def make_output_folders(data_folder, adaIDs, VERBOSE=0):
'''Make output folders for symlinking'''
from hivwholeseq.utils.generic import mkdirs
mkdirs(data_folder)
if VERBOSE >= 1:
print 'Folder created:', data_folder
for adaID in adaIDs + [-1]:
mkdirs(data_folder+foldername_adapter(adaID))
if VERBOSE >= 1:
print 'Folder created:', data_folder+foldername_adapter(adaID)
def make_output_folders(data_folder,
adapters_designed,
VERBOSE=0,
summary=True):
'''Make output folders for all adapters and unclassified (e.g. PhiX)'''
from hivwholeseq.utils.generic import mkdirs
# Make folders for the samples
for (adaID, s) in adapters_designed:
dirname = foldername_adapter(adaID)
mkdirs(data_folder + dirname)
if VERBOSE:
print 'Folder created:', dirname
# Make a default directory for unclassified reads
mkdirs(data_folder + 'unclassified_reads')
if VERBOSE:
print 'Folder created: unclassified reads'
if summary:
with open(get_demultiplex_summary_filename(data_folder), 'a') as f:
f.write('\n')
f.write(
'Folders created for samples and unclassified reads (including phix).'
)
f.write('\n')
def get_reference_premap_hash_filename(data_folder, adaID, ext=True):
'''Get the filename of the stampy hash of the reference used for premapping'''
fn = 'reference'
if ext:
fn = fn + '.sthash'
fn = data_folder + foldername_adapter(adaID) + 'premapped/' + fn
return fn
def make_output_folders(data_folder, adaID, VERBOSE=0):
'''Make output folders for the script'''
from hivwholeseq.utils.generic import mkdirs
dirname = data_folder + foldername_adapter(adaID) + 'map_iter/'
mkdirs(dirname)
if VERBOSE:
print 'Folder created:', dirname
def get_reference_all_filename(data_folder, adaID, fragment, ext=True):
'''Get the file with the cumulated consensi'''
fn = '_'.join(['consensus', 'alliters', fragment])
fn = data_folder + foldername_adapter(adaID) + 'map_iter/' + fn
if ext:
fn = fn + '.fasta'
return fn
def get_mapped_filename(data_folder, adaID=None, fragment=None, type='bam',
bwa=False, filtered=False, sort=False, part=None, unsorted=False,
rescue=False, trashed=False):
'''Get the filename of the mapped reads onto consensus'''
if fragment is None:
raise ValueError('Select a fragment')
filename = fragment
if rescue:
filename = filename + '_rescue'
if bwa:
filename = filename + '_bwa'
if filtered:
filename = filename + '_filtered'
if trashed:
filename = filename + '_trashed'
if sort:
filename = filename + '_sorted'
elif part is not None:
filename = filename+'_part'+str(part)
elif unsorted:
filename = filename+'_unsorted'
filename = 'mapped/'+filename+'.'+type
if adaID is not None:
filename = foldername_adapter(adaID)+filename
return data_folder+filename
def get_reference_premap_hash_filename(data_folder, adaID, ext=True):
'''Get the filename of the stampy hash of the reference used for premapping'''
fn = 'reference'
if ext:
fn = fn + '.sthash'
fn = data_folder+foldername_adapter(adaID)+'premapped/'+fn
return fn
def get_figure_folder(data_folder, adaID=None):
'''Get the folder for figures for this sample'''
folder = 'figures/'
if adaID is not None:
folder = foldername_adapter(adaID)+folder
folder = data_folder+folder
return folder
def make_output_folders(data_folder, adaID, VERBOSE=0):
'''Make output folders for the script'''
from hivwholeseq.utils.generic import mkdirs
dirname = data_folder+foldername_adapter(adaID)+'map_iter/'
mkdirs(dirname)
if VERBOSE:
print 'Folder created:', dirname
def get_mapped_filename(data_folder,
adaID=None,
fragment=None,
type='bam',
bwa=False,
filtered=False,
sort=False,
part=None,
unsorted=False,
rescue=False,
trashed=False):
'''Get the filename of the mapped reads onto consensus'''
if fragment is None:
raise ValueError('Select a fragment')
filename = fragment
if rescue:
filename = filename + '_rescue'
if bwa:
filename = filename + '_bwa'
