def find_clusters_and_survival(tested_gene_list_file_name, total_gene_list_file_name, gene_expression_file_name, phenotype_file_name, survival_file_name, gene_filter_file_name=None, tested_gene_list_path=None, total_gene_list_path=None, gene_expression_path=None, phenotype_path=None, gene_filter_file_path=None, var_th_index=None, is_unsupervised=True, start_k=2, end_k=2, meta_groups=None, filter_expression=None, clustering_algorithm="euclidean" ,plot=True):
data = load_integrated_ge_data(tested_gene_list_file_name=tested_gene_list_file_name, total_gene_list_file_name=total_gene_list_file_name, gene_expression_file_name=gene_expression_file_name, phenotype_file_name=phenotype_file_name, survival_file_name=survival_file_name, var_th_index=var_th_index, meta_groups=meta_groups, filter_expression=filter_expression)
if data is None:
print "insufficient data"
return
gene_expression_top_var, gene_expression_top_var_headers_rows, gene_expression_top_var_headers_columns, labels_assignment, survival_dataset = data
# plot_genes_statistic(gene_expression_top_var, gene_expression_top_var_headers_columns, tested_gene_list_file_name)
clfs_results = None
results = []
if is_unsupervised:
clfs_results = find_clusters(end_k, gene_expression_top_var, gene_expression_top_var_headers_rows,
start_k, e2g_convertor(gene_expression_top_var_headers_columns),
tested_gene_list_file_name, labels_assignment, clustering_algorithm=clustering_algorithm, plot=plot)
for i in range(start_k,end_k+1):
results.append(km_curve(clfs_results[i], survival_dataset[1:], gene_expression_top_var_headers_rows, tested_gene_list_file_name.split(".")[0],i)[0])
else:
for i, cur_groups in enumerate(meta_groups):
labeled_patients = divided_patient_ids_by_label(phenotype_file_name, groups=cur_groups)
plot_heatmap(gene_expression_top_var, e2g_convertor(gene_expression_top_var_headers_columns),
[labels_assignment[i]] + labels_assignment[:i] + labels_assignment[i + 1:],
gene_expression_top_var_headers_rows,
tested_gene_list_file_name, label_index=i)
results.append(km_curve(labeled_patients, survival_dataset[1:], gene_expression_top_var_headers_rows, tested_gene_list_file_name.split(".")[0],label_index=i)[0])
return results ,clfs_results
def find_clusters_and_gene_enrichment(tested_gene_list_file_name,
total_gene_list_file_name,
gene_expression_file_name,
phenotype_file_name,
gene_filter_file_name=None,
tested_gene_list_path=None,
total_gene_list_path=None,
gene_expression_path=None,
phenotype_path=None,
gene_filter_file_path=None,
var_th_index=None,
start_k=2,
end_k=6,
calc_go=True,
enrichment_list_file_names=None,
meta_groups=None,
filter_expression=None,
cluster_algorithm=None):
# fetch gene expression by gene_id, divided by tumor type
gene_sets = []
expression_sets = []
averaged_expression_sets = []
tested_gene_expression = load_gene_expression_profile_by_genes(
tested_gene_list_file_name, gene_expression_file_name,
gene_filter_file_name, tested_gene_list_path, gene_expression_path,
gene_filter_file_path)
tested_gene_expression_headers_rows, tested_gene_expression_headers_columns, tested_gene_expression = separate_headers(
tested_gene_expression)
if filter_expression is not None:
filtered_patients = [
y for x in divided_patient_ids_by_label(phenotype_file_name,
groups=filter_expression)
for y in x
]
print "number of filtered patients from phenotypes: {}".format(
len(filtered_patients))
else:
print "no filter applied"
filtered_patients = tested_gene_expression_headers_columns
tested_gene_expression, tested_gene_expression_headers_columns = filter_genes_dataset_by_patients(
filtered_patients, tested_gene_expression_headers_columns,
tested_gene_expression)
if np.shape(tested_gene_expression)[1] == 1:
print "no expressions were found after filtering by labels {}. skipping...".format(
