def __init__(self,
outFile,
header_prefix='#',
col_chr=1,
col_start=2,
col_stop=2,
preset=None,
zerobased=False,
tabixPath=None):
assert outFile.endswith('.gz')
assert not os.access(outFile, os.F_OK) or os.access(outFile, os.W_OK)
self.outFile = outFile
root_fname = outFile.split('/')[-1].split('.')[0]
self.tmpFile = util_files.mkstempfname(prefix='tabix-%s-' % root_fname,
suffix='.txt')
self.tmp_f = open(self.tmpFile, 'wt')
self.params = {
'seq_col': col_chr,
'start_col': col_start,
'end_col': col_stop,
'preset': preset,
'zerobased': zerobased,
'meta_char': header_prefix,
'line_skip': 0
}
self.header = None
self.n_header = 0
self.n_rows = 0
self.tabixPath = tabixPath
self.last_chr_start = [None, None]
self.seen_chrs = set()
def vcf_bgzip_index(inVcf, outVcf, tabixPath=None, vcftoolsPath=None):
assert (inVcf.endswith('.vcf') or inVcf.endswith('.vcf.gz')) and outVcf.endswith('.vcf.gz')
''' Compress (bgzip) and index (tabix and/or vcftools) a VCF file.'''
if inVcf.endswith('.vcf'):
log.info("compressing output to %s" % outVcf)
cmdline = "%s/bgzip -c %s > %s" % (tabixPath, inVcf, outVcf)
assert not os.system(cmdline)
elif inVcf==outVcf:
log.info("leaving %s, already compressed" % inVcf)
else:
log.info("copying compressed vcf to %s" % outVcf)
shutil.copy(inVcf, outVcf)
log.info("indexing with tabix")
cmdline = "%s/tabix %s -f -p vcf" % (tabixPath, outVcf)
assert not os.system(cmdline)
if vcftoolsPath:
log.info("indexing with vcftools")
tmpFile = util_files.mkstempfname(prefix='vcftools-log-', suffix='.vcf')
cmdline = "%s/vcftools --gzvcf %s --out %s --force-index-write" % (vcftoolsPath, outVcf, tmpFile)
assert not os.system(cmdline)
os.unlink(tmpFile)
os.unlink(tmpFile+'.log')
return outVcf
def vcf_bgzip_index(inVcf, outVcf, tabixPath=None, vcftoolsPath=None):
assert (inVcf.endswith('.vcf')
or inVcf.endswith('.vcf.gz')) and outVcf.endswith('.vcf.gz')
''' Compress (bgzip) and index (tabix and/or vcftools) a VCF file.'''
if inVcf.endswith('.vcf'):
log.info("compressing output to %s" % outVcf)
cmdline = "%s/bgzip -c %s > %s" % (tabixPath, inVcf, outVcf)
assert not os.system(cmdline)
elif inVcf == outVcf:
log.info("leaving %s, already compressed" % inVcf)
else:
log.info("copying compressed vcf to %s" % outVcf)
shutil.copy(inVcf, outVcf)
log.info("indexing with tabix")
cmdline = "%s/tabix %s -f -p vcf" % (tabixPath, outVcf)
assert not os.system(cmdline)
if vcftoolsPath:
log.info("indexing with vcftools")
tmpFile = util_files.mkstempfname(prefix='vcftools-log-',
suffix='.vcf')
cmdline = "%s/vcftools --gzvcf %s --out %s --force-index-write" % (
vcftoolsPath, outVcf, tmpFile)
assert not os.system(cmdline)
os.unlink(tmpFile)
os.unlink(tmpFile + '.log')
return outVcf
def __init__(self,
inVcf,
enforce_unique_pos=True,
sample=None,
interval=None):
assert inVcf.endswith('.vcf.gz')
clens = get_chrlens(inVcf)
self.clens = dict(clens)
self.contigs = [c for c, l in clens]
self.sample_names = vcf_sample_names(inVcf)
root_fname = inVcf[:-7].split('/')[-1]
self.dbFile = util_files.mkstempfname(prefix='%s-' % root_fname,
suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table cons (
chr string not null,
pos integer not null,
allele string not null)""")
self.cur.execute("create %s index cons_idx on cons(chr,pos)" %
(enforce_unique_pos and "unique" or ""))
self.conn.commit()
self.cur.executemany(
"insert into cons (chr,pos,allele) values (?,?,?)",
[(c, p, alleles[genos[0][1]]) for c, p, alleles, genos in
vcf_haploid_iterator(inVcf,
sample_list=sample and [sample] or None,
interval=interval)])
self.conn.commit()
