def write_contig_summary_b(contig_ace_dir, singleton_seq_dir, summary_file):
fd_summary = open(summary_file, 'w')
nr_contigs = 0
summary = ""
# get contig info
os.chdir(contig_ace_dir)
for ace_file in sorted(glob.glob("*.ace")):
ace_record = Ace.read(open(ace_file))
if (ace_record.ncontigs > 1):
contigs = ace_record.contigs
for contig in contigs:
# do not write singletons if found in ace file
if contig.nreads == 1:
continue
summary = summary + contig.name
for read in contig.reads:
summary = summary + "\t" + read.rd.name
summary = summary + "\n"
nr_contigs += 1
header = "# nr Contigs: " + str(nr_contigs) + "\n"
header = header + "# Column 1: Contig_id" + "\n"
header = header + "# Columns 2 to n: Member Sequences" + "\n"
summary = header + summary
fd_summary.write(summary)
fd_summary.close()
def __init__(self,ace_file):
self.ace_file = ace_file
self.records = Ace.read(open(ace_file, 'r'))
assert len(self.records.contigs)==1
self.contig = self.records.contigs[0]
self.consensus = self.contig.sequence
self.consensus_name = self.contig.name
self.number_sequences = len(self.contig.reads)
self.reference = ""
self.reference_name = ""
def report(args):
"""
%prog report [--options] ace_file > report
Prepare a report of read location, consensus location or quality segment per contig
"""
from jcvi.utils.table import tabulate
p = OptionParser(report.__doc__)
types = {"read": ["padded_start", "padded_end", "orient"],
"consensus": ["padded_consensus_start", "padded_consensus_end"],
"quality" : ["qual_clipping_start", "qual_clipping_end", "align_clipping_start", "align_clipping_end"]
}
valid_types = tuple(types.keys())
p.add_option("--type", default="read", choices=valid_types,
help="choose report type [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
acefile, = args
ace = Ace.read(must_open(acefile))
logging.debug('Loaded ace file {0}'.format(acefile))
for c in ace.contigs:
print c.name
table = dict()
if opts.type == "read":
ps, pe = [], []
ps = [read.padded_start for read in c.af]
for i in xrange(1, len(ps)):
pe.append(ps[i] - ps[i-1])
pe.append(c.nbases)
map = dict(zip(ps, pe))
for i, read in enumerate(c.af):
values = [str(x) for x in (read.padded_start, map[read.padded_start], read.coru)]
for i, label in enumerate(types[opts.type]):
table[(str(read.name), label)] = values[i]
elif opts.type == "consensus":
for read in c.bs:
values = [str(x) for x in (read.padded_start, read.padded_end)]
for i, label in enumerate(types[opts.type]):
table[(str(read.name), label)] = values[i]
elif opts.type == "quality":
for read in c.reads:
(r1, r2) = (read.rd, read.qa)
values = [str(x) for x in (r2.qual_clipping_start, r2.qual_clipping_end, r2.align_clipping_start, r2.align_clipping_end)]
for i, label in enumerate(types[opts.type]):
table[(str(r1.name), label)] = values[i]
print tabulate(table), "\n"
def report(args):
"""
%prog report [--options] ace_file > report
Prepare a report of read location, consensus location or quality segment per contig
"""
from jcvi.utils.table import tabulate
p = OptionParser(report.__doc__)
types = {"read": ["padded_start", "padded_end", "orient"],
"consensus": ["padded_consensus_start", "padded_consensus_end"],
"quality" : ["qual_clipping_start", "qual_clipping_end", "align_clipping_start", "align_clipping_end"]
}
valid_types = tuple(types.keys())
p.add_option("--type", default="read", choices=valid_types,
help="choose report type [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
acefile, = args
ace = Ace.read(must_open(acefile))
logging.debug('Loaded ace file {0}'.format(acefile))
for c in ace.contigs:
print c.name
table = dict()
if opts.type == "read":
ps, pe = [], []
ps = [read.padded_start for read in c.af]
for i in xrange(1, len(ps)):
pe.append(ps[i] - ps[i-1])
pe.append(c.nbases)
map = dict(zip(ps, pe))
for i, read in enumerate(c.af):
values = [str(x) for x in (read.padded_start, map[read.padded_start], read.coru)]
for i, label in enumerate(types[opts.type]):
table[(str(read.name), label)] = values[i]
elif opts.type == "consensus":
for read in c.bs:
values = [str(x) for x in (read.padded_start, read.padded_end)]
for i, label in enumerate(types[opts.type]):
table[(str(read.name), label)] = values[i]
elif opts.type == "quality":
for read in c.reads:
(r1, r2) = (read.rd, read.qa)
values = [str(x) for x in (r2.qual_clipping_start, r2.qual_clipping_end, r2.align_clipping_start, r2.align_clipping_end)]
for i, label in enumerate(types[opts.type]):
table[(str(r1.name), label)] = values[i]
print tabulate(table), "\n"
def main():
base_name = 'FX5ZTWB02D1DFX'
#contigs = Ace.parse(open('/Users/bcf/Tmp/tmp2.fa.cap.ace'))
c = Ace.read(open('/Users/bcf/Tmp/tmp2.fa.cap.ace'))
'''for c in contigs:
for r in c.reads:
if r.rd.name == base_name:
contig = c
break
else:
pass'''
write(c, '/Users/bcf/Tmp/tmp2_rewrite.fa.cap.ace')
pdb.set_trace()
def assemble(self):
"""Assemble sequences."""
if 0 < len(self.sequences) < self.seq_limit:
with open(os.devnull, 'w') as DEVNULL:
args = ['cap3', self.input_path, '-p', '75', '-s', '500', '-z', '2']
try:
# Use check call to ignore stdout of cap3
subprocess.check_call(args, stdout=DEVNULL, close_fds=True)
except subprocess.CalledProcessError as e:
logger.error("An error occured while attempting to assemble reads: "
"%s\n The problematic sequences are: %s", e, self.sequences)
return Ace.ACEFileRecord().contigs
return Ace.read(open(os.path.join(self.input_dir, 'multialign.fa.cap.ace'))).contigs
else:
# We return an empty record if there are too many sequences to assemble
return Ace.ACEFileRecord().contigs
def extract(args):
"""
%prog extract [--options] ace_file
Extract contigs from ace file and if necessary reformat header with
a pipe(|) separated list of constituent reads.
"""
p = OptionParser(extract.__doc__)
p.add_option("--format", default=False, action="store_true",
help="enable flag to reformat header into a symbol separated list of constituent reads "+ \
"[default: %default]")
p.add_option("--sep", default="|",
help="choose a separator used to list the reads in the FASTA header [default: '%default']")
p.add_option("--singlets", default=False, action="store_true",
help="ask the program to look in the singlets file (should be in the same folder) for " +\
"unused reads and put them in the resultant fasta file [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
acefile, = args
ace = Ace.read(must_open(acefile))
logging.debug('Loaded ace file {0}'.format(acefile))
fastafile = acefile.rsplit(".", 1)[0] + ".fasta"
fw = open(fastafile, "w")
for c in ace.contigs:
id = c.name
if opts.format:
id = opts.sep.join([read.name for read in c.af])
seqrec = SeqRecord(Seq(c.sequence), id=id, description="")
SeqIO.write([seqrec], fw, "fasta")
if opts.singlets:
singletsfile = acefile.rsplit(".", 1)[0] + ".singlets"
if os.path.getsize(singletsfile) > 0:
fp = SeqIO.parse(must_open(singletsfile), "fasta")
for rec in fp:
SeqIO.write(rec, fw, "fasta")
fw.close()
logging.debug('Wrote contigs to fasta file {0}'.format(fastafile))
def extract(args):
"""
%prog extract [--options] ace_file
Extract contigs from ace file and if necessary reformat header with
a pipe(|) separated list of constituent reads.
