"
mutation_svs_txt_files:
type: File[]
doc: "cbio_fusion_data_filename (CBIO_FUSION_DATA_FILENAME; data_fusions.txt): (MAF_DIR)/*.svs.pass.vep.portal.txt"
mutation_svs_maf_files:
type: File[]
doc: "analysis_sv_filename (ANALYSIS_SV_FILE; <project_id>.svs.maf): (MAF_DIR)/*.svs.pass.vep.maf"
facets_suite_txt_files:
type:
- "null"
- File[]
doc: "Facets Suite .txt files for all samples in the request"
# facets_aggregate_file:
# doc: "Facets Suite .txt file aggregated for all samples in the request"
# type:
# - "null"
# - File
targets_list:
type: File
known_fusions_file:
type: File
data_clinical_file:
type: File
sample_summary_file:
type:
- "null"
- File
IMPACT_gene_list:
type: File
doc: "TSV file with gene labels and corresponding impact assays"
steps:
run_analysis_workflow:
run: analysis-workflow.cwl
in:
analysis_segment_cna_filename: analysis_segment_cna_filename
analysis_sv_filename: analysis_sv_filename
analysis_gene_cna_filename: analysis_gene_cna_filename
analysis_mutations_filename: analysis_mutations_filename
analysis_mutations_share_filename: analysis_mutations_share_filename
mutation_maf_files: mutation_maf_files
facets_hisens_seg_files: facets_hisens_seg_files
facets_hisens_cncf_files: facets_hisens_cncf_files
mutation_svs_maf_files: mutation_svs_maf_files
targets_list: targets_list
argos_version_string: argos_version_string
is_impact: is_impact
helix_filter_version: helix_filter_version
IMPACT_gene_list: IMPACT_gene_list
out:
[ analysis_dir ]
run_portal_workflow:
run: portal-workflow.cwl
in:
project_id: project_id
project_pi: project_pi
request_pi: request_pi
project_short_name: project_short_name
project_name: project_name
project_description: project_description
cancer_type: cancer_type
cancer_study_identifier: cancer_study_identifier
argos_version_string: argos_version_string
helix_filter_version: helix_filter_version
is_impact: is_impact
extra_pi_groups: extra_pi_groups
cbio_segment_data_filename: cbio_segment_data_filename
cbio_meta_cna_segments_filename: cbio_meta_cna_segments_filename
cbio_cases_sequenced_filename: cbio_cases_sequenced_filename
cbio_cases_cna_filename: cbio_cases_cna_filename
cbio_cases_cnaseq_filename: cbio_cases_cnaseq_filename
cbio_cases_all_filename: cbio_cases_all_filename
cbio_meta_mutations_filename: cbio_meta_mutations_filename
cbio_meta_fusions_filename: cbio_meta_fusions_filename
cbio_meta_cna_filename: cbio_meta_cna_filename
cbio_meta_study_filename: cbio_meta_study_filename
cbio_clinical_patient_meta_filename: cbio_clinical_patient_meta_filename
cbio_clinical_sample_meta_filename: cbio_clinical_sample_meta_filename
cbio_clinical_sample_data_filename: cbio_clinical_sample_data_filename
cbio_clinical_patient_data_filename: cbio_clinical_patient_data_filename
cbio_fusion_data_filename: cbio_fusion_data_filename
cbio_mutation_data_filename: cbio_mutation_data_filename
cbio_cna_data_filename: cbio_cna_data_filename
cbio_cna_ascna_data_filename: cbio_cna_ascna_data_filename
cbio_cna_scna_data_filename: cbio_cna_scna_data_filename
mutation_maf_files: mutation_maf_files
facets_hisens_seg_files: facets_hisens_seg_files
facets_hisens_cncf_files: facets_hisens_cncf_files
mutation_svs_txt_files: mutation_svs_txt_files
targets_list: targets_list
known_fusions_file: known_fusions_file
