def __init__(self, expected_attributes=None, **kwargs):
# add expected attributes to super._attributes
self._add_expected_attributes = []
# This is a method of adding expected attributes to StandardData from StandardData children
if isinstance(expected_attributes, list):
self._add_expected_attributes.extend(expected_attributes)
# initialize Standard data with the extended _attributes
# recall that this will check for and/or create the directory structure found at
super(S288C_R54QualAssessAuditObject, self).__init__(self._add_expected_attributes, **kwargs)
# overwrite super.self_type with object type of child (this object)
self.self_type = 'CryptoQualAssessAuditObject'
# create logger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
# extract threshold/status from config file #TODO: move to constructor
qual_assess_config = configparser.ConfigParser()
qual_assess_config.read(self.config_file)
qual_assess_1_dict = qual_assess_config['S288C_R64QualityAssessOne']
# extract thresholds #TODO: CLEAN UP TO DICTIONARY, AUTOMATICALLY EXTRACT
self.library_size_threshold = int(qual_assess_1_dict['LIBRARY_SIZE_THRESHOLD'])
self.not_aligned_total_percent_threshold = float(qual_assess_1_dict['NOT_ALIGNED_TOTAL_PERCENT_THRESHOLD'])
# extract status
self.library_size_bit_status = int(qual_assess_1_dict['LIBRARY_SIZE_STATUS'])
self.not_aligned_total_percent_bit_status = int(qual_assess_1_dict['NOT_ALIGNED_TOTAL_PERCENT_STATUS'])
self.auditQualAssessDataframe()
def __init__(self, expected_attributes=None, **kwargs):
"""
constructor
:param **kwargs: unspecified # keyword arguments. The keywords that are currently handled, if entered:
logger_path = path to the directory in which to deposit the logger
PLEASE NOTE: order of database_subdirectories is important. see comment in constructor
"""
# Call StandardData (parent class) constructor
self._add_expected_attributes = [
'database_subdirectories', 'filter_json_path', 'database_df'
]
super(DatabaseObject, self).__init__(self._add_expected_attributes,
**kwargs)
self.self_type = 'DatabaseObject'
# set DatabaseObject logger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
try:
self.database_directory = kwargs['database_files']
except KeyError:
self.database_directory = self.database_files
# set default database subdirectories. PLEASE NOTE: order is important here -- list in the order you wish them to merge in
try:
self.database_subdirectories = kwargs['database_subdirectories']
except KeyError:
#self.database_subdirectories = ['fastqFiles', 'library', 's2cDNASample', 's1cDNASample', 'rnaSample', 'bioSample'] # concat in reverse order
self.database_subdirectories = [
'bioSample', 'rnaSample', 's1cDNASample', 's2cDNASample',
'library', 'fastqFiles'
]
# see setter setFilterJson()
self.filter_json = None
try:
self.filter_json_path = kwargs['filter_json_path']
except KeyError:
self.filter_json_path = None
# see setter setDatabaseDataframe()
try:
self.database_df = kwargs['database_df']
except KeyError:
self.database_df = None
# see filterDatabaseDataframe()
try:
self.filtered_database_df = kwargs['filtered_database_df']
except KeyError:
self.filtered_database_df = None
# data_dir_dict will store {database_subdirectory: [list, of, filepaths, in, each, subdir], ... }. See self.setDatabaseDict()
self.database_dict = {}
# see setter setDatabaseDict()
self.concat_database_dict = {}
# see setter setKeyColumns()
self.database_key_columns = []
def createOrganismDataLogger(self):
"""
create logger for OrganismData
:raises: NotADirectoryError if logger_directory_path does not exist
"""
logger_directory_path = utils.dirPath(self.log_file_path)
if os.path.isdir(logger_directory_path):
self.logger = utils.createStandardObjectChildLogger(self, __name__)
else:
raise NotADirectoryError('LogDirectoryDoesNotExist')
def __init__(self, expected_attributes=None, **kwargs):
# add expected attributes to super._attributes
self._add_expected_attributes = []
# This is a method of adding expected attributes to StandardData from StandardData children
if isinstance(expected_attributes, list):
self._add_expected_attributes.extend(expected_attributes)
# initialize Standard data with the extended _attributes
# recall that this will check for and/or create the directory structure found at
super(CryptoQualityAssessmentObject,
self).__init__(self._add_expected_attributes, **kwargs)
# overwrite super.self_type with object type of child (this object)
self.self_type = 'CryptoQualityAssessmentObject'
# create logger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
# for ordering columns below. genotype1_coverage and genotype2_coverage added if coverage_check is passed
self.column_order = [
'FASTQFILENAME', 'LIBRARY_SIZE', 'EFFECTIVE_LIBRARY_SIZE',
'EFFECTIVE_UNIQUE_ALIGNMENT', 'EFFECTIVE_UNIQUE_ALIGNMENT_PERCENT',
'MULTI_MAP_PERCENT', 'PROTEIN_CODING_TOTAL',
'PROTEIN_CODING_TOTAL_PERCENT', 'PROTEIN_CODING_COUNTED',
'PROTEIN_CODING_COUNTED_PERCENT', 'AMBIGUOUS_FEATURE_PERCENT',
'NO_FEATURE_PERCENT', 'INTERGENIC_COVERAGE',
'NOT_ALIGNED_TOTAL_PERCENT', 'GENOTYPE1_COVERAGE',
'GENOTYPE1_LOG2CPM', 'GENOTYPE2_COVERAGE', 'GENOTYPE2_LOG2CPM',
'OVEREXPRESSION_FOW', 'NAT_COVERAGE', 'NAT_LOG2CPM',
'G418_COVERAGE', 'G418_LOG2CPM', 'NO_MAP_PERCENT',
'HOMOPOLY_FILTER_PERCENT', 'READ_LENGTH_FILTER_PERCENT',
'TOO_LOW_AQUAL_PERCENT', 'rRNA_PERCENT', 'nctrRNA_PERCENT'
]
print('Quantifying noncoding rRNA (rRNA, tRNA and ncRNA)')
# extract rRNA, tRNA and ncRNA quantification for crypto from bam files -- this takes a long time
ncRNA_df = self.quantifyNonCodingRna(self.qual_assess_df)
# merge this into the self.qual_assess_df
self.qual_assess_df = pd.merge(self.qual_assess_df,
ncRNA_df,
on='FASTQFILENAME')
print('Quantifying intergenic coverage')
self.qual_assess_df = self.calculateIntergenicCoverage(
self.qual_assess_df)
# if coverage_check_flag true, check coverage of perturbed genes
try:
if self.coverage_check_flag:
coverage_df = self.perturbedCheck()
self.qual_assess_df = pd.merge(self.qual_assess_df,
coverage_df,
how='left',
on='FASTQFILENAME')
except AttributeError:
self.logger.info(
'query_df or coverage_check_flag not present -- no coverage check'
)
# format the self.qual_assess_df dataframe
self.qual_assess_df = self.formatQualAssessDataFrame(
self.qual_assess_df)
def __init__(self, expected_attributes=None, **kwargs):
"""
constructor
:param **kwargs: unspecified # keyword arguments. The keywords that are currently handled, if entered:
logger_path = path to the directory in which to deposit the logger
"""
# Call StandardData (parent class) constructor
self._add_expected_attributes = []
super(DatabaseAccuracyObject,
self).__init__(self._add_expected_attributes, **kwargs)
self.self_type = 'DatabaseAccuracyObject'
# set DatabaseAccuracyObjectLogger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
# set the database dictionary ({subdirectory: [list, of, files]} --> see DatabaseObject)
self.setDatabaseDict()
# if full_report passed in constructor
try:
if kwargs['full_report']:
self.fullReport() # Report output to report
except KeyError:
pass
# create specification dict -- see class metadataSpecificationObject below this class
self.specification_dict = metadataSpecificationObject(
).specification_dict
# set last_git_change
try:
self.last_git_change = self.getLastGitChange()
except FileNotFoundError:
print(
'Cannot find .git/FETCH_HEAD in database_files. If this is a new, or newly cloned, directory, pull from the remote.'
)
except AttributeError:
print('.git/FETCH_HEAD is empty. Make a commit and try again.')
