def extract_metadata(src, dest_csv, dest_bed):
"""
Extract metadata for cSNPs or rSNPs by querying UCSC database
:param src: the rsID list
:param dest_csv: the feature matrix
:param dest_bed: the name of bed file to be generated
:return: None
"""
rsid = __read_id(src)
with GenomeBrowserClient('local_hg19') as gb_client:
snps = gb_client.fetch_metadata(rsid)
__print_summary(snps)
snps = __remove_non_regular_chrom(snps, verbose=True)
snps = __remove_non_single_class(snps, verbose=True)
snps = __normalize_allele_strand(snps)
snps = __build_allele_freq_map(snps)
snps = __identify_major_minor_alleles(snps, verbose=True)
snps = __revise_alleles_with_equal_freqs(snps)
snps = __drop_redundant_col(snps)
snps = __normalize_chrom_coord(snps)
snps = CT.remove_dup_on_chrY(snps)
snps = snps.set_index("name")
__to_csv(snps, dest_csv)
snps = snps.reset_index()
__to_bed(snps, dest_bed)
def get_feat(self, _input):
rsid = _input
with GenomeBrowserClient(self.db_config_key) as gb_client:
coord_dfm = gb_client.fetch_coord(rsid)
coord_dfm = remove_dup_on_chrY(coord_dfm)
return coord_dfm
def get_feat(self, _input):
rsid = _input
with GenomeBrowserClient(self.db_config_key) as gb_client:
gb_df = gb_client.fetch_alleles(rsid)
gb_df = remove_dup_on_chrY(gb_df)
gb_df = AlleleUtil.transform_cols(gb_df)
return gb_df
def testRemoveDupOnChrY(self):
dfm = pandas.DataFrame({
'name': ["rs1", "rs2", "rs3", "rs3"],
'chrom': ["chr1", "chr2", "chr3", "chrY"],
"tssDistance": [1, 2, 3, 4]
})
dedup = remove_dup_on_chrY(dfm)
self.assertEqual(dedup.shape[0], 3)
self.assertFalse((dedup["chrom"] == "chrY").any())
self.assertEqual((dedup["name"] == "rs3").sum(), 1)
def __faulty_filter_on_allele(rsid, db_config_key):
maf_thld = 0.05
with GenomeBrowserClient(db_config_key) as gb_client:
snp_allele = gb_client.fetch_alleles(rsid)
snp_allele = ct.remove_dup_on_chrY(snp_allele)
snp_allele = AlleleUtil.transform_cols(snp_allele)
n_allele = snp_allele.loc[:, list("ATCG")].apply(lambda x: sum(x > 0),
axis=1)
# all mono-allelic are excluded
# mono = (n_allele == 1)
# all bi-allelic are included
# The problem of the previous filter: we didn't apply the "MAF >= 5%" rule to biallelic SNPs
bi = (n_allele == 2)
# include if min freq < 0.05 (then we can just discard this min freq);
# This is faulty because we may include an entry with freq = (0.96, 0.02, 0.02)
tri = (n_allele == 3)
# include if min 2 freqs < 0.05 (then we can just discard these 2 min freqs);
# This is faulty because we may include an entry with freq = (0.94, 0.02, 0.02, 0.02)
quad = (n_allele == 4)
bi_dfm = snp_allele.loc[bi, :]
tri_dfm = snp_allele.loc[tri, :]
min_one_under_thld = tri_dfm.loc[:, list("ATCG")].apply(
lambda x: min(x[x > 0]) < maf_thld, axis=1, reduce=True)
tri_dfm = tri_dfm.loc[min_one_under_thld, :]
quad_dfm = snp_allele.loc[quad, :]
min_two_under_thld = quad_dfm.loc[:, list("ATCG")].\
apply(lambda x: (x[x > 0].sort_values().iloc[[0, 1]] < maf_thld).all(), axis=1, reduce=True)
quad_dfm = quad_dfm.loc[min_two_under_thld, :]
# No need to query Biomart because it's known that what Biomart would return is empty
# And PCE exclusion is also done after `get_df_1kb`
return pd.concat([bi_dfm, tri_dfm, quad_dfm], axis=0)
def maf_filter(snp_dfm,
maf_threshold=0.05,
use_biomart=False,
verbose=False):
def __is_freq_valid(freq):
return (freq >= maf_threshold) & (freq > 0)
def __is_allele(freq):
return freq > 0
# We call a SNP not valid if:
# CASE 1: it has only one allele;
# CASE 2: it has two allele but maf < 0.05 (`self.maf_thld`);
# CASE 3: it has three or four allele but you cannot tell which is minor because there are at least 3
# alleles with freq >= 0.05. (If there is one allele with freq < 0.05, we simply discard it)
# SNPs of CASE 1 and CASE 3 will be queried in Biomart for a second chance if you set `self.use_biomart`
snp_valid = snp_dfm.loc[:, list('ATCG')].apply(
lambda x: sum(__is_freq_valid(x)) == 2, axis=1, reduce=True)
if use_biomart:
snp_biallelic = snp_dfm.loc[:, list('ATCG')].apply(
lambda x: sum(__is_allele(x)) == 2, axis=1, reduce=True)
with BiomartClient2() as bm_client:
bm_df = bm_client.query_snp(
rsid_list=snp_dfm.loc[~snp_valid & ~snp_biallelic,
'name'].tolist(),
verbose=verbose)
bm_df = remove_dup_on_chrY(bm_df)
bm_valid = bm_df.loc[:, list('ATCG')].apply(
lambda x: sum(__is_freq_valid(x)) == 2, axis=1)
df = pd.concat(
[snp_dfm.loc[snp_valid, :], bm_df.loc[bm_valid, :]],
axis=0)
else:
df = snp_dfm.loc[snp_valid, :]
return df
