def createConfigTableKeys(self, configParser, configTable):
# Parse fields from FORMAT section of the config file
"""
:param configParser:
:param configTable:
"""
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(configParser, "INFO")
for ID, name in table.items():
configTable.addInfoFieldID(ID, name)
# Parse fields from FORMAT section of the config file
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(configParser, "FORMAT")
for ID, name in table.items():
configTable.addFormatFieldID(ID, name)
# Parse fields from NOT_SPLIT_TAGS section of the config file
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "NOT_SPLIT_TAGS")
for fieldType, IDs in table.items():
configTable.addFieldIDsToNotSplitSet(fieldType, IDs)
# Parse fields from SPLIT_TAGS section of the config file
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "SPLIT_TAGS")
for fieldType, IDs in table.items():
configTable.addFieldIDsToSplitSet(fieldType, IDs)
def createConfigTableKeys(self, configParser, configTable):
# Parse fields from FORMAT section of the config file
"""
:param configParser:
:param configTable:
"""
# Parse fields from INFO section of the config file
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(
configParser, "INFO")
for name, ID in table.items():
configTable.addInfoFieldName(name, ID)
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(
configParser, "FORMAT")
for name, ID in table.items():
configTable.addFormatFieldName(name, ID)
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(
configParser, "OTHER")
for name, ID in table.items():
configTable.addOtherFieldName(name, ID)
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
configParser, "INFO_DESCRIPTION")
for name, description in table.items():
configTable.addInfoFieldNameDescription(
name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
configParser, "FORMAT_DESCRIPTION")
for name, description in table.items():
configTable.addFormatFieldNameDescription(
name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
configParser, "FILTER_DESCRIPTION")
for name, description in table.items():
configTable.addFilterFieldNameDescription(
name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
configParser, "SPLIT_TAGS")
for fieldType, names in table.items():
configTable.addFieldNamesToSplitSet(fieldType, names)
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
configParser, "NOT_SPLIT_TAGS")
for fieldType, names in table.items():
configTable.addFieldNamesToNotSplitSet(fieldType, names)
def __init__(self, filename, configFile="tcgaMAF2.4_output.config", other_options=None):
"""
"""
options = dict() if other_options is None else other_options
self._filename = filename
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self.logger.info("Building alternative keys dictionary...")
self.alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(self.config)
self.options = options
self._prepend = self.config.get("general", "prepend")
if self.options.get(OptionConstants.NO_PREPEND, False):
self._prepend = ""
# _is_reannotating is a flag to determine whether we should give precendence to annotations that were not
# annotated as part of the INPUT.
self._is_reannotating = options.get(OptionConstants.REANNOTATE_TCGA_MAF_COLS, False)
self._is_splitting_allelic_depth = self.options.get(OptionConstants.SPLIT_ALLELIC_DEPTH, True)
self.exposedColumns = set(self.config.get("general", "exposedColumns").split(','))
self._is_entrez_id_message_logged = False
self._is_collapsing_number_cols = options.get(OptionConstants.COLLAPSE_NUMBER_ANNOTATIONS, False)
self._column_collapser = None
self._column_collapser_suffix = None
if self._is_collapsing_number_cols:
self._column_collapser = ColumnCollapser()
self._column_collapser_suffix = "_full"
def __init__(self, filename, configFile="tcgaVCF1.1_output.config", otherOptions=None):
self._filename = filename
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self.alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(self.config)
self.seenDbSNPs = dict()
self.fieldMap = {}
def __init__(self,
filename,
configFile="tcgaMAF2.4_output.config",
other_options=None):
"""
TODO: Need functionality for not prepending the i_ on internal fields.
"""
options = dict() if other_options is None else other_options
self._filename = filename
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self.logger.info("Building alternative keys dictionary...")
self.alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
self.config)
#TODO: Read missing options from the config file or specify that error should be thrown.
