def process_mapping_file(map_f,
barcode_len,
barcode_type,
BARCODE_COLUMN,
REVERSE_PRIMER_COLUMN):
"""Ensures that sample IDs and barcodes are unique, that barcodes are
all the same length, and that primers are present. Ensures barcodes
and primers only contain valid characters.
Parameters
----------
map_f: file
metadata mapping file
barcode_type: string
barcode type, can be either integer or golay_12
barcode_len: int
barcode length
barcode_column: string
header of barcode column
reverse_primer_column: string
header of the reverse primer column
Returns
----------
bc_to_sid: dict
bc_to_fwd_primers: dict
bc_to_rev_primers: dict
"""
_, _, bc_to_sid, _, _, bc_to_fwd_primers, _ = check_map(map_f, False)
map_f.seek(0)
metadata_map = parse_mapping_file_to_dict(map_f)[0]
bc_to_rev_primers = {}
for sid, md in metadata_map.items():
if REVERSE_PRIMER_COLUMN in md:
bc_to_rev_primers[
md[BARCODE_COLUMN]] = expand_degeneracies(
md[REVERSE_PRIMER_COLUMN].upper().split(','))
else:
raise Exception(
"The %s column does not exist in the "
"mapping file. %s is required." %
(REVERSE_PRIMER_COLUMN,
REVERSE_PRIMER_COLUMN))
check_barcodes(bc_to_sid, barcode_len, barcode_type)
return (bc_to_sid,
bc_to_fwd_primers,
bc_to_rev_primers)
def get_mapping_details(mapping_fp):
""" Returns SampleIDs, Barcodes, Primer seqs from mapping file
mapping_fp: filepath to mapping file
"""
mapping_f = open(mapping_fp, "U")
# Only using the id_map and the errors from parsing the mapping file.
hds, mapping_data, run_description, errors, warnings = \
process_id_map(mapping_f)
mapping_f.close()
# Errors means problems with SampleIDs or headers
if errors:
raise ValueError,('Error in mapping file, please validate '+\
'mapping file with check_id_map.py')
# create dict of dicts with SampleID:{each header:mapping data}
id_map = {}
for curr_data in mapping_data:
id_map[curr_data[0]] = {}
for header in range(len(hds)):
for curr_data in mapping_data:
id_map[curr_data[0]][hds[header]] = curr_data[header]
sample_ids = id_map.keys()
barcode_seqs = []
raw_linkerprimer_seqs = []
for curr_id in id_map:
barcode_seqs.append(id_map[curr_id]['BarcodeSequence'])
raw_linkerprimer_seqs.append(id_map[curr_id]['LinkerPrimerSequence'])
# remove duplicates
raw_linkerprimer_seqs = set(raw_linkerprimer_seqs)
linker_primer_seqs = expand_degeneracies(raw_linkerprimer_seqs)
return set(sample_ids), set(barcode_seqs), set(linker_primer_seqs)
def get_mapping_details(mapping_fp):
""" Returns SampleIDs, Barcodes, Primer seqs from mapping file
mapping_fp: filepath to mapping file
"""
mapping_f = open(mapping_fp, "U")
# Only using the id_map and the errors from parsing the mapping file.
hds, mapping_data, run_description, errors, warnings = \
process_id_map(mapping_f)
mapping_f.close()
# Errors means problems with SampleIDs or headers
if errors:
raise ValueError,('Error in mapping file, please validate '+\
'mapping file with check_id_map.py')
# create dict of dicts with SampleID:{each header:mapping data}
id_map = {}
for curr_data in mapping_data:
id_map[curr_data[0]] = {}
for header in range(len(hds)):
for curr_data in mapping_data:
id_map[curr_data[0]][hds[header]] = curr_data[header]
sample_ids = id_map.keys()
barcode_seqs = []
raw_linkerprimer_seqs = []
for curr_id in id_map:
barcode_seqs.append(id_map[curr_id]['BarcodeSequence'])
raw_linkerprimer_seqs.append(id_map[curr_id]['LinkerPrimerSequence'])
# remove duplicates
raw_linkerprimer_seqs = set(raw_linkerprimer_seqs)
linker_primer_seqs = expand_degeneracies(raw_linkerprimer_seqs)
return set(sample_ids), set(barcode_seqs), set(linker_primer_seqs)
def get_mapping_details(mapping_fp,
suppress_barcode_checks=False,
suppress_primer_checks=False):
""" Returns SampleIDs, Barcodes, Primer seqs from mapping file
mapping_fp: filepath to mapping file
suppress_barcode_checks=If True, will skip getting barcodes from mapping
file and searching for these in sequences.
