def separate_amplicons( input_data, reference_fofn, target_loci, output=None ):
"""
Public interface for _separate_subreads
"""
# Check and set the input and output, as needed
log.info("Separating amplicons for these loci[%s]" % ','.join(target_loci))
file_list = _parse_input( input_data )
output = output or _get_output_file( input_data )
references = parse_reference_dict( reference_fofn )
# Iterate over the input subread files, splitting as needed
new_files = []
for filepath in file_list:
locus = get_file_locus( filepath )
if locus in target_loci:
if is_amplicon_specific( filepath ):
log.info("Subreads for Locus %s already split, skipping..." % locus)
new_files.append( filepath )
else:
log.info("Subreads for Locus %s already split, skipping..." % locus)
reference_fasta = references[locus]
new_file_list = _separate_amplicons( file_list, reference_fasta, locus)
continue
# Otherwise, separate the sequences and write the results
log.info("Separating subreads by amplicon for Locus %s" % locus)
new_file_list = _separate_amplicons( file_list, reference_fasta, locus)
write_list_file( new_file_list, output )
def separate_amplicons(input_data, reference_fofn, target_loci, output=None):
"""
Public interface for _separate_subreads
"""
# Check and set the input and output, as needed
log.info("Separating amplicons for these loci[%s]" % ','.join(target_loci))
file_list = _parse_input(input_data)
output = output or _get_output_file(input_data)
references = parse_reference_dict(reference_fofn)
# Iterate over the input subread files, splitting as needed
new_files = []
for filepath in file_list:
locus = get_file_locus(filepath)
if locus in target_loci:
if is_amplicon_specific(filepath):
log.info("Subreads for Locus %s already split, skipping..." %
locus)
new_files.append(filepath)
else:
log.info("Subreads for Locus %s already split, skipping..." %
locus)
reference_fasta = references[locus]
new_file_list = _separate_amplicons(file_list, reference_fasta,
locus)
continue
# Otherwise, separate the sequences and write the results
log.info("Separating subreads by amplicon for Locus %s" % locus)
new_file_list = _separate_amplicons(file_list, reference_fasta, locus)
write_list_file(new_file_list, output)
def summarize_amp_analysis( input_dir, output_dir ):
create_directory( output_dir )
log.info('Combining AmpliconAnalysis output from "{0}" to "{1}"'.format(input_dir, output_dir))
results = list( find_amp_assem_results(input_dir) )
output_files = list( output_amp_assem_results(results, output_dir) )
result_output = os.path.join( output_dir, "AmpliconAssembly_Results.fofn" )
write_list_file( output_files, result_output )
return result_output
def summarize_amp_analysis(input_dir, output_dir):
create_directory(output_dir)
log.info('Combining AmpliconAnalysis output from "{0}" to "{1}"'.format(
input_dir, output_dir))
results = list(find_amp_assem_results(input_dir))
output_files = list(output_amp_assem_results(results, output_dir))
result_output = os.path.join(output_dir, "AmpliconAssembly_Results.fofn")
write_list_file(output_files, result_output)
return result_output
def combine_clusense_output(input_dir, output_dir):
create_directory( output_dir )
log.info('Combining clusense output from "{0}" in "{1}"'.format(input_dir, output_dir))
clusense_dirs = find_clusense_dirs( input_dir )
clusense_clusters = find_clusense_clusters( clusense_dirs )
cns_files, read_files = output_clusters( clusense_clusters, output_dir )
cns_output = os.path.join( output_dir, CNS_FOFN )
write_list_file( cns_files, cns_output )
read_output = os.path.join( output_dir, READ_FOFN )
write_list_file( read_files, read_output )
return cns_output, read_output
def combine_clusense_output(input_dir, output_dir):
create_directory(output_dir)
log.info('Combining clusense output from "{0}" in "{1}"'.format(
input_dir, output_dir))
clusense_dirs = find_clusense_dirs(input_dir)
clusense_clusters = find_clusense_clusters(clusense_dirs)
cns_files, read_files = output_clusters(clusense_clusters, output_dir)
cns_output = os.path.join(output_dir, CNS_FOFN)
write_list_file(cns_files, cns_output)
read_output = os.path.join(output_dir, READ_FOFN)
write_list_file(read_files, read_output)
return cns_output, read_output
def create_baxh5_fofn( input_file, output_file ):
log.info("Converting %s into a FOFN of BaxH5 files" % input_file)
if input_file.endswith('.fofn'):
baxh5_files = _parse_fofn( input_file )
elif input_file.endswith('.bas.h5'):
baxh5_files = _parse_bash5( input_file )
elif input_file.endswith('.bax.h5'):
baxh5_files = [input_file]
elif input_file.endswith('.fa') or input_file.endswith('.fasta'):
baxh5_files = []
else:
msg = 'Invalid input filetype "%s"' % input_file
log.info( msg )
raise TypeError( msg )
log.info("Writing a total of %s BaxH5 files to BaxH5 Fofn" % len(baxh5_files))
write_list_file( baxh5_files, output_file )
return output_file
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)