def testParseLengthCTX(self):
'''Create leght if on same chrom,
otherwiser print CTX
'''
annotsv_df = self.annotsv_df.copy()
annotsv_df = annotsv_df.apply(
annotsv_summary.parse_sv_event1,
axis=1).apply(annotsv_summary.parse_sv_alt, axis=1).apply(
annotsv_summary.parse_gene_promoter,
axis=1).apply(annotsv_summary.parse_dgv, axis=1).apply(
annotsv_summary.parse_repeats,
axis=1).apply(annotsv_summary.parse_info,
axis=1).apply(annotsv_summary.parse_location,
axis=1)
o_event = 'gridss29_10153o'
input_o_data = self.annotsv_df.loc[(annotsv_df['ID'] == o_event)]
o_dict = annotsv_summary.collapse_event(input_o_data)
o_event1 = annotsv_df.loc[annotsv_df['ID'] == o_event,
'Event1'].iloc[0]
o_event2 = annotsv_df.loc[annotsv_df['ID'] == o_event,
'Event2'].iloc[0]
event1 = o_event1
event2 = o_event2
length = annotsv_summary.parse_length(event1, event2)
self.assertEqual(length, 'CTX')
def testCollapseEvent(self):
''' Combine various column entries into one string each'''
o_event = 'gridss137_4056o'
input_o_data = self.annotsv_df.loc[(self.annotsv_df['ID'] == o_event)]
o_dict = annotsv_summary.collapse_event(input_o_data)
expected_o_dict = {
'INFO':
'AS=1;ASQ=85.61;ASRP=3;ASSR=11;BA=0;BANRP=0;BANRPQ=0.00;BANSR=0;BANSRQ=0.00;BAQ=0.00;BASRP=0;BASSR=0;BEID=asm137-11351,asm137-6182;BEIDH=0,0;BEIDL=115,300;BQ=0.00;BSC=0;BSCQ=0.00;BUM=0;BUMQ=0.00;BVF=0;CAS=0;CASQ=0.00;CIPOS=-2,0;CIRPOS=-2,0;CQ=322.03;EVENT=gridss137_4056;HOMLEN=2;HOMSEQ=GA;IC=0;IHOMPOS=-2,0;IQ=0.00;PARID=gridss137_4056h;RAS=1;RASQ=140.29;REF=0;REFPAIR=0;RP=2;RPQ=21.04;SB=0.0;SC=1X1N1X176M;SR=4;SRQ=75.09;SVTYPE=BND;VF=9',
'Repeats_type_right': 'MLT2B1',
'Repeats_type_left': 'MLT2B1',
'NM': 'NM_001164665',
'DGV_GAIN_n_samples_tested': '0',
'DGV_LOSS_n_samples_with_SV': '0',
'promoters': '',
'1000g_max_AF': '',
'DGV_GAIN_n_samples_with_SV': '0',
'SV end': '138541914',
'ID': 'gridss137_4056o',
'FILTER': 'LOW_QUAL',
'QUAL': '322.03',
'Gene name': 'KIAA1549',
'SV start': '138541913',
'DGV_LOSS_n_samples_tested': '0',
'ALT': ']7:140490765]C',
'1000g_event': '',
'SV chrom': '7',
'location': 'intron16-intron6'
}
self.assertEqual(o_dict, expected_o_dict)
def testParseSingleton(self):
annotsv_df=self.annotsv_df.copy()
annotsv_df=annotsv_df.apply(annotsv_summary.parse_sv_event1, axis=1).apply(annotsv_summary.parse_sv_alt, axis=1).apply(annotsv_summary.parse_gene_promoter,axis=1).apply(annotsv_summary.parse_dgv, axis=1).apply(annotsv_summary.parse_repeats,axis=1).apply(annotsv_summary.parse_info, axis=1).apply(annotsv_summary.parse_location, axis=1)
