def MPDE_any_significant_annotated(global_variables, out_path, biotype,
pde_IDs):
out_file = open(
os.path.join(out_path, "data",
"genes_significant_in_any_PDEs_annotated.csv"), "w")
master_gene_table = global_variables["master_gene_table"]
# gets the header
header_list = ["ID"]
header_list += get_gene_background_header(global_variables)
header_list += get_gene_mpde_header(pde_IDs)
header_list += get_gene_normexp_header(global_variables)
header_list += get_gene_normexp_stats_header(global_variables)
header_list += get_gene_annotations_header(global_variables)
out_file.write("\t".join(header_list) + "\n")
# gets the genes
for gene_ID in master_gene_table:
gene_dictionary = master_gene_table[gene_ID]
# tests for a valid gene:
valid_gene = False
present_in_any_pde = False
if gene_dictionary["normexp_flag"]:
if (global_variables["GENE_BIOTYPE_FLAG"] and
(gene_dictionary["BIOTYPE"] == biotype
or biotype == "all_genes")
) or global_variables["GENE_BIOTYPE_FLAG"] == False:
valid_gene = True
for pde_ID in pde_IDs:
if pde_ID not in gene_dictionary:
valid_gene = False
else:
pde_Dict = gene_dictionary[pde_ID]
if not pde_Dict["in_gl"]:
valid_gene = False
if pde_Dict["sig"]:
present_in_any_pde = True
if valid_gene and present_in_any_pde:
gene_out_list = [gene_ID]
gene_out_list += get_gene_background(global_variables,
gene_dictionary)
gene_out_list += get_gene_mpde(global_variables, gene_dictionary,
pde_IDs)
gene_out_list += get_gene_normexp(global_variables,
gene_dictionary)
gene_out_list += get_gene_normexp_stats(global_variables,
gene_dictionary)
gene_out_list += get_gene_annotations(global_variables,
gene_dictionary)
out_file.write("\t".join(str(x) for x in gene_out_list) + "\n")
def Mde_all_significant_annotated(global_variables, out_path, biotype, de_IDs):
out_file = open(
os.path.join(out_path, "data",
"genes_significant_in_all_des_annotated.csv"), "w")
master_gene_table = global_variables["master_gene_table"]
# gets the header
header_list = ["ID"]
header_list += get_gene_background_header(global_variables)
header_list += get_gene_mde_header(de_IDs)
header_list += get_gene_ne_header(global_variables)
header_list += get_gene_ne_stats_header(global_variables)
header_list += get_gene_annotations_header(global_variables)
out_file.write("\t".join(header_list) + "\n")
# gets the genes
for gene_ID in master_gene_table:
gene_dictionary = master_gene_table[gene_ID]
# tests for a valid gene:
valid_gene = False
if gene_dictionary["ne_flag"]:
if global_variables["GENE_BIOTYPE_FLAG"] and (
gene_dictionary["BIOTYPE"] == biotype
or biotype == "all_genes"):
valid_gene = True
if global_variables["GENE_BIOTYPE_FLAG"] == False:
valid_gene = True
# determines if the gene is present in all des of the Mde:
for de_ID in de_IDs:
if de_ID not in gene_dictionary:
valid_gene = False
else:
de_Dict = gene_dictionary[de_ID]
if not de_Dict["in_gl"] or not de_Dict["sig"]:
valid_gene = False
if valid_gene:
gene_out_list = [gene_ID]
gene_out_list += get_gene_background(global_variables,
gene_dictionary)
gene_out_list += get_gene_mde(global_variables, gene_dictionary,
de_IDs)
gene_out_list += get_gene_ne(global_variables, gene_dictionary)
gene_out_list += get_gene_ne_stats(global_variables,
gene_dictionary)
gene_out_list += get_gene_annotations(global_variables,
gene_dictionary)
out_file.write("\t".join(str(x) for x in gene_out_list) + "\n")
def PDE_annotated_significant_upregulated(global_variables, out_path, biotype,
pde_ID):
out_file = open(
os.path.join(out_path, "data",
"PDE_annotated_significant_upregulated.csv"), "w")
master_gene_table = global_variables["master_gene_table"]
# gets the header
header_list = ["ID"]
header_list += get_gene_background_header(global_variables)
header_list += get_gene_pde_header(global_variables)
header_list += get_gene_normexp_header(global_variables)
header_list += get_gene_normexp_stats_header(global_variables)
header_list += get_gene_annotations_header(global_variables)
out_file.write("\t".join(header_list) + "\n")
# gets the genes
for gene_ID in master_gene_table:
gene_dictionary = master_gene_table[gene_ID]
# tests for a valid gene:
valid_gene = False
if gene_dictionary["normexp_flag"] and pde_ID in gene_dictionary:
pde_Dict = gene_dictionary[pde_ID]
if pde_Dict["in_gl"] and pde_Dict[
"sig"] and pde_Dict["log2fold"] > 0:
if global_variables["GENE_BIOTYPE_FLAG"] and (
gene_dictionary["BIOTYPE"] == biotype
or biotype == "all_genes"):
valid_gene = True
if global_variables["GENE_BIOTYPE_FLAG"] == False:
valid_gene = True
if valid_gene:
gene_out_list = [gene_ID]
gene_out_list += get_gene_background(global_variables,
gene_dictionary)
gene_out_list += get_gene_pde(global_variables, pde_Dict)
gene_out_list += get_gene_normexp(global_variables,
gene_dictionary)
gene_out_list += get_gene_normexp_stats(global_variables,
gene_dictionary)
gene_out_list += get_gene_annotations(global_variables,
gene_dictionary)
out_file.write("\t".join(str(x) for x in gene_out_list) + "\n")
def normexp_matrix_annotated(global_variables, out_path, biotype):
out_file = open(
os.path.join(out_path, "data", "normexp_matrix_annotated.csv"), "w")
master_gene_table = global_variables["master_gene_table"]
# gets the header
header_list = ["ID"]
header_list += get_gene_background_header(global_variables)
header_list += get_gene_normexp_header(global_variables)
header_list += get_gene_normexp_stats_header(global_variables)
header_list += get_gene_annotations_header(global_variables)
out_file.write("\t".join(header_list) + "\n")
# gets the gene expression
for gene_ID in master_gene_table:
gene_dictionary = master_gene_table[gene_ID]
# tests for a valid gene:
valid_gene = False
if gene_dictionary["normexp_flag"]:
if global_variables["GENE_BIOTYPE_FLAG"] and (
gene_dictionary["BIOTYPE"] == biotype
or biotype == "all_genes"):
valid_gene = True
if global_variables["GENE_BIOTYPE_FLAG"] == False:
valid_gene = True
if valid_gene:
gene_out_list = [gene_ID]
gene_out_list += get_gene_background(global_variables,
gene_dictionary)
gene_out_list += get_gene_normexp(global_variables,
gene_dictionary)
gene_out_list += get_gene_normexp_stats(global_variables,
gene_dictionary)
gene_out_list += get_gene_annotations(global_variables,
gene_dictionary)
out_file.write("\t".join(str(x) for x in gene_out_list) + "\n")