def __init__(self, dbFile=None):
if dbFile==None:
dbFile = util_files.mkstempfname(suffix='.db')
self.conn = sqlite3.connect(dbFile, isolation_level='DEFERRED')
assert self.conn.isolation_level
self.cur = self.conn.cursor()
self.cur.execute("PRAGMA foreign_keys=ON")
self.cur.execute("PRAGMA foreign_keys")
fk = self.cur.fetchone()
log.debug("SQLite version: %s" % sqlite3.sqlite_version)
log.debug("SQLite foreign key support: %s" % ((fk and fk[0]) and 'true' or 'false'))
self.start()
def __init__(self,
inVcf,
enforce_unique_pos=True,
sample_list=None,
drop_indels=False,
drop_monomorphic=False,
drop_multiallelic=False,
interval=None):
assert inVcf.endswith('.vcf.gz')
clens = get_chrlens(inVcf)
self.clens = dict(clens)
self.contigs = [c for c, l in clens]
self.sample_names = vcf_sample_names(inVcf)
root_fname = inVcf[:-7].split('/')[-1]
self.dbFile = util_files.mkstempfname(prefix='%s-' % root_fname,
suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table snp (
chr string not null,
pos integer not null,
alleles string not null)""")
self.cur.execute("""create table geno (
chr string not null,
pos integer not null,
sample string not null,
allele integer not null)""")
self.cur.execute("create %s index snp_idx on snp(chr,pos)" %
(enforce_unique_pos and "unique" or ""))
self.cur.execute("create %s index geno_idx on geno(chr,pos,sample)" %
(enforce_unique_pos and "unique" or ""))
self.conn.commit()
self.cur.executemany(
"insert into snp (chr,pos,alleles) values (?,?,?)",
[(c, p, ','.join(alleles)) for c, p, alleles, genos in
vcf_haploid_iterator(inVcf,
sample_list=sample_list,
drop_indels=drop_indels,
drop_monomorphic=drop_monomorphic,
drop_multiallelic=drop_multiallelic,
interval=interval)])
self.conn.commit()
self.cur.executemany(
"insert into geno (chr,pos,sample,allele) values (?,?,?,?)",
self._geno_iterator(
vcf_haploid_iterator(inVcf,
sample_list=sample_list,
drop_indels=drop_indels,
drop_monomorphic=drop_monomorphic,
drop_multiallelic=drop_multiallelic,
interval=interval)))
self.conn.commit()
def get_chroms(inVcf, tabixPath=None):
''' Get a list of unique chromosomes for this genome, in sort order.
(Use tabix to do it quickly)
'''
tmpFile = util_files.mkstempfname(prefix='chrnames-', suffix='.txt')
cmdline = "%s/tabix -l %s > %s" % (tabixPath, inVcf, tmpFile)
assert not os.system(cmdline)
chroms = []
with open(tmpFile, 'rt') as inf:
for line in inf:
chroms.append(line.rstrip('\r\n'))
os.unlink(tmpFile)
return chroms
def __init__(self, dbFile=None):
if dbFile == None:
dbFile = util_files.mkstempfname(suffix='.db')
self.conn = sqlite3.connect(dbFile, isolation_level='DEFERRED')
assert self.conn.isolation_level
self.cur = self.conn.cursor()
self.cur.execute("PRAGMA foreign_keys=ON")
self.cur.execute("PRAGMA foreign_keys")
fk = self.cur.fetchone()
log.debug("SQLite version: %s" % sqlite3.sqlite_version)
log.debug("SQLite foreign key support: %s" %
((fk and fk[0]) and 'true' or 'false'))
self.start()
def get_chroms(inVcf, tabixPath=None):
''' Get a list of unique chromosomes for this genome, in sort order.
(Use tabix to do it quickly)
'''
tmpFile = util_files.mkstempfname(prefix='chrnames-', suffix='.txt')
cmdline = "%s/tabix -l %s > %s" % (tabixPath, inVcf, tmpFile)
assert not os.system(cmdline)
chroms = []
with open(tmpFile, 'rt') as inf:
for line in inf:
chroms.append(line.rstrip('\r\n'))
os.unlink(tmpFile)
return chroms
def vcf_subset(inVcf, c, start_stop=None, outVcf=None, keepHeader=False, tabixPath=None):
''' Pull just a piece of a VCF file into a new VCF file (create a temp
file if outVcf is not specified).