# set accuracyCheckFilename (expecting to be overwritten by @property method below when needed)
self.accuracy_check_output_file = self.accuracyCheckFilename()
self.key_column_dict = {
"fastqFiles":
['libraryDate', 'libraryPreparer', 'librarySampleNumber'],
"library":
['libraryDate', 'libraryPreparer', 'librarySampleNumber'],
"s2cDNASample":
['s2cDNADate', 's2cDNAPreparer', 's2cDNASampleNumber'],
"s1cDNASample":
['s1cDNADate', 's1cDNAPreparer', 's1cDNASampleNumber'],
"rnaSample": ['rnaDate', 'rnaPreparer', 'rnaSampleNumber'],
"bioSample": ['harvestDate', 'harvester', 'bioSampleNumber']
}
def __init__(self, expected_attributes=None, **kwargs):
# add expected attributes to super._attributes
self._add_expected_attributes = []
# This is a method of adding expected attributes to StandardData from StandardData children
if isinstance(expected_attributes, list):
self._add_expected_attributes.extend(expected_attributes)
# initialize Standard data with the extended _attributes
# recall that this will check for and/or create the directory structure found at
super(CryptoQualAssessAuditObject, self).__init__(self._add_expected_attributes, **kwargs)
# overwrite super.self_type with object type of child (this object)
self.self_type = 'CryptoQualAssessAuditObject'
# create logger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
# extract threshold/status from config file #TODO: move to constructor
qual_assess_config = configparser.ConfigParser()
qual_assess_config.read(self.config_file)
qual_assess_1_dict = qual_assess_config['KN99QualityAssessOne']
# extract thresholds #TODO: CLEAN UP TO DICTIONARY, AUTOMATICALLY EXTRACT
self.protein_coding_total_threshold = int(qual_assess_1_dict['PROTEIN_CODING_TOTAL_THRESHOLD'])
self.not_aligned_total_percent_threshold = float(qual_assess_1_dict['NOT_ALIGNED_TOTAL_PERCENT_THRESHOLD'])
self.perturbed_coverage_threshold = float(qual_assess_1_dict['PERTURBED_COVERAGE_THRESHOLD'])
self.nat_expected_coverage_threshold = float(qual_assess_1_dict['NAT_EXPECTED_COVERAGE_THRESHOLD'])
self.nat_expected_log2cpm_threshold = float(qual_assess_1_dict['NAT_EXPECTED_LOG2CPM_THRESHOLD'])
self.nat_unexpected_coverage_threshold = float(qual_assess_1_dict['NAT_UNEXPECTED_COVERAGE_THRESHOLD'])
self.nat_unexpected_log2cpm_threshold = float(qual_assess_1_dict['NAT_UNEXPECTED_LOG2CPM_THRESHOLD'])
self.g418_log2cpm_threshold = float(qual_assess_1_dict['G418_LOG2CPM_THRESHOLD'])
self.overexpression_fow_threshold = float(qual_assess_1_dict['OVEREXPRESSION_FOW_THRESHOLD'])
# extract status
self.protein_coding_total_bit_status = int(qual_assess_1_dict['PROTEIN_CODING_TOTAL_STATUS'])
self.not_aligned_total_percent_bit_status = int(qual_assess_1_dict['NOT_ALIGNED_TOTAL_PERCENT_STATUS'])
self.perturbed_coverage_bit_status = int(qual_assess_1_dict['PERTURBED_COVERAGE_STATUS'])
self.nat_expected_marker_status = int(qual_assess_1_dict['NAT_EXPECTED_MARKER_STATUS'])
self.nat_unexpected_marker_status = int(qual_assess_1_dict['NAT_UNEXPECTED_MARKER_STATUS'])
self.g418_expected_marker_status = int(qual_assess_1_dict['G418_EXPECTED_MARKER_STATUS'])
self.g418_unexpected_marker_status = int(qual_assess_1_dict['G418_UNEXPECTED_MARKER_STATUS'])
self.overexpression_fow_status = int(qual_assess_1_dict['OVEREXPRESSION_FOW_STATUS'])
self.no_metadata_marker_status = int(qual_assess_1_dict['NO_METADATA_MARKER_STATUS'])
self.auditQualAssessDataframe()
def __init__(self, expected_attributes=None, **kwargs):
# add expected attributes to super._attributes
self._add_expected_attributes = [
'organism', 'output_dir', 'wildtype', 'experiment_dir',
'norm_count_path', 'max_replicates', 'drug_marker', 'qc_config',
'experiment_conditions'
]
# TODO: This is a messy and repetitive way of adding expected attributes from children of OrganismData to add to StandardData
if isinstance(expected_attributes, list):
self._add_expected_attributes.extend(expected_attributes)
# initialize Standard data with the extended _attributes
# recall that this will check for and/or create the directory structure found at
super(OrganismData, self).__init__(self._add_expected_attributes,
**kwargs)
# overwrite super.self_type with object type of child (this object)
self.self_type = 'OrganismData'
# set organism, if an organism is passed
if hasattr(self, 'organism'):
# set organism directory
self.organism_directory = os.path.join(
self.user_rnaseq_pipeline_directory, self.genome_files,
self.organism)
# set OrganismData config found in rnaseq_pipeline/genome_files/<organism>/OrganismData_config.ini
self.organism_config_file = os.path.join(
self.organism_directory, 'OrganismData_config.ini')
if self.organism in self._configured_organisms_list:
self.setOrganismData()
else:
print(
'\n{self.organism} is not configured. You will have to set the OrganismData attributes manually. '
'See the config/rnaseq_pipeline_config.ini. Alternatively, see one of the configured genome_files (in {self.genome_files}) '
'and create a subdir of genomes_files with an OrganismData_config.ini file, zip it into '
'/lts/mblab/Crypto/rnaseq_data/genome_files.zip, remove your genome_files in your {self.user_rnaseq_pipeline_directory}'
'and either re-run this script or start an interactive python session, import and instantiate a StandardData object.\n'
)
# see [OrganismData] in config/rnaseq_pipeline_config.ini
utils.configure(self, self.config_file, self.self_type)
# create OrganismData logger
self.logger = utils.createStandardObjectChildLogger(self, __name__)
