def main():
input_filename = sys.argv[1]
output_filename = sys.argv[2]
input_type = sys.argv[3] or 'sanger' # input type should ordinarily be unnecessary
num_reads = None
fastq_read = None
out = fastaWriter(path=output_filename, format="fasta")
for num_reads, fastq_read in enumerate(fastqReader(path=input_filename, format=input_type)):
out.write(fastq_read)
out.close()
if num_reads is None:
print("No valid FASTQ reads could be processed.")
else:
print("%i FASTQ reads were converted to FASTA." % (num_reads + 1))
record.quality = record.quality[:cut]
clipped += 1
writer.write(record)
else:
short_clipped += 1
elif keep_negatives:
if len(record) >= min_len:
negs += 1
writer.write(record)
else:
short_negs += 1
elif seq_format.lower() == "fasta":
in_handle = open(in_file, "rU")
out_handle = open(out_file, "w")
reader = fastaReader(in_handle)
writer = fastaWriter(out_handle)
#Following code is identical to that for FASTQ but without editing qualities
if forward:
for record in reader:
seq = record.sequence.upper()
result = primer.search(seq)
if result:
#Forward primer, take everything after it
cut = result.end()
record.sequence = seq[cut:]
if len(record.sequence) >= min_len:
clipped += 1
writer.write(record)
else:
short_clipped += 1
elif keep_negatives:
manifest = ReadRocheXmlManifest(in_handle)
except ValueError:
manifest = None
out_handle = open(out_file, "wb")
writer = SffWriter(out_handle, xml=manifest)
in_handle.seek(0) #start again after getting manifest
count = writer.write_file(rename_seqrecords(SffIterator(in_handle), rename))
out_handle.close()
in_handle.close()
else:
#Use Galaxy for FASTA, QUAL or FASTQ
if seq_format.lower() in ["fasta", "csfasta"] \
or seq_format.lower().startswith("qual"):
from galaxy_utils.sequence.fasta import fastaReader, fastaWriter
reader = fastaReader(open(in_file, "rU"))
writer = fastaWriter(open(out_file, "w"))
marker = ">"
elif seq_format.lower().startswith("fastq"):
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter
reader = fastqReader(open(in_file, "rU"))
writer = fastqWriter(open(out_file, "w"))
marker = "@"
else:
sys.exit("Unsupported file type %r" % seq_format)
#Now do the renaming
count = 0
renamed = 0
for record in reader:
#The [1:] is because the fastaReader leaves the > on the identifier,
#likewise the fastqReader leaves the @ on the identifier
try:
record.quality = record.quality[:cut]
clipped += 1
writer.write(record)
else:
short_clipped += 1
elif keep_negatives:
if len(record) >= min_len:
negs += 1
writer.write(record)
else:
short_neg += 1
elif seq_format.lower()=="fasta":
in_handle = open(in_file, "rU")
out_handle = open(out_file, "w")
reader = fastaReader(in_handle)
writer = fastaWriter(out_handle)
#Following code is identical to that for FASTQ but without editing qualities
if forward:
for record in reader:
seq = record.sequence.upper()
result = primer.search(seq)
if result:
#Forward primer, take everything after it
cut = result.end()
record.sequence = seq[cut:]
if len(record.sequence) >= min_len:
clipped += 1
writer.write(record)
else:
short_clipped += 1
elif keep_negatives:
manifest = None
out_handle = open(out_file, "wb")
writer = SffWriter(out_handle, xml=manifest)
in_handle.seek(0) # start again after getting manifest
count = writer.write_file(rename_seqrecords(SffIterator(in_handle), rename))
out_handle.close()
in_handle.close()
else:
# Use Galaxy for FASTA, QUAL or FASTQ
if seq_format.lower() in ["fasta", "csfasta"] or seq_format.lower().startswith(
"qual"
):
from galaxy_utils.sequence.fasta import fastaReader, fastaWriter
reader = fastaReader(open(in_file, "rU"))
writer = fastaWriter(open(out_file, "w"))
marker = ">"
elif seq_format.lower().startswith("fastq"):
from galaxy_utils.sequence.fastq import fastqReader, fastqWriter
reader = fastqReader(open(in_file, "rU"))
writer = fastqWriter(open(out_file, "w"))
marker = "@"
else:
sys.exit("Unsupported file type %r" % seq_format)
# Now do the renaming
count = 0
renamed = 0
for record in reader:
# The [1:] is because the fastaReader leaves the > on the identifier,
# likewise the fastqReader leaves the @ on the identifier
print("Using %i IDs from %i columns of tabular file" %
(len(ids), len(columns)))
else:
# Single column, special case speed up
col = columns[0]
for line in handle:
if not line.startswith("#"):
ids.add(line.rstrip("\n").split("\t")[col])
print("Using %i IDs from tabular file" % (len(ids)))
handle.close()
# Write filtered FASTA file based on IDs from tabular file
reader = fastaReader(open(in_file, "rU"))
if out_positive_file != "-" and out_negative_file != "-":
print("Generating two FASTA files")
positive_writer = fastaWriter(open(out_positive_file, "w"))
negative_writer = fastaWriter(open(out_negative_file, "w"))
for record in reader:
# The [1:] is because the fastaReader leaves the > on the identifer.
if record.identifier and record.identifier.split()[0][1:] in ids:
positive_writer.write(record)
else:
negative_writer.write(record)
positive_writer.close()
negative_writer.close()
elif out_positive_file != "-":
print("Generating matching FASTA file")
positive_writer = fastaWriter(open(out_positive_file, "w"))
for record in reader:
# The [1:] is because the fastaReader leaves the > on the identifer.
if record.identifier and record.identifier.split()[0][1:] in ids:
