def get_exp_proportion(exp):
study = v5.exp_to_study(exp)
nonzero = pd.read_csv(decon_temp + 'nonzero_Weight_'
+ study + '.tsv', sep = '\t',index_col=0)
exps = v5.study_to_exps(study)
if len(exps) == 1:
singleExp = True
else:
singleExp = False
return get_proportion(exp, nonzero,singleExp)
def scatterplot(ax, exp, celltype, remove_study = False):
study = v5.exp_to_study(exp)
if remove_study:
if not is_type_available(celltype, study):
print("Cell type ({}) not provided in reference ".format(celltype)
+ "matrix for this study.")
return
query = get_query_expression(exp)
exp_list = v5.study_to_exps(study)
reference = get_reference_expression(celltype, exp_list, remove_study)
ax.scatter(reference[0], query)
ax.set(xlim=(0, 450000), ylim=(0, 450000))
diag_line, = ax.plot(ax.get_xlim(), ax.get_ylim(), ls="--", c=".3")
xstick = np.arange(0, 450000 ,100000)
ax.set_xticks(xstick)
ax.set_yticks(xstick)
ax.set(xlabel = "{} ({} experiments)".format(co.get_term_name(celltype),
reference[1]), ylabel = exp)
def multi_core(cell_exp_count, studies, exp_acc, gene_ids, countspermillion,
qualified_cell_type_name, cell_type_file, qualified_cell_type):
exp_acc_list = list(exp_acc)
cell_types_selected = qualified_cell_type
# Construct the noise added reference matrix
reference_matrix = []
select_study_list = {}
for i in qualified_cell_type:
tmp_exp = V5.celltype_to_exp(i)
select_sample = random.choice(tmp_exp)
select_study_list[i] = V5.exp_to_study(select_sample)
exp_index = exp_acc_list.index(select_sample)
reference_matrix.append(exp_index)
# print(select_study_list)
# Build the noise added reference matrix
for i in range(len(reference_matrix)):
if i == 0:
reference = countspermillion[reference_matrix[i]]
else:
tmp = countspermillion[reference_matrix[i]]
reference = np.vstack((reference, tmp))
reference_noise = reference
# Build the reference matrix
reference_noise_free = []
for i in range(len(qualified_cell_type)):
tmp_exp = V5.celltype_to_exp(qualified_cell_type[i])
tmp_ref = []
# Since all cell type will be included, therefore we can simply using the previous one`
for j in tmp_exp:
# Only one study wll be chosen to construct the noisy reference, therefore using !=
if V5.exp_to_study(j) != select_study_list[qualified_cell_type[i]]:
tmp_ref.append(exp_acc_list.index(j))
for j in range(len(tmp_ref)):
if j == 0:
reference = countspermillion[tmp_ref[j]]
else:
tmp = countspermillion[tmp_ref[j]]
reference = np.vstack((reference, tmp))
if len(tmp_ref) > 1:
ref_mean = np.mean(reference, axis=0)
else:
ref_mean = reference
reference_noise_free.append(ref_mean)
reference_noise_free_np = np.array(reference_noise_free)
signature_np = np.transpose(reference_noise_free_np)
reference_noise_np = reference_noise.copy()
signature_noise_np = np.transpose(reference_noise_np)
# signature_temp = signature_np.copy()
# Transform to pandas
signature_np = signature_np.transpose()
signature_noise_np = signature_noise_np.transpose()
signature_pd = pd.DataFrame(data=signature_np,
columns=gene_ids,
index=qualified_cell_type_name)
signature_noise_np_pd = pd.DataFrame(
data=signature_noise_np,
columns=gene_ids,
index=[co.get_term_name(i) for i in qualified_cell_type])
# Save the signature and noisy signature for future analysis
signature_pd.to_csv('~/IndependentStudy/Data/SignatureSimulation/' +
str(cell_exp_count) + '_signature.tsv',
sep='\t')
signature_noise_np_pd.to_csv(
'~/IndependentStudy/Data/SignatureSimulation/' + str(cell_exp_count) +
'_signature_noise.tsv',
sep='\t')
# Build the variance data set
# Eliminate the redundant cell type in all exp
cell_type_specific_file = {}
for i in cell_type_file:
cell_type_specific_file[i] = co.get_terms_without_children(
cell_type_file[i])
# Build the exp to study check dictionary
studyexpMap = {}
expstudyMap = {}
for i in range(len(exp_acc)):
expstudyMap[exp_acc[i]] = studies[i]
if studies[i] not in studyexpMap:
studyexpMap[studies[i]] = [exp_acc[i]]
else:
studyexpMap[studies[i]].append(exp_acc[i])
# Build the variance matrix
variance_matrix = []
cell_types_48 = []
for cell_co in range(len(cell_types_selected)):
# Get the cell type
cellExpDict = {}
for i in cell_type_specific_file:
if cell_types_selected[cell_co] in cell_type_specific_file[i]:
cellExpDict[i] = [cell_types_selected[cell_co]]
# cell type specific Exp to Study dictionary
expPerStudy = []
keys = list(cellExpDict.keys())
# print(keys)
studyList = []
for i in keys:
if expstudyMap[i] not in studyList:
studyList.append(expstudyMap[i])
expPerStudy.append(i)
else:
continue
tmp_exp_study = {}
for i in cellExpDict.keys():
if expstudyMap[i] not in tmp_exp_study.keys():
tmp_exp_study[expstudyMap[i]] = [i]
else:
tmp_exp_study[expstudyMap[i]].append(i)
# Get the within study variance
# Generate the mean profile
tmp_mean = []
within_study_var = []
# Build the exp expression matrix
# print(tmp_exp_study.items())
for j in tmp_exp_study.items():
# print(select_study_list[cell_types_selected[cell_co]])
# print(j[0])
if j[0] not in select_study_list[cell_types_selected[cell_co]]:
# Garb the cell index
specific_cell_exp_index = []
for i in range(len(exp_acc)):
if exp_acc[i] in j[1]:
specific_cell_exp_index.append(i)
else:
continue
specific_cell_exp_signature = get_signatures(
specific_cell_exp_index, countspermillion)
# Generate the cell_type specific mean (j[1] is a tuple), tmp_mean consist study mean
if len(j[1]) == 1:
tmp_mean.append(specific_cell_exp_signature)
else:
tmp_mean.append(
np.mean(specific_cell_exp_signature, axis=1))
# Calculate the residue (if j[1] > 1)
if len(j[1]) > 1:
tmp_residue_list = []
for index in specific_cell_exp_index:
tmp_exp = get_signatures([index], countspermillion)
tmp_residue = np.abs(
tmp_exp -
np.mean(specific_cell_exp_signature, axis=1))
tmp_residue_list.append(tmp_residue)
# Construct the within study variance
tmp_residue_list = np.array(tmp_residue_list)
within_study_var.append(np.var(tmp_residue_list, axis=0))
else:
within_study_var.append(
np.zeros(specific_cell_exp_signature.shape[0]))
else:
continue
cell_types_48 += tmp_mean
within_study_var = np.array(within_study_var)
# Construct the study variance
tmp_mean = np.array(tmp_mean)
study_variance = np.var(tmp_mean, axis=0)
# We assume variance sum law here
total_variance = np.zeros(study_variance.shape[0])
total_variance = total_variance + study_variance
for i in within_study_var:
total_variance = total_variance + i
variance_matrix.append(total_variance)
variance_matrix = np.array(variance_matrix)
print(variance_matrix.shape)
os.system("touch " + '~/IndependentStudy/Data/Variance/' +
str(cell_exp_count) + '_variance.txt')
np.savetxt('/ua/shi235/IndependentStudy/Data/Variance/' +
str(cell_exp_count) + '_variance.txt',
variance_matrix,
delimiter="\t")