if filtered:
filename = filename + '_filtered'
if trashed:
filename = filename + '_trashed'
if sort:
filename = filename + '_sorted'
elif part is not None:
filename = filename + '_part' + str(part)
elif unsorted:
filename = filename + '_unsorted'
filename = 'mapped/' + filename + '.' + type
if adaID is not None:
filename = foldername_adapter(adaID) + filename
return data_folder + filename
def get_reference_all_filename(data_folder, adaID, fragment, ext=True):
'''Get the file with the cumulated consensi'''
fn = '_'.join(['consensus', 'alliters', fragment])
fn = data_folder+foldername_adapter(adaID)+'map_iter/'+fn
if ext:
fn = fn+'.fasta'
return fn
def get_premapped_filename(data_folder,
adaID=None,
type='bam',
bwa=False,
part=None,
unsorted=False):
'''Get the filename of the readed mapped to reference to split into fragments'''
filename = 'premapped'
filename = 'premapped/' + filename
if adaID is not None:
filename = foldername_adapter(adaID) + filename
if part is not None:
filename = filename + '_part' + str(part)
elif unsorted:
filename = filename + '_unsorted'
if bwa:
filename = filename + '_bwa'
if type == 'sam':
filename = filename + '.sam'
elif type == 'bam':
filename = filename + '.bam'
else:
raise ValueError('Type of mapped reads file not recognized')
return data_folder + filename
def get_figure_folder(data_folder, adaID=None):
'''Get the folder for figures for this sample'''
folder = 'figures/'
if adaID is not None:
folder = foldername_adapter(adaID) + folder
folder = data_folder + folder
return folder
def get_reference_premap_filename(data_folder, adaID, fragment=None):
'''Get the filename of the reference used from premapping'''
fn = 'reference'
if fragment is not None:
fn = fn+'_'+fragment
fn = fn+'.fasta'
fn = data_folder+foldername_adapter(adaID)+'premapped/'+fn
return fn
def get_consensus_old_filename(data_folder, adaID, fragment, trim_primers=True):
'''Find the filename of the final consensus'''
filename = 'consensus_old_'+fragment
if not trim_primers:
filename = filename+'_with_primers'
filename = filename+'.fasta'
filename = foldername_adapter(adaID)+filename
return data_folder+filename
def get_hash_file(data_folder, adaID, fragment, ext=True):
'''Get the index filename, with or w/o extension'''
filename = 'consensus_' + fragment
filename = 'hash/' + filename
filename = foldername_adapter(adaID) + filename
if ext:
filename = filename + '.sthash'
return data_folder + filename
def get_merged_consensus_filename(data_folder, adaID=None,
fragments=['F1', 'F2', 'F3', 'F4', 'F5', 'F6']):
'''Get the merged consensus of several fragments'''
filename = 'consensus_'+'-'.join(fragments)+'.fasta'
if adaID is not None:
filename = foldername_adapter(adaID)+filename
filename = data_folder+filename
return filename
def get_hash_file(data_folder, adaID, fragment, ext=True):
'''Get the index filename, with or w/o extension'''
filename = 'consensus_'+fragment
filename = 'hash/'+filename
filename = foldername_adapter(adaID)+filename
if ext:
filename = filename+'.sthash'
return data_folder+filename
def get_reference_premap_filename(data_folder, adaID, fragment=None):
'''Get the filename of the reference used from premapping'''
fn = 'reference'
if fragment is not None:
fn = fn + '_' + fragment
fn = fn + '.fasta'
fn = data_folder + foldername_adapter(adaID) + 'premapped/' + fn
return fn
def get_build_consensus_summary_filename(data_folder, adaID, fragment='general',
iterative=True):
'''Get the filename of the summary of the iterative consensus'''
filename = 'summary_build_consensus_'+fragment+'.txt'
if iterative:
filename = 'map_iter/'+filename
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_mapped_filename(data_folder, adaID, fragment, n_iter, type='bam'):
'''Get the mapped filenames'''
filename = 'mapped_to_'
