def extract_alleles(input_file,
output_file=None,
reference_file=None,
alignment_file=None,
method=METHOD,
sort=SORT,
loci=LOCI):
"""Pick the top 2 Amplicon Analysis consensus seqs per group from a Fasta"""
method = method or METHOD
loci = loci or LOCI
# Set the output file if not specified
output_file = output_file or _get_output_file(input_file)
output_type = get_file_type(output_file)
# If align to reference for breaking ties
alignment_file = get_alignment_file(input_file, reference_file,
alignment_file)
alignments = list(BlasrReader(alignment_file))
# Run the appropriate grouping
if method == 'locus':
groups = _group_by_locus(alignments, loci)
elif method == 'barcode':
groups = _group_by_barcode(alignments)
elif method == 'both':
groups = _group_by_both(alignments, loci)
elif method == 'all':
groups = {a.qname: [a] for a in alignments}
else:
msg = "Invalid Selection Metric: %s" % method
log.error(msg)
raise ValueError(msg)
# Read the input sequences and use them to generate our sorting data
sequences = read_sequences(input_file)
if sort == 'num_reads':
sorting_data = {s.name: consensus_size(s) for s in sequences}
elif sort == 'accuracy':
assert get_file_type(input_file) == 'fastq'
sorting_data = {s.name: record_accuracy(s) for s in sequences}
else:
msg = "Invalid Sorting Metric: %s" % sort
log.error(msg)
raise ValueError(msg)
log.info('Sorting sequences for selection according to "%s"' % sort)
ordered = _sort_groups(groups, sorting_data)
log.info('Selecting top sequences from %s according to the "%s" policy' %
(input_file, method))
selected = list(_select_sequences(ordered))
log.info('Selected %s sequences from %s total for further analysis' %
(len(selected), len(sequences)))
log.info('Writing the selected sequences out to %s' % output_file)
subset = list(_subset_sequences(sequences, selected))
_write_output(subset, output_file, output_type)
return output_file
def extract_alleles( input_file, output_file=None, reference_file=None,
alignment_file=None,
method=METHOD,
sort=SORT,
loci=LOCI ):
"""Pick the top 2 Amplicon Analysis consensus seqs per group from a Fasta"""
method = method or METHOD
loci = loci or LOCI
# Set the output file if not specified
output_file = output_file or _get_output_file( input_file )
output_type = get_file_type( output_file )
# If align to reference for breaking ties
alignment_file = get_alignment_file( input_file, reference_file, alignment_file )
alignments = list( BlasrReader( alignment_file ))
# Run the appropriate grouping
if method == 'locus':
groups = _group_by_locus( alignments, loci )
elif method == 'barcode':
groups = _group_by_barcode( alignments )
elif method == 'both':
groups = _group_by_both( alignments, loci )
elif method == 'all':
groups = {a.qname: [a] for a in alignments}
else:
msg = "Invalid Selection Metric: %s" % method
log.error( msg )
raise ValueError( msg )
# Read the input sequences and use them to generate our sorting data
sequences = read_sequences( input_file )
if sort == 'num_reads':
sorting_data = {s.name: consensus_size(s) for s in sequences}
elif sort == 'accuracy':
assert get_file_type(input_file) == 'fastq'
sorting_data = {s.name: record_accuracy(s) for s in sequences}
else:
msg = "Invalid Sorting Metric: %s" % sort
log.error( msg )
raise ValueError( msg )
log.info('Sorting sequences for selection according to "%s"' % sort)
ordered = _sort_groups( groups, sorting_data )
log.info('Selecting top sequences from %s according to the "%s" policy' % (input_file, method))
selected = list( _select_sequences( ordered ))
log.info('Selected %s sequences from %s total for further analysis' % (len(selected), len(sequences)))
log.info('Writing the selected sequences out to %s' % output_file)
subset = list( _subset_sequences( sequences, selected ))
_write_output( subset, output_file, output_type )
return output_file
def get_output_file( input_file, modifier ):
"""
Get a modified output file name based on some input file
"""
basename = '.'.join( input_file.split('.')[:-1] )
file_type = get_file_type( input_file )
return '%s.%s.%s' % (basename, modifier, file_type)
def _get_output_file(input_file):
"""
Get the output file, either as provided or from the input filename
"""
basename = '.'.join(input_file.split('.')[:-1])
input_type = get_file_type(input_file)
return '%s.oriented.%s' % (basename, input_type)
def get_output_file(input_file, modifier):
"""
Get a modified output file name based on some input file
"""
basename = '.'.join(input_file.split('.')[:-1])
file_type = get_file_type(input_file)
return '%s.%s.%s' % (basename, modifier, file_type)
def _get_output_file( input_file ):
"""
Get the output file, either as provided or from the input filename
"""
basename = '.'.join( input_file.split('.')[:-1] )
input_type = get_file_type( input_file )
return '%s.oriented.%s' % (basename, input_type)
def _get_output_type( output_file ):
"""
Get the output filetype and confirm the format is valid
"""
output_type = get_file_type( output_file )
if output_type in ['fasta', 'fastq']:
return output_type
else:
msg = "Output file must be either Fasta or Fastq format"
log.error( msg )
raise TypeError( msg )
def _get_output_type(output_file):
"""
Get the output filetype and confirm the format is valid
"""
output_type = get_file_type(output_file)
if output_type in ['fasta', 'fastq']:
return output_type
else:
msg = "Output file must be either Fasta or Fastq format"
log.error(msg)
raise TypeError(msg)
def _parse_input_records( input_file ):
"""
Parse the input sequence records with the appropriate pbcore Reader
"""
input_type = get_file_type( input_file )
if input_type == 'fasta':
return list( FastaReader( input_file ))
elif input_type == 'fastq':
return list( FastqReader( input_file ))
else:
msg = 'Input file must be either Fasta or Fastq'
log.error( msg )
def exons_to_cDNA( exon_file ):
"""
Combine a multi-Fasta of Exon sequences into a mock cDNA
"""
output_type = get_file_type( exon_file )
output_file = _get_output_file( exon_file, output_type )
records = _parse_exon_records( exon_file, output_type )
log.info("Combinging %s exons sequences to cDNA" % len(records))
if len( records ):
sorted_records = _sort_records( records )
cDNA_record = _combine_records( sorted_records )
log.info("Writing cDNA sequence out to %s" % output_file)
write_sequences( cDNA_record, output_file )
def exons_to_cDNA(exon_file):
"""
Combine a multi-Fasta of Exon sequences into a mock cDNA
"""
output_type = get_file_type(exon_file)
output_file = _get_output_file(exon_file, output_type)
records = _parse_exon_records(exon_file, output_type)
log.info("Combinging %s exons sequences to cDNA" % len(records))
if len(records):
sorted_records = _sort_records(records)
cDNA_record = _combine_records(sorted_records)
log.info("Writing cDNA sequence out to %s" % output_file)
write_sequences(cDNA_record, output_file)
def extract_alleles( input_file, min_reads, min_length, output_file=None ):
"""
Pick the top N Amplicon Analysis consensus seqs from a Fasta by Nreads
"""
# Set the output file if not specified
output_file = output_file or _get_output_file( input_file )
output_type = get_file_type( output_file )
# Parse the alignment data and extract the target sequences
sequences = _parse_input_records( input_file )
sequences = _filter_on_length( sequences, min_length )
sequences = _filter_on_numreads( sequences, min_reads )
_write_output( sequences, output_file, output_type )
return output_file
def extract_exons(input_record, exon_fofn, directory=None):
"""
Extract all exons from a particular Fasta File into a separate Fasta File
"""
if isinstance(input_record, str):
output_type = get_file_type(input_record)
input_record = _read_fasta_record(input_record)
elif isinstance(input_record, FastaRecord):
output_type = 'fasta'
elif isinstance(input_record, FastqRecord):
output_type = 'fastq'
else:
msg = 'Input record must be Filename, FastaRecord or FastqRecord'
log.error(msg)
raise TypeError(msg)
return _extract_exons(input_record, exon_fofn, output_type, directory)
def extract_exons( input_record, exon_fofn, directory=None ):
"""
Extract all exons from a particular Fasta File into a separate Fasta File
"""
if isinstance( input_record, str ):
output_type = get_file_type( input_record )
input_record = _read_fasta_record( input_record )
elif isinstance( input_record, FastaRecord ):
output_type = 'fasta'
elif isinstance( input_record, FastqRecord ):
output_type = 'fastq'
else:
msg = 'Input record must be Filename, FastaRecord or FastqRecord'
log.error( msg )
raise TypeError( msg )
return _extract_exons( input_record, exon_fofn, output_type, directory )
def trim_alleles(input_file, output_file=None, trim=0):
"""Pick the top 2 Amplicon Analysis consensus seqs per group from a Fasta"""
# If no trim or output file is specified, we can skip this module
if trim == 0 and output_file is None:
log.info('No trimming necessary for "%s", skipping...' % input_file)
return input_file
# Set the output file if not specified
output_file = output_file or _get_output_file(input_file)
output_type = get_file_type(output_file)
# Read the input sequences and trim each record
sequences = read_sequences(input_file)
log.info("Trimming sequences by %s bp from each end" % trim)
trimmed = _trim_sequences(sequences, trim)
log.info("Writing the trimmed sequences out to %s" % output_file)
_write_output(trimmed, output_file, output_type)
return output_file
def trim_alleles(input_file, output_file=None, trim=0):
"""Pick the top 2 Amplicon Analysis consensus seqs per group from a Fasta"""
# If no trim or output file is specified, we can skip this module
if trim == 0 and output_file is None:
log.info('No trimming necessary for "%s", skipping...' % input_file)
return input_file
# Set the output file if not specified
output_file = output_file or _get_output_file(input_file)
output_type = get_file_type(output_file)
# Read the input sequences and trim each record
sequences = read_sequences(input_file)
log.info('Trimming sequences by %s bp from each end' % trim)
trimmed = _trim_sequences(sequences, trim)
log.info('Writing the trimmed sequences out to %s' % output_file)
_write_output(trimmed, output_file, output_type)
return output_file
def _get_output_file( input_file ):
basename = '.'.join( input_file.split('.')[:-1] )
file_type = get_file_type( input_file )
return '%s.filtered.%s' % (basename, file_type)
def _get_output_file( input_file ):
basename = '.'.join( input_file.split('.')[:-1] )
file_type = get_file_type( input_file )
return '%s.selected.%s' % (basename, file_type)
def _get_output_file(input_file):
basename = ".".join(input_file.split(".")[:-1])
file_type = get_file_type(input_file)
return "%s.trimmed.%s" % (basename, file_type)
