-
Notifications
You must be signed in to change notification settings - Fork 0
/
whole_genome.py
1200 lines (915 loc) · 42.7 KB
/
whole_genome.py
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
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# -*- coding: utf-8 -*-
"""
Created on Fri Jun 9 10:42:36 2023
@author: rjovelin
"""
import os
import itertools
from utilities import connect_to_db, convert_epoch_time, remove_non_analysis_workflows,\
get_children_workflows, get_workflow_names, get_donors
def get_parent_workflows(project_name, database):
'''
(str, str) -> dict
Returns a dictionary with workflow name, list of workflow_ids that are parent
to all each workflow (i.e immediate upstream workflow) for a given project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
'''
conn = connect_to_db(database)
data = conn.execute("SELECT Workflows.wf, Parents.parents_id, Parents.children_id \
FROM Parents JOIN Workflows WHERE Parents.project_id = ? \
AND Workflows.project_id = ? AND Workflows.wfrun_id = Parents.parents_id;", (project_name, project_name)).fetchall()
data= list(set(data))
conn.close()
D = {}
for i in data:
if i['children_id'] not in D:
D[i['children_id']] = {}
if i['wf'] not in D[i['children_id']]:
D[i['children_id']][i['wf']] = []
D[i['children_id']][i['wf']].append(i['parents_id'])
return D
def get_workflows_analysis_date(project_name, database):
'''
(str, str) -> dict
Returns the creation date of any file for each workflow id for the project of interest
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
'''
# connect to db
conn = connect_to_db(database)
# extract project info
data = conn.execute("SELECT DISTINCT creation_date, wfrun_id FROM Files WHERE project_id= ?;", (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
D[i['wfrun_id']] = i['creation_date']
return D
def get_workflow_file_count(project_name, database, workflow_table='Workflows'):
'''
(str, str, str) -> dict
Returns a dictionary with the number of files for each workflow in project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- workflow_table (str): Name of the table containing the workflow information in database
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT {0}.file_count, {0}.wfrun_id FROM {0} WHERE {0}.project_id = ?;".format(workflow_table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
counts = {}
for i in data:
counts[i['wfrun_id']] = i['file_count']
return counts
def get_workflow_limskeys(project_name, database, workflow_input_table='Workflow_Inputs'):
'''
(str, str, str) -> dict
Returns a dictionary with list of limskeys for each workflow id in project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- workflow_input_table (str): Name of the table with worklow input information in the database
'''
conn = connect_to_db(database)
query = "SELECT {0}.limskey, {0}.wfrun_id FROM {0} WHERE {0}.project_id = ?;".format(workflow_input_table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
if i['wfrun_id'] not in D:
D[i['wfrun_id']] = []
D[i['wfrun_id']].append(i['limskey'])
return D
def get_amount_data(project_name, database, workflow_table='Workflows'):
'''
(str, str, str) -> dict
Returns a dictionary with the amount of data (ie, lane count) for each workflow in project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- workflow_table (str): Name of the table containing the workflow information in database
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT {0}.lane_count, {0}.wfrun_id FROM {0} WHERE {0}.project_id = ?;".format(workflow_table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
counts = {}
for i in data:
counts[i['wfrun_id']] = i['lane_count']
return counts
def create_WG_block_json(database, project_name, case, blocks, block, anchor_workflow, workflow_names, selected_workflows, selection):
'''
(str, str, dict, str, str, dict, dict, str)
Returns a dictionary with workflow information for a given block (ie, sample pair)
and anchor parent workflow (bmpp or star)
Parameters
----------
- database (str): Path to the sqlite database
- project_name (str): Name of project of interest
- case (str): Donor identifier
- blocks (dict): Dictionary with block information
- block (str): Sample pair in blocks
- anchor_workflow (str): bamMergePreprocessing parent workflow(s) or star_call_ready parent workflow
- workflow_names (dict): Dictionary with workflow name and version for each workflow in project
- selected_workflows (dict): Dictionary with selected status of each workflow in project
- selection (str): Include files from all selected workflows or files from the standard deliverables
Values: standard or all
'''
libraries = map_limskey_to_library(project_name, database, table='Workflow_Inputs')
sample_names = map_library_to_sample(project_name, database, table = 'Libraries')
donors = map_library_to_case(project_name, database, table = 'Libraries')
workflow_outputfiles = get_workflow_output(project_name, database, libraries, sample_names, donors, 'Files')
# create a lambda to evaluate the deliverable files
# x is a pair of (file, file_ending)
G = lambda x: x[1] in x[0] and x[0][x[0].rindex(x[1]):] == x[1]
# get the deliverables
if selection == 'standard':
