def filter_gene_expression_profile(gene_list_file_name,
gene_expression_file_name,
gene_filter_file_name=None,
gene_list_path=None,
gene_expression_path=None,
gene_filter_path=None,
source="GDC-TCGA",
dataset="melanoma",
by_gene=False):
pd = load_phenotype_data("TCGA-SKCM.GDC_phenotype.tsv",
phenotype_list_path=None,
source="GDC-TCGA",
dataset="melanoma")
pd_headers = pd[0]
label_index = [i for i, v in enumerate(pd_headers) if v == LABEL_ID][0]
invalid_labels = [
cur[0] for i, cur in enumerate(pd) if cur[label_index] == METASTATIC
or cur[label_index] == PRIMARY_TUMOR or i == 0
]
gene_list = load_gene_list(gene_list_file_name=gene_list_file_name,
gene_list_path=gene_list_path,
source=source,
dataset=dataset)
if gene_filter_file_name:
filter_gene_list = load_gene_list(
gene_list_file_name=gene_filter_file_name,
gene_list_path=gene_filter_path,
source=source,
dataset=dataset)
gene_list = [
cur for cur in gene_list if cur in filter_gene_list
or cur[:cur.find('.')] in filter_gene_list
]
if gene_expression_path == None:
gene_expression_path = os.path.join(BASE_PROFILE, source, dataset,
gene_expression_file_name)
f = open(gene_expression_path, 'r')
expression_profiles_filtered = [
l for i, l in enumerate(f) if i == 0 or any([
l.strip()[0:l.strip().find('\t')] in gene_list
or l.strip()[0:l.strip().find('\t')].split(".")[0] in gene_list
])
]
f.close()
expression_profiles_filtered_out = []
expression_headers = expression_profiles_filtered[0].split()
for cur in expression_profiles_filtered:
splited = cur.split("\t")
splited = [
cur for i, cur in enumerate(splited)
if expression_headers[i] not in invalid_labels
]
expression_profiles_filtered_out.append("\t".join(splited))
f = open(gene_expression_path + "_filtered", 'w+')
f.writelines(expression_profiles_filtered)
f.close()
def fetch_string_ppi_edges():
go_edges = {}
grid_len = 0
if constants.USE_CACHE:
if os.path.isfile(
os.path.join(constants.DICTIONARIES_DIR,
"GO_edges_ppi_total.txt")):
print "about to load ppi"
GO_edges_ppi_grid = infra.load_phenotype_data(
"GO_edges_ppi_total.txt",
phenotype_list_path=constants.DICTIONARIES_DIR)
grid_len = len(GO_edges_ppi_grid)
print "done load ppi ({} lines). about to load to dict".format(
grid_len)
for cur in GO_edges_ppi_grid:
go_edges[cur[0]] = int(cur[1])
print "done load to dict"
return go_edges
print "fetching ensg"
ensg_dict = get_ensg_dict()
print "fetching ensp"
ensp_dict = get_ensp_dict()
print "fetching string ppi"
string_ppi_dict = get_string_ppi_dict()
go_edges = {}
count = 0
for cur_edge, cur_score in string_ppi_dict.iteritems():
count += 1
print count
vertices = cur_edge.split("=")
if not ensp_dict.has_key(vertices[0]) or not ensp_dict.has_key(
vertices[1]):
continue
go_src = ensp_dict[vertices[0]]["GO Terms"]
go_dst = ensp_dict[vertices[1]]["GO Terms"]
for cur_src in go_src:
for cur_dst in go_dst:
edge = "{}={}".format(cur_src, cur_dst)
edge_alt = "{}={}".format(cur_dst, cur_src)
if go_edges.has_key(edge):
go_edges[edge] += int(cur_score)
elif go_edges.has_key(edge_alt):
go_edges[edge_alt] += int(cur_score)
else:
go_edges[edge] = int(cur_score)
with file(
os.path.join(constants.OUTPUT_GLOBAL_DIR,
"GO_edges_ppi_total.txt"), "w+") as f:
count = 0
for k, v in go_edges.iteritems():
count += 1
print "{}/{}".format(count, grid_len)
f.write("{}\t{}\n".format(k, v))
return go_edges
from infra import load_phenotype_data
from infra import load_gene_expression_profile_by_genes
SEPARATOR = "@%@"
LABEL_ID = "sample_type.samples"
PRIMARY_TUMOR = "Primary Tumor"
METASTATIC = "Metastatic"
pd = load_phenotype_data("TCGA-SKCM.GDC_phenotype.tsv",
phenotype_list_path=None,
source="GDC-TCGA",
dataset="melanoma")
# pd = np.flip(np.rot90(pd, k=1, axes=(1, 0)), 1)
epd = load_gene_expression_profile_by_genes("protein_coding.txt",
"TCGA-SKCM.htseq_counts.tsv",
gene_filter_file_name=None,
gene_list_path=None,
gene_expression_path=None,
gene_filter_path=None,
source="GDC-TCGA",
dataset="melanoma")
pd_headers = pd[0]
label_index = [i for i, v in enumerate(pd_headers) if v == LABEL_ID][0]
pd = sorted(filter(lambda i: i[0] in epd[0], pd),
key=lambda i: epd[0].index(i[0]))
# for i, cur in enumerate(pd):
# print pd[i]
# print epd[0][i]
map = {
if not os.path.exists(association_file_location):
wget.download(constants.GO_ASSOCIATION_GENE2GEO_URL,
os.path.join(constants.GO_DIR, constants.GO_ASSOCIATION_FILE_NAME))
print "Loading gene-GO associations"
# gene2go = download_ncbi_associations(obo_file_location) - why does this line needed?
go2geneids = read_ncbi_gene2go(association_file_location, taxids=[9606], go2geneids=True)
geneids2go = read_ncbi_gene2go(association_file_location, taxids=[9606])
return (go2geneids, geneids2go)
def fetch_string_ppi_edges():
go_edges = {}
if constants.USE_CACHE:
if os.path.isfile(os.path.join(constants.DICTIONARIES_DIR,"GO_edges_ppi_total.txt")):
GO_edges_ppi_grid = infra.load_phenotype_data("GO_edges_ppi_total.txt",phenotype_list_path=constants.DICTIONARIES_DIR)
for cur in GO_edges_ppi_grid:
go_edges[cur[0]] = int(cur[1])
return go_edges
print "fetching ensg"
ensg_dict = get_ensg_dict()
print "fetching ensp"
ensp_dict = get_ensp_dict()
print "fetching string ppi"
string_ppi_dict = get_string_ppi_dict()
go_edges = {}
count = 0
for cur_edge, cur_score in string_ppi_dict.iteritems():
count +=1
print count
