def reduce_genesets():
sample = read_file("enrich_red/gae-hom-hom.csv")
red = read_file("enrich_red/selected_genesets.csv")
temp = {}
for i in red:
if i in sample:
temp[i] = red[i]
write_file("enrich_red/selected_genesets.csv", temp)
def save_enrichment_set():
lib = gp.get_library_name('Human')
lib = lib[53]
files = [("gcn-hom-hom", "enrich/gcn-hom-hom.csv"),
("gcn-hom-onto", "enrich/gcn-hom-onto.csv"),
("gcn-onto-onto", "enrich/gcn-onto-onto.csv"),
("gae-hom-hom", "enrich/gae-hom-hom.csv"),
("gae-hom-onto", "enrich/gae-hom-onto.csv"),
("gae-onto-onto", "enrich/gae-onto-onto.csv")]
enrich_set = {}
for key, file in files:
print(file)
cluster_data = read_file(file)
for i in cluster_data:
print(len(cluster_data[i][2]))
try:
enr = gp.enrichr(gene_list=list(cluster_data[i][2])[:1000], gene_sets=lib, organism='Human', cutoff=0.05).results
name = key + "-" + str(i)
term = enr['Term'].to_list()
enrich_set[name] = term
# print(i)
print(enr)
except:
pass
write_file("enrich-cluster/full_result_dic.csv", enrich_set)
def line_plots():
pairs = [('gae-hom-hom', 'jcd-hom'), ('gae-hom-onto', 'jcd-hom'),
('gae-onto-onto', 'jcd-onto'), ('gae-hom-onto', 'jcd-onto')]
dic = {}
for i in pairs:
file_one = read_file("top_4_bio_process/" + i[0] + ".csv")
file_two = read_file("top_4_bio_process/" + i[1] + ".csv")
name = i[0] + "-" + i[1]
dic[name] = {0: 0, 5: 0, 10: 0, 15: 0, 20: 0}
for j in keys:
x = file_one[str(j)] if str(j) in file_one else set()
y = file_two[str(j)] if str(j) in file_two else set()
intersect = len(x & y)
if intersect == 0:
dic[name][0] = dic[name][0] + 1
elif intersect < 5:
dic[name][5] = dic[name][5] + 1
elif intersect < 10:
dic[name][10] = dic[name][10] + 1
elif intersect < 15:
dic[name][15] = dic[name][15] + 1
else:
dic[name][20] = dic[name][20] + 1
# normalise
# for i in dic:
# mean = 20
# std = stat.stdev(dic[i].values())
#
# for j in dic[i]:
# dic[i][j] = dic[i][j]/100
pd.DataFrame(dic).plot(kind='bar')
plt.xlabel("# of nearest x")
plt.ylabel("# of Occurrence")
plt.title("# of Nearest-x-genesets in common between selected graphs")
plt.show()
def scatter_plots():
for i in files:
file_one = "enrich_red/"+i[0]+".csv"
file_two = "enrich_red/"+i[1]+".csv"
one = read_file(file_one)
two = read_file(file_two)
array = []
for x, y in zip(one, two):
x_one = list(one[x])
y_one = list(two[y])
array.extend(res(x_one, y_one))
array.extend(res(y_one, x_one))
x, y = zip(*array)
plt.scatter(x, y)
linreg = spy.stats.linregress(x, y)
temp = [linreg.intercept + linreg.slope.item() * k for k in x]
plt.plot(x, temp, 'r')
x_min = min(x)
x_max = max(x) + statistics.stdev(x)
y_min = min(y)
y_max = max(y) + statistics.stdev(y)
plt.xlim(x_min, x_max)
plt.ylim(y_min, y_max)
plt.ylabel("Corresponding P-value")
plt.xlabel("Actual P-value")
plt.text(i[2], i[3], 'R2 = %0.2f' % linreg.rvalue)
plt.text(i[2], i[4], 'Slope = %0.2f' % linreg.slope)
plt.title(i[0]+" and "+i[1])
plt.show()
def save_top4_csvs():
for i in files:
file_name = "enrich/" + i + ".csv"
file = read_file(file_name)
temp = {}
for j in file:
gene_list = list(file[j][2])
enr_x_one = None
try:
enr_x_one = gp.enrichr(
gene_list=gene_list,
gene_sets=lib,
organism='Human',
cutoff=0.05).results.head(10)['Term'].tolist()
temp[j] = set(enr_x_one)
except:
pass
write_file("top_4_bio_process/" + i + ".csv", temp)
try:
enr = gp.enrichr(gene_list=list(cluster_data[i][2])[:1000], gene_sets=lib, organism='Human', cutoff=0.05).results
name = key + "-" + str(i)
term = enr['Term'].to_list()
enrich_set[name] = term
# print(i)
print(enr)
except:
pass
write_file("enrich-cluster/full_result_dic.csv", enrich_set)
save_enrichment_set()
x = read_file("enrich-cluster/full_result_dic.csv")
l1 = {}
for i in x.keys():
l2 = []
for j in x.keys():
l2.append(jac_sim(x[i], x[j]))
l1[i] = l2
df = pd.DataFrame.from_dict(l1, orient='index').transpose()
col = {}
col_name = list(df.columns.values)
for i in range(len(col_name)):
col[col_name[i]] = i
print(col)
if i in sample:
temp[i] = red[i]
write_file("enrich_red/selected_genesets.csv", temp)
# reduce_genesets()
lib = gp.get_library_name('Human')[53]
files = [("gae-hom-hom", 1, 1), ("gae-hom-onto", 1, 2),
("gae-onto-onto", 2, 3), ("jcd-hom-hom", 1, 4),
("jcd-onto-onto", 2, 5)]
data_desc = read_file_2("data\ms-project\data-description.csv")
for i in files:
file_name = "enrich_red/" + i[0] + ".csv"
file = read_file(file_name)
# if i[1] == 1:
# neigh = read_file_2("data/ms-project/neig_len_hom.csv")
# else:
# neigh = read_file_2("data/ms-project/neig_len_onto.csv")
if i[2] == 1:
rank = read_file_2(
"ranking_results/ -- GAE -- Homology -- Homology.csv")
elif i[2] == 2:
rank = read_file_2(
"ranking_results/ -- GAE -- Homology -- Ontology.csv")
elif i[2] == 3:
rank = read_file_2(
"ranking_results/ -- GAE -- Ontology -- Ontology.csv")
elif i[2] == 4: