def main(configfilename):
"""
Prefer 450K files over 270k (delete transformed 270K files)
"""
with open(configfilename) as configfile:
config = json.load(configfile)
print '*'*30 + "\nExtract - methylation"
data_library = methylation.extract.identify_data(config)
hiseq_aliquots = data_library.query('Platform == "HumanMethylation450"')['AliquotBarcode'].drop_duplicates().values.tolist()
IlluminaGA_df = data_library.query('Platform == "HumanMethylation27"')
IlluminaHiSeq_GA_df = IlluminaGA_df[ (IlluminaGA_df['AliquotBarcode'].isin(hiseq_aliquots))]
project_id = config['project_id']
bucket_name = config['buckets']['open']
gcs = GcsConnector(project_id, bucket_name)
for _, row in IlluminaHiSeq_GA_df.iterrows():
blob = row.to_dict()['OutDatafileNameKey']
gcs.delete_blob(blob)
def main():
"""
Pipeline
"""
#--------------
# methylation
#--------------
config = json.load(open(sys.argv[1]))
project_id = config['project_id']
bucket_name = config['buckets']['open']
print '*'*30 + "\nExtract - methylation"
data_library = methylation.extract.identify_data(config)
hiseq_aliquots = data_library.query('Platform == "HumanMethylation450"')['AliquotBarcode'].drop_duplicates().values.tolist()
IlluminaGA_df = data_library.query('Platform == "HumanMethylation27"')
IlluminaHiSeq_GA_df = IlluminaGA_df[ (IlluminaGA_df['AliquotBarcode'].isin(hiseq_aliquots))]
gcs = GcsConnector(project_id, bucket_name)
for idx, row in IlluminaHiSeq_GA_df.iterrows():
blob = row.to_dict()['OutDatafileNameKey']
print gcs.delete_blob(blob)
def main():
"""
Pipeline
"""
#--------------
# methylation
#--------------
config = json.load(open(sys.argv[1]))
project_id = config['project_id']
bucket_name = config['buckets']['open']
print '*' * 30 + "\nExtract - methylation"
data_library = methylation.extract.identify_data(config)
hiseq_aliquots = data_library.query('Platform == "HumanMethylation450"')[
'AliquotBarcode'].drop_duplicates().values.tolist()
IlluminaGA_df = data_library.query('Platform == "HumanMethylation27"')
IlluminaHiSeq_GA_df = IlluminaGA_df[(
IlluminaGA_df['AliquotBarcode'].isin(hiseq_aliquots))]
gcs = GcsConnector(project_id, bucket_name)
for idx, row in IlluminaHiSeq_GA_df.iterrows():
blob = row.to_dict()['OutDatafileNameKey']
print gcs.delete_blob(blob)
def process_user_gen_files(project_id, user_project_id, study_id, bucket_name, bq_dataset, cloudsql_tables, files):
print 'Begin processing user_gen files.'
