def get_isabl_scrna_analyses(type):
latest_scrna_rdata = []
all_analyses = ii.get_instances(
'analyses',
application__name__in=
'CELLASSIGN Individual Application, CELLASSIGN Project Application')
if type == "cohort":
cohort_analyses = [
analysis for analysis in all_analyses
if is_cohort_analysis(analysis)
]
cohort_analyses = [{
**_process_analysis(analysis), "dashboard_id":
"cohort_all"
} for analysis in cohort_analyses]
return cohort_analyses
else: # is patient
analyses = [{
**_process_analysis(analysis), "dashboard_id":
analysis["individual_level_analysis"]["identifier"]
} for analysis in all_analyses if is_patient_analysis(analysis)]
return analyses
def get_scgenome_isabl_data(target_aliquot):
APP_VERSION = '1.0.0'
os.environ["ISABL_API_URL"] = 'https://isabl.shahlab.mskcc.org/api/v1/'
os.environ['ISABL_CLIENT_ID'] = '1'
VERSION = "0.0.1"
experiment = ii.get_instances("experiments", aliquot_id=target_aliquot)[0]
alignment = get_analyses('SCDNA-ALIGNMENT', VERSION, experiment.system_id)
hmmcopy = get_analyses('SCDNA-HMMCOPY', VERSION, experiment.system_id)
annotation = get_analyses('SCDNA-ANNOTATION', VERSION,
experiment.system_id)
#current = [alignment.pk, hmmcopy.pk, annotation.pk]
#retrieve paths
annotation_metrics = get_annotation_path(annotation.pk)
hmmcopy_metrics, hmmcopy_reads, hmmcopy_segs = get_hmmcopy_path(hmmcopy.pk)
alignment_metrics, gc_metrics = get_alignment_path(alignment.pk)
results = get_qc_data_from_filenames([annotation_metrics], [hmmcopy_reads],
[hmmcopy_segs], [hmmcopy_metrics],
[alignment_metrics], [gc_metrics])
hmmcopy_data = collections.defaultdict(list)
for table_name, data in results.items():
hmmcopy_data[table_name].append(data)
for table_name in hmmcopy_data:
hmmcopy_data[table_name] = pd.concat(hmmcopy_data[table_name],
ignore_index=True)
return hmmcopy_data
def get_analyses(app, version, exp_system_id):
analyses = ii.get_instances('analyses',
application__name=app,
application__version=version,
targets__system_id=exp_system_id)
assert len(analyses) == 1
return analyses[0]
def get_scgenome_isabl_annotation_pk(target_aliquot):
APP_VERSION = '1.0.0'
os.environ["ISABL_API_URL"] = 'https://isabl.shahlab.mskcc.org/api/v1/'
os.environ['ISABL_CLIENT_ID'] = '1'
VERSION = "0.0.1"
experiment = ii.get_instances("experiments", aliquot_id=target_aliquot)[0]
alignment = get_analyses('SCDNA-ALIGNMENT', VERSION, experiment.system_id)
return alignment.pk
def list_projects():
"""
List projects currently in Isabl
"""
projects = ii.get_instances('projects')
data = []
for project in projects:
data.append({'project_title': project.title})
df = pd.DataFrame(data).sort_values(by=['project_title'], ascending=True)
for index, row in df.iterrows():
print(row['project_title'])
def list_apps():
"""
List apps currently in Isabl
"""
apps = ii.get_instances('applications')
data = []
for app in apps:
data.append({'app_name': app.name})
df = pd.DataFrame(data).sort_values(by=['app_name'],
ascending=True).drop_duplicates()
for index, row in df.iterrows():
print(row['app_name'])
def get_data(apps, project):
"""
Retrieve analyses paths from Isabl.
"""
analyses = ii.get_instances('analyses',
application__name__in=apps,
projects__title__in=project)
data = get_parent_paths(analyses)
return pd.DataFrame(data)[[
"individual", "app", "target_sample_category", "target_sample", "path"
]]
def get_paths(apps, projects, details):
"""
Retrieve analyses paths from Isabl.
"""
# apps = apps.replace(' ', '')
# projects = projects.replace(' ', '')
analyses = ii.get_instances('analyses',
application__name__in=apps,
projects__title__in=projects)
if details:
data = get_detailed_paths(analyses)
else:
data = get_parent_paths(analyses)
df = pd.DataFrame(data)
df.to_csv(f'./isabl_paths_{time.strftime("%Y%m%d-%H%M%S")}.csv',
index=False)
