def find_flanking_regions(start,stop,strand,site,fna_filename):
genome = genome_from_fna(fna_filename)
offset = 100
ufr = genome[start-offset:start]
dfr = genome[stop:stop+offset]
if strand == -1:
ufr,dfr = wc(dfr),wc(ufr)
assert wc(ufr + site + dfr) in genome
else:
assert ufr + site + dfr in genome
return ufr,dfr
def cumsum_test():
arca_reads = get_arca_reads(1000000)
true_rdm = density_from_reads(arca_reads, G)
pssm = make_pssm(Escherichia_coli.ArcA)
comb_rdm = true_rdm[0] + true_rdm[1]
print "fwd_scores"
fwd_scores = score_genome_np(pssm, genome)
print "rev_scores"
rev_scores = score_genome_np(pssm, wc(genome))
scores = np.log(np.exp(fwd_scores) + np.exp(rev_scores))
probs = np.exp(scores)/np.sum(np.exp(scores))
print "sorting scores"
score_js = sorted_indices(scores)[::-1] # order scores from greatest to least
print "sorting probs"
prob_js = sorted_indices(probs)[::-1] # ditto
plt.plot(cumsum(rslice(comb_rdm, score_js)), label="scores")
plt.plot(cumsum(rslice(comb_rdm, prob_js)), label="boltzmann probs")
comb_rdm_copy = list(comb_rdm)
controls = 5
for i in range(controls):
print i
random.shuffle(comb_rdm_copy)
plt.plot(cumsum(comb_rdm_copy), color='r')
plt.legend(loc=0)
plt.xlim(0, 1)
plt.ylim(0, 1)
plt.show()
def update_scores_np(fwd_scores,rev_scores,fwd_i,fwd_j,dw,w,genome):
G = len(genome)
rel_fwd_base = {v:k for (k,v) in base_index.items()}[fwd_j]
rel_rev_base = wc(rel_fwd_base)
rev_i = w - fwd_i - 1
fwd_dscores = (np.roll(np.array(list(genome)),-fwd_i) == rel_fwd_base) * dw
rev_dscores = (np.roll(np.array(list(genome)),-rev_i) == rel_rev_base) * dw
return fwd_scores + fwd_dscores,rev_scores + rev_dscores
def arca_motif_comparison():
arca_reads = get_arca_reads()
true_rdm = density_from_reads(arca_reads, G)
pssm = make_pssm(Escherichia_coli.ArcA)
plt.plot(true_rdm[0])
plt.plot(true_rdm[1])
fwd_scores, rev_scores = score_genome_np(pssm, genome)
scores = np.log(np.exp(fwd_scores) + np.exp(rev_scores))
sites = concat([(site, wc(site)) for site in Escherichia_coli.ArcA])
site_locations = [m.start(0) for site in sites
for m in re.finditer(site, genome)]
site_locations_np = np.zeros(G)
for site_loc in site_locations:
site_locations_np[site_loc] = 1
plt.plot(site_locations_np)
plt.plot(scores)
def find_site(site,fna_filename,return_all=False):
genome = genome_from_fna(fna_filename)
fwd_regexp = re.compile(site)
rev_regexp = re.compile(wc(site))
fwd_matches = [(lambda (start,stop):(start,stop,+1))(m.span()) for m in fwd_regexp.finditer(genome)]
rev_matches = [(lambda (start,stop):(start,stop,-1))(m.span()) for m in rev_regexp.finditer(genome)]
matches = fwd_matches + rev_matches
#print matches
if len(matches) == 1:
print "found unique match for %s in %s" % (site,fna_filename)
return head(matches) if not return_all else matches
elif len(matches) > 1:
print "found multiple matches for %s in %s" % (site,fna_filename)
return (None,None,None) if not return_all else matches
else:
print "couldn't find' match for %s in %s" % (site,fna_filename)
return (None,None,None) if not return_all else []
def model_f(dinuc):
print dinuc
oligos = model["oligo"].split()
if dinuc in oligos:
i = oligos.index(dinuc)
d = {prop:model[prop][i]
for prop in "twist tilt roll".split()}
else:
print "elsing"
cunid = wc(dinuc)
print cunid
i = oligos.index(cunid)
d = {prop:model[prop][i]
for prop in "twist roll".split()}
print "d"
d["tilt"] = -model["tilt"][i] # flip sign of tilt if reverse complementing
d["rise"] = model["rise"]
print "returning d"
return d
def find_site_ref(site,fna_filename):
"""WRONG: rev matches are indexed backwards"""
genome = genome_from_fna(fna_filename)
regexp = re.compile(site)
fwd_matches = [(lambda (start,stop):(start,stop,+1))(m.span()) for m in regexp.finditer(genome)]
rev_matches = [(lambda (start,stop):(start,stop,-1))(m.span()) for m in regexp.finditer(wc(genome))]
matches = fwd_matches + rev_matches
print matches
if len(matches) == 1:
print "found unique match for %s in %s" % (site,fna_filename)
return head(matches)
elif len(matches) > 1:
print "found multiple matches for %s in %s" % (site,fna_filename)
return head(matches)
else:
print "couldn't find' match for %s in %s" % (site,fna_filename)
return (None,None,None)