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
data_df = pd.DataFrame()
# Collect all columns that get passed in for generating BQ schema later
all_columns = []
# For each file, download, convert to df
for idx, file in enumerate(files):
blob_name = file['FILENAME'].split('/')[1:]
all_columns += file['COLUMNS']
metadata = {
'sample_barcode': file.get('SAMPLEBARCODE', ''),
'participant_barcode': file.get('PARTICIPANTBARCODE', ''),
'study_id': study_id,
'platform': file.get('PLATFORM', ''),
'pipeline': file.get('PIPELINE', ''),
'file_path': file['FILENAME'],
'file_name': file['FILENAME'].split('/')[-1],
'data_type': file['DATATYPE']
}
# download, convert to df
filebuffer = gcs.download_blob_to_file(blob_name)
# Get column mapping
column_mapping = get_column_mapping(file['COLUMNS'])
if idx == 0:
data_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
data_df = cleanup_dataframe(data_df)
data_df.rename(columns=column_mapping, inplace=True)
# Generate Metadata for this file
insert_metadata(data_df, metadata, cloudsql_tables['METADATA_DATA'])
else:
# convert blob into dataframe
new_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
new_df = cleanup_dataframe(new_df)
new_df.rename(columns=column_mapping, inplace=True)
# Generate Metadata for this file
insert_metadata(new_df, metadata, cloudsql_tables['METADATA_DATA'])
# TODO: Write function to check for participant barcodes, for now, we assume each file contains SampleBarcode Mapping
data_df = pd.merge(data_df, new_df, on='sample_barcode', how='outer')
# For complete dataframe, create metadata_samples rows
print 'Inserting into data into {0}.'.format(cloudsql_tables['METADATA_SAMPLES'])
data_df = cleanup_dataframe(data_df)
data_df['has_mrna'] = 0
data_df['has_mirna'] = 0
data_df['has_protein'] = 0
data_df['has_meth'] = 0
insert_metadata_samples(data_df, cloudsql_tables['METADATA_SAMPLES'])
# Update and create bq table file
temp_outfile = cloudsql_tables['METADATA_SAMPLES'] + '.out'
tmp_bucket = os.environ.get('tmp_bucket')
gcs.convert_df_to_njson_and_upload(data_df, temp_outfile, tmp_bucket=tmp_bucket)
# Using temporary file location (in case we don't have write permissions on user's bucket?
source_path = 'gs://' + tmp_bucket + '/' + temp_outfile
schema = generate_bq_schema(all_columns)
table_name = 'cgc_user_{0}_{1}'.format(user_project_id, study_id)
load_data_from_file.run(
project_id,
bq_dataset,
table_name,
schema,
source_path,
source_format='NEWLINE_DELIMITED_JSON',
write_disposition='WRITE_APPEND',
is_schema_file=False)
# Generate feature_defs
feature_defs = generate_feature_defs(study_id, project_id, bq_dataset, table_name, schema)
# Update feature_defs table
insert_feature_defs_list(cloudsql_tables['FEATURE_DEFS'], feature_defs)
# Delete temporary files
print 'Deleting temporary file {0}'.format(temp_outfile)
gcs = GcsConnector(project_id, tmp_bucket)
gcs.delete_blob(temp_outfile)
def parse_file(project_id, bq_dataset, bucket_name, file_data, filename, outfilename, metadata, cloudsql_tables):
print 'Begin processing {0}.'.format(filename)
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
filebuffer = gcs.download_blob_to_file(filename)
# convert blob into dataframe
data_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
# clean-up dataframe
data_df = cleanup_dataframe(data_df)
new_df_data = []
map_values = {}
# Get basic column information depending on datatype
column_map = get_column_mapping(metadata['data_type'])
# Column headers are sample ids
for i, j in data_df.iteritems():
if i in column_map.keys():
map_values[column_map[i]] = [k for d, k in j.iteritems()]
else:
for k, m in j.iteritems():
new_df_obj = {}
new_df_obj['sample_barcode'] = i # Normalized to match user_gen
new_df_obj['project_id'] = metadata['project_id']
new_df_obj['study_id'] = metadata['study_id']
new_df_obj['Platform'] = metadata['platform']
new_df_obj['Pipeline'] = metadata['pipeline']
# Optional values
new_df_obj['Symbol'] = map_values['Symbol'][k] if 'Symbol' in map_values.keys() else ''
new_df_obj['ID'] = map_values['ID'][k] if 'ID' in map_values.keys() else ''
new_df_obj['TAB'] = map_values['TAB'][k] if 'TAB' in map_values.keys() else ''
new_df_obj['Level'] = m
new_df_data.append(new_df_obj)
new_df = pd.DataFrame(new_df_data)
# Get unique barcodes and update metadata_data table
sample_barcodes = list(set([k for d, k in new_df['sample_barcode'].iteritems()]))
sample_metadata_list = []
for barcode in sample_barcodes:
new_metadata = metadata.copy()
new_metadata['sample_barcode'] = barcode
sample_metadata_list.append(new_metadata)
update_metadata_data_list(cloudsql_tables['METADATA_DATA'], sample_metadata_list)
# Update metadata_samples table
update_molecular_metadata_samples_list(cloudsql_tables['METADATA_SAMPLES'], metadata['data_type'], sample_barcodes)
# Generate feature names and bq_mappings
table_name = file_data['BIGQUERY_TABLE_NAME']
feature_defs = generate_feature_Defs(metadata['data_type'], metadata['study_id'], project_id, bq_dataset, table_name, new_df)
# Update feature_defs table
insert_feature_defs_list(cloudsql_tables['FEATURE_DEFS'], feature_defs)
# upload the contents of the dataframe in njson format
tmp_bucket = os.environ.get('tmp_bucket')
gcs.convert_df_to_njson_and_upload(new_df, outfilename, metadata=metadata, tmp_bucket=tmp_bucket)
