def main():
gff_to_rename, gff_with_perfect_names, output_gff = sys.argv[1:]
perfect_names = io.read_tsv(gff_with_perfect_names)
strain = '15V' # add parser!
to_rename = io.read_tsv(gff_to_rename)
new_genes = []
new_gene_count = 0
with open(output_gff, 'w') as out:
for line_to_rename in to_rename:
found = False
for perfect_line in perfect_names:
# the same contig, the same start or end
if line_to_rename[0] == perfect_line[0] \
and (line_to_rename[3] == perfect_line[3]
or line_to_rename[4] == perfect_line[4]):
#change the next line to something more flexible
out.write('\t'.join(line_to_rename[:8]) + '\t' +
perfect_line[8] + '_15V-P4' + '\n')
found = True
if not found:
out.write('\t'.join(line_to_rename[:8]) + '\t' +
'ID=new_gene_' + str(new_gene_count) + '\n')
if line_to_rename[2] == 'gene' and 'trna' not in line_to_rename[
8]: #we don't need 'new' tRNA genes
print('\t'.join(line_to_rename[:8]) + '\t' +
'ID=new_gene_' + str(new_gene_count))
new_genes.append(line_to_rename)
new_gene_count += 1
def main():
gff_to_rename, gff_with_perfect_names, output_gff = sys.argv[1:]
perfect_names = io.read_tsv(gff_with_perfect_names)
strain = '15V' # add parser!
to_rename = io.read_tsv(gff_to_rename)
new_genes = []
new_gene_count = 0
with open(output_gff, 'w') as out:
for line_to_rename in to_rename:
found = False
for perfect_line in perfect_names:
# the same contig, the same start or end
if line_to_rename[0] == perfect_line[0] \
and (line_to_rename[3] == perfect_line[3]
or line_to_rename[4] == perfect_line[4]):
#change the next line to something more flexible
out.write('\t'.join(line_to_rename[:8]) + '\t' + perfect_line[8] + '_15V-P4' + '\n')
found = True
if not found:
out.write('\t'.join(line_to_rename[:8]) + '\t' + 'ID=new_gene_' + str(new_gene_count) + '\n')
if line_to_rename[2] == 'gene' and 'trna' not in line_to_rename[8]: #we don't need 'new' tRNA genes
print('\t'.join(line_to_rename[:8]) + '\t' + 'ID=new_gene_' + str(new_gene_count))
new_genes.append(line_to_rename)
new_gene_count += 1
def main():
"""
Inputs: input file, output file, conversion function, other arguments
"""
parser = argparse.ArgumentParser()
required = parser.add_argument_group('required arguments')
required.add_argument("-f", "--function", help="function name "
"(currently implemented functions: "
"\n gtf_to_gff3, gff_to_bed, bed_to_gff3)", required=True)
required.add_argument("-i", "--input_filename", help="input file to work with", required=True)
required.add_argument("-o", "--output_filename", help="output file to write to", required=True)
parser.add_argument("--source", default="bed2gff", help="source information in gtf "
"(program that generated this file,"
"database or project name)")
parser.add_argument("--cds_only", type=bool, default=False, help="generate only CDS lines"
"(default is FALSE)")
args = parser.parse_args()
input_list_of_lists = io.read_tsv(args.input_filename)
if args.function == 'gtf_to_gff3':
gtf_to_gff3(input_list_of_lists, args.output_filename, args.cds_only)
elif args.function == "gff_to_bed":
gff_to_bed(input_list_of_lists, args.output_filename)
elif args.function == "bed_to_gff3":
bed_to_gff3(input_list_of_lists, args.output_filename, args.source)
else:
print(args.function, ': This function is not implemented')
print("Currently implemented functions: gtf_to_gff3, gff_to_bed, bed_to_gff3")
def main():
input_name, output_name = sys.argv[1:]
features = read_tsv(input_name)
strange_contigs = check_for_peculiarities(features)
with open(output_name, 'w') as out:
out.write('\n'.join(strange_contigs))
