yielded_score_dfm = list(self.__yield_score_dfm(snp_dfm))
# result = pd.concat(yielded_score_dfm, axis=1)
result = reduce(lambda left, right: pd.merge(left, right, on='name'),
yielded_score_dfm)
return result
def save_temp(self, _result):
_result.to_csv(self.temp_dest, sep='\t', index=False, header=True)
if __name__ == '__main__':
rc_util = RepliChipUtil()
snp_bed_fn = os.path.join(sys_tool.find_directory("fsu_repli_chip"),
'RSNP_50kb.bed')
snp_dfm = pd.read_table(snp_bed_fn,
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
rc_util.src_data_dir = sys_tool.find_directory("fsu_repli_chip")
rc_util.src_data_fn = dict(
FsuBg02esRep1="wgEncodeFsuRepliChipBg02esWaveSignalRep1.bed",
FsuBg02esRep2="wgEncodeFsuRepliChipBg02esWaveSignalRep2.bed",
FsuGm06990Rep1="wgEncodeFsuRepliChipGm06990WaveSignalRep1.bed",
FsuGm06990Rep2="wgEncodeFsuRepliChipGm06990WaveSignalRep2.bed",
FsuH1hescRep1="wgEncodeFsuRepliChipH1hescWaveSignalRep1.bed",
FsuH1hescRep2="wgEncodeFsuRepliChipH1hescWaveSignalRep2.bed",
FsuH1hescRep3="wgEncodeFsuRepliChipH1hescWaveSignalRep3.bed",
FsuH7esRep1="wgEncodeFsuRepliChipH7esWaveSignalRep1.bed",
'tfbsName': 'pwm'
})
result = snp_dfm.merge(result,
how='left',
on=['name', 'chrom'],
copy=True)
return result.loc[:, ['name', 'pwm']]
def save_temp(self, _result):
_result.to_csv(self.temp_dest, sep='\t', index=False, header=True)
if __name__ == '__main__':
rsnp_bed_fn = os.path.join(find_directory('dhs'), "RSNP_50kb.bed")
rsnp_dfm = pd.read_table(rsnp_bed_fn,
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
jaspar_tf_util = JasparTfbsUtil()
jaspar_tf_util.src_data_dir = find_directory('Jaspar_TFBS')
jaspar_tf_util.src_data_fn = 'jaspar_tfbs_ensembl_75_hg19.txt'
result = jaspar_tf_util.extract(rsnp_dfm)
result.to_csv("FOO_RSNP.tsv", sep='\t', header=True, index=False)
# if __name__ == '__main__':
# rsnp_bed_fn = "{}/RSNP_50kb.bed".format(find_directory('dhs'))
# rsnp_dfm = pd.read_table(rsnp_bed_fn, header=None,
index_names=False),
from_string=True)
yielded_dfms = list(self.__yield_fitcons_dfm(snp_bed_obj))
snp_fitcons = reduce(
lambda left, right: pd.merge(left, right, on='name'), yielded_dfms)
return snp_fitcons
def save_temp(self, _result):
_result.to_csv(self.temp_dest, sep='\t', index=False, header=True)
if __name__ == '__main__':
fitcons_util = FitconsUtil()
fitcons_util.src_data_dir = find_directory("fitcons")
fitcons_util.src_data_fn = dict(
fitConsGm="fc-gm-0.bed",
fitConsH1="fc-h1-0.bed",
fitConsHu="fc-hu-0.bed",
fitConsI6="fc-i6-0.bed",
)
rsnp_dfm = pd.read_table(os.path.join(find_directory('fitcons'),
"RSNP_50kb.bed"),
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
fitcons_util.temp_dest = 'foo_rsnp.txt'
fitcons_util.extract(_input=rsnp_dfm)
csnp_dfm = pd.read_table(os.path.join(find_directory('fitcons'),
# find minimum non-NAN 'P_Val' for each SNP
result = result.groupby('name').agg(min).reset_index()
# some SNPs has no non-NAN 'P_Val'; mark their aggregated 'P_VAL' NAN
result = snp_dfm.merge(result, how='left', on='name', copy=True)
result.loc[:, 'P_Val'] = result.loc[:, 'P_Val'].apply(
self.__transform_p_value)
result = result.rename(columns={'P_Val': 'eqtlPvalue'})
