def load_pheno_list():
"""
Loads a list of phenotypes from multiple files.
"""
result = []
result.extend(util.read_file_lines(PHENO_LIST))
result.extend(util.read_tsv_flat(PHENO_EQ_LIST, delimiter=";"))
result.extend(util.read_file_lines(PHENO_MANUAL))
result.extend(load_pheno_ontology())
'''
full_result = []
for p in result:
p = re.sub(r'\([^)]*\)',' ',p)
full_result.extend(p.split())
result.extend(full_result)
result = list(set(result))
'''
# Filter by blacklist
blacklist = read_blacklist()
return [
pheno.lower() for pheno in result
if pheno.lower() not in blacklist and len(pheno) > 1
]
def load_pheno_list():
"""
Loads a list of phenotypes from multiple files.
"""
result = []
result.extend(util.read_file_lines(PHENO_LIST))
result.extend(util.read_tsv_flat(PHENO_EQ_LIST, delimiter=";"))
result.extend(util.read_file_lines(PHENO_MANUAL))
#result.extend(load_pheno_ontology())
# Filter by blacklist
blacklist = read_blacklist()
return [
pheno.lower() for pheno in result
if pheno.lower() not in blacklist and len(pheno) > 1
]
def load_pheno_list():
"""
Loads a list of phenotypes from multiple files.
"""
result = []
result.extend(util.read_file_lines(PHENO_LIST))
split = []
for r in result:
split.extend(r.split(r'[\.,;]'))
result.extend(split)
result.extend(util.read_tsv_flat(PHENO_EQ_LIST, delimiter=";"))
result.extend(util.read_file_lines(PHENO_MANUAL))
# Filter by blacklist
blacklist = read_blacklist()
#blacklist = [stem_word(b) for b in blacklist]
return [pheno.lower() for pheno in result if pheno.lower() not in blacklist and len(pheno)>1]
def load_gene_list():
"""
Loads a list of genes from the genes dictionary, sans those present in the
gene blacklist.
"""
blacklist = read_blacklist()
gene_blacklist = [item.lower() for item in blacklist]
genes = util.read_tsv_flat(GENE_LIST)
genes_filtered = [
gene.lower() for gene in genes if gene.lower() not in gene_blacklist
]
genes_filtered = [gene for gene in genes_filtered if len(gene) >= 1]
genes_filtered.extend(enumerate_allele_extensions(genes_filtered))
genes_filtered = [
gene.lower() for gene in genes if gene.lower() not in gene_blacklist
]
return genes_filtered