def main():
global meta_config
global study_config
global janus_path
global verb
from support import helper
from generate.analysis_pipelines.MUTATION_EXTENDED import support_functions
import logging
verb = logger.isEnabledFor(
logging.INFO) # TODO replace the 'verb' switch with logger
logger.info('Transferring VCF files to temporary folder')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info(
'Ensuring both columns exist, otherwise adding UNMATCHED column ...')
support_functions.verify_dual_columns(meta_config, verb)
logger.info('Exporting vcf2maf...')
logger.info('And deleting .vcf s...')
meta_config = support_functions.export2maf(meta_config, study_config, verb)
# Generate the meta data files for mutation extended data
logger.info('Generating MUTATION_EXTENDED Meta ...')
meta.generate_meta_type(meta_config, study_config, logger)
logger.info('Cleaning MAF Files ...')
support_functions.clean_head(meta_config, verb)
logger.info('Concating MAF Files to export folder ...')
helper.concat_files(meta_config, study_config, verb)
def main():
global meta_config
global study_config
global janus_path
global logger
import logging
from support import helper
from generate import meta
from generate.analysis_pipelines.COPY_NUMBER_ALTERATION.support_functions import fix_chrom, fix_seg_id
verb = logger.isEnabledFor(logging.INFO) # TODO replace the 'verb' switch with logger
logger.info('Gathering and decompressing SEG files into temporary folder, and updating config')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info('Done.')
logger.info('Fixing Chromosome numbering ...')
fix_chrom(meta_config, study_config, logger)
logger.info('Done.')
logger.info('Fixing .SEG IDs')
fix_seg_id(meta_config, study_config, logger)
logger.info('Done.')
logger.info('Concatenating SEG Files to export folder')
helper.concat_files(meta_config, study_config, verb)
logger.info('Done.')
logger.info('Generating segments Meta ...')
meta.generate_meta_type(meta_config,study_config,logger)
logger.info('Done.')
def test_relocate_inputs(self):
test_name = 'relocate_inputs'
input_dir = os.path.join(self.dataDir, test_name)
out_dir = os.path.join(self.tmp.name, test_name)
os.mkdir(out_dir)
inputs = [
'blue.txt', 'green.tar.gz', 'yellow.tgz', 'purple.tar',
'red.txt.gz'
]
df = pd.DataFrame({'FILE_NAME': inputs})
mutate_config = mock_legacy_config({'input_folder': input_dir}, df)
study_config = mock_legacy_config({'output_folder': out_dir})
updated_mutate_config = relocate_inputs(mutate_config, study_config,
True)
outputs = [
'blue.txt', 'green/green.txt', 'yellow/yellow.txt',
'purple/purple.txt', 'red.txt'
]
md5sum = 'edc715389af2498a623134608ba0a55b' # all output files should be identical
checksums = {output: md5sum for output in outputs}
mock_output = os.path.join(out_dir, 'temp', 'temp_mock')
self.verify_checksums(checksums, mock_output)
self.assertEqual(updated_mutate_config.config_map['input_folder'],
mock_output, 'input folder updated')
outputs = set([
'blue.txt', 'green.tar.gz', 'yellow.tgz', 'purple.tar', 'red.txt'
])
self.assertTrue(
outputs == set(
updated_mutate_config.data_frame['FILE_NAME'].values),
'filenames updated')
def main():
global meta_config
global study_config
global janus_path
global logger
import logging
import os
from support import helper
from generate import meta
from generate.analysis_pipelines.MUTATION_EXTENDED import support_functions
verb = logger.isEnabledFor(
logging.INFO) # TODO replace the 'verb' switch with logger
logger.info('Started processing data for CAP_mutation pipeline')
# Decompress MAF files to temp folder
logger.info('Decompressing MAF files to temporary folder')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
# Clean MAF files
logger.info('Cleaning MAF Files ...')