return result.loc[:, ['name', 'eqtlPvalue']]
def save_temp(self, _result):
_result.to_csv(self.temp_dest, sep='\t', header=True, index=False)
if __name__ == '__main__':
rsnp_dfm = pd.read_table(os.path.join(find_directory('CADD'),
"RSNP_50kb.bed"),
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
print(rsnp_dfm.shape)
eqtl_util = EqtlUtil()
eqtl_util.src_data_dir = find_directory('eqtl')
# eqtl_util.src_data_fn = ['Stomach.portal.eqtl', 'Heart_Left_Ventricle.portal.eqtl']
eqtl_util.temp_dest = 'foo_rsnp.txt'
result = eqtl_util.extract(rsnp_dfm)
print(result)
on=['name', 'chrom'],
copy=True)
return snp_dfm.loc[:, ["name", "masterDhsScore", "masterDhsCount"
]].fillna(0)
def save_temp(self, _result):
_result.to_csv(self.temp_dest,
sep='\t',
header=True,
index=False,
columns=["name", "masterDhsScore", "masterDhsCount"])
if __name__ == '__main__':
rsnp_bed_fn = os.path.join(find_directory('dhs'), "RSNP_50kb.bed")
rsnp_dfm = pd.read_table(rsnp_bed_fn,
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
csnp_bed_fn = os.path.join(find_directory('dhs'), "CSNP_50kb.bed")
csnp_dfm = pd.read_table(csnp_bed_fn,
header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
dhs_util = MasterDhsUtil()
dhs_util.db_config_key = 'local_hg19'
dhs_util.temp_dest = 'FOO_CSNP.tsv'
dhs_util.extract(csnp_dfm)
dhs_util.temp_dest = 'FOO_RSNP.tsv'
coord_util = CoordUtil()
coord_util.db_config_key = db_config_key
tf_util = TfUtil(reproduce_osu17=True)
tf_util.db_config_key = db_config_key
# jaspar_tfbs_util = JasparTfbsUtil()
# jaspar_tfbs_util.src_data_dir = sys_tool.find_directory('Jaspar_TFBS')
# jaspar_tfbs_util.src_data_fn = 'jaspar_tfbs_ensembl_75_hg19.txt'
mst_dhs_util = MasterDhsUtil()
mst_dhs_util.db_config_key = db_config_key
uni_dhs_util = UniformDhsUtil()
uni_dhs_util.src_data_dir = sys_tool.find_directory("dhs")
uni_dhs_util.src_data_fn = "UniformDnaseIHS"
phastcons_util = PhastconsUtil()
phastcons_util.db_config_key = db_config_key
tss_dist_util = TssDistUtil()
tss_dist_util.db_config_key = db_config_key
eqtl_util = EqtlUtil()
eqtl_util.src_data_dir = sys_tool.find_directory('eqtl')
gerp_util = GerpUtil()
gerp_util.src_data_dir = sys_tool.find_directory("gerp")
gerp_util.src_data_fn = "All_hg19_RS.bw"
'CTCF': 'CTCF_REG',
'E': 'ENH',
'PF': 'TSS_FLANK',
'R': 'REP',
'T': 'TRAN',
'TSS': 'TSS',
'WE': 'WEAK_ENH'
}
gwava_dfm = pd.DataFrame(results, index=names.keys()).T.rename(columns=names)
snp_dfm = snp_dfm.merge(gwava_dfm, how='left', left_on='name', right_index=True, copy=True)
return snp_dfm.fillna(0).drop(['chrom', 'chromStart', 'chromEnd'], axis=1)
def save_temp(self, _result):
_result.to_csv(self.temp_dest, sep='\t', index=False, header=True)
if __name__ == '__main__':
snp_bed_fn = os.path.join(sys_tool.find_directory("fsu_repli_chip"), 'RSNP_50kb.bed')
snp_dfm = pd.read_table(snp_bed_fn, header=None,
names=['chrom', 'chromStart', 'chromEnd', 'name'])
gwava_util = GwavaUtil()
gwava_util.src_data_dir = sys_tool.find_directory('GWAVA')
gwava_util.src_data_fn = 'segmentation.bed.gz'
gwava_util.temp_dest = 'GWAVA_RSNP.txt'
gwava_util.extract(_input=snp_dfm)