filter_expression)
return None
total_gene_list = load_gene_list(total_gene_list_file_name)
tested_gene_list = load_gene_list(tested_gene_list_file_name)
row_var = np.var(tested_gene_expression, axis=1)
row_var_sorted = np.sort(row_var)[::-1]
labels_assignment_patients = None
if meta_groups is not None:
print "clustering patients by groups"
labels_assignment_patients = labels_assignments(
meta_groups, phenotype_file_name,
tested_gene_expression_headers_columns)
enrichment_lists = []
if enrichment_list_file_names is not None:
for cur in enrichment_list_file_names:
enrichment_lists.append(load_gene_list(cur))
if var_th_index is None:
var_th_index = len(row_var_sorted) - 1
row_var_th = row_var_sorted[var_th_index]
row_var_masked_indices = np.where(row_var_th > row_var)[0]
gene_expression_top_var = np.delete(tested_gene_expression,
row_var_masked_indices,
axis=0)
gene_expression_top_var_header_rows = np.delete(
tested_gene_expression_headers_rows, row_var_masked_indices, axis=0)
gene_expression_top_var_header_columns = tested_gene_expression_headers_columns
clfs_results = {}
output_rows = []
if calc_go:
if not os.path.exists(
os.path.join(constants.GO_DIR, constants.GO_FILE_NAME)):
wget.download(
constants.GO_OBO_URL,
os.path.join(constants.GO_DIR, constants.GO_FILE_NAME))
# if not os.path.exists(os.path.join(constants.TCGA_DATA_DIR, 'goa_human.gaf')):
# wget.download(go_obo_url, os.path.join(constants.TCGA_DATA_DIR, 'goa_human.gaf'))
obo_dag = GODag(os.path.join(constants.GO_DIR, constants.GO_FILE_NAME))
assoc = read_ncbi_gene2go(os.path.join(
constants.GO_DIR, constants.GO_ASSOCIATION_FILE_NAME),
no_top=True)
g = GOEnrichmentStudy(
[int(cur) for cur in ensembl2entrez_convertor(total_gene_list)],
assoc,
obo_dag,
methods=["bonferroni", "fdr_bh"])
g_res = g.run_study([
int(cur) for cur in ensembl2entrez_convertor(
gene_expression_top_var_header_rows)
])
GO_results = [(cur.NS, cur.GO, cur.goterm.name, cur.p_uncorrected,
cur.p_fdr_bh) for cur in g_res if cur.p_fdr_bh <= 0.05]
print GO_results
if cluster_algorithm == "kmeans":
for n_clusters in range(start_k, end_k + 1):
clfs_results[n_clusters] = []
centres, km_clf, dist = kmeanssample(X=gene_expression_top_var,
k=n_clusters,
metric="euclidean")
for i in range(n_clusters):
ranks = []
for j in range(n_clusters):
ranks.append(
np.average(
np.delete(gene_expression_top_var,
np.where(km_clf != j)[0],
axis=0)))
ranks = rankdata(ranks)
cluster_labels = np.array(km_clf)
for j in range(n_clusters):
cluster_labels[np.where(km_clf == ranks[j] - 1)] = j
labels_assignment = [cluster_labels + 1]
cluster_indices = np.where(km_clf != i)[0]
gene_expression_cluster = np.delete(
gene_expression_top_var_header_rows,
cluster_indices,
axis=0)
gene_headers_row_cluster = np.delete(
gene_expression_top_var_header_rows,
cluster_indices,
axis=0)
clfs_results[n_clusters].append(
(gene_headers_row_cluster, gene_headers_row_cluster))
desc = "k={} clustering cluster {} has {} genes".format(
n_clusters, i, len(gene_expression_cluster))
gene_list = ",".join(gene_headers_row_cluster)
url = check_enrichment(gene_list)
go_terms = []
uncorrectd_pvals = []
FDRs = []
go_names = []
go_ns = []
if calc_go:
g_res = g.run_study([
int(cur) for cur in ensembl2entrez_convertor(
gene_headers_row_cluster)
])
GO_results = [(cur.NS, cur.GO, cur.goterm.name,
cur.p_uncorrected, cur.p_fdr_bh)
for cur in g_res if cur.p_fdr_bh <= 0.05]
if len(GO_results) > 0:
go_ns, go_terms, go_names, uncorrectd_pvals, FDRs = zip(
*GO_results)
if len(enrichment_lists) != 0:
for j, cur in enumerate(enrichment_lists):
go_terms.append(
enrichment_list_file_names[j].split(".")[0])
uncorrectd_pvals.append(
calc_HG_test(
[x.split(".")[0] for x in tested_gene_list],
[x.split(".")[0] for x in cur], [
x.split(".")[0]
for x in gene_headers_row_cluster
]))
FDRs.append(".")
go_names.append(".")
go_ns.append(".")
output_rows.append((desc, "\r\n".join([
x.split(".")[0] for x in gene_headers_row_cluster
]), url, "\r\n".join(go_ns), "\r\n".join(go_terms),
"\r\n".join(go_names),
"\r\n".join(map(str, uncorrectd_pvals)),
"\r\n".join(map(str, FDRs))))
gene_sorted_heatmap = np.rot90(np.flip(
gene_expression_top_var[cluster_labels.argsort(), :], 1),
k=-1,
axes=(1, 0))
find_clusters(end_k,
gene_sorted_heatmap,
gene_expression_top_var_header_columns,
start_k,
e2g_convertor(gene_expression_top_var_header_rows),
tested_gene_list_file_name,
labels_assignment=labels_assignment_patients)
plot_heatmap(gene_expression_top_var,
gene_expression_top_var_header_columns,
labels_assignment,
gene_expression_top_var_header_rows,
tested_gene_list_file_name,
n_clusters=None,
label_index=None,
phenotype_heatmap=None)
gene_sorted_heatmap = np.rot90(np.flip(gene_expression_top_var, 1),
k=-1,
axes=(1, 0))
if cluster_algorithm == "hierarchical":
df = pd.DataFrame(data=gene_sorted_heatmap,
index=gene_expression_top_var_header_columns,
columns=gene_expression_top_var_header_rows)
# correlations = df.corr()
# correlations_array = np.asarray(df.corr())
#
# row_linkage = hierarchy.linkage(
# distance.pdist(correlations_array), method='average')
#
# col_linkage = hierarchy.linkage(
# distance.pdist(correlations_array.T), method='average')
# enrichment_gene_list = load_gene_list("uvm_mito_part.txt")
dct = dict(zip(np.unique(labels_assignment_patients[0]), "rbg"))
row_colors = map(dct.get, labels_assignment_patients[0])
dct = {1: 'b', 2: 'r'}
gene_expression_top_var_header_rows_trimmed = [
x.split(".")[0] for x in gene_expression_top_var_header_rows
]
# col_colors = map(dct.get, [2 if x in enrichment_gene_list else 1 for x in gene_expression_top_var_header_rows_trimmed])
g = sns.clustermap(df,
row_colors=row_colors,
metric="euclidean",
robust=True,
method="single")
# den_patients = scipy.cluster.hierarchy.dendrogram(g.dendrogram_row.linkage,
# labels=df.index,
# color_threshold=0.60)
den_genes = scipy.cluster.hierarchy.dendrogram(
g.dendrogram_col.linkage, labels=df.columns, color_threshold=0.7)
clusters = get_cluster_classes(den_genes)
g.savefig(
os.path.join(constants.BASE_PROFILE, "output",
"hierarchical_cluster_{}.png".format(time.time())))
for cur_labels_assignment_patient in labels_assignment_patients:
plot_heatmap(gene_sorted_heatmap,
gene_expression_top_var_header_rows,
[cur_labels_assignment_patient],
gene_expression_top_var_header_columns,
tested_gene_list_file_name,
n_clusters=None,
label_index=None,
phenotype_heatmap=None)
print_to_excel(
output_rows=output_rows,
gene_list_file_name=tested_gene_list_file_name.split(".")[0],
gene_expression_file_name=gene_expression_file_name.split(".")[0],
var_th_index=var_th_index)
