def split_and_rename(infile, outdir):
contigs = fastaparser.read_fasta(infile)
for contig in contigs:
filename = contig[0].split()[0][1:]
filename = join(outdir, filename + ".fasta")
print filename
fastaparser.write_fasta_to_file(filename, [contig])
def parse_mash(contig_file, table):
contigs = fastaparser.read_fasta(contig_file)
similar_lists = {}
for contig in contigs:
similar_lists[get_short_name(contig[0])] = []
for line in open(table, 'r'):
arr = line.split()
dist = float(arr[2])
if dist < 0.1:
similar_lists[arr[0]].append(arr[1])
print "processed input"
to_sort = []
for l in similar_lists:
to_sort.append([l, len(similar_lists[l])])
sorted_similar = sorted(to_sort, key=itemgetter(1), reverse=True)
outcontigs = []
used = set()
for contig_info in sorted_similar:
if contig_info[0] not in used:
for similar in similar_lists[contig_info[0]]:
used.add(similar)
if contig_info[1] > 10:
print contig_info
print similar_lists[contig_info[0]]
#far from optimal but whynot
for contig in contigs:
if get_short_name(contig[0]) == contig_info[0]:
outcontigs.append(contig)
break
result_f = join(os.path.dirname(contig_file), "interesting.fasta")
os.system("rm " + result_f)
fastaparser.write_fasta_to_file(result_f, outcontigs)
def extract_circular_from_file(file, indir, outdir):
out_file = join(outdir, os.path.splitext(file)[0] + ".circular.fasta")
contigs = fastaparser.read_fasta(join(sys.argv[1], file))
circulars = []
count = []
for contig in contigs:
arr = contig[0].strip(';').split('_')
# if float(arr[3]) > 500:
if len(contig[1]) < 500: continue
for kval in range(200, 50, -1):
# kval = 55
if kval >= len(contig[1]) or len(contig[1]) < 500:
continue
start = contig[1][:kval]
end = contig[1][-kval:]
if start == end:
# print (">" + contig[0][1:])
# print (contig[1])
# print (" k equal " + str(kval))
print(contig[0] + " is circular " + str(kval))
# contig[0] = contig[0] + " k: " + str(kval)
circulars.append(contig)
break
fastaparser.write_fasta_to_file(out_file, circulars)
def glue_and_rename(indir, outfile):
for file in os.listdir(indir):
arr = file.split('.')
if len(arr) < 4:
continue
contigs = fastaparser.read_fasta(join(indir, file))
for contig in contigs:
new_name = contig[0] + " " + arr[0] + "." + arr[1]
print new_name
fastaparser.write_fasta_to_file(outfile,
zip([new_name], [contig[1]]))
def extract_not_listed(infasta, list):
listed = set()
for line in open(list, 'r'):
listed.add(">" + line.split()[0])
print len(listed)
contigs = fastaparser.read_fasta(infasta)
print len(contigs)
outcontigs = []
for contig in contigs:
if not contig[0].split()[0] in listed:
# print contig[0]
outcontigs.append(contig)
# else:
# listed.remove(contig[0])
# for c in listed:
# print c
print len(outcontigs)
outfasta = infasta[:-6] + ".unknown.fasta"
os.system("rm " + outfasta)
fastaparser.write_fasta_to_file(outfasta, outcontigs)
def break_scaffolds(argv):
if (len(argv) != 4) and (len(argv) != 2):
print(
"Usage: " + argv[0] +
" <input fasta (scaffolds)> (to get stats on sizes of Ns regions)")
print(
"Usage: " + argv[0] +
" <input fasta (scaffolds)> <THRESHOLD> <output fasta (contigs)> (to break contigs on Ns regions of size >= THRESHOLD)"
)
sys.exit()
BREAK_SCAFFOLDS = False
if len(argv) == 4:
BREAK_SCAFFOLDS = True
N_NUMBER = None
counter = 0
if BREAK_SCAFFOLDS:
N_NUMBER = int(argv[2])
sizes_of_Ns_regions = dict()
new_fasta = []
for id, (name, seq) in enumerate(fastaparser.read_fasta(argv[1])):
i = 0
cur_contig_number = 1