deliverables = get_WGS_standard_deliverables()
elif selection == 'all':
deliverables = {}
# organize the workflows by block and samples
D = {}
# re-organize the sample pair
sample_id = '.'.join(list(map(lambda x: x.strip(), block.split('|'))))
# get the workflow ids for that block
for i in blocks[block]:
if i['anchor_wf'] == anchor_workflow:
D[sample_id] = map(lambda x: x.strip(), i['workflows'].split(';'))
block_data = {}
for sample in D:
for workflow_id in D[sample]:
# check if workflow is selected
if selected_workflows[workflow_id]:
# get workflow name and version
workflow_name = workflow_names[workflow_id][0]
workflow_version = workflow_names[workflow_id][1]
# needed to sort outputs by sample pairs or by sample for call-ready workflows
# even if all files are recorded
#outputfiles = get_workflow_output(project_name, case, workflow_id, database, libraries, sample_names, 'Files')
outputfiles = workflow_outputfiles[workflow_id]
# check that only workflows in standard WGS deliverables are used
if deliverables:
key = workflow_name.split('_')[0].lower()
if key in deliverables:
for j in outputfiles:
# list all deliverable files
L = []
# gather all file paths for workflow and sample(s)
files = [i[0] for i in outputfiles[j]]
# map all file endings of deliverables with files
groups = list(itertools.product(files, deliverables[key]))
# determine which files are part of the deliverables
F = list(map(G, groups))
L = [groups[k][0] for k in range(len(F)) if F[k]]
if L:
sample_id = j.replace(';', '.')
if case not in block_data:
block_data[case] = {}
if sample_id not in block_data[case]:
block_data[case][sample_id] = {}
if workflow_name not in block_data[case][sample_id]:
block_data[case][sample_id][workflow_name] = []
d = {'workflow_id': workflow_id,
'workflow_version': workflow_version,
'files': L}
if d not in block_data[case][sample_id][workflow_name]:
block_data[case][sample_id][workflow_name].append(d)
else:
for j in outputfiles:
sample_id = j.replace(';', '.')
d = {'workflow_id': workflow_id,
'workflow_version': workflow_version,
'files': [i[0] for i in outputfiles[j]]}
if case not in block_data:
block_data[case] = {}
if sample_id not in block_data[case]:
block_data[case][sample_id] = {}
if workflow_name not in block_data[case][sample_id]:
block_data[case][sample_id][workflow_name] = []
if d not in block_data[case][sample_id][workflow_name]:
block_data[case][sample_id][workflow_name].append(d)
return block_data
def create_WGS_project_block_json(project_name, database, blocks, block_status, selected_workflows, workflow_names, deliverables=None):
'''
(str, str, dict, dict, dict, dict, None | dict)
Returns a dictionary with workflow information for a given block (ie, sample pair)
and anchor bmpp parent workflow
Parameters
----------
- project_name (None | str): None or name of project of interest
- database (None | str): None or path to the sqlite database
- blocks (dict): Dictionary with block information
- block_status (dict): Dictionary with review status of each block
- selected_workflows (dict): Dictionary with selected status of each workflow in project
- workflow_names (dict): Dictionary with workflow name and version for each workflow in project
- deliverables (None | dict): None or dictionary with file extensions of standard WGS deliverables
'''
libraries = map_limskey_to_library(project_name, database, table='Workflow_Inputs')
sample_names = map_library_to_sample(project_name, database, table = 'Libraries')
donors = map_library_to_case(project_name, database, table = 'Libraries')
workflow_outputfiles = get_workflow_output(project_name, database, libraries, sample_names, donors, 'Files')
# create a lambda to evaluate the deliverable files
# x is a pair of (file, file_ending)
G = lambda x: x[1] in x[0] and x[0][x[0].rindex(x[1]):] == x[1]
D = {}
for case in blocks:
for samples in blocks[case]:
# check the selection status of the block
if block_status[case][samples] not in ['ready', 'review']:
# block already reviewed and workflows selected
anchor_wf = block_status[case][samples]
for workflow in blocks[case][samples][anchor_wf]['workflows']:
workflow = os.path.basename(workflow)
# get workflow name and version
workflow_name = workflow_names[workflow][0]
workflow_version = workflow_names[workflow][1]
# check workflow status
if selected_workflows[workflow]:
# get workflow output files
# needed to sort outputs by sample pairs or by sample for call-ready workflows
# even if all files are recorded
#outputfiles = get_workflow_output(project_name, case, workflow, database, libraries, sample_names, 'Files')
outputfiles = workflow_outputfiles[workflow]
# check that only workflows in standard WGS deliverables are used
if deliverables:
key = workflow_names[workflow][0].split('_')[0].lower()
if key in deliverables:
for j in outputfiles:
# list all deliverable files
L = []
# gather all file paths for workflow and sample(s)
files = [i[0] for i in outputfiles[j]]
# map all file endings of deliverables with files
groups = list(itertools.product(files, deliverables[key]))
# determine which files are part of the deliverables
F = list(map(G, groups))
L = [groups[k][0] for k in range(len(F)) if F[k]]
if L:
sample_id = j.replace(';', '.')
