type=int,
default=-1,
help='max paths depth (default len of baseline)')
parser.add_argument('--tails',
type=int,
default=5,
help='length of tails (default 5)')
parser.add_argument('--names_list',
type=str,
default='all',
help='names list txt file')
args = parser.parse_args()
graph = GenomeGraph()
graph.read_graph(args.input_file)
subgraph, aim_chain = graph.generate_subgraph(args.start,
args.end,
reference=args.reference,
window=args.window,
tails=args.tails,
depth=args.depth)
f_out = open(args.outfile + '.sif', '+a')
f_freq = open(args.outfile + '_freq.sif', '+a')
in_aim = 0
is_ref = 0
for stamm in subgraph:
print(stamm)
for contig in subgraph[stamm]:
for line in f:
code = line.split(' ')[-1][:-3]
name = ''.join(line.split(' ')[:-1])
codes[code] = name
org = args.out_dir
files = os.listdir(org + '/')
if '.dump' not in ' '.join(files):
print(org, end=' ')
print('dumping...')
try:
g = GenomeGraph()
g.read_graph(org + '/' + org + '.sif')
dump_file = open(org + '/' + org + '.dump', 'wb')
dump(g, dump_file)
except:
pass
try:
g = GenomeGraph()
g.read_graph(org + '/' + org + '_pars.sif')
dump_file = open(org + '/' + org + '_pars.dump', 'wb')
dump(g, dump_file)
except:
pass
skip = os.path.isfile(org + '/' + org + '.db')
if args.dbpar != 'no':
#pars table
connect = sqlite3.connect(data_path + org + '/' + org + '_pars.db')
c = connect.cursor()
genome_codes = [q for q in c.execute('select genome_id,genome_code from genomes_table')]
for code in genome_codes:
for ref_code in codes:
if ref_code in code[1]:
c.execute('update genomes_table set genome_name="' + codes[ref_code] + '" where genome_id=' + str(code[0]))
connect.commit()
connect.close()
print('dumping...')
g = GenomeGraph()
g.read_graph('data/' + name + '/' + name + '.sif')
dump_file = open('data/' + name + '/' + name + '.dump', 'wb')
dump(g, dump_file)
if args.dbpar != 'no':
g = GenomeGraph()
g.read_graph('data/' + name + '/' + name + '_pars.sif')
dump_file = open('data/' + name + '/' + name + '_pars.dump', 'wb')
dump(g, dump_file)
if check_conservativity(
graph,
c[i + 1],
c[i + j - 1],
c,
c[i],
c[i + j],
depth=depth,
filter=filter) >= non_conservativity:
hits.append((graph.genes_decode[c[i]],
graph.genes_decode[c[i + j]]))
print('Hits:')
print(hits)
hits_sum += len(hits)
print('--------------------')
print('SUM: ' + str(hits_sum))
print('Input file: ' + args.input_file)
g = GenomeGraph()
g.read_graph(args.input_file, generate_freq=True)
find_smile_template(g,
allowed_deviating=args.ad,
non_conservativity=args.nc,
depth=args.d,
max_insertion_len=args.il,
filter=args.ip)
parser = argparse.ArgumentParser(prog='start.sh')
parser.add_argument('-i', '--input_file', default='no', type=str, help='input_file (Orthofinder file)')
parser.add_argument('-o', '--output_dir', default='STDOUT', type=str, help='Output directory')
parser.add_argument('--reference', type=str, default='auto', help='name of reference genome')
parser.add_argument('--window', type=int, default=20, help='Size of window (default is 20)')
parser.add_argument('--iterations', type=int, default=500, help='number of iterations in stat computing (default is 500)')
parser.add_argument('--genomes_list', type=str, default='all', help='genomes list txt file')
parser.add_argument('--min_depth', type=int, default=0, help='min length of deviating path (default is 0)')
parser.add_argument('--max_depth', type=int, default=200, help='max length of deviating path (default is 200)')
parser.add_argument('--save_db', type=str, default=None, help='db path')
args = parser.parse_args()
try:
os.stat(args.output_dir)
except FileNotFoundError:
os.mkdir(args.output_dir)
f_params = open(args.output_dir + '/params.txt', 'a+')
f_params.write('reference: ' + args.reference + '\n')
f_params.write('window: ' + str(args.window) + '\n')
f_params.write('iterations: ' + str(args.iterations) + '\n')
graph = GenomeGraph()
graph.read_graph(args.input_file, names_list=args.genomes_list)
graph.compute_subgraph_complexity(args.output_dir, args.reference, window=args.window, iterations=args.iterations, min_depth=args.min_depth, max_depth=args.max_depth, save_db=args.save_db)
name = ''.join(line.split(' ')[:-1])
codes[code] = name
for org in orgs:
try:
files = os.listdir('data/' + org + '/')
if '.dump' not in ' '.join(files):
print(org, end=' ')
print('dumping...')
try:
g = GenomeGraph()
g.read_graph('data/' + org + '/' + org + '.sif')
dump_file = open('data/' + org + '/' + org + '.dump', 'wb')
dump(g, dump_file)
except:
pass
try:
g = GenomeGraph()
g.read_graph('data/' + org + '/' + org + '_pars.sif')
dump_file = open('data/' + org + '/' + org + '_pars.dump', 'wb')
dump(g, dump_file)
except:
pass
skip = os.path.isfile(data_path + org + '/' + org + '.db')