self.options = options
self._prepend = self.config.get("general", "prepend")
if self.options.get(OptionConstants.NO_PREPEND, False):
self._prepend = ""
self.exposedColumns = set(
self.config.get("general", "exposedColumns").split(','))
self._is_entrez_id_message_logged = False
def __init__(self,
mut,
configFile="sample_name_selection.config",
section="SAMPLE_NAME"):
config = ConfigUtils.createConfigParser(configFile)
self.logger = logging.getLogger(__name__)
aliases = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
config, section)
self.configFile = configFile
sampleAnnotation = self._getAnnotationFromAliases(
mut, aliases["sample_name"])
tumorAnnotation = self._getAnnotationFromAliases(
mut, aliases["sample_tumor_name"])
normalAnnotation = self._getAnnotationFromAliases(
mut, aliases["sample_normal_name"])
source_column = self._getSourceColumn(sampleAnnotation,
tumorAnnotation,
normalAnnotation)
self._logSampleNameColumnDescription(source_column, sampleAnnotation,
tumorAnnotation, normalAnnotation)
self.sampleNameGrabber = self._getSampleNameGrabber(
source_column, sampleAnnotation, tumorAnnotation, normalAnnotation)
self.outputAnnotationName = self._deriveOutputAnnotationName(
sampleAnnotation)
self.annotationSource = self._deriveAnnotationSource(source_column)
def __init__(self,
filename,
mutation_data_factory=None,
configFile='maflite_input.config',
genomeBuild="hg19",
other_options=None):
"""
Constructor
"""
super(MafliteInputMutationCreator,
self).__init__(filename, mutation_data_factory, configFile,
genomeBuild, other_options)
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self._tsvReader = GenericTsvReader(filename)
# Key is the required columns and the values are a list of valid alternative headers.
# Key is column name to an alternative.
self._alternativeDict = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
self.config)
self._reverseAlternativeDict = ConfigUtils.buildReverseAlternativeDictionary(
self._alternativeDict)
missingRequiredHeaders = []
required_columns = sorted(
self.config.get("general", "required_headers").split(","))
self._build = genomeBuild
self.logger.info(
"Initializing a maflite file with the following header: " +
str(self._tsvReader.getFieldNames()))
# The specified fields are those that were given in the input.
self._specified_fields = self._tsvReader.getFieldNames()
for col in required_columns:
if col not in self._specified_fields:
isAltFound = False
for alt in self._alternativeDict.get(col, []):
if alt in self._specified_fields:
isAltFound = True
break
if not isAltFound:
# build is optional.
if col != "build":
missingRequiredHeaders.append(col)
missingRequiredHeaders.sort()
if len(missingRequiredHeaders) > 0:
raise MafliteMissingRequiredHeaderException(
"Specified maflite file (" + filename +
") missing required headers: " +
",".join(missingRequiredHeaders))
def __init__(self,
filename,
configFile="tcgaVCF1.1_output.config",
otherOptions=None):
self._filename = filename
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self.alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
self.config)
self.seenDbSNPs = dict()
self.fieldMap = {}
def createConfigTableKeys(self, configParser, configTable):
# Parse fields from FORMAT section of the config file
"""
:param configParser:
:param configTable:
"""
# Parse fields from INFO section of the config file
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(configParser, "INFO")
for name, ID in table.items():
configTable.addInfoFieldName(name, ID)
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(configParser, "FORMAT")
for name, ID in table.items():
configTable.addFormatFieldName(name, ID)
table = ConfigUtils.buildReverseAlternativeDictionaryFromConfig(configParser, "OTHER")
for name, ID in table.items():
configTable.addOtherFieldName(name, ID)
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "INFO_DESCRIPTION")
for name, description in table.items():
configTable.addInfoFieldNameDescription(name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "FORMAT_DESCRIPTION")
for name, description in table.items():
configTable.addFormatFieldNameDescription(name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "FILTER_DESCRIPTION")
for name, description in table.items():
configTable.addFilterFieldNameDescription(name, string.join(description, ","))
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "SPLIT_TAGS")
for fieldType, names in table.items():
configTable.addFieldNamesToSplitSet(fieldType, names)
table = ConfigUtils.buildAlternateKeyDictionaryFromConfig(configParser, "NOT_SPLIT_TAGS")
for fieldType, names in table.items():
configTable.addFieldNamesToNotSplitSet(fieldType, names)
def __init__(self, mut, configFile="sample_name_selection.config", section="SAMPLE_NAME"):
config = ConfigUtils.createConfigParser(configFile)
self.logger = logging.getLogger(__name__)
aliases = ConfigUtils.buildAlternateKeyDictionaryFromConfig(config, section)
self.configFile=configFile
sampleAnnotation = self._getAnnotationFromAliases(mut, aliases["sample_name"])
tumorAnnotation = self._getAnnotationFromAliases(mut, aliases["sample_tumor_name"])
normalAnnotation = self._getAnnotationFromAliases(mut, aliases["sample_normal_name"])
source_column = self._getSourceColumn(sampleAnnotation,tumorAnnotation,normalAnnotation)
self._logSampleNameColumnDescription(source_column, sampleAnnotation, tumorAnnotation, normalAnnotation)
self.sampleNameGrabber = self._getSampleNameGrabber(source_column, sampleAnnotation, tumorAnnotation, normalAnnotation)
self.outputAnnotationName = self._deriveOutputAnnotationName(sampleAnnotation)
self.annotationSource = self._deriveAnnotationSource(source_column)
def __init__(self,
filename,
configFile='maflite_input.config',
genomeBuild="hg19",
other_options=None):
"""
Constructor
Currently, this InputCreator does not support any other options. The parameter is ignored.