support_functions.clean_head(meta_config, verb)
# Concatenate MAF files
logger.info('Concatenating MAF Files to export folder ...')
helper.concat_files(meta_config, study_config, verb)
# Generate the meta data files for mutation extended data
logger.info('Generating MUTATION_EXTENDED Meta ...')
meta.generate_meta_type(meta_config, study_config, logger)
#Filtering MAF Files
logger.info('Filtering MAF Files ...')
support_functions.maf_filter(
meta_config, study_config, meta_config.config_map['Mutation_Type'],
meta_config.config_map['Filter_Exception'],
meta_config.config_map['Minimum_Tumour_Depth'],
meta_config.config_map['Minimum_Tumour_AF'],
meta_config.config_map['Maximum_gnomAD_AF'],
meta_config.config_map['Maximum_Local_Freq'])
#oncokb-annotation
logger.info('Annotating MAF files ...')
support_functions.oncokb_annotation(
meta_config, study_config, meta_config.config_map['oncokb_api_token'],
verb)
#TGL Pipe Filtering
logger.info('Filtering TGL pipe ...')
try:
support_functions.TGL_filter(meta_config, study_config)
except FileNotFoundError as err: # eg. failure to read vep_keep_columns.txt
logger.error("Cannot read file: {0}".format(err))
raise
logger.info('Finished processing data for CAP_mutation pipeline')
def main():
global meta_config
global study_config
global janus_path
global logger
import logging
from constants.constants import config2name_map
from support import helper
from generate import meta
from generate.analysis_pipelines.MRNA_EXPRESSION.support_functions import alpha_sort, generate_expression_matrix, generate_expression_zscore
verb = logger.isEnabledFor(
logging.INFO) # TODO replace the 'verb' switch with logger
logger.info(
'Gathering and decompressing MRNA_EXPRESSION files into temporary folder'
)
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info('Alpha sorting each file ...')
alpha_sort(meta_config, verb)
logger.info('Generating expression matrix ...')
generate_expression_matrix(meta_config, study_config, verb)
logger.info('Generating expression Meta ...')
meta.generate_meta_type(meta_config, study_config, logger)
if 'zscores' in meta_config.config_map.keys(
) and meta_config.config_map['zscores']:
logger.info('Generating expression Z-Score Data ...')
generate_expression_zscore(
meta_config,
os.path.join(
study_config.config_map['output_folder'], 'data_{}.txt'.format(
config2name_map[meta_config.alterationtype + ":" +
meta_config.datahandler])),
study_config.config_map['output_folder'], False, False, verb)
logger.info('Generating expression Z-Score Meta ...')
# Tweak the config to write zscore metadata; TODO do this more transparently
meta_config.datahandler = 'Z-SCORE'
meta.generate_meta_type(meta_config, study_config, logger)
def main():
global meta_config
global study_config
global janus_path
global logger
import logging
from support import helper
from generate import meta
from generate.analysis_pipelines.MUTATION_EXTENDED import support_functions
verb = logger.isEnabledFor(
logging.INFO) # TODO replace the 'verb' switch with logger
logger.info('Decompressing VCF files to temporary folder')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info(
'Ensuring both columns exist, otherwise adding UNMATCHED column ...')
support_functions.verify_dual_columns(meta_config, verb)
logger.info('Filtering for only PASS ...')
support_functions.filter_vcf_rejects(meta_config, verb)
logger.info('Exporting vcf2maf, and deleting .VCFs')
meta_config = support_functions.export2maf(meta_config, study_config, verb)
# Generate the meta data files for mutation extended data
logger.info('Generating MUTATION_EXTENDED Meta ...')
meta.generate_meta_type(meta_config, study_config, logger)
logger.info('Cleaning MAF Files ...')
support_functions.clean_head(meta_config, verb)
logger.info('Concating MAF Files to export folder ...')