suppress_primer_checks=If True, will skip getting primers from mapping
file and searching for these in sequences
"""
mapping_f = open(mapping_fp, "U")
# Only using the id_map and the errors from parsing the mapping file.
hds, mapping_data, run_description, errors, warnings = \
process_id_map(mapping_f)
mapping_f.close()
# Should raise errors for barcodes or primers unless suppressed, and
# should raise errors for headers or duplicate SampleIDs in any case.
loc_bcs = ",1"
loc_primers = ",2"
if errors:
for curr_error in errors:
# Halt when header has error
if curr_error.startswith("Found header field"):
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
elif curr_error.endswith(loc_bcs):
# Halt for barcode errors unless suppressed
if suppress_barcode_checks:
continue
else:
raise ValueError(
'Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
elif curr_error.endswith(loc_primers):
# Halt for primer errors unless suppressed
if suppress_primer_checks:
continue
else:
raise ValueError(
'Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
# Raise error on duplicate sample IDs
elif curr_error.startswith("Duplicate SampleID"):
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
# create dict of dicts with SampleID:{each header:mapping data}
id_map = {}
for curr_data in mapping_data:
id_map[curr_data[0]] = {}
for header in range(len(hds)):
for curr_data in mapping_data:
id_map[curr_data[0]][hds[header]] = curr_data[header]
sample_ids = id_map.keys()
barcode_seqs = []
raw_linkerprimer_seqs = []
for curr_id in id_map:
if not suppress_barcode_checks:
barcode_seqs.append(id_map[curr_id]['BarcodeSequence'])
if not suppress_primer_checks:
raw_linkerprimer_seqs.append(
id_map[curr_id]['LinkerPrimerSequence'])
# remove duplicates
raw_linkerprimer_seqs = set(raw_linkerprimer_seqs)
linker_primer_seqs = expand_degeneracies(raw_linkerprimer_seqs)
return set(sample_ids), set(barcode_seqs), set(linker_primer_seqs)
def get_mapping_details(mapping_fp,
suppress_barcode_checks=False,
suppress_primer_checks=False):
""" Returns SampleIDs, Barcodes, Primer seqs from mapping file
mapping_fp: filepath to mapping file
suppress_barcode_checks=If True, will skip getting barcodes from mapping
file and searching for these in sequences.
suppress_primer_checks=If True, will skip getting primers from mapping
file and searching for these in sequences
"""
mapping_f = open(mapping_fp, "U")
# Only using the id_map and the errors from parsing the mapping file.
hds, mapping_data, run_description, errors, warnings = \
process_id_map(mapping_f)
mapping_f.close()
# Should raise errors for barcodes or primers unless suppressed, and
# should raise errors for headers or duplicate SampleIDs in any case.
loc_bcs = ",1"
loc_primers = ",2"
if errors:
for curr_error in errors:
# Halt when header has error
if curr_error.startswith("Found header field"):
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
elif curr_error.endswith(loc_bcs):
# Halt for barcode errors unless suppressed
if suppress_barcode_checks:
continue
else:
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
elif curr_error.endswith(loc_primers):
# Halt for primer errors unless suppressed
if suppress_primer_checks:
continue
else:
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
# Raise error on duplicate sample IDs
elif curr_error.startswith("Duplicate SampleID"):
raise ValueError('Error in mapping file, please validate '
'mapping file with validate_mapping_file.py')
# create dict of dicts with SampleID:{each header:mapping data}
id_map = {}
for curr_data in mapping_data:
id_map[curr_data[0]] = {}
for header in range(len(hds)):
for curr_data in mapping_data:
id_map[curr_data[0]][hds[header]] = curr_data[header]
sample_ids = id_map.keys()
barcode_seqs = []
raw_linkerprimer_seqs = []
for curr_id in id_map:
if not suppress_barcode_checks:
barcode_seqs.append(id_map[curr_id]['BarcodeSequence'])
if not suppress_primer_checks:
raw_linkerprimer_seqs.append(
id_map[curr_id]['LinkerPrimerSequence'])
# remove duplicates
raw_linkerprimer_seqs = set(raw_linkerprimer_seqs)
linker_primer_seqs = expand_degeneracies(raw_linkerprimer_seqs)
return set(sample_ids), set(barcode_seqs), set(linker_primer_seqs)
def test_expand_degeneracies(self):
"""generate_possibilities should make possible strings"""
self.assertEqual(expand_degeneracies('ACG'), ['ACG'])
self.assertEqual(expand_degeneracies('RGY'),
['AGT', 'AGC', 'GGT', 'GGC'])
