def unique_combos(self, background_strains, foreground_strains):
""" finds combinations at interval pairs that is absent from the background but shared by all foreground samples
:param background_strains: list of strain names
:param foreground_strains: list of strain names
:return: json object containing interval pairs
"""
elem_intervals = self.make_elementary_intervals(
[self.sample_dict[sn][0] for sn in background_strains + foreground_strains])
background = self.build_pairwise_matrix(background_strains, elem_intervals)
foreground = self.build_pairwise_matrix(foreground_strains, elem_intervals)
output = []
uniquities = np.logical_and(foreground == len(foreground_strains), np.logical_not(background))
for combo in xrange(subspecies.NUM_SUBSPECIES**2):
combo_uniquities = np.where(uniquities[combo])
combo_color = subspecies.to_color(combo, ordinal=True)
for i, j in zip(combo_uniquities[0], combo_uniquities[1]):
output.append([
# proximal interval start, end
elem_intervals[i - 1],
elem_intervals[i],
# distal interval start, end
elem_intervals[j - 1],
elem_intervals[j],
combo_color
])
return output
def pairwise_frequencies(self, strain_names):
""" For every locus pair and every label pair, count the number of strains which have those
labels at those pairs of loci.
:param strain_names: list of strain names to analyze (must be a subset of the output from preprocess())
"""
output = [[[], [], [], []] for _ in xrange(subspecies.NUM_SUBSPECIES**2)]
for strain_name in strain_names:
intervals, sources = self.sample_dict[strain_name]
for i in xrange(len(intervals)):
# only upper triangle is meaningful
if subspecies.is_known(sources[i]):
for j in xrange(i, len(intervals)):
if subspecies.is_known(sources[j]):
combo_output = output[subspecies.to_ordinal(subspecies.combine(sources[i], sources[j]))]
combo_output[0].append(intervals[i-1])
combo_output[1].append(intervals[i])
combo_output[2].append(intervals[j-1])
combo_output[3].append(intervals[j])
return output, [subspecies.to_color(i, True) for i in xrange(subspecies.NUM_SUBSPECIES**2)]
def not_in_background(self, background_strains, foreground_strains):
""" finds combinations at interval pairs that are present in 1+ fg strains but is absent from the background
:param background_strains: list of strain names
:param foreground_strains: list of strain names
:return: json object containing interval pairs
"""
output = [[[], [], [], [], []] for _ in xrange(subspecies.NUM_SUBSPECIES**2)]
for strain in foreground_strains:
elem_intervals = self.make_elementary_intervals(
[self.sample_dict[sn][0] for sn in background_strains + [strain]])
background_absent = np.logical_not(self.build_pairwise_matrix(background_strains, elem_intervals))
foreground = self.build_pairwise_matrix([strain], elem_intervals)
uniquities = np.logical_and(foreground, background_absent)
for combo in xrange(subspecies.NUM_SUBSPECIES**2):
combo_uniquities = np.where(uniquities[combo])
for i, j in zip(combo_uniquities[0], combo_uniquities[1]):
output[combo][0].append(elem_intervals[i-1])
output[combo][1].append(elem_intervals[i])
output[combo][2].append(elem_intervals[j-1])
output[combo][3].append(elem_intervals[j])
output[combo][4].append(strain)
return output, [subspecies.to_color(combo, ordinal=True) for combo in xrange(subspecies.NUM_SUBSPECIES**2)]