def main():
if len(sys.argv) < 3:
print('Usage: \n'
'compare_vcf.py <reference_filename> <mutant_filename> <output_filename>')
sys.exit(2)
reference_filename, mutant_filename = sys.argv[1:3]
output_filename = sys.stdout
if len(sys.argv) == 4:
output_filename = sys.argv[3]
reference = read_tsv(reference_filename)
mutant = read_tsv(mutant_filename)
result = compare(reference, mutant)
write_tsv(result, output_filename)
def main():
"""
Inputs: input file, output file, conversion function, other arguments
"""
parser = argparse.ArgumentParser()
required = parser.add_argument_group('required arguments')
required.add_argument("-f",
"--function",
help="function name "
"(currently implemented functions: "
"\n gtf_to_gff3, gff_to_bed, bed_to_gff3)",
required=True)
required.add_argument("-i",
"--input_filename",
help="input file to work with",
required=True)
required.add_argument("-o",
"--output_filename",
help="output file to write to",
required=True)
parser.add_argument("--source",
default="bed2gff",
help="source information in gtf "
"(program that generated this file,"
"database or project name)")
parser.add_argument("--cds_only",
type=bool,
default=False,
help="generate only CDS lines"
"(default is FALSE)")
args = parser.parse_args()
input_list_of_lists = io.read_tsv(args.input_filename)
if args.function == 'gtf_to_gff3':
gtf_to_gff3(input_list_of_lists, args.output_filename, args.cds_only)
elif args.function == "gff_to_bed":
gff_to_bed(input_list_of_lists, args.output_filename)
elif args.function == "bed_to_gff3":
bed_to_gff3(input_list_of_lists, args.output_filename, args.source)
else:
print(args.function, ': This function is not implemented')
print(
"Currently implemented functions: gtf_to_gff3, gff_to_bed, bed_to_gff3"
)
def main():
gff_to_rename, table_for_rename, output_gff = sys.argv[1:]
table = io.read_tsv(table_for_rename)
strain = '' # add parser!
to_rename = io.read_tsv(gff_to_rename)
new_genes = []
new_gene_count = 0
with open(output_gff, 'w') as out:
for line_to_rename in to_rename:
if line_to_rename[2] == 'mRNA':
found = False
for cluster in table:
#exchange the next two lines if necessary (depends on the order in the table)
#maker_name = cluster[3][:-27] #unique part of the name
#maker_name = cluster[3][:-7] #unique part of the name if using augustus
maker_name = cluster[
4] # [:7] is not truly unique because there might be '01' and '013'
#print(maker_name)
proper_name = cluster[3]
if maker_name in line_to_rename[8]:
out.write('\t'.join(line_to_rename[:8]) + '\t' +
'ID=' + proper_name + '\n') # '_' + strain
#print('yeap')
found = True
# continue
if not found:
out.write('\t'.join(line_to_rename[:8]) + '\t' +
'ID=new_gene_' + str(new_gene_count) + '\n')
if line_to_rename[
2] == 'mRNA' and 'trna' not in line_to_rename[
8]: # we don't need 'new' tRNA genes
print('\t'.join(line_to_rename[:8]) + '\t' +
'ID=new_gene_' + str(new_gene_count))
new_genes.append(line_to_rename)
new_gene_count += 1
def main():
"""
Inputs: input file, output file name
"""
parser = argparse.ArgumentParser()
parser.add_argument("-i", "--input_filename", help="input file to work with", required=True)
parser.add_argument("-o", "--out", default="corrected.gff", help="output gff / bed file")
args = parser.parse_args()
input_list_of_lists = io.read_tsv(args.input_filename)
filetype = os.path.splitext(args.input_filename)[1]
if filetype not in [".bed", ".gff"]:
print("Unknown file extension. Please make sure you have a .bed or .gff file")
sys.exit("Unknown file type")
correct_coord(input_list_of_lists, filetype, args.out)