"""
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self._tsvReader = GenericTsvReader(filename)
# Key is the required columns and the values are a list of valid alternative headers.
# Key is column name to an alternative.
self._alternativeDict = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
self.config)
self._reverseAlternativeDict = ConfigUtils.buildReverseAlternativeDictionary(
self._alternativeDict)
missingRequiredHeaders = []
specifiedFields = self._tsvReader.getFieldNames()
required_columns = sorted(
self.config.get("general", "required_headers").split(","))
self._build = genomeBuild
for col in required_columns:
if col not in specifiedFields:
isAltFound = False
for alt in self._alternativeDict.get(col, []):
if alt in specifiedFields:
isAltFound = True
break
if not isAltFound:
# build is optional.
if col != "build":
missingRequiredHeaders.append(col)
missingRequiredHeaders.sort()
self.logger.info(
"Initializing a maflite file with the following header: " +
str(self._tsvReader.getFieldNames()))
if len(missingRequiredHeaders) > 0:
raise MafliteMissingRequiredHeaderException(
"Specified maflite file (" + filename +
") missing required headers: " +
",".join(missingRequiredHeaders))
def __init__(self, filename, mutation_data_factory=None, configFile='maflite_input.config', genomeBuild="hg19", other_options=None):
"""
Constructor
"""
super(MafliteInputMutationCreator, self).__init__(filename, mutation_data_factory, configFile, genomeBuild, other_options)
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self._tsvReader = GenericTsvReader(filename)
# Key is the required columns and the values are a list of valid alternative headers.
# Key is column name to an alternative.
self._alternativeDict = ConfigUtils.buildAlternateKeyDictionaryFromConfig(self.config)
self._reverseAlternativeDict = ConfigUtils.buildReverseAlternativeDictionary(self._alternativeDict)
missingRequiredHeaders = []
required_columns = sorted(self.config.get("general", "required_headers").split(","))
self._build = genomeBuild
self.logger.info("Initializing a maflite file with the following header: " + str(self._tsvReader.getFieldNames()))
# The specified fields are those that were given in the input.
self._specified_fields = self._tsvReader.getFieldNames()
for col in required_columns:
if col not in self._specified_fields:
isAltFound = False
for alt in self._alternativeDict.get(col, []):
if alt in self._specified_fields:
isAltFound = True
break
if not isAltFound:
# build is optional.
if col != "build":
missingRequiredHeaders.append(col)
missingRequiredHeaders.sort()
if len(missingRequiredHeaders) > 0:
raise MafliteMissingRequiredHeaderException("Specified maflite file (" + filename + ") missing required headers: " + ",".join(missingRequiredHeaders) )
def __init__(self, filename, configFile='maflite_input.config', genomeBuild="hg19", other_options=None):
"""
Constructor
Currently, this InputCreator does not support any other options. The parameter is ignored.
"""
self.logger = logging.getLogger(__name__)
self.config = ConfigUtils.createConfigParser(configFile)
self._tsvReader = GenericTsvReader(filename)
# Key is the required columns and the values are a list of valid alternative headers.
# Key is column name to an alternative.
self._alternativeDict = ConfigUtils.buildAlternateKeyDictionaryFromConfig(self.config)
self._reverseAlternativeDict = ConfigUtils.buildReverseAlternativeDictionary(self._alternativeDict)
missingRequiredHeaders = []
specifiedFields = self._tsvReader.getFieldNames()
required_columns = sorted(self.config.get("general", "required_headers").split(","))
self._build = genomeBuild
for col in required_columns:
if col not in specifiedFields:
isAltFound = False
for alt in self._alternativeDict.get(col, []):
if alt in specifiedFields:
isAltFound = True
break
if not isAltFound:
# build is optional.
if col != "build":
missingRequiredHeaders.append(col)
missingRequiredHeaders.sort()
self.logger.info("Initializing a maflite file with the following header: " + str(self._tsvReader.getFieldNames()))
if len(missingRequiredHeaders) > 0:
raise MafliteMissingRequiredHeaderException("Specified maflite file (" + filename + ") missing required headers: " + ",".join(missingRequiredHeaders) )
def renderMutations(self, segments, metadata=None, comments=None):
"""Render segments into a gene list as described in the docs for this class.