helper.concat_files(meta_config, study_config, verb)
logger.info('Finished processing data for Mutect pipeline')
def main():
global meta_config
global study_config
global janus_path
global logger
# imports are moved into the main (and only) method to work with the legacy component class
import logging
import os
from support import helper
from generate import meta
from generate.analysis_pipelines.MRNA_EXPRESSION.support_functions import alpha_sort, generate_expression_matrix, generate_expression_percentile, generate_expression_zscore, preProcRNA
from constants.constants import config2name_map
from utilities.constants import DATA_DIRNAME
verb = logger.isEnabledFor(logging.INFO) # TODO replace the 'verb' switch with logger
if meta_config.config_map.get('genelist'):
genelist = meta_config.config_map.get('genelist')
else:
genelist = os.path.join(os.path.dirname(__file__), DATA_DIRNAME, 'targeted_genelist.txt')
if meta_config.config_map.get('enscon'):
enscon = meta_config.config_map.get('enscon')
else:
enscon = os.path.join(os.path.dirname(__file__), DATA_DIRNAME, 'ensemble_conversion.txt')
logger.info('Started processing data for CAP_expression pipeline')
logger.info('Decompressing MRNA_EXPRESSION files to temporary folder')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info('Alpha sorting each file ...')
alpha_sort(meta_config, verb)
logger.info('Generating expression matrix ...')
generate_expression_matrix(meta_config, study_config, verb)
#preProcRNA - generate processed continuous data using the generated expression matrix - one for study and one for study comparison and one for TCGA data
preProcRNA(meta_config, study_config, '/data_{}_gepcomp.txt'.format(config2name_map[meta_config.alterationtype + ":" + meta_config.datahandler]), enscon, genelist, True, False)
preProcRNA(meta_config, study_config, '/data_{}.txt'.format(config2name_map[meta_config.alterationtype + ":" + meta_config.datahandler]), enscon, genelist, False, True)
if meta_config.config_map.get('zscores'):
# Generate the z-scores for mRNA expression data
logger.info('Generating expression Z-Score Data ...')
generate_expression_zscore(meta_config, os.path.join(study_config.config_map['output_folder'],
'data_{}.txt'.format(config2name_map[meta_config.alterationtype + ":" + meta_config.datahandler])),
study_config.config_map['output_folder']
, False, False, verb)
# Generate the mRNA expression percentile data
logger.info('Generating expression Percentile Data ...')
generate_expression_percentile(meta_config, os.path.join(study_config.config_map['output_folder'],
'data_{}.txt'.format(config2name_map[meta_config.alterationtype + ":" + 'Z-SCORE'])),
study_config.config_map['output_folder']
, False, False, verb)
# Generate the z-score sfor mRNA expression comparison data
logger.info('Generating expression Z-Score comparison Data ...')
generate_expression_zscore(meta_config, os.path.join(study_config.config_map['output_folder'],
'data_{}_gepcomp.txt'.format(config2name_map[meta_config.alterationtype + ":" + meta_config.datahandler])),
study_config.config_map['output_folder']
, True, False, verb)
# Generate the mRNA expression comparison percentile data
logger.info('Generating expression Percentile comparison Data ...')
generate_expression_percentile(meta_config, os.path.join(study_config.config_map['output_folder'], 'data_{}.txt'.format(config2name_map[meta_config.alterationtype + ":" + 'Z-SCORE'])),
study_config.config_map['output_folder']
, True, False, verb)
# Generate the z-scores for mRNA expression TCGA data
helper.working_on(verb, message='Generating expression TCGA Z-Score Data ...')
generate_expression_zscore(meta_config, os.path.join(study_config.config_map['output_folder'],
'data_{}_tcga.txt'.format(config2name_map[meta_config.alterationtype + ":" + meta_config.datahandler])),
study_config.config_map['output_folder']
, False, True, verb)
# Generate the TCGA mRNA expression percentile data
logger.info('Generating expression TCGA Percentile Data ...')