if case not in D:
D[case] = {}
if sample_id not in D[case]:
D[case][sample_id] = {}
if workflow_name not in D[case][sample_id]:
D[case][sample_id][workflow_name] = []
d = {'workflow_id': workflow,
'workflow_version': workflow_version,
'files': L}
if d not in D[case][sample_id][workflow_name]:
D[case][sample_id][workflow_name].append(d)
else:
for j in outputfiles:
sample_id = j.replace(';', '.')
d = {'workflow_id': workflow,
'workflow_version': workflow_version,
'files': [i[0] for i in outputfiles[j]]}
if case not in D:
D[case] = {}
if sample_id not in D[case]:
D[case][sample_id] = {}
if workflow_name not in D[case][sample_id]:
D[case][sample_id][workflow_name] = []
if d not in D[case][sample_id][workflow_name]:
D[case][sample_id][workflow_name].append(d)
return D
def get_call_ready_cases(project_name, platform, library_type, database):
'''
(str, str, str, str) -> dict
Returns a dictionary with samples and libraries and bmpp and downstream workflow ids for each case in a project,
restricting data to specified platform and library type
Parameters
----------
- project_name (str): Name of the project
- platform (str): Name of sequencing platform.
Accepted values: novaseq, nextseq, hiseq, miseq
- library_type (str): 2 letters-code indicating the type of library
- database (str): Path to the sqlite database
'''
# get all the samples for project name
conn = connect_to_db(database)
query = "SELECT Libraries.library, Libraries.case_id, Libraries.project_id, \
Libraries.ext_id, Libraries.group_id, Libraries.library_type, \
Libraries.tissue_type, Libraries.tissue_origin, \
Workflows.wf, Workflows.wfrun_id, Workflow_Inputs.platform \
from Workflow_Inputs JOIN Libraries JOIN Workflows \
WHERE Libraries.project_id = ? AND Workflow_Inputs.project_id = ? \
AND Workflows.project_id = ? AND Workflow_Inputs.wfrun_id = Workflows.wfrun_id \
AND Workflow_Inputs.library = Libraries.library AND Libraries.library_type = ?;"
data = conn.execute(query, (project_name, project_name, project_name, library_type)).fetchall()
conn.close()
cases = {}
for i in data:
# select bmpp data sequenced on novaseq
if platform in i['platform'].lower():
if 'bammergepreprocessing' in i['wf'].lower():
if i['case_id'] not in cases:
cases[i['case_id']] = {'project': i['project_id'], 'samples': set(), 'libraries': set(), 'bmpp': set()}
cases[i['case_id']]['bmpp'].add(i['wfrun_id'])
sample = '_'.join([i['case_id'], i['tissue_type'], i['tissue_origin'], i['library_type'], i['group_id']])
cases[i['case_id']]['samples'].add(sample)
cases[i['case_id']]['libraries'].add(i['library'])
# get parent-children workflow relationships
parents = get_children_workflows(project_name, database)
# find the bmpp downstream workflows
for sample in cases:
downstream = []
for bmpp in cases[sample]['bmpp']:
if bmpp in parents:
# get the bmpp downstream workflows
children = parents[bmpp]
# removed any non-analysis workflow
children = remove_non_analysis_workflows(children)
# list all downtream workflows
downstream.extend([i['children_id'] for i in children])
# get the downstream workflows of downstream workflows
# remove non-analysis workflows
for workflow in downstream:
if workflow in parents:
L = remove_non_analysis_workflows(parents[workflow])
downstream.extend([i['children_id'] for i in L])
cases[sample]['downstream'] = list(set(downstream))
return cases
def get_call_ready_samples(project_name, bmpp_run_id, database):
'''
(str, str, str) -> dict
Returns a dictionary with normal and tumour samples from project_name processed through bamMergePreprcessing
workflow with bmpp_run_id
Parameters
----------
- project_name (str): Name of the project of interest
- bmpp_run_id (str): BamMergePreprocessing workflow run identifier
- database (str): Path to the sqlite database
'''
conn = connect_to_db(database)
query = "SELECT Libraries.case_id, Libraries.group_id, Libraries.library, Libraries.tissue_type, \
Libraries.tissue_origin, Libraries.library_type \
FROM Libraries JOIN Workflow_Inputs WHERE Workflow_Inputs.library = Libraries.library \
AND Workflow_Inputs.wfrun_id = ? AND Libraries.project_id = ? \
AND Workflow_Inputs.project_id = ?"
data = conn.execute(query, (os.path.basename(bmpp_run_id), project_name, project_name)).fetchall()
conn.close()
data = list(set(data))
samples = {'normal': [], 'tumour': []}
for i in data:
if i['tissue_type'] == 'R':
tissue = 'normal'
else:
tissue = 'tumour'
sample = '_'.join([i['case_id'], i['tissue_type'], i['tissue_origin'], i['library_type'], i['group_id']])
if sample not in samples[tissue]:
samples[tissue].append(sample)
return samples
def map_samples_to_bmpp_runs(project_name, bmpp_ids, database):
'''
(str, list, str) -> dict
Returns a dictionary with normal, tumor samples for each bmpp run id
Parameters
----------
- project_name (str): Name of the project of interest
- bmpp_ids (list): List of BamMergePreprocessing workflow run identifiers for a single case
- database (str): Path to the sqlite database
'''
D = {}
for i in bmpp_ids:
# initiate dictionary
samples = get_call_ready_samples(project_name, i, database)
D[i] = samples
return D
def get_WGTS_blocks_info(project_name, case, database, table):
'''
(str, str, str, str) -> list
Returns a list of dictionaries containing WGS or WT block information for a given project and case
Parameters
----------
- project_name (str): Name of project of interest
- case (str): Donor id
- database (str): Path to the sqlite database
- table (str): Table with block information: WGS_blocks, WT_blocks or EX_blocks
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT samples, anchor_wf, workflows, name, date, \
complete, clean, network from {0} WHERE project_id = ? AND \
case_id = ?;".format(table)
data = conn.execute(query, (project_name, case)).fetchall()
conn.close()
L = [dict(i) for i in data]
D = {}
# group by samples
for i in L:
samples = i['samples']
if samples not in D:
D[samples] = []
# add call ready workflows
call_ready = list(map(lambda x: x.strip(), i['anchor_wf'].split('.')))
i['call_ready'] = call_ready
workflows = list(map(lambda x: x.strip(), i['workflows'].split(';')))
# add caller workflows
callers = set(workflows).difference(set(call_ready))
i['callers'] = callers
# map each sample to the
bmpp_samples = map_samples_to_bmpp_runs(project_name, call_ready, database)
i['pairs'] = bmpp_samples
D[samples].append(i)
# sort according to sub-block name
D[samples].sort(key = lambda x: x['name'])
return D
def get_sequencing_platform(project_name, database, table = 'Workflow_Inputs'):
'''
(str, str, str) -> list
Returns a dictionary with the sequencing platform of input raw sequences
for each workflow for project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- table (str): Table with workflow input information
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT wfrun_id, platform FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
D[i['wfrun_id']] = i['platform']
return D
def get_selected_workflows(project_name, database, table = 'Workflows'):
'''
(str, str, str) -> dict
Returns a dictionary with the selected status of each workflow for the given project
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- table (str): Table with workflow information
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT wfrun_id, selected FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
D[i['wfrun_id']] = int(i['selected'])
return D
def get_case_workflows(case, database, table = 'WGS_blocks'):
'''
(str, str, str) -> dict
Returns a dictionary of all workflows in each block and sample pair for a given case
Parameters
----------
- case (str): Donor identifier
- database (str): Path to the sqlite database
- table (str): Name of the table storing analysis blocks
'''
conn = connect_to_db(database)
query = "SELECT samples, anchor_wf, workflows FROM {0} WHERE case_id = ?;".format(table)
data = conn.execute(query, (case,)).fetchall()
conn.close()
D = {}
for i in data:
samples = i['samples']
block = i['anchor_wf']
workflows = i['workflows'].split(';')
if samples not in D:
D[samples] = {}
if block not in D[samples]:
D[samples][block] = []
D[samples][block].extend(workflows)
D[samples][block] = list(set(workflows))
return D
def update_wf_selection(workflows, selected_workflows, selection_status, database, table='Workflows'):
'''
(list, list, dict, str, str)
Update the selection status of workflows
Parameters
----------
- workflows (list): List of workflows from a single analysis block for which
status needs to be updated
- selected_workflows (list): List of selected workflows from the application form for a given case
