def main():
parser = argparse.ArgumentParser(
description='Adds gene features for RNAs which lack them')
## output file to be written
parser.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input GFF3 file')
parser.add_argument('-o',
'--output',
type=str,
required=True,
help='Output GFF3 file to write')
args = parser.parse_args()
infile = open(args.input)
ofh = open(args.output, 'wt')
for line in infile:
if line.startswith('#'):
ofh.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
ofh.write("{0}\n".format(line))
continue
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
if cols[2].endswith('RNA') and parent is None:
gene_cols = list(cols)
gene_cols[2] = 'gene'
gene_cols[8] = biocodegff.set_column_9_value(
gene_cols[8], 'ID', "{0}.gene".format(id))
ofh.write("{0}\n".format("\t".join(gene_cols)))
cols[8] = biocodegff.set_column_9_value(cols[8], 'Parent',
"{0}.gene".format(id))
ofh.write("{0}\n".format("\t".join(cols)))
else:
ofh.write("{0}\n".format(line))
def main():
parser = argparse.ArgumentParser(
description=
'Updates exon Parent attributes to point at the correct RNA feature')
## output file to be written
parser.add_argument('-i',
'--input',
type=str,
required=True,
help='Path to the input GFF3 file')
parser.add_argument('-o',
'--output',
type=str,
required=True,
help='Output GFF3 file to write')
args = parser.parse_args()
infile = open(args.input)
ofh = open(args.output, 'wt')
last_rna_id = None
for line in infile:
if line.startswith('#'):
ofh.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
ofh.write("{0}\n".format(line))
continue
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
if cols[2].endswith('RNA'):
last_rna_id = id
ofh.write("{0}\n".format(line))
elif cols[2] == 'exon':
if parent != last_rna_id:
print(
"INFO: correcting unexpected parentage for feature ({0}) type {2}. Expected ({1})"
.format(id, last_rna_id, cols[2]))
cols[8] = biocodegff.set_column_9_value(
cols[8], 'Parent', last_rna_id)
ofh.write("{0}\n".format("\t".join(cols)))
else:
ofh.write("{0}\n".format(line))
else:
ofh.write("{0}\n".format(line))
def main():
parser = argparse.ArgumentParser(description="Adds gene features for RNAs which lack them")
## output file to be written
parser.add_argument("-i", "--input", type=str, required=True, help="Path to the input GFF3 file")
parser.add_argument("-o", "--output", type=str, required=True, help="Output GFF3 file to write")
args = parser.parse_args()
infile = open(args.input)
ofh = open(args.output, "wt")
for line in infile:
if line.startswith("#"):
ofh.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
ofh.write("{0}\n".format(line))
continue
id = biocodegff.column_9_value(cols[8], "ID")
parent = biocodegff.column_9_value(cols[8], "Parent")
if cols[2].endswith("RNA") and parent is None:
gene_cols = list(cols)
gene_cols[2] = "gene"
gene_cols[8] = biocodegff.set_column_9_value(gene_cols[8], "ID", "{0}.gene".format(id))
ofh.write("{0}\n".format("\t".join(gene_cols)))
cols[8] = biocodegff.set_column_9_value(cols[8], "Parent", "{0}.gene".format(id))
ofh.write("{0}\n".format("\t".join(cols)))
else:
ofh.write("{0}\n".format(line))
def main():
parser = argparse.ArgumentParser( description='Updates exon Parent attributes to point at the correct RNA feature')
## output file to be written
parser.add_argument('-i', '--input', type=str, required=True, help='Path to the input GFF3 file' )
parser.add_argument('-o', '--output', type=str, required=True, help='Output GFF3 file to write' )
args = parser.parse_args()
infile = open(args.input)
ofh = open(args.output, 'wt')
last_rna_id = None
for line in infile:
if line.startswith('#'):
ofh.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
ofh.write("{0}\n".format(line) )
continue
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
if cols[2].endswith('RNA'):
last_rna_id = id
ofh.write("{0}\n".format(line) )
elif cols[2] == 'exon':
if parent != last_rna_id:
print("INFO: correcting unexpected parentage for feature ({0}) type {2}. Expected ({1})".format(id, last_rna_id, cols[2]) )
cols[8] = biocodegff.set_column_9_value(cols[8], 'Parent', last_rna_id)
ofh.write("{0}\n".format("\t".join(cols)) )
else:
ofh.write("{0}\n".format(line) )
else:
ofh.write("{0}\n".format(line) )
def main():
parser = argparse.ArgumentParser(
description='Converts glimmerHMM GFF output to GFF3')
# output file to be written
parser.add_argument('-i',
'--input_file',
type=str,
required=True,
help='Path to an input file to parse')
parser.add_argument('-o',
'--output_file',
type=str,
required=True,
help='Path to an output file to be created')
args = parser.parse_args()
fout = open(args.output_file, 'w')
current_gene = None
current_mRNA = None
next_exon_num = defaultdict(int)
for line in open(args.input_file, 'r'):
if line.startswith('#'):
fout.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
continue
mol_id = cols[0]
feat_type = cols[2]
feat_fmin = int(cols[3]) - 1
feat_fmax = int(cols[4])
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
if feat_type == 'mRNA':
gene_cols = list(cols)
gene_cols[2] = 'gene'
cols[8] = biocodegff.set_column_9_value(cols[8], 'ID',
"{0}.mRNA".format(id))
cols[8] = biocodegff.set_column_9_value(cols[8], 'Name',
"{0}.mRNA".format(id))
cols[8] = biocodegff.order_column_9(cols[8])
# print the gene and mRNA
fout.write("{0}\n".format("\t".join(gene_cols)))
fout.write("{0}\n".format("\t".join(cols)))
elif feat_type == 'CDS':
exon_cols = list(cols)
cols[8] = biocodegff.set_column_9_value(cols[8], 'ID',
"{0}.cds".format(parent))
cols[8] = biocodegff.set_column_9_value(cols[8], 'Name',
"{0}.cds".format(parent))
cols[8] = biocodegff.set_column_9_value(cols[8], 'Parent',
"{0}.mRNA".format(parent))
cols[8] = biocodegff.order_column_9(cols[8])
exon_id = "{0}.exon.{1}".format(parent, next_exon_num[parent])
next_exon_num[parent] += 1
exon_cols[2] = 'exon'
exon_cols[7] = '.'
