def plot_motif(motif, file_name, title, fout=None):
print 'Generating %s ...' % file_name
# convert probabilities to counts by simply scaling the pobabilities,
# this is ok, since the logo is scaled by the discrete entropy and not
# the differential entropy of the Dirichlet-compound posterior distribution
counts = [ [ int(round(motif[j][i]*1000)) for j in range(len(motif)) ] for i in range(len(motif[0])) ]
alphabet = Alphabet(DNA.letters, zip(DNA.letters.lower(), DNA.letters))
data = LogoData.from_counts(alphabet, np.array(counts))
options = LogoOptions()
options.color_scheme = nucleotide
options.logo_title = title
options.creator_text = ''
options.fineprint = ''
options.stacks_per_line = 60
options.yaxis_scale = 1.0
options.scale_width = False
# use the natural logarithm as unit
options.unit_name = "nats"
options.yaxis_label = "p"
# use discrete entropy to scale the logo
# note: somehow the weblogo library requires that the entropy is inverted:
# Log(|A|) - H(X)
# that is, the stack height is simply defined by what is given by data.entropy,
# since we use nats, the entropy should also be in the interval [0, 1]!
data.entropy = map(lambda x: 1.0 - x/math.log(4), information.entropy(motif, len(motif), len(motif[0])))
data.entropy_interval = None
format = LogoFormat(data, options)
if not fout:
fout = open(file_name, 'w')
pdf_formatter(data, format, fout)
fout.close()
else:
pdf_formatter(data, format, fout)
p = p_independent(N_hypercolumns, units_per_hypercolumn, X)
p_i = p[i, :]
p_j = p[j, :]
p_joint = joint(i, j, X, distribution, units_per_hypercolumn)
aux = np.copy(p_joint)
if np.any(p_joint == 0):
# Joint
p_joint[p_joint < low_noise] = low_noise
sum = p_joint.sum()
p_joint = p_joint / sum
p_i = p_joint.sum(axis=1)
p_j = p_joint.sum(axis=0)
# Calculate the entropies
x1 = entropy(p_i)
x2 = entropy(p_j)
x3 = joint_entropy(p_joint)
MI = mutual_information(p_i, p_j, p_joint)
MI2 = mutual_information2(p_i, p_j, p_joint)
MI_alt = x1 + x2 - x3
D1 = x3 - MI
D2 = x3 - MI2
print 'MI', MI
print 'MI2', MI2
print 'MI_alt', MI_alt
print np.isclose(MI, MI2)
print 'distances 1, 2', D1, D2
def entropy(self):
return information.entropy(self.motif())
def entropy(self):
motif = self.motif()
return information.entropy(motif, self.n, self.m)