generate_expression_percentile(meta_config, os.path.join(study_config.config_map['output_folder'], 'supplementary_data',
'data_{}_tcga.txt'.format(config2name_map[meta_config.alterationtype + ":" + 'Z-SCORE'])),
study_config.config_map['output_folder']
, False, True, verb)
# Generate meta data within the handler and not in generator.py
# Generate metadata for mRNA expression continuous data
logger.info('Generating expression Meta ...')
meta.generate_meta_type(meta_config,study_config,logger)
# Generate metadata for mRNA expression z-score data
if meta_config.config_map.get('zscores'):
logger.info('Generating expression Z-Score Meta ...')
meta_config.datahandler = 'Z-SCORE'
meta.generate_meta_type(meta_config,study_config,logger)
logger.info('Finished processing data for CAP_expression pipeline')
def main():
global meta_config
global study_config
global janus_path
global logger
import logging
import os
from support import helper
from generate.analysis_pipelines.COPY_NUMBER_ALTERATION.support_functions import fix_chrom, fix_seg_id, preProcCNA, ProcCNA
from generate import meta
from utilities.constants import DATA_DIRNAME
AP_NAME = 'analysis_pipelines'
CNA_NAME = 'COPY_NUMBER_ALTERATION'
verb = logger.isEnabledFor(
logging.INFO) # TODO replace the 'verb' switch with logger
# note that __file__ is the path to the executing module components.py, not this script
if meta_config.config_map.get('genebed'):
genebed = meta_config.config_map.get('genebed')
else:
genebed = os.path.join(os.path.dirname(__file__), AP_NAME, CNA_NAME,
DATA_DIRNAME, 'ncbi_genes_hg19_canonical.bed')
if meta_config.config_map.get('genelist'):
genelist = meta_config.config_map.get('genelist')
else:
genelist = os.path.join(os.path.dirname(__file__), AP_NAME, CNA_NAME,
DATA_DIRNAME, 'targeted_genelist.txt')
logger.info('Transferring SEG files to temporary folder')
meta_config = helper.relocate_inputs(meta_config, study_config, verb)
logger.info('Done.')
logger.info('Fixing Chromosome numbering ...')
fix_chrom(meta_config, study_config, logger)
logger.info('Done.')
logger.info('Fixing .SEG IDs')
fix_seg_id(meta_config, study_config, logger)
logger.info('Done.')
logger.info('Concatenating SEG Files to export folder')
helper.concat_files(meta_config, study_config, verb)
logger.info('Done.')
#Call preProcCNA.r to generate reduced seg files
logger.info('Generating reduced SEG files ...')
preProcCNA(meta_config, study_config, genebed, genelist,
meta_config.config_map['gain'], meta_config.config_map['ampl'],
meta_config.config_map['htzd'], meta_config.config_map['hmzd'],
logger)
logger.info('Done.')
logger.info('Generating CNA and log2CNA files ...')
ProcCNA(meta_config, study_config, genebed, genelist,
meta_config.config_map['gain'], meta_config.config_map['ampl'],
meta_config.config_map['htzd'], meta_config.config_map['hmzd'],
meta_config.config_map['oncokb_api_token'], verb)
logger.info('Done.')
# TODO legacy metadata generation left in place for now. But does it make sense for data to be *both* discrete and continuous?
logger.info('Generating segments Meta ...')
meta.generate_meta_type(meta_config, study_config, logger)
logger.info('Done.')
if meta_config.config_map.get('DISCRETE'):
logger.info('Generating DISCRETE Meta ...')
meta_config.datahandler = 'DISCRETE'
meta.generate_meta_type(meta_config, study_config, logger)
logger.info('Done.')
if meta_config.config_map.get('CONTINUOUS'):
logger.info('Generating CONTINUOUS Meta ...')
meta_config.datahandler = 'CONTINUOUS'
meta.generate_meta_type(meta_config, study_config, logger)
logger.info('Done.')
