def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [ReadPair(Kdmer(r.split('|')[0], r.split('|')[2], int(r.split('|')[1])), i) for r, c in counter.items() for i in range(c)]
else:
raise
graph = to_debruijn_graph(frags)
print(f'Given the fragments {lines}, the de Bruijn graph is...', end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```\n\n')
print(f'... and a Eulerian cycle is ...', end="\n\n")
path = walk_eulerian_cycle(graph, frags[0].prefix())
print(f'{" -> ".join([str(p) for p in path])}')
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
def main():
print("<div style=\"border:1px solid black;\">", end="\n\n")
print("`{bm-disable-all}`", end="\n\n")
try:
lines = []
while True:
try:
line = input().strip()
if len(line) > 0:
lines.append(line)
except EOFError:
break
command = lines[0]
lines = lines[1:]
counter = Counter(lines)
if command == 'reads':
frags = [Read(r, i) for r, c in counter.items() for i in range(c)]
elif command == 'read-pairs':
frags = [
ReadPair(
Kdmer(
r.split('|')[0],
r.split('|')[2], int(r.split('|')[1])), i)
for r, c in counter.items() for i in range(c)
]
else:
raise
graph = to_debruijn_graph(frags)
graph, head_nodes, tail_nodes = balance_graph(graph)
print(
f'Given the fragments {lines}, the artificially balanced de Bruijn graph is...',
end="\n\n")
print(f'```{{dot}}\n{to_graphviz(graph)}\n```\n\n')
print(
f'... with original head nodes at {head_nodes} and tail nodes at {tail_nodes}.'
)
finally:
print("</div>", end="\n\n")
print("`{bm-enable-all}`", end="\n\n")
from Read import Read
from ToDeBruijnGraph import to_debruijn_graph
from Utils import slide_window
with open('/home/user/Downloads/dataset_240257_6(1).txt',
mode='r',
encoding='utf-8') as f:
data = f.read()
lines = data.split('\n')
k = int(lines[0].strip())
dna = lines[1].strip()
reads = [Read(kmer) for kmer, _ in slide_window(dna, k)]
graph = to_debruijn_graph(reads)
for node, other_nodes in graph.get_all_outputs():
other_nodes = list(other_nodes)
if len(other_nodes) == 0:
continue
print(f'{node} -> {",".join([str(x) for x in other_nodes])}')
from ToDeBruijnGraph import to_debruijn_graph
reads_filepath = 'FinalChallengeReads.txt.xz'
with lzma.open(reads_filepath, mode='rt', encoding='utf-8') as f:
lines = f.read().splitlines()
lines = [l.strip() for l in lines] # get rid of whitespace
lines = [l for l in lines if len(l) > 0] # get rid of empty lines
lines_split = [tuple(l.split('|', maxsplit=2)) for l in lines]
kdmers = [Kdmer(k1, k2, 1000) for k1, k2 in lines_split]
rps = [ReadPair(kdmer) for kdmer in kdmers]
broken_rps = [broken_rp for rp in rps for broken_rp in rp.shatter(40)]
broken_rps = list(set(broken_rps))
graph = to_debruijn_graph(broken_rps)
contig_paths = find_maximal_non_branching_paths(graph)
contig_paths.sort(key=lambda x: len(x))
for path in contig_paths:
if len(path) >= path[0].d:
out = path[0].stitch(path)
print(f'{len(path)} kd-mers = {out}')
else:
heads = [Read(p.data.head) for p in path]
heads_out = heads[0].stitch(heads)
tails = [Read(p.data.tail) for p in path]
tails_out = tails[0].stitch(tails)
print(f'{len(heads)} k-mers = {heads_out}')
print(f'{len(tails)} k-mers = {tails_out}')