- selection_status (dict): Selection status of all workflows for a given project
- database (str): Path to the sqlite database
- table (str): Table storing workflows information
'''
# update selected status
conn = connect_to_db(database)
for i in workflows:
if i in selected_workflows:
status = 1
else:
status = 0
# update only if status has changed
if selection_status[os.path.basename(i)] != status:
query = 'UPDATE Workflows SET selected = ? WHERE wfrun_id = ?;'
conn.execute(query, (status, i))
conn.commit()
conn.close()
def get_wgs_blocks(project, database, table = 'WGS_blocks'):
'''
(str, str, str) -> dict
Returns a dictionary with analysis block names for each case in project
Parameters
----------
- project (str): Name of project of interest
- database (str): Path to the sqlite database
- table (str): Table with analysis blocks
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT * FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project,)).fetchall()
conn.close()
D = {}
for i in data:
case, samples, anchor = i['case_id'], i['samples'], i['anchor_wf']
workflows = i['workflows'].split(';')
clean, complete = int(i['clean']), int(i['complete'])
if case not in D:
D[case] = {}
if samples not in D[case]:
D[case][samples] = {}
assert anchor not in D[case][samples]
D[case][samples][anchor] = {'workflows': workflows, 'clean': clean,
'complete': complete}
return D
def get_block_counts(analysis_blocks):
'''
(dict) -> dict
Returns a dictionary with block counts for each case and sample pairs in given project
Parameters
----------
- analysis_blocks (dict): Dictionary with analysis blocks for a given project
'''
D = {}
for i in analysis_blocks:
for j in analysis_blocks[i]:
if i not in D:
D[i] = {}
assert j not in D[i]
D[i][j] = len(analysis_blocks[i][j])
return D
def review_wgs_blocks(blocks, selected_workflows):
'''
(dict, dict) -> dict
Returns a dictionary with status for analysis blocks for each case in project
Parameters
----------
- blocks (dict):
- selected_workflows (dict):
'''
D = {}
for case in blocks:
if case not in D:
D[case] = {}
for samples in blocks[case]:
for anchor in blocks[case][samples]:
# do not include call-ready workflows to determine selection/review status
# these may be shared across multiple blocks
L = [selected_workflows[os.path.basename(i)] for i in blocks[case][samples][anchor]['workflows'] if i not in anchor]
if any(L):
D[case][samples] = anchor
break
else:
if blocks[case][samples][anchor]['clean'] and \
blocks[case][samples][anchor]['complete'] and \
blocks[case][samples][anchor]['release_status']:
D[case][samples] = 'ready'
break
else:
D[case][samples] = 'review'
return D
def map_limskey_to_library(project_name, database, table='Workflow_Inputs'):
'''
(str, str, str) -> dict
Returns a dictionary mapping limskey ids to library ids for each workflow in project
Parameters
----------
- project_name (str): Name of the project of interest
- database (str): Path to the sqlite database
- table (str): Table storing the workflow input information
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT library, limskey, wfrun_id FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
workflow = i['wfrun_id']
if workflow not in D:
D[workflow] = {}
assert i['limskey'] not in D[workflow]
D[workflow][i['limskey']] = i['library']
return D
def map_library_to_sample(project_name, database, table = 'Libraries'):
'''
(str, str, str) -> dict
Returns a dictionary mapping sample ids to library ids
Parameters
----------
- project_name (str): Name of the project of interest
- database (str): Path to the sqlite database
- table (str): Table storing the libraries information
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT library, case_id, tissue_type, tissue_origin, \
library_type, group_id FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
donor = i['case_id']
library = i['library']
sample = [i['case_id'], i['tissue_type'], i['tissue_origin'],
i['library_type'], i['group_id']]
if not i['group_id']:
sample = sample[:-1]
sample = '_'.join(sample)
if donor not in D:
D[donor] = {}
if library in D[donor]:
assert D[donor][library] == sample
else:
D[donor][library] = sample
return D
def map_library_to_case(project_name, database, table = 'Libraries'):
'''
(str, str, str) -> dict
Returns a dictionary mapping each library to its donor identifier
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- table (str): Table in database storing library information.