if n_iter == 1:
filename = filename + 'reference'
else:
filename = filename + 'consensus_' + str(n_iter - 1)
filename = filename + '_' + fragment + '.' + type
return data_folder + foldername_adapter(adaID) + 'map_iter/' + filename
def get_map_summary_filename(data_folder, adaID, fragment, rescue=False):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_map'+fragment
if rescue:
filename = filename+'_rescue'
filename = filename+'.txt'
filename = 'mapped/'+filename
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_mapped_filename(data_folder, adaID, fragment, n_iter, type='bam'):
'''Get the mapped filenames'''
filename = 'mapped_to_'
if n_iter == 1:
filename = filename + 'reference'
else:
filename = filename + 'consensus_'+str(n_iter - 1)
filename = filename+'_'+fragment+'.'+type
return data_folder+foldername_adapter(adaID)+'map_iter/'+filename
def get_map_summary_filename(data_folder, adaID, fragment, rescue=False):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_map' + fragment
if rescue:
filename = filename + '_rescue'
filename = filename + '.txt'
filename = 'mapped/' + filename
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def __init__(self, *args, **kwargs):
'''Initialize a sequenced sample'''
super(SampleSeq, self).__init__(*args, **kwargs)
from hivwholeseq.sequencing.filenames import get_seqrun_foldername
from hivwholeseq.sequencing.adapter_info import foldername_adapter
seq_run = self.loc['seq run']
adaID = self.loc['adapter']
self['folder'] = str(get_seqrun_foldername(seq_run)+foldername_adapter(adaID))
self['seqrun_folder'] = str(get_seqrun_foldername(seq_run))
def get_build_consensus_summary_filename(data_folder,
adaID,
fragment='general',
iterative=True):
'''Get the filename of the summary of the iterative consensus'''
filename = 'summary_build_consensus_' + fragment + '.txt'
if iterative:
filename = 'map_iter/' + filename
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def get_merged_allele_frequencies_filename(data_folder,
adaID,
fragments=[
'F1', 'F2', 'F3', 'F4', 'F5',
'F6'
]):
'''Get the merged allele frequencies of several fragments'''
filename = 'allele_frequencies_' + '-'.join(fragments) + '.fasta'
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def __init__(self, *args, **kwargs):
'''Initialize a sequenced sample'''
super(SampleSeq, self).__init__(*args, **kwargs)
from hivwholeseq.sequencing.filenames import get_seqrun_foldername
from hivwholeseq.sequencing.adapter_info import foldername_adapter
seq_run = self.loc['seq run']
adaID = self.loc['adapter']
self['folder'] = str(
get_seqrun_foldername(seq_run) + foldername_adapter(adaID))
self['seqrun_folder'] = str(get_seqrun_foldername(seq_run))
def get_consensus_old_filename(data_folder,
adaID,
fragment,
trim_primers=True):
'''Find the filename of the final consensus'''
filename = 'consensus_old_' + fragment
if not trim_primers:
filename = filename + '_with_primers'
filename = filename + '.fasta'
filename = foldername_adapter(adaID) + filename
return data_folder + filename
def get_merged_consensus_filename(data_folder,
adaID=None,
fragments=[
'F1', 'F2', 'F3', 'F4', 'F5', 'F6'
]):
'''Get the merged consensus of several fragments'''
filename = 'consensus_' + '-'.join(fragments) + '.fasta'
if adaID is not None:
filename = foldername_adapter(adaID) + filename
filename = data_folder + filename
return filename
def get_reference_filename(data_folder, adaID, fragment, n_iter, ext=True):
'''Get the reference filename for the intermediate mappings'''
if n_iter == 1:
fn = get_reference_premap_filename(data_folder, adaID, fragment)
if not ext:
fn = fn[:-6]
else:
fn = '_'.join(['consensus', str(n_iter-1), fragment])
fn = data_folder+foldername_adapter(adaID)+'map_iter/'+fn
if ext:
fn = fn+'.fasta'
return fn