def patient_sets_distribution_differences(tested_gene_list_file_name, total_gene_list_file_name, gene_expression_file_name, phenotype_file_name, survival_file_name, gene_filter_file_name=None, tested_gene_list_path=None, total_gene_list_path=None, gene_expression_path=None, phenotype_path=None, gene_filter_file_path=None, var_th_index=None, is_unsupervised=True, start_k=2, end_k=2, meta_groups=None, filter_expression=None, clustering_algorithm="euclidean", average_patients=True, compute_hotelling=False):
data = load_integrated_ge_data(tested_gene_list_file_name=tested_gene_list_file_name, total_gene_list_file_name=total_gene_list_file_name, gene_expression_file_name=gene_expression_file_name, phenotype_file_name=phenotype_file_name, survival_file_name=survival_file_name, var_th_index=var_th_index, meta_groups=meta_groups, filter_expression=filter_expression)
if data is None:
print "insufficient data"
return
gene_expression_top_var, gene_expression_top_var_headers_rows, gene_expression_top_var_headers_columns, labels_assignment, survival_dataset = data
for i, cur_groups in enumerate(meta_groups):
labeled_patients = divided_patient_ids_by_label(phenotype_file_name, groups=cur_groups)
ordered_gene_expression = gene_expression_top_var[labels_assignment[i].argsort(), :]
labels_assignment[i].sort()
heatmap_values = gene_expression_top_var
if average_patients:
avgs = None
for cur_label_1 in np.unique(labels_assignment[i]):
avg = np.average(ordered_gene_expression[np.where(labels_assignment[i] == cur_label_1)[0],:], axis=0)
if avgs is None:
avgs = avg.reshape(1,len(avg))
else:
avgs = np.r_[avgs, avg.reshape(1,len(avg))]
heatmap_values=avgs
plot_pca(ordered_gene_expression, [labels_assignment[i]], [meta_groups[i]], tested_gene_list_file_name = tested_gene_list_file_name)
plot_pca_by_samples(ordered_gene_expression, [labels_assignment[i]], [meta_groups[i]], tested_gene_list_file_name = tested_gene_list_file_name)
plot_heatmap(heatmap_values, e2g_convertor(gene_expression_top_var_headers_columns),
[np.unique(labels_assignment[i])],
gene_expression_top_var_headers_rows,
tested_gene_list_file_name, label_index=i)
if compute_hotelling:
with file(os.path.join(constants.BASE_PROFILE,"output", "hotelling_{}_{}_{}.txt".format(constants.CANCER_TYPE, tested_gene_list_file_name.split(".")[0], time.time())),"w+") as f:
output = "\t"
for cur_label_1 in np.unique(labels_assignment[i]):
output+= "group {}\t".format(cur_label_1)
output += "\n"
for cur_label_1 in np.unique(labels_assignment[i]):
output += "group {}\t".format(cur_label_1)
for cur_label_2 in np.unique(labels_assignment[i]):
if cur_label_2 > cur_label_1: continue
cur_label_2_start = np.where(labels_assignment[i]==cur_label_2)[0][0]
cur_label_1_end = len(labels_assignment[i])
if cur_label_1 != labels_assignment[i][-1]:
cur_label_1_end = np.where(labels_assignment[i]==cur_label_1+1)[0][0]
cur_label_2_end = len(labels_assignment[i])
if cur_label_2 != labels_assignment[i][-1]:
cur_label_2_end = np.where(labels_assignment[i] == cur_label_2 + 1)[0][0]
T2 = spm1d.stats.hotellings2(ordered_gene_expression[cur_label_1_start:cur_label_1_end], ordered_gene_expression[cur_label_2_start:cur_label_2_end])
T2i = T2.inference(0.05)
output+="{}\t".format(T2i.p)
# km_curve(labeled_patients, survival_dataset[1:], gene_expression_top_var_headers_rows, tested_gene_list_file_name.split(".")[0],label_index=i)
output+="\n"
f.write(output)
def find_clusters_and_survival(reduced_dim_file_name,
total_gene_list_file_name,
gene_expression_file_name,
phenotype_file_name,
survival_file_name,
gene_filter_file_name=None,
tested_gene_list_path=None,
total_gene_list_path=None,
gene_expression_path=None,
phenotype_path=None,
gene_filter_file_path=None,
var_th_index=None,
is_unsupervised=True,
start_k=2,
end_k=2,
meta_groups=None,
filter_expression=None,
clustering_algorithm="euclidean"):
data = load_integrated_ge_data(
tested_gene_list_file_name=reduced_dim_file_name,
total_gene_list_file_name=total_gene_list_file_name,
gene_expression_file_name=gene_expression_file_name,
gene_expression_path=os.path.join(constants.OUTPUT_GLOBAL_DIR,
gene_expression_file_name),
phenotype_file_name=phenotype_file_name,
survival_file_name=survival_file_name,
var_th_index=var_th_index,
meta_groups=meta_groups,
filter_expression=filter_expression)
if data is None:
print "insufficient data"
return
gene_expression_top_var, gene_expression_top_var_headers_rows, gene_expression_top_var_headers_columns, labels_assignment, survival_dataset = data
tmp = gene_expression_top_var_headers_rows
gene_expression_top_var_headers_rows = gene_expression_top_var_headers_columns
gene_expression_top_var_headers_columns = tmp
gene_expression_top_var = np.rot90(np.flip(gene_expression_top_var, 1),
k=-1,
axes=(1, 0))
# plot_genes_statistic(gene_expression_top_var, gene_expression_top_var_headers_columns, tested_gene_list_file_name)
lr_results_global = []
if is_unsupervised:
clfs_results = find_clusters(
end_k,
gene_expression_top_var,
gene_expression_top_var_headers_rows,
start_k,
e2g_convertor(gene_expression_top_var_headers_columns),
reduced_dim_file_name,
labels_assignment,
clustering_algorithm=clustering_algorithm)
for i in range(start_k, end_k + 1):
lr_results_global.append(
km_curve(clfs_results[i], survival_dataset[1:],
gene_expression_top_var_headers_rows,
reduced_dim_file_name.split(".")[0], i))
# B1 = ['TCGA-V4-A9E7-01A', 'TCGA-V4-A9E8-01A', 'TCGA-V4-A9EE-01A', 'TCGA-V4-A9EF-01A', 'TCGA-V4-A9EI-01A', 'TCGA-V4-A9EJ-01A', 'TCGA-V4-A9EK-01A', 'TCGA-V4-A9EL-01A', 'TCGA-V4-A9EQ-01A', 'TCGA-V4-A9ET-01A', 'TCGA-V4-A9EX-01A', 'TCGA-V4-A9F0-01A', 'TCGA-V4-A9F3-01A', 'TCGA-V4-A9F7-01A', 'TCGA-V4-A9F8-01A', 'TCGA-VD-A8KG-01A', 'TCGA-VD-A8KJ-01A', 'TCGA-VD-A8KL-01A', 'TCGA-VD-A8KM-01A', 'TCGA-VD-A8KN-01A', 'TCGA-VD-AA8M-01A', 'TCGA-VD-AA8N-01A', 'TCGA-VD-AA8S-01B', 'TCGA-WC-A87Y-01A', 'TCGA-WC-A880-01A', 'TCGA-WC-A883-01A', 'TCGA-WC-A884-01A', 'TCGA-WC-A885-01A', 'TCGA-WC-A888-01A', 'TCGA-YZ-A980-01A', 'TCGA-YZ-A982-01A', 'TCGA-YZ-A983-01A']
# B2 = ['TCGA-V4-A9E5-01A', 'TCGA-V4-A9E9-01A', 'TCGA-V4-A9EA-01A', 'TCGA-V4-A9EC-01A', 'TCGA-V4-A9ED-01A', 'TCGA-V4-A9EH-01A', 'TCGA-V4-A9EM-01A', 'TCGA-V4-A9EO-01A', 'TCGA-V4-A9ES-01A', 'TCGA-V4-A9EW-01A', 'TCGA-V4-A9EY-01A', 'TCGA-V4-A9EZ-01A', 'TCGA-V4-A9F1-01A', 'TCGA-V4-A9F2-01A', 'TCGA-V4-A9F4-01A', 'TCGA-VD-A8K7-01B', 'TCGA-VD-A8K9-01A', 'TCGA-VD-A8KA-01B', 'TCGA-VD-A8KB-01A', 'TCGA-VD-A8KE-01A', 'TCGA-VD-A8KH-01A', 'TCGA-VD-A8KK-01A', 'TCGA-VD-A8KO-01A', 'TCGA-VD-AA8P-01A', 'TCGA-VD-AA8R-01A', 'TCGA-VD-AA8T-01A', 'TCGA-WC-A87T-01A', 'TCGA-WC-A87U-01A', 'TCGA-WC-A87W-01A', 'TCGA-WC-A881-01A', 'TCGA-WC-A882-01A', 'TCGA-WC-AA9E-01A', 'TCGA-YZ-A985-01A']
# N = ['TCGA-V4-A9E7-01A', 'TCGA-V4-A9E8-01A', 'TCGA-V4-A9EE-01A', 'TCGA-V4-A9EF-01A', 'TCGA-V4-A9EI-01A', 'TCGA-V4-A9EJ-01A', 'TCGA-V4-A9EK-01A', 'TCGA-V4-A9EL-01A', 'TCGA-V4-A9EQ-01A', 'TCGA-V4-A9ET-01A', 'TCGA-V4-A9EX-01A', 'TCGA-V4-A9F0-01A', 'TCGA-V4-A9F3-01A', 'TCGA-V4-A9F7-01A', 'TCGA-V4-A9F8-01A', 'TCGA-VD-A8KG-01A', 'TCGA-VD-A8KJ-01A', 'TCGA-VD-A8KL-01A', 'TCGA-VD-A8KM-01A', 'TCGA-VD-A8KN-01A', 'TCGA-VD-AA8M-01A', 'TCGA-VD-AA8N-01A', 'TCGA-VD-AA8S-01B', 'TCGA-WC-A87Y-01A', 'TCGA-WC-A880-01A', 'TCGA-WC-A883-01A', 'TCGA-WC-A884-01A', 'TCGA-WC-A885-01A', 'TCGA-WC-A888-01A', 'TCGA-YZ-A980-01A', 'TCGA-YZ-A982-01A', 'TCGA-YZ-A983-01A', 'TCGA-V4-A9E5-01A', 'TCGA-V4-A9E9-01A', 'TCGA-V4-A9EA-01A', 'TCGA-V4-A9EC-01A', 'TCGA-V4-A9ED-01A', 'TCGA-V4-A9EH-01A', 'TCGA-V4-A9EM-01A', 'TCGA-V4-A9EO-01A', 'TCGA-V4-A9ES-01A', 'TCGA-V4-A9EW-01A', 'TCGA-V4-A9EY-01A', 'TCGA-V4-A9EZ-01A', 'TCGA-V4-A9F1-01A', 'TCGA-V4-A9F2-01A', 'TCGA-V4-A9F4-01A', 'TCGA-VD-A8K7-01B', 'TCGA-VD-A8K9-01A', 'TCGA-VD-A8KA-01B', 'TCGA-VD-A8KB-01A', 'TCGA-VD-A8KE-01A', 'TCGA-VD-A8KH-01A', 'TCGA-VD-A8KK-01A', 'TCGA-VD-A8KO-01A', 'TCGA-VD-AA8P-01A', 'TCGA-VD-AA8R-01A', 'TCGA-VD-AA8T-01A', 'TCGA-WC-A87T-01A', 'TCGA-WC-A87U-01A', 'TCGA-WC-A87W-01A', 'TCGA-WC-A881-01A', 'TCGA-WC-A882-01A', 'TCGA-WC-AA9E-01A', 'TCGA-YZ-A985-01A']
# print "Group Low HG:"
# print calc_HG_test(N,B1,clfs_results[i][0])
# print calc_HG_test(N, B1, clfs_results[i][1])
# print "Group High HG:"
# print calc_HG_test(N, B2, clfs_results[i][0])
# print calc_HG_test(N, B2, clfs_results[i][1])
else:
for i, cur_groups in enumerate(meta_groups):
labeled_patients = divided_patient_ids_by_label(
phenotype_file_name, groups=cur_groups)
plot_heatmap(
gene_expression_top_var,
e2g_convertor(gene_expression_top_var_headers_columns),
[labels_assignment[i]] + labels_assignment[:i] +
labels_assignment[i + 1:],
gene_expression_top_var_headers_rows,
reduced_dim_file_name,
label_index=i)
lr_results_global.append(
km_curve(labeled_patients,
survival_dataset[1:],
gene_expression_top_var_headers_rows,
reduced_dim_file_name.split(".")[0],
label_index=i))
return lr_results_global
def predict_ge_by_mutation(tested_gene_list_file_name, total_gene_list_file_name, gene_expression_file_name, phenotype_file_name, survival_file_name, mutation_file_name, gene_filter_file_name=None, tested_gene_list_path=None, total_gene_list_path=None, gene_expression_path=None, phenotype_path=None, gene_filter_file_path=None, var_th_index=None, is_unsupervised=True, start_k=2, end_k=2, meta_groups=None, phenotype_labels_heatmap = None, filter_expression=None, integ=False, min_ratio=0.1 , included_mutation_gene_list=None, excluded_mutation_gene_list=None):
integ_data = load_integrated_mutation_data(
mutation_file_name=mutation_file_name,
phenotype_file_name=phenotype_file_name,
survival_file_name=survival_file_name, var_th_index=var_th_index,
meta_groups=meta_groups, phenotype_labels_heatmap = phenotype_labels_heatmap,
filter_expression=filter_expression)
if integ_data is None:
print "insufficient data"
return
mu_data, mu_data_headers_rows, mu_data_headers_columns, labels_assignment, survival_dataset, phenotype_heatmap = integ_data
all_patients = np.unique(mu_data_headers_rows).flatten()
all_mutated_genes = np.unique(mu_data[:,0]).flatten()
# mis_mutated_genes = np.unique(mu_data[np.where(np.core.defchararray.find(mu_data[1:, 8], "missense")!=-1), 1]).flatten()
all_mutated_vectors = np.zeros((len(all_patients), len(all_mutated_genes)))
# mis_mutated_vectors = np.array([[0 for y in mis_mutated_genes] for x in range(len(all_patients))])
print "build vectors from {} entries".format(len(mu_data))
stopwatch = Stopwatch()
stopwatch.start()
a = list(all_patients)
b = list(all_mutated_genes)
for i, x in enumerate(mu_data):
all_mutated_vectors[a.index(mu_data_headers_rows[i])][b.index(x[0])] += 1
print stopwatch.stop("end mut")
all_mutated_vectors[all_mutated_vectors>5] =5
if included_mutation_gene_list is not None:
included_mutation_gene = load_gene_list(included_mutation_gene_list)
all_mutated_vectors = all_mutated_vectors[:, np.in1d(all_mutated_genes,included_mutation_gene)]
all_mutated_genes = all_mutated_genes[np.in1d(all_mutated_genes,included_mutation_gene)]
if excluded_mutation_gene_list is not None:
excluded_mutation_gene = load_gene_list(excluded_mutation_gene_list)
for cur in excluded_mutation_gene:
all_mutated_vectors = all_mutated_vectors[:,all_mutated_genes!=cur ]
all_mutated_genes = all_mutated_genes[all_mutated_genes!=cur ]
all_mutated_vectors[all_mutated_vectors > 5] = 5
all_mutated_genes = all_mutated_genes[(all_mutated_vectors != 0).sum(axis=0) > np.shape(all_mutated_vectors)[0] * min_ratio]
all_mutated_vectors = all_mutated_vectors[:,(all_mutated_vectors != 0).sum(axis=0) > np.shape(all_mutated_vectors)[0] * min_ratio]
print "all_mutated_vectors after filter sparse: {}".format(np.shape(all_mutated_vectors))
if np.size(all_mutated_genes) == 0:
return
mutation_expression_integ = all_mutated_vectors
mutual_patients = all_patients
mutation_expression_integ_headers_columns = all_mutated_genes
mutual_phenotype_heatmap = phenotype_heatmap
# mutation_expression_integ = zscore(mutation_expression_integ, axis=0)
if integ:
ge_data = load_integrated_ge_data(tested_gene_list_file_name=tested_gene_list_file_name,
total_gene_list_file_name=total_gene_list_file_name,
gene_expression_file_name=gene_expression_file_name,
phenotype_file_name=phenotype_file_name,
survival_file_name=survival_file_name, var_th_index=var_th_index,
meta_groups=meta_groups, filter_expression=filter_expression)
if ge_data is None:
print "insufficient data"
return
gene_expression_top_var, gene_expression_top_var_headers_rows, gene_expression_top_var_headers_columns, _ , survival_dataset = ge_data
all_mutated_vectors = np.nan_to_num(zscore(all_mutated_vectors, axis=0))
gene_expression_top_var = np.nan_to_num(zscore(gene_expression_top_var, axis=0))
mutual_patients = np.array([x for x in all_patients if x in gene_expression_top_var_headers_rows])
mutual_mutations = all_mutated_vectors[np.in1d(all_patients, mutual_patients)]
mutual_mutations = mutual_mutations[mutual_patients.argsort()]
if phenotype_labels_heatmap is not None:
mutual_phenotype_heatmap = phenotype_heatmap[np.in1d(all_patients, mutual_patients)]
mutual_phenotype_heatmap = mutual_phenotype_heatmap[mutual_patients.argsort()]
mutual_patients = np.array([x for x in gene_expression_top_var_headers_rows if x in all_patients])
mutual_expressions = gene_expression_top_var[np.in1d(gene_expression_top_var_headers_rows, mutual_patients)]
mutual_expressions = mutual_expressions[mutual_patients.argsort()]
mutual_patients.sort()
mutation_expression_integ = np.c_[mutual_mutations, mutual_expressions]
mutation_expression_integ_headers_columns = np.r_[all_mutated_genes, gene_expression_top_var_headers_columns]
else:
survival_dataset = np.array(load_survival_data(survival_file_name))
if is_unsupervised:
print "find clusters"
clfs_results = find_clusters(end_k, mutation_expression_integ, mutual_patients,
start_k, mutation_expression_integ_headers_columns,
tested_gene_list_file_name, labels_assignment=labels_assignment, phenotype_heatmap=mutual_phenotype_heatmap)
for cur_k in range(start_k, end_k+1):
km_curve(clfs_results[cur_k], survival_dataset[1:], mutual_patients,
tested_gene_list_file_name.split(".")[0], i)
else:
for i, cur_groups in enumerate(meta_groups):
labeled_patients = divided_patient_ids_by_label(phenotype_file_name, groups=cur_groups)
plot_heatmap(mutation_expression_integ, mutation_expression_integ_headers_columns,
[labels_assignment[i]] + labels_assignment[:i] + labels_assignment[i + 1:],
mutual_patients,
tested_gene_list_file_name, label_index=i)
km_curve(labeled_patients, survival_dataset[1:], mutual_patients, tested_gene_list_file_name.split(".")[0],label_index=i)