"""
p = OptionParser(extract.__doc__)
p.add_option("--format", default=False, action="store_true",
help="enable flag to reformat header into a symbol separated list of constituent reads "+ \
"[default: %default]")
p.add_option("--sep", default="|",
help="choose a separator used to list the reads in the FASTA header [default: '%default']")
p.add_option("--singlets", default=False, action="store_true",
help="ask the program to look in the singlets file (should be in the same folder) for " +\
"unused reads and put them in the resultant fasta file [default: %default]")
opts, args = p.parse_args(args)
if len(args) != 1:
sys.exit(not p.print_help())
acefile, = args
ace = Ace.read(must_open(acefile))
logging.debug('Loaded ace file {0}'.format(acefile))
fastafile = acefile.rsplit(".", 1)[0] + ".fasta"
fw = open(fastafile, "w")
for c in ace.contigs:
id = c.name
if opts.format:
id = opts.sep.join([read.name for read in c.af])
seqrec = SeqRecord(Seq(c.sequence), id=id, description="")
SeqIO.write([seqrec], fw, "fasta")
if opts.singlets:
singletsfile = acefile.rsplit(".", 1)[0] + ".singlets"
if os.path.getsize(singletsfile) > 0:
fp = SeqIO.parse(must_open(singletsfile), "fasta")
for rec in fp:
SeqIO.write(rec, fw, "fasta")
fw.close()
logging.debug('Wrote contigs to fasta file {0}'.format(fastafile))
def parse_singletons_fasta_in_ace(contig_ace_dir, singleton_seq_dir):
# get contig info
os.chdir(contig_ace_dir)
for ace_file in sorted(glob.glob("*.ace")):
ace_record = Ace.read(open(ace_file))
contigs = ace_record.contigs
for contig in contigs:
if contig.nreads == 1:
singleton_name = contig.reads[0].rd.name
singleton_seq = Seq(contig.reads[0].rd.sequence)
singleton_record = SeqRecord(seq=singleton_seq,
id="",
name="",
description=singleton_name)
singleton_file = singleton_seq_dir + "/" + singleton_name + ".fsa"
singleton_fd = open(singleton_file, "w")
SeqIO.write([singleton_record], singleton_fd, "fasta")
singleton_fd.close()
os.system("sed -i \"s/> />/g\" " + singleton_file)
from Bio.Sequencing import Ace
fn = '../../samples/contig1.ace'
acefilerecord = Ace.read(open(fn))
# For each contig:
for ctg in acefilerecord.contigs:
print('==========================================')
print('Contig name: %s'%ctg.name)
print('Bases: %s'%ctg.nbases)
print('Reads: %s'%ctg.nreads)
print('Segments: %s'%ctg.nsegments)
print('Sequence: %s'%ctg.sequence)
print('Quality: %s'%ctg.quality)
# For each read in contig:
for read in ctg.reads:
print('Read name: %s'%read.rd.name)
print('Align start: %s'%read.qa.align_clipping_start)
print('Align end: %s'%read.qa.align_clipping_end)
print('Qual start: %s'%read.qa.qual_clipping_start)
print('Qual end: %s'%read.qa.qual_clipping_end)
print('Read sequence: %s'%read.rd.sequence)
print('==========================================')
from Bio.Sequencing import Ace
fn = '../../samples/contig1.ace'
acefilerecord = Ace.read(open(fn))
# For each contig:
for ctg in acefilerecord.contigs:
print('==========================================')
print('Contig name: %s' % ctg.name)
print('Bases: %s' % ctg.nbases)
print('Reads: %s' % ctg.nreads)
print('Segments: %s' % ctg.nsegments)
print('Sequence: %s' % ctg.sequence)
print('Quality: %s' % ctg.quality)
# For each read in contig:
for read in ctg.reads:
print('Read name: %s' % read.rd.name)
print('Align start: %s' % read.qa.align_clipping_start)
print('Align end: %s' % read.qa.align_clipping_end)
print('Qual start: %s' % read.qa.qual_clipping_start)
print('Qual end: %s' % read.qa.qual_clipping_end)
print('Read sequence: %s' % read.rd.sequence)
print('==========================================')