Default is Libraries
'''
# get the workflow output files sorted by sample
conn = connect_to_db(database)
query = "SELECT DISTINCT library, case_id FROM {0} WHERE project_id = ?".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
assert i['library'] not in D
D[i['library']] = i['case_id']
return D
def get_workflow_output(project_name, database, libraries, samples, donors, table = 'Files'):
'''
(str, str, dict, dict, dict, str) -> dict
Returns a dictionary with workflow output files sorted by sample
Parameters
----------
- project_name (str): Name of project of interest
- database (str): Path to the sqlite database
- libraries (dict): Dictionary mapping libraries to limskeys
- samples (dict): Dictionary mapping libraries to samples
- donors (dict): Dictionary mapping libraries to donors
- table (str): Table in database storing File information
'''
# get the workflow output files sorted by sample
conn = connect_to_db(database)
query = "SELECT DISTINCT file, limskey, file_swid, wfrun_id FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
file = i['file']
limskeys = i['limskey'].split(';')
fileswid = i['file_swid']
workflow_id = i['wfrun_id']
libs = list(set([libraries[workflow_id][j] for j in limskeys]))
#sample_names = ';'.join(sorted(list(set([samples[case][j] for j in libs]))))
sample_names = ';'.join(sorted(list(set([samples[donors[j]][j] for j in libs]))))
if workflow_id not in D:
D[workflow_id] = {}
if sample_names in D[workflow_id]:
D[workflow_id][sample_names].append([file, fileswid])
else:
D[workflow_id][sample_names] = [[file, fileswid]]
return D
def map_fileswid_to_filename(project_name, database, table='Files'):
'''
'''
# get the workflow output files sorted by sample
conn = connect_to_db(database)
query = "SELECT DISTINCT file_swid, file FROM {0} WHERE project_id = ?;".format(table)
data = conn.execute(query, (project_name,)).fetchall()
conn.close()
D = {}
for i in data:
D[i['file_swid']] = i['file']
return D
def get_WGS_standard_deliverables():
'''
(None) -> dict
Returns a dictionary with the file extensions or file endings for each workflow
for which output files are released as part of the standard WGS package
Parameters
----------
None
'''
deliverables = {'bammergepreprocessing': ['.bai', '.bam'],
'varianteffectpredictor': ['.mutect2.filtered.vep.vcf.gz',
'.mutect2.filtered.vep.vcf.gz.tbi',
'.mutect2.filtered.maf.gz'],
'delly': ['.somatic_filtered.delly.merged.vcf.gz',
'.somatic_filtered.delly.merged.vcf.gz.tbi'],
'sequenza': ['results.zip', 'summary.pdf', 'alternative_solutions.json'],
'mavis': ['.tab', '.zip']}
return deliverables
def get_contamination(sample_id, database, table = 'Calculate_Contamination'):
'''
(str, str, str) -> dict
Returns a dictionary with call-ready contamination and merged limskey for sample_id
Parameters
----------
- sample_id (str): Sample identifier
- database (str): Path to the sqlite database
- table (str): Table in database storing the call-ready contamination. Default is Calculate_Contamination
'''
conn = connect_to_db(database)
query = "SELECT DISTINCT contamination, merged_limskey FROM {0} WHERE sample_id = ?;".format(table)
data = conn.execute(query, (sample_id,)).fetchall()
conn.close()
D = {}
for i in data:
if i['merged_limskey'] in D:
D[i['merged_limskey']].append(i['contamination'])
else:
D[i['merged_limskey']] = [i['contamination']]
for i in D:
D[i] = max(D[i])
return D
def group_limskeys(block_limskeys):
'''
(list) -> list
Sort the limskeys of an analysis block by sample
Parameters
----------
- block_limskeys (list): List of limskeys for a given block
Examples
--------
>>> group_limskeys(['4991_1_LDI51430', '5073_4_LDI57812', '5073_3_LDI57812', '5073_2_LDI57812'])
['4991_1_LDI51430', '5073_4_LDI57812;5073_3_LDI57812;5073_2_LDI57812']
'''