def main(argv):
options, args = parse_args(argv)
if not options:
return 1
print("Generating %i lane(s) of synthetic reads ...\nDISCLAIMER: For "
"demonstration of PALEOMIX usage only; not for serious usage!"
% (options.lanes_num,))
specimen = Specimen(options, args[0])
sample = Sample(options, specimen)
damage = Damage(options, sample)
library = Library(options, damage)
for (lnum, lane) in enumerate(library.lanes, start=1):
fragments = fragment(options.lanes_per_file, lane.sequences)
for (readsnum, reads) in enumerate(fragments, start=1):
templ = "%s%s_L%i_R%%s_%02i.fastq.gz" % (args[1], library.barcode,
lnum, readsnum)
print(" Writing %s" % (templ % "{Pair}",))
with gzip.open(templ % 1, "w") as out_1:
with gzip.open(templ % 2, "w") as out_2:
for (name, seq_1, seq_2) in reads:
out_1.write("@%s%s/1\n%s\n" % (library.barcode, name, seq_1))
out_1.write("+\n%s\n" % ("I" * len(seq_1),))
out_2.write("@%s%s/2\n%s\n" % (library.barcode, name, seq_2))
out_2.write("+\n%s\n" % ("H" * len(seq_2),))
def _run(self, _config, temp):
msa = read_msa(self._input_file)
for excluded_group in self._excluded:
msa.pop(excluded_group)
lines = []
lines.append(" %i %i" % (len(msa), len(msa.itervalues().next())))
for (name, seq) in sorted(msa.iteritems()):
lines.append("")
lines.append(name)
for line in fragment(60, seq.upper()):
lines.append(" ".join(fragment(3, line)))
with open(fileutils.reroot_path(temp, self._output_file), "w") as output:
output.write("\n".join(lines))
def main(argv):
options, args = parse_args(argv)
if not options:
return 1
print("Generating %i lane(s) of synthetic reads ...\nDISCLAIMER: For "
"demonstration of PALEOMIX usage only; not for serious usage!"
% (options.lanes_num,))
specimen = Specimen(options, args[0])
sample = Sample(options, specimen)
damage = Damage(options, sample)
library = Library(options, damage)
for (lnum, lane) in enumerate(library.lanes, start=1):
fragments = fragment(options.lanes_per_file, lane.sequences)
for (readsnum, reads) in enumerate(fragments, start=1):
templ = "%s%s_L%i_R%%s_%02i.fastq.gz" % (args[1], library.barcode,
lnum, readsnum)
print(" Writing %s" % (templ % "{Pair}",))
with gzip.open(templ % 1, "w") as out_1:
with gzip.open(templ % 2, "w") as out_2:
for (name, seq_1, seq_2) in reads:
out_1.write("@%s%s/1\n%s\n" % (library.barcode, name, seq_1))
out_1.write("+\n%s\n" % ("I" * len(seq_1),))
out_2.write("@%s%s/2\n%s\n" % (library.barcode, name, seq_2))
out_2.write("+\n%s\n" % ("H" * len(seq_2),))
def _run(self, _config, temp):
msa = read_msa(self._input_file)
for excluded_group in self._excluded:
msa.pop(excluded_group)
lines = []
lines.append(" %i %i" % (len(msa), len(msa.itervalues().next())))
for (name, seq) in sorted(msa.iteritems()):
lines.append("")
lines.append(name)
for line in fragment(60, seq.upper()):
lines.append(" ".join(fragment(3, line)))
with open(fileutils.reroot_path(temp, self._output_file),
"w") as output:
output.write("\n".join(lines))
def flush_fasta(sequence):
"""Takes a FASTA sequence as a string, fragments it into lines of exactly
_FASTA_COLUMNS chars (e.g. 60), and prints all complete lines. The final
incomplete line (if any) is returned.
"""
for seq_frag in utilities.fragment(_FASTA_COLUMNS, sequence):
if len(seq_frag) < _FASTA_COLUMNS:
return seq_frag
print(seq_frag)
return ""
def flush_fasta(sequence):
"""Takes a FASTA sequence as a string, fragments it into lines of exactly
_FASTA_COLUMNS chars (e.g. 60), and prints all complete lines. The final
incomplete line (if any) is returned.
"""
for seq_frag in utilities.fragment(_FASTA_COLUMNS, sequence):
if len(seq_frag) < _FASTA_COLUMNS:
return seq_frag
print(seq_frag)
return ""
def _run(self, _config, temp):
fastas = {}
for (name, filename) in self._infiles.iteritems():
current_fastas = {}
for ((name, _meta), sequence) in read_fasta(filename):
current_fastas[name] = sequence
fastas[name] = current_fastas
fastas = list(sorted(fastas.items()))
for (sequence_name, taxa_map) in sorted(self._sequences.iteritems()):
lines = []
for (taxon_name, sequences) in fastas:
fastaseq = "\n".join(fragment(60, sequences[sequence_name]))
current_name = taxa_map[taxon_name]
lines.append(">%s %s\n%s\n" % (taxon_name, current_name, fastaseq))
filename = os.path.join(temp, sequence_name + ".fasta")
with open(filename, "w") as fasta:
fasta.write("".join(lines))
def _run(self, _config, temp):
fastas = {}
for (name, filename) in self._infiles.iteritems():
current_fastas = {}
for ((name, _meta), sequence) in read_fasta(filename):
current_fastas[name] = sequence
fastas[name] = current_fastas
fastas = list(sorted(fastas.items()))
for (sequence_name, taxa_map) in sorted(self._sequences.iteritems()):
lines = []
for (taxon_name, sequences) in fastas:
fastaseq = "\n".join(fragment(60, sequences[sequence_name]))
current_name = taxa_map[taxon_name]
lines.append(">%s %s\n%s\n" %
(taxon_name, current_name, fastaseq))
filename = os.path.join(temp, sequence_name + ".fasta")
with open(filename, "w") as fasta:
fasta.write("".join(lines))
def test_fragment__multiple_fragments_partial():
assert_equal(list(utils.fragment(3, "abcdefgh")), ["abc", "def", "gh"])
assert_equal(
list(utils.fragment(3, list("abcdefgh"))),
[list("abc"), list("def"), list("gh")])
def test_fragment__single_fragment():
assert_equal(list(utils.fragment(3, "abc")), ["abc"])
assert_equal(list(utils.fragment(3, ["a", "b", "c"])), [["a", "b", "c"]])
def test_fragment__partial_fragment():
assert_equal(list(utils.fragment(3, "ab")), ["ab"])
assert_equal(list(utils.fragment(3, ["a", "b"])), [["a", "b"]])
def test_fragment__empty():
assert_equal(list(utils.fragment(5, "")), [])
assert_equal(list(utils.fragment(5, [])), [])
def _format_int(self, value):
return (",".join(fragment(3, str(value)[::-1])))[::-1]
def test_fragment__empty():
assert_equal(list(utils.fragment(5, "")), [])
assert_equal(list(utils.fragment(5, [])), [])
def test_fragment__partial_fragment():
assert_equal(list(utils.fragment(3, "ab")), ["ab"])
assert_equal(list(utils.fragment(3, ["a", "b"])), [["a", "b"]])
def test_fragment__single_fragment():
assert_equal(list(utils.fragment(3, "abc")), ["abc"])
assert_equal(list(utils.fragment(3, ["a", "b", "c"])), [["a", "b", "c"]])
def test_fragment__multiple_fragments_partial():
assert_equal(list(utils.fragment(3, "abcdefgh")), ["abc", "def", "gh"])
assert_equal(list(utils.fragment(3, list("abcdefgh"))), [list("abc"), list("def"), list("gh")])
def _format_int(self, value):
return (",".join(fragment(3, str(value)[::-1])))[::-1]
def __repr__(self):
"""Process a printable FASTA sequence, wrapping long sequences at 60 chars."""
name = self.name
if self.meta:
name = "%s %s" % (name, self.meta)
return ">%s\n%s\n" % (name, "\n".join(fragment(60, self.sequence)))
def test_fragment__iterable():
list(utils.fragment(3, xrange(6)))
def wrap_fasta(name, sequence):
"""Process a printable FASTA sequence, wrapping long sequences at 60 chars."""
return ">%s\n%s\n" % (name, "\n".join(fragment(60, sequence)))
def test_fragment__iterable():
list(utils.fragment(3, xrange(6)))
def test_fragment__set():
list(utils.fragment(3, set(range(6))))
def test_fragment__set():
list(utils.fragment(3, set(range(6))))
def wrap_fasta(name, sequence):
"""Process a printable FASTA sequence, wrapping long sequences at 60 chars."""
return ">%s\n%s\n" % (name, "\n".join(fragment(60, sequence)))