def get_divided_filename(data_folder, adaID=None, fragment=None, type='bam', chunk=None):
'''Get the filename of the BAM files divided for a single fragment'''
filename = 'divided'
filename = 'divided/'+filename
if adaID is not None:
filename = foldername_adapter(adaID)+filename
filename = data_folder+filename
filename = filename+'_'+fragment
if chunk is not None:
filename = filename+'_chunk_'+str(chunk)
filename = filename+'.'+type
return filename
def get_reference_filename(data_folder, adaID, fragment, n_iter, ext=True):
'''Get the reference filename for the intermediate mappings'''
if n_iter == 1:
fn = get_reference_premap_filename(data_folder, adaID, fragment)
if not ext:
fn = fn[:-6]
else:
fn = '_'.join(['consensus', str(n_iter - 1), fragment])
fn = data_folder + foldername_adapter(adaID) + 'map_iter/' + fn
if ext:
fn = fn + '.fasta'
return fn
def get_divided_filenames(data_folder, adaID=None, fragments=None, type='bam'):
'''Get the filenames of the BAM files divided by fragment'''
filename = 'divided'
filename = 'divided/' + filename
if adaID is not None:
filename = foldername_adapter(adaID) + filename
filename = data_folder + filename
filenames = []
for fragment in (list(fragments) +
['ambiguous', 'crossmapped', 'unmapped', 'low_quality']):
fnf = filename + '_' + fragment + '.' + type
filenames.append(fnf)
return filenames
def get_divided_filenames(data_folder, adaID=None, fragments=None, type='bam'):
'''Get the filenames of the BAM files divided by fragment'''
filename = 'divided'
filename = 'divided/'+filename
if adaID is not None:
filename = foldername_adapter(adaID)+filename
filename = data_folder+filename
filenames = []
for fragment in (list(fragments) + ['ambiguous', 'crossmapped',
'unmapped', 'low_quality']):
fnf = filename+'_'+fragment+'.'+type
filenames.append(fnf)
return filenames
def get_read_filenames(data_folder, adaID=None, fragment=None, suffix='',
gzip=False, trimmed=False):
'''Get the filenames of the demultiplexed reads'''
filenames = ['read1', 'read2']
for i,fn in enumerate(filenames):
if adaID is not None:
fn = foldername_adapter(adaID)+fn
fn = data_folder+fn
if trimmed:
fn = fn+'_trimmed'
fn = fn+suffix+'.fastq'
if gzip:
fn = fn+'.gz'
filenames[i] = fn
return filenames
def get_divided_filename(data_folder,
adaID=None,
fragment=None,
type='bam',
chunk=None):
'''Get the filename of the BAM files divided for a single fragment'''
filename = 'divided'
filename = 'divided/' + filename
if adaID is not None:
filename = foldername_adapter(adaID) + filename
filename = data_folder + filename
filename = filename + '_' + fragment
if chunk is not None:
filename = filename + '_chunk_' + str(chunk)
filename = filename + '.' + type
return filename
def get_read_filenames(data_folder,
adaID=None,
fragment=None,
suffix='',
gzip=False,
trimmed=False):
'''Get the filenames of the demultiplexed reads'''
filenames = ['read1', 'read2']
for i, fn in enumerate(filenames):
if adaID is not None:
fn = foldername_adapter(adaID) + fn
fn = data_folder + fn
if trimmed:
fn = fn + '_trimmed'
fn = fn + suffix + '.fastq'
if gzip:
fn = fn + '.gz'
filenames[i] = fn
return filenames
def make_output_folders(data_folder, adapters_designed, VERBOSE=0, summary=True):
'''Make output folders for all adapters and unclassified (e.g. PhiX)'''
from hivwholeseq.utils.generic import mkdirs
# Make folders for the samples
for (adaID, s) in adapters_designed:
dirname = foldername_adapter(adaID)
mkdirs(data_folder+dirname)
if VERBOSE:
print 'Folder created:', dirname
# Make a default directory for unclassified reads
mkdirs(data_folder+'unclassified_reads')
if VERBOSE:
print 'Folder created: unclassified reads'
if summary:
with open(get_demultiplex_summary_filename(data_folder), 'a') as f:
f.write('\n')
f.write('Folders created for samples and unclassified reads (including phix).')