:param segments: iterable of MutationData
:param metadata:
:param comments:
"""
config_parser = ConfigUtils.createConfigParser(self._config_file)
logging.getLogger(__name__).info(
"Building alternative keys dictionary...")
self._alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(
config_parser)
if metadata is None:
metadata = OrderedDict()
if comments is None:
comments = []
fp = file(self._filename, 'w')
for c in comments:
fp.write("## " + c + "\n")
# TODO: Define constant for "genes", and other annotations
headers = config_parser.options("alternatives")
gene_to_segment_dict = dict()
annotations = None
i = 0
for i, seg in enumerate(segments):
if annotations is None:
annotations = seg.keys()
field_mapping = FieldMapCreator.create_field_map(
headers,
seg,
self._alternativeDictionary,
is_render_internal_fields=True,
prepend="")
gene_list = seg['genes'].split(",")
for g in gene_list:
if g == seg["start_gene"]:
gene_to_segment_dict[g + " " + seg["start_exon"]] = seg
elif g == seg["end_gene"]:
gene_to_segment_dict[g + " " + seg["end_exon"]] = seg
else:
gene_to_segment_dict[g] = seg
if i == 0:
logging.getLogger(__name__).info(
"No segments given. There will be no genes in the list.")
writer = csv.DictWriter(fp,
headers,
delimiter="\t",
lineterminator="\n",
extrasaction="ignore")
writer.writeheader()
logging.getLogger(__name__).info("Rendering gene list...")
all_genes_seen = sorted(gene_to_segment_dict.keys())
num_genes = len(all_genes_seen)
for i, gene in enumerate(all_genes_seen):
# This next line may be slow...
line_dict = dict()
seg = gene_to_segment_dict[gene]
for h in headers:
annotation_field = field_mapping.get(h, h)
line_dict[h] = seg.get(annotation_field, "")
line_dict["gene"] = gene
writer.writerow(line_dict)
if i % 1000 == 0:
logging.getLogger(__name__).info("Rendered %d/%d genes ..." %
((i + 1), num_genes))
fp.close()
def renderMutations(self, segments, metadata=None, comments=None):
"""Render segments into a gene list as described in the docs for this class.
:param segments: iterable of MutationData
:param metadata:
:param comments:
"""
config_parser = ConfigUtils.createConfigParser(self._config_file)
logging.getLogger(__name__).info("Building alternative keys dictionary...")
self._alternativeDictionary = ConfigUtils.buildAlternateKeyDictionaryFromConfig(config_parser)
if metadata is None:
metadata = OrderedDict()
if comments is None:
comments = []
fp = file(self._filename, 'w')
for c in comments:
fp.write("## " + c + "\n")
# TODO: Define constant for "genes", and other annotations
headers = config_parser.options("alternatives")
gene_to_segment_dict = dict()
annotations = None
i = 0
for i, seg in enumerate(segments):
if annotations is None:
annotations = seg.keys()
field_mapping = MutUtils.createFieldsMapping(headers, annotations, self._alternativeDictionary, isRenderInternalFields=True, prepend="")
gene_list = seg['genes'].split(",")
for g in gene_list:
if g == seg["start_gene"]:
gene_to_segment_dict[g + " " + seg["start_exon"]] = seg
elif g == seg["end_gene"]:
gene_to_segment_dict[g + " " + seg["end_exon"]] = seg
else:
gene_to_segment_dict[g] = seg
if i == 0:
logging.getLogger(__name__).info("No segments given. There will be no genes in the list.")
writer = csv.DictWriter(fp, headers, delimiter="\t", lineterminator="\n", extrasaction="ignore")
writer.writeheader()
logging.getLogger(__name__).info("Rendering gene list...")
all_genes_seen = sorted(gene_to_segment_dict.keys())
num_genes = len(all_genes_seen)
for i,gene in enumerate(all_genes_seen):
# This next line may be slow...
line_dict = dict()
seg = gene_to_segment_dict[gene]
for h in headers:
annotation_field = field_mapping.get(h, h)
line_dict[h] = seg.get(annotation_field, "")
line_dict["gene"] = gene
writer.writerow(line_dict)
if i % 1000 == 0:
logging.getLogger(__name__).info("Rendered %d/%d genes ..." % ((i+1),num_genes))
fp.close()