data_clinical_file: data_clinical_file
sample_summary_file: sample_summary_file
facets_suite_txt_files: facets_suite_txt_files
out:
# [ portal_dir ]
[
portal_meta_clinical_sample_file, # meta_clinical_sample.txt
portal_data_clinical_patient_file, # data_clinical_patient.txt
portal_data_clinical_sample_file, # data_clinical_sample.txt
portal_meta_study_file, # meta_study.txt
portal_clinical_patient_meta_file, # meta_clinical_patient.txt
portal_meta_cna_file, # meta_CNA.txt
portal_meta_fusions_file, # meta_fusions.txt
portal_meta_mutations_extended_file, # meta_mutations_extended.txt
portal_meta_cna_segments_file, # <project_id>_meta_cna_hg19_seg.txt
portal_cna_data_file, # data_CNA.txt
portal_cna_ascna_file, # data_CNA.ascna.txt
portal_muts_file, # data_mutations_extended.txt
portal_hisens_segs, # <project_id>_data_cna_hg19.seg
portal_fusions_data_file, # data_fusions.txt
portal_case_list_dir
]
# create the "portal" directory in the output dir and put cBioPortal files in it
make_portal_dir:
run: put_in_dir.cwl
in:
portal_meta_clinical_sample_file: run_portal_workflow/portal_meta_clinical_sample_file # meta_clinical_sample.txt
portal_data_clinical_patient_file: run_portal_workflow/portal_data_clinical_patient_file # data_clinical_patient.txt
portal_data_clinical_sample_file: run_portal_workflow/portal_data_clinical_sample_file # data_clinical_sample.txt
portal_meta_study_file: run_portal_workflow/portal_meta_study_file # meta_study.txt
portal_clinical_patient_meta_file: run_portal_workflow/portal_clinical_patient_meta_file # meta_clinical_patient.txt
portal_meta_cna_file: run_portal_workflow/portal_meta_cna_file # meta_CNA.txt
portal_meta_fusions_file: run_portal_workflow/portal_meta_fusions_file # meta_fusions.txt
portal_meta_mutations_extended_file: run_portal_workflow/portal_meta_mutations_extended_file # meta_mutations_extended.txt
portal_meta_cna_segments_file: run_portal_workflow/portal_meta_cna_segments_file # <project_id>_meta_cna_hg19_seg.txt
portal_cna_data_file: run_portal_workflow/portal_cna_data_file # data_CNA.txt
portal_cna_ascna_file: run_portal_workflow/portal_cna_ascna_file # data_CNA.ascna.txt
portal_muts_file: run_portal_workflow/portal_muts_file # data_mutations_extended.txt
portal_hisens_segs: run_portal_workflow/portal_hisens_segs # # <project_id>_data_cna_hg19.seg
portal_fusions_data_file: run_portal_workflow/portal_fusions_data_file # data_fusions.txt
portal_case_list_dir: run_portal_workflow/portal_case_list_dir
output_directory_name:
valueFrom: ${ return "portal"; }
files:
valueFrom: ${return [
inputs.portal_meta_clinical_sample_file,
inputs.portal_data_clinical_patient_file,
inputs.portal_data_clinical_sample_file,
inputs.portal_meta_study_file,
inputs.portal_clinical_patient_meta_file,
inputs.portal_meta_cna_file,
inputs.portal_meta_fusions_file,
inputs.portal_meta_mutations_extended_file,
inputs.portal_meta_cna_segments_file,
inputs.portal_cna_data_file,
inputs.portal_cna_ascna_file,
inputs.portal_muts_file,
inputs.portal_hisens_segs,
inputs.portal_fusions_data_file,
inputs.portal_case_list_dir,
]}
out: [ directory ]
outputs:
portal_dir:
type: Directory
outputSource: make_portal_dir/directory
analysis_dir:
type: Directory
outputSource: run_analysis_workflow/analysis_dir