def testRangeAnnotation(self):
''' Test a simple case with range.
'''
datasource = GenericGeneProteinPositionDatasource("testdata/simple_uniprot_natvar/simple_uniprot_natvar.tsv", title="UniProt_NatVar", version="2011_09")
m = MutationData()
m.createAnnotation("gene", "TP53")
m.createAnnotation("protein_change", "p.SLEELEE370_376del") # This is not valid, but does the test.
m2 = datasource.annotate_mutation(m)
annotationName= "UniProt_NatVar_natural_variations"
self.assertTrue(sorted(m[annotationName].split("|")) == sorted("K -> Q (in a sporadic cancer; somatic mutation).|S -> T (in a sporadic cancer; somatic mutation).|S -> A (in a sporadic cancer; somatic mutation).".split("|")), "Incorrect annotation value seen: " + m[annotationName])
def testBasicAnnotation(self):
''' Test an extremely simple case.
'''
datasource = GenericGeneProteinPositionDatasource("testdata/simple_uniprot_natvar/simple_uniprot_natvar.tsv", title="UniProt_NatVar", version="2011_09")
m = MutationData()
m.createAnnotation("gene", "TP53")
m.createAnnotation("protein_change", "p.S376C")
m2 = datasource.annotate_mutation(m)
annotationName= "UniProt_NatVar_natural_variations"
self.assertTrue(sorted(m[annotationName].split("|")) == sorted("S -> T (in a sporadic cancer; somatic mutation).|S -> A (in a sporadic cancer; somatic mutation).".split("|")), "Incorrect annotation value seen: " + m[annotationName])
def testRangeAnnotation(self):
''' Test a simple case with range.
'''
datasource = GenericGeneProteinPositionDatasource("testdata/simple_uniprot_natvar/simple_uniprot_natvar.tsv", title="UniProt_NatVar", version="2011_09")
m = MutationDataFactory.default_create()
m.createAnnotation("gene", "TP53")
m.createAnnotation("protein_change", "p.SLEELEE370_376del") # This is not valid, but does the test.
m2 = datasource.annotate_mutation(m)
annotationName= "UniProt_NatVar_natural_variations"
self.assertTrue(sorted(m[annotationName].split("|")) == sorted("K -> Q (in a sporadic cancer; somatic mutation).|S -> T (in a sporadic cancer; somatic mutation).|S -> A (in a sporadic cancer; somatic mutation).".split("|")), "Incorrect annotation value seen: " + m[annotationName])
def testBasicAnnotation(self):
''' Test an extremely simple case.
'''
datasource = GenericGeneProteinPositionDatasource("testdata/simple_uniprot_natvar/simple_uniprot_natvar.tsv", title="UniProt_NatVar", version="2011_09")
m = MutationData()
m.createAnnotation("gene", "TP53")
m.createAnnotation("protein_change", "p.S376C")
m.createAnnotation("other_transcripts", "TP53_uc002gig.1_Intron|TP53_uc002gih.2_Intron|TP53_uc010cne.1_RNA|TP53_uc010cnf.1_3'UTR|TP53_uc010cng.1_3'UTR|TP53_uc002gii.1_Missense_Mutation_p.S244C|TP53_uc010cnh.1_3'UTR|TP53_uc010cni.1_3'UTR|TP53_uc002gij.2_Missense_Mutation_p.S376C")
m2 = datasource.annotate_mutation(m)
annotationName= "UniProt_NatVar_natural_variations"
self.assertTrue(sorted(m[annotationName].split("|")) == sorted("S -> T (in a sporadic cancer; somatic mutation).|S -> A (in a sporadic cancer; somatic mutation).".split("|")), "Incorrect annotation value seen: " + m[annotationName])
def testMissingAnnotations(self):
''' Tests that if the required annotations ("gene", "protein_change", and "other_transcripts") are missing, an exception is thrown.
'''
datasource = GenericGeneProteinPositionDatasource("testdata/simple_uniprot_natvar/simple_uniprot_natvar.tsv", title="SmallNatVar", version="test")
m = MutationData()
m.createAnnotation("gene", "TP53")
#m.createAnnotation("protein_change", "p.S376C")
self.assertRaisesRegexp(MissingAnnotationException, "protein_change", datasource.annotate_mutation, m)
def createDatasourceFromConfigParser(configParser, leafDir):
"""
configParser -- config parser instance from the config file in the leafdir. For information on config file format/conventions see (TODO)
leafDir -- contains the file and necessary files (post indexing and install steps) to instantiate a datasource.