# Load into BigQuery
# Using temporary file location (in case we don't have write permissions on user's bucket?)
source_path = 'gs://' + tmp_bucket + '/' + outfilename
schema = get_molecular_schema()
load_data_from_file.run(
project_id,
bq_dataset,
table_name,
schema,
source_path,
source_format='NEWLINE_DELIMITED_JSON',
write_disposition='WRITE_APPEND',
is_schema_file=False)
# Delete temporary files
print 'Deleting temporary file {0}'.format(outfilename)
gcs = GcsConnector(project_id, tmp_bucket)
gcs.delete_blob(outfilename)
def parse_file(project_id, bq_dataset, bucket_name, file_data, filename,
outfilename, metadata, cloudsql_tables):
print 'Begin processing {0}.'.format(filename)
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
filebuffer = gcs.download_blob_to_file(filename)
# convert blob into dataframe
data_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
# clean-up dataframe
data_df = cleanup_dataframe(data_df)
new_df_data = []
map_values = {}
# Get basic column information depending on datatype
column_map = get_column_mapping(metadata['data_type'])
# Column headers are sample ids
for i, j in data_df.iteritems():
if i in column_map.keys():
map_values[column_map[i]] = [k for d, k in j.iteritems()]
else:
for k, m in j.iteritems():
new_df_obj = {}
new_df_obj[
'sample_barcode'] = i # Normalized to match user_gen
new_df_obj['Project'] = metadata['project_id']
new_df_obj['Study'] = metadata['study_id']
new_df_obj['Platform'] = metadata['platform']
new_df_obj['Pipeline'] = metadata['pipeline']
# Optional values
new_df_obj['Symbol'] = map_values['Symbol'][
k] if 'Symbol' in map_values.keys() else ''
new_df_obj['ID'] = map_values['ID'][
k] if 'ID' in map_values.keys() else ''
new_df_obj['TAB'] = map_values['TAB'][
k] if 'TAB' in map_values.keys() else ''
new_df_obj['Level'] = m
new_df_data.append(new_df_obj)
new_df = pd.DataFrame(new_df_data)
# Get unique barcodes and update metadata_data table
sample_barcodes = list(
set([k for d, k in new_df['SampleBarcode'].iteritems()]))
sample_metadata_list = []
for barcode in sample_barcodes:
new_metadata = metadata.copy()
new_metadata['sample_barcode'] = barcode
sample_metadata_list.append(new_metadata)
update_metadata_data_list(cloudsql_tables['METADATA_DATA'],
sample_metadata_list)
# Update metadata_samples table
update_molecular_metadata_samples_list(cloudsql_tables['METADATA_SAMPLES'],
metadata['data_type'],
sample_barcodes)
# Generate feature names and bq_mappings
table_name = file_data['BIGQUERY_TABLE_NAME']
feature_defs = generate_feature_Defs(metadata['data_type'],
metadata['study_id'], project_id,
bq_dataset, table_name, new_df)
# Update feature_defs table
insert_feature_defs_list(cloudsql_tables['FEATURE_DEFS'], feature_defs)
# upload the contents of the dataframe in njson format
tmp_bucket = os.environ.get('tmp_bucket_location')
gcs.convert_df_to_njson_and_upload(new_df,
outfilename,
metadata=metadata,
tmp_bucket=tmp_bucket)