'''
if outVcf==None:
outVcf = util_files.mkstempfname(prefix='vcf_subset-%s-'%c, suffix='.vcf')
assert inVcf.endswith('.vcf.gz') and outVcf.endswith('.vcf')
cmdline = "%s/tabix" % tabixPath
if keepHeader:
cmdline += ' -h'
cmdline += ' %s %s' % (inVcf, c)
if start_stop:
cmdline += ':%d-%d' % start_stop
cmdline += ' > %s' % outVcf
assert not os.system(cmdline)
return outVcf
def __init__(self, outFile, header_prefix='#',
col_chr=1, col_start=2, col_stop=2, preset=None, zerobased=False,
tabixPath=None):
assert outFile.endswith('.gz')
assert not os.access(outFile, os.F_OK) or os.access(outFile, os.W_OK)
self.outFile = outFile
root_fname = outFile.split('/')[-1].split('.')[0]
self.tmpFile = util_files.mkstempfname(prefix='tabix-%s-'%root_fname,suffix='.txt')
self.tmp_f = open(self.tmpFile, 'wt')
self.params = {'seq_col':col_chr, 'start_col':col_start, 'end_col':col_stop,
'preset':preset, 'zerobased':zerobased, 'meta_char':header_prefix,
'line_skip':0}
self.header = None
self.n_header = 0
self.n_rows = 0
self.tabixPath=tabixPath
self.last_chr_start = [None,None]
self.seen_chrs = set()
def __init__(self, inVcf,
enforce_unique_pos=True, sample_list=None,
drop_indels=False, drop_monomorphic=False, drop_multiallelic=False,
interval=None):
assert inVcf.endswith('.vcf.gz')
clens = get_chrlens(inVcf)
self.clens = dict(clens)
self.contigs = [c for c,l in clens]
self.sample_names = vcf_sample_names(inVcf)
root_fname = inVcf[:-7].split('/')[-1]
self.dbFile = util_files.mkstempfname(prefix='%s-'%root_fname,suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table snp (
chr string not null,
pos integer not null,
alleles string not null)""")
self.cur.execute("""create table geno (
chr string not null,
pos integer not null,
sample string not null,
allele integer not null)""")
self.cur.execute("create %s index snp_idx on snp(chr,pos)" % (
enforce_unique_pos and "unique" or ""))
self.cur.execute("create %s index geno_idx on geno(chr,pos,sample)" % (
enforce_unique_pos and "unique" or ""))
self.conn.commit()
self.cur.executemany("insert into snp (chr,pos,alleles) values (?,?,?)",
[(c,p,','.join(alleles))
for c,p,alleles,genos in vcf_haploid_iterator(inVcf,
sample_list=sample_list,
drop_indels=drop_indels, drop_monomorphic=drop_monomorphic,
drop_multiallelic=drop_multiallelic,
interval=interval)])
self.conn.commit()
self.cur.executemany("insert into geno (chr,pos,sample,allele) values (?,?,?,?)",
self._geno_iterator(vcf_haploid_iterator(inVcf, sample_list=sample_list,
drop_indels=drop_indels, drop_monomorphic=drop_monomorphic,
drop_multiallelic=drop_multiallelic,
interval=interval)))
self.conn.commit()
def __init__(self, snpEffVcf=None, snpIterator=None):
self.snpIterator = snpIterator
self.dbFile = util_files.mkstempfname(prefix='SnpAnnotater-', suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table annot (
chr not null,
pos integer not null,
allele_ref not null,
allele_alt not null,
effect not null,
impact not null,
gene_id,
gene_name,
protein_pos integer,
residue_ref,
residue_alt
)""")
self.cur.execute("create index idx_annot on annot(chr,pos)")
if snpEffVcf:
self.loadVcf(snpEffVcf)
def __init__(self, snpEffVcf=None, snpIterator=None):
self.snpIterator = snpIterator
self.dbFile = util_files.mkstempfname(prefix='SnpAnnotater-',
suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table annot (
chr not null,
pos integer not null,
allele_ref not null,
allele_alt not null,
effect not null,
impact not null,
gene_id,
gene_name,
protein_pos integer,
residue_ref,
residue_alt
)""")
self.cur.execute("create index idx_annot on annot(chr,pos)")
if snpEffVcf:
self.loadVcf(snpEffVcf)
def vcf_subset(inVcf,
c,
start_stop=None,
outVcf=None,
keepHeader=False,
tabixPath=None):
''' Pull just a piece of a VCF file into a new VCF file (create a temp
file if outVcf is not specified).
'''
if outVcf == None:
outVcf = util_files.mkstempfname(prefix='vcf_subset-%s-' % c,
suffix='.vcf')
assert inVcf.endswith('.vcf.gz') and outVcf.endswith('.vcf')
cmdline = "%s/tabix" % tabixPath
if keepHeader:
cmdline += ' -h'
cmdline += ' %s %s' % (inVcf, c)
if start_stop:
cmdline += ':%d-%d' % start_stop
cmdline += ' > %s' % outVcf
assert not os.system(cmdline)
return outVcf
def __init__(self, inVcf,
enforce_unique_pos=True, sample=None, interval=None):
assert inVcf.endswith('.vcf.gz')
clens = get_chrlens(inVcf)
self.clens = dict(clens)
self.contigs = [c for c,l in clens]
self.sample_names = vcf_sample_names(inVcf)
root_fname = inVcf[:-7].split('/')[-1]
self.dbFile = util_files.mkstempfname(prefix='%s-'%root_fname,suffix='.db')
self.conn = sqlite3.connect(self.dbFile, isolation_level='DEFERRED')
self.cur = self.conn.cursor()
self.cur.execute("""create table cons (
chr string not null,
pos integer not null,
allele string not null)""")
self.cur.execute("create %s index cons_idx on cons(chr,pos)" % (
enforce_unique_pos and "unique" or ""))
self.conn.commit()
self.cur.executemany("insert into cons (chr,pos,allele) values (?,?,?)",
[(c,p,alleles[genos[0][1]])
for c,p,alleles,genos in vcf_haploid_iterator(inVcf,
sample_list=sample and [sample] or None,
interval=interval)])
self.conn.commit()