cur_contig_start = 0
while (i < len(seq)) and (seq.find("N", i) != -1):
start = seq.find("N", i)
end = start + 1
while (end != len(seq)) and (seq[end] == 'N'):
end += 1
i = end + 1
if BREAK_SCAFFOLDS and (end - start) >= N_NUMBER:
new_fasta.append(
(name.split()[0] + "_" + str(cur_contig_number),
seq[cur_contig_start:start]))
cur_contig_number += 1
cur_contig_start = end
if not BREAK_SCAFFOLDS:
if (end - start) in sizes_of_Ns_regions:
sizes_of_Ns_regions[(end - start)] += 1
else:
sizes_of_Ns_regions[(end - start)] = 1
if BREAK_SCAFFOLDS:
new_fasta.append((name.split()[0] + "_" + str(cur_contig_number),
seq[cur_contig_start:]))
counter += cur_contig_number
if BREAK_SCAFFOLDS:
fastaparser.write_fasta_to_file(argv[3], new_fasta)
#print (" * " + str(id + 1) + " scaffold(s) were broken into " + str(counter) + " contig(s)")
else:
list_of_sizes = sizes_of_Ns_regions.keys()
list_of_sizes.sort()
avg_len = 0.0
nruns = 0
for k, v in sizes_of_Ns_regions:
avg_len += k * v
nruns += v
print k, sizes_of_Ns_regions[k]
avg_len /= nruns
print "N-runs: " + str(nruns) + ", avg. len: " + str(avg_len)
if not os.path.isdir(output_dir):
os.makedirs(output_dir)
# creating single-entry references and chains
params_subst_dict = dict()
input_fasta = fastaparser.read_fasta(sys.argv[1])
cwd = os.getcwd()
os.chdir(ideal_assembler_bin_dir)
for K in K_list:
print("Starting with K=" + str(K))
result_fasta = []
for id, fasta_entry in enumerate(input_fasta):
cur_ref_name = os.path.join(output_dir, 'chr_' + str(id) + '.fasta')
cur_chain_name = os.path.join(output_dir, 'chr_' + str(id) + '_K' + str(K) + '_chain')
log_filename = os.path.join(output_dir, 'chr_' + str(id) + '_K' + str(K) + '.log')
fastaparser.write_fasta_to_file(cur_ref_name, [fasta_entry])
shutil.copy(chain_template, cur_chain_name)
cur_params_subst_dict = dict(params_subst_dict)
cur_params_subst_dict['OUT_BASE'] = 'chr_' + str(id) + '_K' + str(K)
tmp_dir = os.path.join(ideal_assembler_bin_dir, 'data/cap/cache/env_' + cur_params_subst_dict['OUT_BASE'])
cur_params_subst_dict['REFERENCE'] = cur_ref_name
cur_params_subst_dict['KMER_SIZE'] = str(K)
update_template_params(cur_chain_name, cur_params_subst_dict)
cmd_line = ideal_assembler_bin + ' ' + cur_chain_name + ' >> ' + log_filename + ' 2>> ' + log_filename
print('running with ' + os.path.basename(cur_ref_name) + ' on K=' + str(K))
return_code = os.system(cmd_line)
if return_code:
print("Error happened when executing cmd_line " + cmd_line)
sys.exit(1)
catch_phrase = 'Outputting contigs to'
for line in open(log_filename):
#!/usr/bin/python
############################################################################
# Copyright (c) 2015 Saint Petersburg State University
# Copyright (c) 2011-2014 Saint Petersburg Academic University
# All Rights Reserved
# See file LICENSE for details.
############################################################################
# Convert contigs (i.e a reference) for experiment of running SPAdes on E. coli MC reads in "IonTorrent" mode
# (all series of repeated nucleotides are changed to single nucleotides).
import sys
import os
import fastaparser
# MAIN
if len(sys.argv) < 3:
print("Usage: " + sys.argv[0] + " <input fasta> <output fasta>")
sys.exit()
new_fasta = []
for name, seq in fastaparser.read_fasta(sys.argv[1]):
new_seq = seq[0]
for i in range(1, len(seq)):
if seq[i - 1] != seq[i]:
new_seq += seq[i]
new_fasta.append((name, new_seq))
fastaparser.write_fasta_to_file(sys.argv[2], new_fasta)