# Load into BigQuery
# Using temporary file location (in case we don't have write permissions on user's bucket?)
source_path = 'gs://' + tmp_bucket + '/' + outfilename
schema = get_molecular_schema()
load_data_from_file.run(project_id,
bq_dataset,
table_name,
schema,
source_path,
source_format='NEWLINE_DELIMITED_JSON',
write_disposition='WRITE_APPEND',
is_schema_file=False)
# Delete temporary files
print 'Deleting temporary file {0}'.format(outfilename)
gcs = GcsConnector(project_id, tmp_bucket)
gcs.delete_blob(outfilename)
def process_user_gen_files(project_id, user_project_id, study_id, bucket_name, bq_dataset, cloudsql_tables, files):
print 'Begin processing user_gen files.'
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
data_df = pd.DataFrame()
# Collect all columns that get passed in for generating BQ schema later
all_columns = []
# For each file, download, convert to df
for idx, file in enumerate(files):
blob_name = file['FILENAME'].split('/')[1:]
all_columns += file['COLUMNS']
metadata = {
'sample_barcode': file.get('SAMPLEBARCODE', ''),
'participant_barcode': file.get('PARTICIPANTBARCODE', ''),
'study_id': study_id,
'platform': file.get('PLATFORM', ''),
'pipeline': file.get('PIPELINE', ''),
'file_path': file['FILENAME'],
'file_name': file['FILENAME'].split('/')[-1],
'data_type': file['DATATYPE']
}
# download, convert to df
filebuffer = gcs.download_blob_to_file(blob_name)
# Get column mapping
column_mapping = get_column_mapping(file['COLUMNS'])
if idx == 0:
data_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
data_df = cleanup_dataframe(data_df)
data_df.rename(columns=column_mapping, inplace=True)
# Generate Metadata for this file
insert_metadata(data_df, metadata, cloudsql_tables['METADATA_DATA'])
else:
# convert blob into dataframe
new_df = convert_file_to_dataframe(filebuffer, skiprows=0, header=0)
new_df = cleanup_dataframe(new_df)
new_df.rename(columns=column_mapping, inplace=True)
# Generate Metadata for this file
insert_metadata(new_df, metadata, cloudsql_tables['METADATA_DATA'])
# TODO: Write function to check for participant barcodes, for now, we assume each file contains SampleBarcode Mapping
data_df = pd.merge(data_df, new_df, on='sample_barcode', how='outer')
# For complete dataframe, create metadata_samples rows
print 'Inserting into data into {0}.'.format(cloudsql_tables['METADATA_SAMPLES'])
data_df = cleanup_dataframe(data_df)
data_df['has_mrna'] = 0
data_df['has_mirna'] = 0
data_df['has_protein'] = 0
data_df['has_meth'] = 0
insert_metadata_samples(data_df, cloudsql_tables['METADATA_SAMPLES'])
# Update and create bq table file
temp_outfile = cloudsql_tables['METADATA_SAMPLES'] + '.out'
tmp_bucket = os.environ.get('tmp_bucket_location')
gcs.convert_df_to_njson_and_upload(data_df, temp_outfile, tmp_bucket=tmp_bucket)
# Using temporary file location (in case we don't have write permissions on user's bucket?
source_path = 'gs://' + tmp_bucket + '/' + temp_outfile
schema = generate_bq_schema(all_columns)
table_name = 'cgc_user_{0}_{1}'.format(user_project_id, study_id)
load_data_from_file.run(
project_id,
bq_dataset,
table_name,
schema,
source_path,
source_format='NEWLINE_DELIMITED_JSON',
write_disposition='WRITE_APPEND',
is_schema_file=False)
# Generate feature_defs
feature_defs = generate_feature_defs(study_id, project_id, bq_dataset, table_name, schema)
# Update feature_defs table
insert_feature_defs_list(cloudsql_tables['FEATURE_DEFS'], feature_defs)
# Delete temporary files
print 'Deleting temporary file {0}'.format(temp_outfile)
gcs = GcsConnector(project_id, tmp_bucket)
gcs.delete_blob(temp_outfile)