o_event='gridss133_319o'
o_dict = annotsv_summary.collapse_event(annotsv_df.loc[(annotsv_df['ID']==o_event)])
output=annotsv_summary.parse_singleton(o_dict)
expected_output=['chr7:98550671', 'chr7:98550704', 'TRRAP', 'TRRAP', 'intron37', 'SINGLETON EVENT', 'NM_003496', '215.25', 'SINGLETON EVENT;LOW_QUAL', '', '', 'MER4C/(TG)n[left];MER4C/(TG)n[right]', 'SINGLETON EVENT', '0|0', '0|0']
self.assertEqual(sorted(output), sorted(expected_output))
def testCollapseEvent(self):
''' Combine various column entries into one string each'''
o_event='gridss137_4056o'
input_o_data=self.annotsv_df.loc[(self.annotsv_df['ID']==o_event)]
o_dict = annotsv_summary.collapse_event(input_o_data)
expected_o_dict={'INFO': 'AS=1;ASQ=85.61;ASRP=3;ASSR=11;BA=0;BANRP=0;BANRPQ=0.00;BANSR=0;BANSRQ=0.00;BAQ=0.00;BASRP=0;BASSR=0;BEID=asm137-11351,asm137-6182;BEIDH=0,0;BEIDL=115,300;BQ=0.00;BSC=0;BSCQ=0.00;BUM=0;BUMQ=0.00;BVF=0;CAS=0;CASQ=0.00;CIPOS=-2,0;CIRPOS=-2,0;CQ=322.03;EVENT=gridss137_4056;HOMLEN=2;HOMSEQ=GA;IC=0;IHOMPOS=-2,0;IQ=0.00;PARID=gridss137_4056h;RAS=1;RASQ=140.29;REF=0;REFPAIR=0;RP=2;RPQ=21.04;SB=0.0;SC=1X1N1X176M;SR=4;SRQ=75.09;SVTYPE=BND;VF=9', 'Repeats_type_right': 'MLT2B1', 'Repeats_type_left': 'MLT2B1', 'NM': 'NM_001164665', 'DGV_GAIN_n_samples_tested': '0', 'DGV_LOSS_n_samples_with_SV': '0', 'promoters': '', '1000g_max_AF': '', 'DGV_GAIN_n_samples_with_SV': '0', 'SV end': '138541914', 'ID': 'gridss137_4056o', 'FILTER': 'LOW_QUAL', 'QUAL': '322.03', 'Gene name': 'KIAA1549', 'SV start': '138541913', 'DGV_LOSS_n_samples_tested': '0', 'ALT': ']7:140490765]C', '1000g_event': '', 'SV chrom': '7', 'location': 'intron16-intron6'}
self.assertEqual(o_dict, expected_o_dict)
def testParseSingleton(self):
annotsv_df = self.annotsv_df.copy()
annotsv_df = annotsv_df.apply(
annotsv_summary.parse_sv_event1,
axis=1).apply(annotsv_summary.parse_sv_alt, axis=1).apply(
annotsv_summary.parse_gene_promoter,
axis=1).apply(annotsv_summary.parse_dgv, axis=1).apply(
annotsv_summary.parse_repeats,
axis=1).apply(annotsv_summary.parse_info,
axis=1).apply(annotsv_summary.parse_location,
axis=1)
o_event = 'gridss133_319o'
o_dict = annotsv_summary.collapse_event(
annotsv_df.loc[(annotsv_df['ID'] == o_event)])
output = annotsv_summary.parse_singleton(o_dict)
expected_output = [
'chr7:98550671', 'chr7:98550704', 'TRRAP', 'TRRAP', 'intron37',
'SINGLETON EVENT', 'NM_003496', '215.25',
'SINGLETON EVENT;LOW_QUAL', '', '',
'MER4C/(TG)n[left];MER4C/(TG)n[right]', 'SINGLETON EVENT', '0|0',
'0|0'
]
self.assertEqual(sorted(output), sorted(expected_output))