exon_cols[8] = biocodegff.set_column_9_value(
exon_cols[8], 'ID', exon_id)
exon_cols[8] = biocodegff.set_column_9_value(
exon_cols[8], 'Name', exon_id)
exon_cols[8] = biocodegff.set_column_9_value(
exon_cols[8], 'Parent', "{0}.mRNA".format(parent))
exon_cols[8] = biocodegff.order_column_9(exon_cols[8])
fout.write("{0}\n".format("\t".join(exon_cols)))
fout.write("{0}\n".format("\t".join(cols)))
def main():
parser = argparse.ArgumentParser( description='Converts glimmerHMM GFF output to GFF3')
# output file to be written
parser.add_argument('-i', '--input_file', type=str, required=True, help='Path to an input file to parse' )
parser.add_argument('-o', '--output_file', type=str, required=True, help='Path to an output file to be created' )
args = parser.parse_args()
fout = open(args.output_file, 'w')
current_gene = None
current_mRNA = None
next_exon_num = defaultdict(int)
for line in open(args.input_file, 'r'):
if line.startswith('#'):
fout.write(line)
continue
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
continue
mol_id = cols[0]
feat_type = cols[2]
feat_fmin = int(cols[3]) - 1
feat_fmax = int(cols[4])
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
if feat_type == 'mRNA':
gene_cols = list(cols)
gene_cols[2] = 'gene'
cols[8] = biocodegff.set_column_9_value( cols[8], 'ID', "{0}.mRNA".format(id) )
cols[8] = biocodegff.set_column_9_value( cols[8], 'Name', "{0}.mRNA".format(id) )
cols[8] = biocodegff.order_column_9(cols[8])
# print the gene and mRNA
fout.write( "{0}\n".format("\t".join(gene_cols)) )
fout.write( "{0}\n".format("\t".join(cols)) )
elif feat_type == 'CDS':
exon_cols = list(cols)
cols[8] = biocodegff.set_column_9_value( cols[8], 'ID', "{0}.cds".format(parent) )
cols[8] = biocodegff.set_column_9_value( cols[8], 'Name', "{0}.cds".format(parent) )
cols[8] = biocodegff.set_column_9_value( cols[8], 'Parent', "{0}.mRNA".format(parent) )
cols[8] = biocodegff.order_column_9(cols[8])
exon_id = "{0}.exon.{1}".format(parent, next_exon_num[parent] )
next_exon_num[parent] += 1
exon_cols[2] = 'exon'
exon_cols[7] = '.'
exon_cols[8] = biocodegff.set_column_9_value( exon_cols[8], 'ID', exon_id )
exon_cols[8] = biocodegff.set_column_9_value( exon_cols[8], 'Name', exon_id )
exon_cols[8] = biocodegff.set_column_9_value( exon_cols[8], 'Parent', "{0}.mRNA".format(parent) )
exon_cols[8] = biocodegff.order_column_9(exon_cols[8])
fout.write( "{0}\n".format("\t".join(exon_cols)) )
fout.write( "{0}\n".format("\t".join(cols)) )
def main():
parser = argparse.ArgumentParser( description='Adds locus tag identifiers to GFF3 features')
## output file to be written
parser.add_argument('-i', '--input_file', type=str, required=True, help='TA file of source molecules' )
parser.add_argument('-o', '--output_file', type=str, required=False, help='Optional output file path (else STDOUT)' )
parser.add_argument('-p', '--prefix', type=str, required=True, help='The prefix portion of IDs to be generated')
parser.add_argument('-a', '--padding', type=int, required=True, help='Specify the minimum with to reserve for the numeric portion of the IDs. Smaller numbers will be zero-padded.' )
parser.add_argument('-n', '--interval', type=int, required=False, default=1, help='Interval between generated identifiers' )
parser.add_argument('-s', '--starting_id', type=int, required=False, default=0, help='Initial numeric portion of IDs to be generated (do not zero-pad)' )
parser.add_argument('-d', '--id_file', type=str, required=False, help='Pass a 2-column file of IDs to retain (in case you have mapped genes, for example)')
parser.add_argument('-m', '--molecule_map', type=str, required=False, help='Pass a 2-column file of molecule->token identifiers (see documentation)')
parser.add_argument('-c', '--custom', type=str, required=False, help='For custom parsing steps. Most should ignore this.')
