There are Metamist wrappers built to get input sequencing groups.
You can import these from the cpg_flow package:
from cpg_flow.inputs import add_sg_to_dataset, get_multicohort, create_multicohort
add_sg_to_dataset(dataset, sg_data)
Adds a sequencing group to a dataset.
| PARAMETER |
DESCRIPTION |
dataset
|
Dataset to insert the SequencingGroup into
TYPE:
Dataset
|
sg_data
|
data from the metamist API
TYPE:
dict
|
Source code in src/cpg_flow/inputs.py
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 | def add_sg_to_dataset(dataset: Dataset, sg_data: dict) -> SequencingGroup:
"""
Adds a sequencing group to a dataset.
Args:
dataset (Dataset): Dataset to insert the SequencingGroup into
sg_data (dict): data from the metamist API
Returns:
The SequencingGroup object
"""
# TODO: The update_dict calls are a bit of a hack, we should be able to do this in a cleaner way
# scavenge all the metadata from the SG dict (SG/Sample/Participant)
metadata = sg_data.get('meta', {})
update_dict(metadata, sg_data['sample']['participant'].get('meta', {}))
# phenotypes are managed badly here, need a cleaner way to get them into the SG
update_dict(
metadata,
{'phenotypes': sg_data['sample']['participant'].get('phenotypes', {})},
)
# create a SequencingGroup object from its component parts
sequencing_group = dataset.add_sequencing_group(
id=str(sg_data['id']),
external_id=str(sg_data['sample']['externalId']),
participant_id=sg_data['sample']['participant'].get('externalId'),
meta=metadata,
sequencing_type=sg_data['type'],
sequencing_technology=sg_data['technology'],
sequencing_platform=sg_data['platform'],
)
if reported_sex := sg_data['sample']['participant'].get('reportedSex'):
sequencing_group.pedigree.sex = Sex.parse(reported_sex)
# parse the assays and related dict content
_populate_alignment_inputs(sequencing_group, sg_data)
return sequencing_group
|
Return the cohort or multicohort object based on the workflow configuration.
Source code in src/cpg_flow/inputs.py
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82 | def get_multicohort() -> MultiCohort:
"""
Return the cohort or multicohort object based on the workflow configuration.
"""
input_datasets = config_retrieve(['workflow', 'input_datasets'], None)
# pull the list of cohort IDs from the config
custom_cohort_ids = config_retrieve(['workflow', 'input_cohorts'], None)
if input_datasets:
raise ValueError('Argument input_datasets is deprecated, use input_cohorts instead')
if isinstance(custom_cohort_ids, list) and len(custom_cohort_ids) <= 0:
raise ValueError('No custom_cohort_ids found in the config')
# NOTE: When configuring sgs in the config is deprecated, this will be removed.
if custom_cohort_ids and not isinstance(custom_cohort_ids, list):
raise ValueError('Argument input_cohorts must be a list')
return create_multicohort()
|
Add cohorts in the multicohort.
Source code in src/cpg_flow/inputs.py
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 | def create_multicohort() -> MultiCohort:
"""
Add cohorts in the multicohort.
"""
config = config_retrieve(['workflow'])
# pull the list of cohort IDs from the config
custom_cohort_ids = config_retrieve(['workflow', 'input_cohorts'], [])
# get a unique set of cohort IDs
custom_cohort_ids_unique = sorted(set(custom_cohort_ids))
custom_cohort_ids_removed = sorted(set(custom_cohort_ids) - set(custom_cohort_ids_unique))
# if any cohort id duplicates were removed we log them
if len(custom_cohort_ids_unique) != len(custom_cohort_ids):
get_logger(__file__).warning(
f'Removed {len(custom_cohort_ids_removed)} non-unique cohort IDs',
)
duplicated_cohort_ids = ', '.join(custom_cohort_ids_removed)
get_logger(__file__).warning(f'Non-unique cohort IDs: {duplicated_cohort_ids}')
multicohort = MultiCohort()
# for each Cohort ID
for cohort_id in custom_cohort_ids_unique:
# get the dictionary representation of all SGs in this cohort
# dataset_id is sequencing_group_dict['sample']['project']['name']
cohort_sg_dict = get_cohort_sgs(cohort_id)
cohort_name = cohort_sg_dict.get('name', cohort_id)
cohort_sgs = cohort_sg_dict.get('sequencing_groups', [])
if len(cohort_sgs) == 0:
raise MetamistError(f'Cohort {cohort_id} has no sequencing groups')
# create a new Cohort object
cohort = multicohort.create_cohort(id=cohort_id, name=cohort_name)
# first populate these SGs into their Datasets
# required so that the SG objects can be referenced in the collective Datasets
# SG.dataset.prefix is meaningful, to correctly store outputs in the project location
for entry in cohort_sgs:
sg_dataset = entry['sample']['project']['name']
dataset = multicohort.create_dataset(sg_dataset.removesuffix('-test'))
sequencing_group = add_sg_to_dataset(dataset, entry)
# also add the same sequencing group to the cohort
cohort.add_sequencing_group_object(sequencing_group)
# we've populated all the sequencing groups in the cohorts and datasets
# all SequencingGroup objects should be populated uniquely (pointers to instances, so updating Analysis entries
# for each SG should update both the Dataset's version and the Cohort's version)
# only go to metamist once per dataset to get analysis entries
for dataset in multicohort.get_datasets():
_populate_analysis(dataset)
if config.get('read_pedigree', True):
_populate_pedigree(dataset)
return multicohort
|