def walk_over_read_bipartite(mode, subread_ipds, ref_str, read_ipds, strand,
opts):
"""
Loop over each position in the read string, adding motifs as they
are encountered in the walk.
"""
firsts = opts.bipart_config[0]
Ns = opts.bipart_config[1]
seconds = opts.bipart_config[2]
for first in firsts:
last_mod_pos = first - 1
for N in Ns:
for second in seconds:
length = first + N + second
for j in range(len(ref_str) - (length - 1)):
seq = ref_str[j:j + length]
ipds = read_ipds[j:j + length]
if seq.find("*") == -1 and seq.find("X") == -1:
if mode == "aligned":
if strand == 0:
q_motif = motif_tools.rev_comp_motif(seq)
elif strand == 1:
q_motif = motif_tools.comp_motif(seq)
elif mode == "unaligned":
q_motif = motif_tools.rev_comp_motif(seq)
for base in opts.mod_bases:
ref_indexes = [
m.start() for m in re.finditer(base, q_motif)
if m.start() <= last_mod_pos
]
for ref_index in ref_indexes:
rc_index = len(q_motif) - 1 - ref_index
if mode == "aligned":
if strand == 0:
idx = rc_index
elif strand == 1:
idx = ref_index
elif mode == "unaligned":
idx = rc_index
IPD = ipds[idx]
bi_motif = "".join([
q_motif[:first], "N" * N, q_motif[-second:]
])
ref_motif_str = "%s-%s" % (bi_motif, ref_index)
try:
subread_ipds[ref_motif_str].append(IPD)
except KeyError:
# logging.warning("Motif %s has unexpected characters (N,etc). Skipping..." % ref_motif_str)
pass
return subread_ipds
def find_motif_matches(mode, motif, ref_str, strand):
if mode == "cmp":
if strand == 0:
q_motif = motif_tools.sub_bases(motif_tools.rev_comp_motif(motif))
elif strand == 1:
q_motif = motif_tools.sub_bases(motif_tools.comp_motif(motif))
matches_iter = re.finditer(q_motif, ref_str)
elif mode == "bas":
q_motif = motif_tools.sub_bases(motif_tools.rev_comp_motif(motif))
matches_iter = re.finditer(q_motif, ref_str)
matches_list = []
for match in matches_iter:
matches_list.append(match)
return matches_list
def walk_over_read(mode, subread_ipds, ref_str, read_ipds, strand, k, opts):
"""
Loop over each position in the read string, adding motifs as they
are encountered in the walk.
"""
for j in range(len(ref_str) - 3):
seq = ref_str[j:j + k]
ipds = read_ipds[j:j + k]
if seq.find("*") == -1 and seq.find("X") == -1:
if mode == "cmp":
if strand == 0:
q_motif = motif_tools.rev_comp_motif(seq)
elif strand == 1:
q_motif = motif_tools.comp_motif(seq)
elif mode == "bas":
q_motif = motif_tools.rev_comp_motif(ref_str[j:j + k])
for base in opts.mod_bases:
ref_indexes = [m.start() for m in re.finditer(base, q_motif)]
for ref_index in ref_indexes:
rc_index = len(q_motif) - 1 - ref_index
if mode == "cmp":
if strand == 0:
idx = rc_index
elif strand == 1:
idx = ref_index
elif mode == "bas":
idx = rc_index
IPD = ipds[idx]
# If a contiguous motif contains an N, skip
# if q_motif.find("N")>-1 and not opts.bipartite:
# continue
ref_motif_str = "%s-%s" % (q_motif, ref_index)
try:
subread_ipds[ref_motif_str].append(IPD)
except KeyError:
# logging.warning("Motif %s has unexpected characters (N,etc). Skipping..." % ref_motif_str)
pass
return subread_ipds
def kmer_freq(mode, ref_str, strand, opts):
ref_str = ref_str.upper()
if strand == 1:
ref_str = ref_str[::-1]
k = opts.comp_kmer
kmers = []
for seq in product("ATGC", repeat=k):
kmers.append("".join(seq))
kmer_counts = Counter()
for j in range(len(ref_str) - (k - 1)):
motif = ref_str[j:j + k]
kmer_counts[motif] += 1
# Combine forward and reverse complement motifs into one count
combined_kmer = Counter()
for kmer in kmers:
kmer_rc = motif_tools.rev_comp_motif(kmer)
if not combined_kmer.get(kmer_rc):
combined_kmer[kmer] = kmer_counts[kmer] + kmer_counts[kmer_rc] + 1
return combined_kmer