def main():
input_filename = sys.argv[1]
input_type = sys.argv[2]
output_filename = sys.argv[3]
output_type = sys.argv[4]
force_quality_encoding = sys.argv[5]
summarize_input = sys.argv[6] == 'summarize_input'
if force_quality_encoding == 'None':
force_quality_encoding = None
aggregator = fastqAggregator()
out = fastqWriter( open( output_filename, 'wb' ), format = output_type, force_quality_encoding = force_quality_encoding )
read_count = None
if summarize_input:
reader = fastqVerboseErrorReader
else:
reader = fastqReader
for read_count, fastq_read in enumerate( reader( open( input_filename ), format = input_type, apply_galaxy_conventions = True ) ):
if summarize_input:
aggregator.consume_read( fastq_read )
out.write( fastq_read )
out.close()
if read_count is not None:
print "Groomed %i %s reads into %s reads." % ( read_count + 1, input_type, output_type )
if input_type != output_type and 'solexa' in [ input_type, output_type ]:
print "Converted between Solexa and PHRED scores."
if summarize_input:
print "Based upon quality and sequence, the input data is valid for: %s" % ( ", ".join( aggregator.get_valid_formats() ) or "None" )
ascii_range = aggregator.get_ascii_range()
decimal_range = aggregator.get_decimal_range()
print "Input ASCII range: %s(%i) - %s(%i)" % ( repr( ascii_range[0] ), ord( ascii_range[0] ), repr( ascii_range[1] ), ord( ascii_range[1] ) ) #print using repr, since \x00 (null) causes info truncation in galaxy when printed
print "Input decimal range: %i - %i" % ( decimal_range[0], decimal_range[1] )
else:
print "No valid FASTQ reads were provided."
def main():
input_filename = sys.argv[1]
output_filename = sys.argv[2]
input_type = sys.argv[3] or 'sanger'
aggregator = fastqAggregator()
num_reads = None
fastq_read = None
for num_reads, fastq_read in enumerate(
fastqReader(open(input_filename), format=input_type)):
aggregator.consume_read(fastq_read)
out = open(output_filename, 'wb')
valid_nucleotides = VALID_NUCLEOTIDES
if fastq_read:
if fastq_read.sequence_space == 'base':
out.write(
'#column\tcount\tmin\tmax\tsum\tmean\tQ1\tmed\tQ3\tIQR\tlW\trW\toutliers\tA_Count\tC_Count\tG_Count\tT_Count\tN_Count\tother_bases\tother_base_count\n'
)
else:
out.write(
'#column\tcount\tmin\tmax\tsum\tmean\tQ1\tmed\tQ3\tIQR\tlW\trW\toutliers\t0_Count\t1_Count\t2_Count\t3_Count\t4_Count\t5_Count\t6_Count\t._Count\tother_bases\tother_base_count\n'
)
valid_nucleotides = VALID_COLOR_SPACE
for i in range(aggregator.get_max_read_length()):
column_stats = aggregator.get_summary_statistics_for_column(i)
out.write('%i\t' % (i + 1))
out.write('%s\t' * len(SUMMARY_STAT_ORDER) %
tuple([column_stats[key] for key in SUMMARY_STAT_ORDER]))
out.write('%s\t' % ','.join(map(str, column_stats['outliers'])))
base_counts = aggregator.get_base_counts_for_column(i)
for nuc in valid_nucleotides:
out.write("%s\t" % base_counts.get(nuc, 0))
extra_nucs = sorted([
nuc for nuc in base_counts.keys() if nuc not in valid_nucleotides
])
out.write("%s\t%s\n" % (','.join(extra_nucs), ','.join(
str(base_counts[nuc]) for nuc in extra_nucs)))
out.close()
if num_reads is None:
print "No valid fastq reads could be processed."
