def calc_MI_matrix():
matrix = {}
for i, c1 in enumerate(clusters):
for j, c2 in enumerate(clusters):
if j >= i: continue
matrix[(i, j)] = round(prog4.calc_MI_fast(c1, c2, profile_pair_freq, profile_freq), 4)
return matrix
def remove_orphans(cc): ## cc - current clusters
initial_clusters = find_initial_clusters_and_their_info_from_table2()
current_clusters = cc #list os sets
import prog4
profile_freq = prog4.get_profile_freq()
profile_pair_freq = prog4.get_profile_pair_freq()
covered_clusters = []
for i_c in initial_clusters:
best_MI = -100
best_final_cluster = set()
for c in current_clusters:
MI = prog4.calc_MI_fast(
set(i_c.split(",")), c, profile_pair_freq, profile_freq
) # calculate MI between initial profile combination (i_c) and each of the current combinations (c)
if MI > best_MI:
best_MI = MI
best_final_cluster = c
best_final_cluster = sorted(list(best_final_cluster))
covered_clusters.append(best_final_cluster)
#now we have to remove duplicates and transform a list of lists into a list of sets
s = []
new_list = []
for i in covered_clusters:
if i not in s:
s.append(i)
new_list.append(set(i))
return new_list
def remove_orphans():
covered_clusters = []
for i_c in initial_clusters:
best_MI = -100
best_final_cluster = set()
for c in clusters:
MI = prog4.calc_MI_fast(i_c,c,profile_pair_freq,profile_freq) # calculate MI between initial profile combination (i_c) and each of the current combinations (c)
if MI > best_MI:
best_MI = MI
best_final_cluster = c
best_final_cluster = sorted(list(best_final_cluster))
covered_clusters.append(best_final_cluster)
#now we have to remove duplicates and transform a list of lists into a list of sets
s = []
clusters[:] = [] # empty the list
for i in covered_clusters:
if i not in s:
s.append(i)
clusters.append(set(i))
new_file = open(WORK_DIR + "active_clusters.csv", "w")
new_file.write("number_of_clusters\tnumber_of_active_clusters\n")
initial_clusters = prog8.find_initial_clusters_and_their_info_from_table2()
for step in range(260, 0, -1):
try:
current_clusters = prog8.find_clusters_on_a_given_step(step)
profile_freq = prog4.get_profile_freq()
profile_pair_freq = prog4.get_profile_pair_freq()
covered_clusters = set()
for i_c in initial_clusters:
best_MI = -100
best_final_cluster = ""
for c in current_clusters:
MI = prog4.calc_MI_fast(
set(i_c.split(",")), set(c.split(",")), profile_pair_freq,
profile_freq
) # calculate MI between initial profile combination (i_c) and each of the current combinations (c)
if MI > best_MI:
best_MI = MI
best_final_cluster = c
covered_clusters.add(best_final_cluster)
print step, " step"
new_file.write(
str(len(current_clusters)) + '\t' + str(len(covered_clusters)) +
"\n")
except IOError:
print step, 'step doesn\'t exist'
for step in range(260, 0, -1):
try:
print step, " step"
current_clusters = prog8.find_clusters_on_a_given_step(step)
new_file.write(str(len(current_clusters)) + "\t")
best_subgroup_of_final_cluster = {
} # here I will store the name of the "nearest" subgroup for each of the current clusters. For instance, in figure 6A (https://www.dropbox.com/s/bew8l8vszgkgjs5/fig6.png), p3 is the nearest for C1, and p4 is the nearest for C2.
for c in current_clusters:
best_MI = -100 # best MI so far for this current cluster
best_subgroups_in_current_clusters = {}
for i_c in initial_clusters:
MI = prog4.calc_MI_fast(
set(i_c.split(",")), set(c.split(",")), profile_pair_freq,
profile_freq
) # calculate MI between an initial cluster and a current cluster
if MI > best_MI and initial_clusters[i_c][
'subgroups'] != {}: # if MI is higher than the best MI so far, and there exist any proteins with known subgroup in this initial cluster
best_MI = MI
best_subgroups_in_current_clusters = {}
if MI == best_MI: # there can be several initial clusters with equally short distance (MI) to the current cluster
for subgr in initial_clusters[i_c]['subgroups'].keys(
): # keys are the names of the subgroups, values are the numbers of proteins from the given subgroup
if subgr not in best_subgroups_in_current_clusters:
best_subgroups_in_current_clusters[subgr] = 0
best_subgroups_in_current_clusters[
subgr] += initial_clusters[i_c]['subgroups'][subgr]
best_subgr = max(