f.write('\n')
def get_premapped_filename(data_folder, adaID=None, type='bam', bwa=False,
part=None, unsorted=False):
'''Get the filename of the readed mapped to reference to split into fragments'''
filename = 'premapped'
filename = 'premapped/'+filename
if adaID is not None:
filename = foldername_adapter(adaID)+filename
if part is not None:
filename = filename+'_part'+str(part)
elif unsorted:
filename = filename+'_unsorted'
if bwa:
filename = filename + '_bwa'
if type == 'sam':
filename = filename + '.sam'
elif type == 'bam':
filename = filename + '.bam'
else:
raise ValueError('Type of mapped reads file not recognized')
return data_folder+filename
def get_fragment_positions_filename(data_folder, adaID):
'''Get the filename of the positions of fragments in the reference for premap'''
filename = 'fragment_positions_premapped.dat'
filename = 'divided/'+filename
return data_folder+foldername_adapter(adaID)+filename
def get_mutations_file(data_folder, adaID, fragment):
'''Get the filename with the mutations for all reads'''
filename = 'mutations_' + fragment + '.pickle'
filename = foldername_adapter(adaID) + filename
return data_folder + filename
def get_filter_mapped_summary_filename(data_folder, adaID, fragment):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_filter_'+fragment+'.txt'
filename = 'mapped/'+filename
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_filter_mapped_summary_filename(data_folder, adaID, fragment):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_filter_' + fragment + '.txt'
filename = 'mapped/' + filename
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def get_fragment_positions_filename(data_folder, adaID):
'''Get the filename of the positions of fragments in the reference for premap'''
filename = 'fragment_positions_premapped.dat'
filename = 'divided/' + filename
return data_folder + foldername_adapter(adaID) + filename
def get_premap_summary_filename(data_folder, adaID):
'''Get the filename of the premap to reference'''
filename = 'summary_premapped.txt'
filename = 'premapped/'+filename
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_divide_summary_filename(data_folder, adaID):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_divide.txt'
filename = 'divided/' + filename
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def get_premap_summary_filename(data_folder, adaID):
'''Get the filename of the premap to reference'''
filename = 'summary_premapped.txt'
filename = 'premapped/' + filename
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def get_trim_summary_filename(data_folder, adaID):
'''Get the filename of the trim low quality'''
filename = 'summary_trim.txt'
filename = data_folder + foldername_adapter(adaID) + filename
return filename
def get_divide_summary_filename(data_folder, adaID):
'''Get the filename of the summary of the division into fragments'''
filename = 'summary_divide.txt'
filename = 'divided/'+filename
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_trim_summary_filename(data_folder, adaID):
'''Get the filename of the trim low quality'''
filename = 'summary_trim.txt'
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_read_unpaired_filename(data_folder, adaID):
'''Get the reads pairs for which one read is low quality'''
fn = 'reads_unpaired.fastq'
fn = foldername_adapter(adaID) + fn
fn = data_folder + fn
return fn
def get_mapped_suspicious_filename(data_folder, adaID, fragment, type='bam'):
'''The the filename of the mapped reads with many mutations from consensus'''
filename = fragment + '_suspicious.' + type
filename = data_folder + foldername_adapter(adaID) + 'mapped/' + filename
return filename
def get_merged_allele_frequencies_filename(data_folder, adaID,
fragments=['F1', 'F2', 'F3', 'F4', 'F5', 'F6']):
'''Get the merged allele frequencies of several fragments'''
filename = 'allele_frequencies_'+'-'.join(fragments)+'.fasta'
filename = data_folder+foldername_adapter(adaID)+filename
return filename
def get_read_unpaired_filename(data_folder, adaID):
'''Get the reads pairs for which one read is low quality'''
fn = 'reads_unpaired.fastq'
fn = foldername_adapter(adaID)+fn
fn = data_folder+fn
return fn
def get_allele_frequencies_filename(data_folder, adaID, fragment):
'''Get the filename with the corrected allele frequencies'''
filename = 'allele_frequencies_'+fragment+'.npy'
filename = foldername_adapter(adaID)+filename
return data_folder+filename
def get_mapped_suspicious_filename(data_folder, adaID, fragment, type='bam'):
'''The the filename of the mapped reads with many mutations from consensus'''
filename = fragment+'_suspicious.'+type
filename = data_folder+foldername_adapter(adaID)+'mapped/'+filename
return filename
def get_allele_frequencies_filename(data_folder, adaID, fragment):
'''Get the filename with the corrected allele frequencies'''
filename = 'allele_frequencies_' + fragment + '.npy'
filename = foldername_adapter(adaID) + filename
return data_folder + filename
def get_mutations_file(data_folder, adaID, fragment):
'''Get the filename with the mutations for all reads'''
filename = 'mutations_'+fragment+'.pickle'
filename = foldername_adapter(adaID)+filename
return data_folder+filename