else:
print "%i fastq reads were processed." % (num_reads + 1)
print "Based upon quality values and sequence characters, the input data is valid for: %s" % (
", ".join(aggregator.get_valid_formats()) or "None")
ascii_range = aggregator.get_ascii_range()
decimal_range = aggregator.get_decimal_range()
print "Input ASCII range: %s(%i) - %s(%i)" % (
repr(ascii_range[0]), ord(ascii_range[0]), repr(
ascii_range[1]), ord(ascii_range[1])
) #print using repr, since \x00 (null) causes info truncation in galaxy when printed
print "Input decimal range: %i - %i" % (decimal_range[0],
decimal_range[1])
def main():
input_filename = sys.argv[1]
input_type = sys.argv[2]
output_filename = sys.argv[3]
output_type = sys.argv[4]
force_quality_encoding = sys.argv[5]
summarize_input = sys.argv[6] == 'summarize_input'
if force_quality_encoding == 'None':
force_quality_encoding = None
aggregator = fastqAggregator()
out = fastqWriter(path=output_filename,
format=output_type,
force_quality_encoding=force_quality_encoding)
read_count = None
if summarize_input:
reader = fastqVerboseErrorReader
else:
reader = fastqReader
for read_count, fastq_read in enumerate(
reader(path=input_filename,
format=input_type,
apply_galaxy_conventions=True)):
if summarize_input:
aggregator.consume_read(fastq_read)
out.write(fastq_read)
out.close()
if read_count is not None:
print("Groomed %i %s reads into %s reads." %
(read_count + 1, input_type, output_type))
if input_type != output_type and 'solexa' in [input_type, output_type]:
print("Converted between Solexa and PHRED scores.")
if summarize_input:
print(
"Based upon quality and sequence, the input data is valid for: %s"
% (", ".join(aggregator.get_valid_formats()) or "None"))
ascii_range = aggregator.get_ascii_range()
decimal_range = aggregator.get_decimal_range()
print(
"Input ASCII range: %s(%i) - %s(%i)" %
(repr(ascii_range[0]), ord(ascii_range[0]), repr(
ascii_range[1]), ord(ascii_range[1]))
) # print using repr, since \x00 (null) causes info truncation in galaxy when printed
print("Input decimal range: %i - %i" %
(decimal_range[0], decimal_range[1]))
else:
print("No valid FASTQ reads were provided.")
def partition(input_filename, temp_output_filename, fileCount,
quality_encoding, verbose):
# print 'Starting Thread: ' + str(fileCount)
input_type = ARGV[1]
output_type = ARGV[3]
force_quality_encoding = quality_encoding
summarize_input = verbose
if force_quality_encoding == 'None':
force_quality_encoding = None
aggregator = fastqAggregator()
temp_process_file = fastqWriter(
open(temp_output_filename, 'wb'),
format=output_type,
force_quality_encoding=force_quality_encoding)
read_count = None
if summarize_input:
reader = fastqVerboseErrorReader
else:
reader = fastqReader
for read_count, fastq_read in enumerate(
reader(open(input_filename, 'rb'),
format=input_type,
apply_galaxy_conventions=True)):
if summarize_input:
aggregator.consume_read(fastq_read)
temp_process_file.write(fastq_read)
# print "Just wrote (%d): " % read_count + str(fastq_read)
temp_process_file.close()
if read_count is not None:
if input_type != output_type and 'solexa' in [input_type, output_type]:
print "Converted between Solexa and PHRED scores."
if summarize_input:
with open(temp_output_filename + "_summary",
'w') as summaryLogFile:
pickle.dump(aggregator, summaryLogFile)
else:
print "No valid FASTQ reads were provided."