args = parser.parse_args()
check_arguments(args)
# used to store locus_tags associated with each gene (so children can inherit)
gene_loci = dict()
next_id = args.starting_id
last_molecule = None
id_mapping = parse_mapping_file( args.id_file )
mol_mapping = parse_mapping_file( args.molecule_map )
loci_assigned = list()
## if using Joana's custom options, check assumptions
if args.custom == 'joana':
if args.molecule_map is None or args.id_file is None:
raise Exception("ERROR: Expected --molecule_map and --id_file options when using --custom=joana")
else:
## need to process the ID map to reformat IDs
for id in id_mapping:
# TP05_0002 -> TpMuguga_05g00002
m = re.match('TP(\d\d)_(\d+)', id_mapping[id])
if m:
id_mapping[id] = "{0}_{1}g0{2}".format(args.prefix, m.group(1), m.group(2) )
elif args.custom == 'bmicroti':
microti_map = { 'I':'01', 'II':'02', 'III':'03', 'IV':'04' }
if args.molecule_map is None or args.id_file is None:
raise Exception("ERROR: Expected --molecule_map and --id_file options when using --custom=bmicroti")
else:
for id in id_mapping:
m = re.match('BBM_(\D+)(\d+)', id_mapping[id])
if m:
print("Changing id from {0} to ".format(id))
id_mapping[id] = "{0}_{1}g{2}".format(args.prefix, microti_map[m.group(1)], m.group(2) )
print(id_mapping[id])
else:
raise Exception("ERROR: id ({0}) didn't match expected convention.".format(id_mapping[id]))
## output will either be a file or STDOUT
fout = sys.stdout
if args.output_file is not None:
fout = open(args.output_file, 'wt')
last_number_portion_assigned = 0
for line in open(args.input_file):
line = line.rstrip()
cols = line.split("\t")
if len(cols) != 9:
fout.write(line + "\n")
continue
if last_molecule is None or (args.molecule_map is not None and mol_mapping[cols[0]] != mol_mapping[last_molecule]):
print("Found molecule {0}, resetting id counter from {1}".format(cols[0], next_id) )
next_id = args.starting_id
last_molecule = cols[0]
# grab the ID column if any
id = biocodegff.column_9_value(cols[8], 'ID')
parent = biocodegff.column_9_value(cols[8], 'Parent')
type = cols[2]
# issue
# 66F4EEF2E3C863C251F831817FF71233
# 7F1917E4D81A959078C9A38E15488BC0
# E22888670919A4A888572155F40F2654
# B9D9CF1F7A8E5A2E1124F0A6C68840DC -> BBM_I00232
# gene before is: 6DE6BCCE69CCDC39994A0940B2ED524A - novel
# errors on: BmicrotiR1_01g00233 -> BBM_I00233
#5800A4110A62E4EAE57AFAD1F8D65CB3 BBM_I00233
if type == 'gene':
while True:
if id in id_mapping:
locus_id = id_mapping[id]
else:
if args.molecule_map is None:
locus_id = "{0}_{1}".format(args.prefix, str(next_id).zfill(args.padding))
else:
if cols[0] in mol_mapping:
if args.custom == 'bmicroti':
locus_id = "{0}_{2}g{1}".format(args.prefix, str(int(last_number_portion_assigned) + 1).zfill(args.padding), mol_mapping[cols[0]])
else:
locus_id = "{0}_{2}g{1}".format(args.prefix, str(next_id).zfill(args.padding), mol_mapping[cols[0]])
else:
raise Exception("ERROR: --molecule_map passed but {0} wasn't found in it.".format(cols[0]) )
next_id += args.interval
cols[8] = biocodegff.set_column_9_value(cols[8], 'locus_tag', locus_id )
## make sure this wasn't generated already (possibly conflict between --id_file and an
# auto-generated ID?
if locus_id not in loci_assigned:
break
else:
print("DEBUG: Duplicate ID assigned ({0}), trying again.".format(locus_id) )
loci_assigned.append(locus_id)
gene_loci[id] = locus_id
m = re.search(r"(\d+)$", locus_id)
if m:
last_number_portion_assigned = m.group(1)
elif type.endswith('RNA'):
if parent in gene_loci:
cols[8] = biocodegff.set_column_9_value(cols[8], 'locus_tag', gene_loci[parent] )
else:
raise Exception("ERROR: found RNA {0} whose parent {1} wasn't found yet".format(id, parent))
fout.write("\t".join(cols) + "\n")