"""
result = None
# Determine the type
dsType = configParser.get("general", "type")
# TODO: Replace these if statements with something a bit more robust, such as a proper dependency injection framework
filePrefix = leafDir + "/"
if dsType == "gaf":
gaf_fname = filePrefix + configParser.get('general', 'gaf_fname')
gaf_transcript_sequences_fname = filePrefix + configParser.get('general', 'gaf_transcript_seqs_fname')
result = Gaf(gaf_fname, gaf_transcript_sequences_fname, title=configParser.get("general", "title"), version=configParser.get("general", "version"), protocol=configParser.get("general", "protocol"))
elif dsType == "dbsnp":
result = dbSNP(filePrefix + configParser.get('general', 'src_file'), title=configParser.get('general', 'title'), version=configParser.get('general', 'version'))
elif dsType == "ensembl":
result = EnsemblTranscriptDatasource(filePrefix + configParser.get('general', 'src_file'),
title=configParser.get('general', 'title'),
version=configParser.get('general', 'version'),
tx_filter=configParser.get('general', 'transcript_filter'))
elif dsType == "cosmic":
result = Cosmic(src_file=filePrefix + configParser.get('general', 'src_file'), version=configParser.get('general', 'version'), gpp_tabix_file=filePrefix + configParser.get('general', 'gpp_src_file'))
elif dsType == 'ref':
if configParser.has_option('general', 'windowSizeRef'):
window_size = configParser.get('general', 'windowSizeRef')
else:
window_size = 10
result = ReferenceDatasource(filePrefix, title=configParser.get("general", "title"), version=configParser.get('general', 'version'), windowSizeRef=window_size)
elif dsType == 'gene_tsv':
result = GenericGeneDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), geneColumnName=configParser.get('general', 'gene_col'))
elif dsType == 'transcript_tsv':
result = GenericTranscriptDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), geneColumnName=configParser.get('general', 'transcript_col'))
elif dsType == 'vc_tsv':
result = GenericVariantClassificationDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), geneColumnName=configParser.get('general', 'vc_col'))
elif dsType == 'gp_tsv':
result = GenericGenomicPositionDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), gpColumnNames=configParser.get('general', 'genomic_position_cols'))
elif dsType == 'gm_tsv':
result = GenericGenomicMutationDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), gpColumnNames=configParser.get('general', 'genomic_position_cols'))
elif dsType == 'gm_tsv_reverse_complement':
result = GenericGenomicMutationDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'), gpColumnNames=configParser.get('general', 'genomic_position_cols'), use_complementary_strand_alleles_for_negative_strand_transcripts=True)
elif dsType == 'gpp_tsv':
result = GenericGeneProteinPositionDatasource(src_file=filePrefix + configParser.get('general', 'src_file'),title=configParser.get("general", "title"), version=configParser.get('general', 'version'), gpColumnNames=configParser.get('general', 'gene_protein_position_cols'))
elif dsType == "transcript_to_uniprot_aa":
result = TranscriptToUniProtProteinPositionTransformingDatasource(title=configParser.get("general", "title"),
version=configParser.get('general', 'version'),
src_file="file://" + filePrefix + configParser.get('general', 'src_file'), # three slashes for sqlite
inputPositionAnnotationName=configParser.get('general', 'inputPositionAnnotationName'),
outputPositionAnnotationName=configParser.get('general','outputPositionAnnotationName'))
elif dsType == "mock_exception":
result = MockExceptionThrowingDatasource(title=configParser.get("general", "title"), version=configParser.get('general', 'version'))
elif dsType == "indexed_vcf":
result = IndexedVcfDatasource(src_file=filePrefix + configParser.get('general', 'src_file'),
title=configParser.get("general", "title"),
version=configParser.get('general', 'version'),
match_mode=configParser.get('general', 'match_mode'))
elif dsType == "indexed_tsv":
columnNames = configParser.get("general", "column_names")
columnNames = columnNames.split(",")
annotationColumnNames = configParser.get("general", "annotation_column_names")
annotationColumnNames = annotationColumnNames.split(",")
indexColumnNames = configParser.get("general", "index_column_names")
indexColumnNames = indexColumnNames.split(",")
DatasourceFactory._log_missing_column_name_msg(columnNames, annotationColumnNames)
columnDataTypes = dict()
for columnName in annotationColumnNames:
if columnName.strip() == "":
continue
columnDataTypes[columnName] = configParser.get("data_types", columnName)
result = IndexedTsvDatasource(src_file=filePrefix + configParser.get("general", "src_file"),
title=configParser.get("general", "title"),
version=configParser.get("general", "version"),
colNames=columnNames,
annotationColNames=annotationColumnNames,
indexColNames=indexColumnNames,
match_mode=configParser.get("general", "match_mode"),
colDataTypes=columnDataTypes)
elif dsType == 'bigwig':
if not NGSLIB_INSTALLED:
raise RuntimeError("Bigwig datasource found in db-dir but ngslib library not installed.")
result = BigWigDatasource(src_file=filePrefix + configParser.get('general', 'src_file'), title=configParser.get("general", "title"), version=configParser.get('general', 'version'))
else:
raise RuntimeError('Unknown datasource type: %s' % dsType)
hashcode = DatasourceFactory._retrieve_hash_code(leafDir)
result.set_hashcode(hashcode)
return result