def main():
input_filename = sys.argv[1]
output_filename = sys.argv[2]
input_type = sys.argv[3] or 'sanger'
aggregator = fastqAggregator()
num_reads = None
fastq_read = None
for num_reads, fastq_read in enumerate(fastqReader(path=input_filename, format=input_type)):
aggregator.consume_read(fastq_read)
out = open(output_filename, 'w')
valid_nucleotides = VALID_NUCLEOTIDES
if fastq_read:
if fastq_read.sequence_space == 'base':
out.write('#column\tcount\tmin\tmax\tsum\tmean\tQ1\tmed\tQ3\tIQR\tlW\trW\toutliers\tA_Count\tC_Count\tG_Count\tT_Count\tN_Count\tother_bases\tother_base_count\n')
else:
out.write('#column\tcount\tmin\tmax\tsum\tmean\tQ1\tmed\tQ3\tIQR\tlW\trW\toutliers\t0_Count\t1_Count\t2_Count\t3_Count\t4_Count\t5_Count\t6_Count\t._Count\tother_bases\tother_base_count\n')
valid_nucleotides = VALID_COLOR_SPACE
for i in range(aggregator.get_max_read_length()):
column_stats = aggregator.get_summary_statistics_for_column(i)
out.write('%d\t' % (i + 1))
out.write("%d\t%d\t%d\t%d\t%f\t%f\t%f\t%f\t%f\t%d\t%d\t" % tuple(column_stats[key] for key in SUMMARY_STAT_ORDER))
out.write('%s\t' % ','.join(map(str, column_stats['outliers'])))
base_counts = aggregator.get_base_counts_for_column(i)
for nuc in valid_nucleotides:
out.write("%s\t" % base_counts.get(nuc, 0))
extra_nucs = sorted(nuc for nuc in base_counts.keys() if nuc not in valid_nucleotides)
out.write("%s\t%s\n" % (','.join(extra_nucs), ','.join(str(base_counts[nuc]) for nuc in extra_nucs)))
out.close()
if num_reads is None:
print("No valid fastq reads could be processed.")
else:
print("%i fastq reads were processed." % (num_reads + 1))
print("Based upon quality values and sequence characters, the input data is valid for: %s" % (", ".join(aggregator.get_valid_formats()) or "None"))
ascii_range = aggregator.get_ascii_range()
decimal_range = aggregator.get_decimal_range()
print("Input ASCII range: %s(%i) - %s(%i)" % (repr(ascii_range[0]), ord(ascii_range[0]), repr(ascii_range[1]), ord(ascii_range[1]))) # print(using repr, since \x00 (null) causes info truncation in galaxy when printed)
print("Input decimal range: %i - %i" % (decimal_range[0], decimal_range[1]))
def run(self):
aggregator = fastqAggregator()
reader_class = fastqReader
if self.summarize_input:
reader_class = fastqVerboseErrorReader
read_count = None
writer = fastqWriter(
path=self.output_filename,
format=self.output_type,
force_quality_encoding=self.force_quality_encoding)
reader = reader_class(fh=self.file_handle,
path=self.input_filename,
format=self.input_type,
apply_galaxy_conventions=True,
fix_id=self.fix_id)
with writer, reader:
for read_count, fastq_read in enumerate(reader):
if self.summarize_input:
aggregator.consume_read(fastq_read)
writer.write(fastq_read)
self._print_output(read_count, aggregator)
def main():
input_filename = sys.argv[1]
input_type = sys.argv[2]
output_filename = sys.argv[3]
output_type = sys.argv[4]
force_quality_encoding = sys.argv[5]
summarize_input = sys.argv[6] == 'summarize_input'
if force_quality_encoding == 'None':
force_quality_encoding = None
fix_id = False # fix inconsistent identifiers (SRA data dumps)
if len(sys.argv) > 7:
fix_id = sys.argv[7] == 'fix_id'
aggregator = fastqAggregator()
out = fastqWriter(path=output_filename,
format=output_type,
force_quality_encoding=force_quality_encoding)
read_count = None
if summarize_input:
reader_type = fastqVerboseErrorReader
else:
reader_type = fastqReader
reader = reader_type(path=input_filename,
format=input_type,
apply_galaxy_conventions=True,
fix_id=fix_id)
for read_count, fastq_read in enumerate(reader):
if summarize_input:
aggregator.consume_read(fastq_read)
out.write(fastq_read)
out.close()
_print_output(read_count, input_type, output_type, summarize_input,
aggregator)
