def _extract_exons( record, exon_fofn, output_type, directory ):
"""
Extract Fasta Records of each Exon from a Fasta Record
"""
log.info('Extracting exons from "%s"' % record.name)
temp_fasta = _write_temp_fasta( record )
output_file = os.path.join( directory, 'all_exons.%s' % output_type )
output_handle = _open_output_handle( output_file, output_type )
# Iterate over the individual Exon Fasta files looking for alignments
exon_count = 0
for exon_fasta in read_list_file( exon_fofn ):
exon_num = exon_fasta[-7]
start, end = _find_exon_position( temp_fasta, exon_fasta, directory )
if start is None or end is None:
continue
exon_count += 1
exon_record = _extract_exon_record( record, exon_num, start, end )
output_handle.writeRecord( exon_record )
os.unlink( temp_fasta )
output_handle.close()
if exon_count:
log.info("Extracted %s exons from %s" % (exon_count, record.name))
else:
log.warn("No valid exons found for %s!" % record.name)
return None
check_output_file( output_file )
return output_file
def _extract_exons(record, exon_fofn, output_type, directory):
"""
Extract Fasta Records of each Exon from a Fasta Record
"""
log.info('Extracting exons from "%s"' % record.name)
temp_fasta = _write_temp_fasta(record)
output_file = os.path.join(directory, 'all_exons.%s' % output_type)
output_handle = _open_output_handle(output_file, output_type)
# Iterate over the individual Exon Fasta files looking for alignments
exon_count = 0
for exon_fasta in read_list_file(exon_fofn):
exon_num = exon_fasta[-7]
start, end = _find_exon_position(temp_fasta, exon_fasta, directory)
if start is None or end is None:
continue
exon_count += 1
exon_record = _extract_exon_record(record, exon_num, start, end)
output_handle.writeRecord(exon_record)
os.unlink(temp_fasta)
output_handle.close()
if exon_count:
log.info("Extracted %s exons from %s" % (exon_count, record.name))
else:
log.warn("No valid exons found for %s!" % record.name)
return None
check_output_file(output_file)
return output_file
def _parse_input(input_data):
"""
Parse the list of subread files from the input if needed
"""
if isinstance(input_data, str):
return read_list_file(input_data)
elif isinstance(input_data, list):
return input_data
else:
msg = 'Input must be FOFN or List'
log.error(msg)
raise TypeError(msg)
def _parse_input(input_data):
"""
Parse the list of subread files from the input if needed
"""
if isinstance(input_data, str):
return read_list_file( input_data )
elif isinstance(input_data, list):
return input_data
else:
msg = 'Input must be FOFN or List'
log.error( msg )
raise TypeError( msg )
def separate_amplicons( subread_input, reference_fofn, locus, output=None ):
"""
Public interfact for _separate_subreads
"""
# Convert input to list if needed
if isinstance(subread_input, str):
file_list = read_list_file( subread_input )
if output is None:
output = subread_input
elif isinstance(subread_input, list):
file_list = subread_input
if output is None:
msg = 'Output file must be specified with file-list input!'
log.error( msg )
raise ValueError( msg )
# If the inputs are valid, check that the files haven't already been split
if _split_exists( file_list, locus ):
log.info("Separating subreads by amplicon for Locus %s" % locus)
return
# Otherwise, separate the sequences and write the results
log.info("Separating subreads by amplicon for Locus %s" % locus)
reference_fasta = _parse_reference_fofn( reference_fofn, locus )
new_file_list = _separate_amplicons( file_list, reference_fasta, locus)
write_list_file( new_file_list, output )
def separate_amplicons(subread_input, reference_fofn, locus, output=None):
"""
Public interfact for _separate_subreads
"""
# Convert input to list if needed
if isinstance(subread_input, str):
file_list = read_list_file(subread_input)
if output is None:
output = subread_input
elif isinstance(subread_input, list):
file_list = subread_input
if output is None:
msg = 'Output file must be specified with file-list input!'
log.error(msg)
raise ValueError(msg)
# If the inputs are valid, check that the files haven't already been split
if _split_exists(file_list, locus):
log.info("Separating subreads by amplicon for Locus %s" % locus)
return
# Otherwise, separate the sequences and write the results
log.info("Separating subreads by amplicon for Locus %s" % locus)
reference_fasta = _parse_reference_fofn(reference_fofn, locus)
new_file_list = _separate_amplicons(file_list, reference_fasta, locus)
write_list_file(new_file_list, output)
