def test_create_from_patterns():
patterns = ['GAGG', 'CAGG', 'GGGG', 'GGGA', 'CAGG', 'AGGG', 'GGAG']
expected = {'AGG': ['GGG'], 'CAG': ['AGG', 'AGG'], 'GAG': ['AGG'], 'GGA': ['GAG'], 'GGG': ['GGG', 'GGA']}
actual = debruijn.create_from_patterns(patterns)
assert (expected == actual)
def create_circular_string(k):
format_string = '{0:0' + str(k) + 'b}'
strings = [format_string.format(x) for x in range(0, 2 ** k)]
graph = debruijn.create_from_patterns(strings)
cycle = eulerian.cycle.find_cycle(graph)[:-(k-1)]
text = kmer_reconstruction.reconstruct(cycle)
return text
def reconstruct(kmers):
graph = debruijn.create_from_patterns(kmers)
path = eulerian.path.find_path(graph)
text = kmer_reconstruction.reconstruct(path)
return text
import contigs
import kmer_reconstruction
import sys
import debruijn
filename = sys.argv[1]
with open(filename, 'r') as f:
lines = [l.strip() for l in f.readlines() if l.strip() != '']
graph = debruijn.create_from_patterns(lines)
res = contigs.maximal_non_branching_paths(graph)
cgs = [kmer_reconstruction.reconstruct(ks) for ks in res]
output = '\n'.join(cgs)
print(output)
import debruijn, sys
mode = sys.argv[1]
filename = sys.argv[2]
with open(filename, 'r') as f:
if mode == 'patterns':
kmers = [line.strip() for line in f.readlines() if line.strip() != '']
graph = debruijn.create_from_patterns(kmers)
else:
k = int(f.readline())
text = f.readline()
graph = debruijn.create(text, k)
print(debruijn.to_string(graph))
