def __get_consensus_from_files(self, folder_consensus: str):
for sc in self.__scoring_schemes:
self.__consensus[sc] = []
for dataset in self._datasets:
self.__consensus[sc].append(
(dataset, Consensus.get_consensus_from_file(
join_paths(folder_consensus, str(sc.b5), name_file(dataset.name)))))
def __init__(self, dataset_folder: str, dataset_selector: DatasetSelector = None):
super().__init__(dataset_folder, dataset_selector)
self._orphanetParser = OrphanetParser.get_orpha_base_for_vldb(join_paths(get_parent_path(
get_parent_path(dataset_folder)),
"supplementary_data"))
self._datasets_gs = {}
self._remove_datasets_empty_goldstandard()
def __init__(self,
dataset_folder: str,
scoring_schemes: List[ScoringScheme],
top_k_to_test: List[int],
algo: MedianRanking = get_algorithm(Algorithm.ParCons, parameters={"bound_for_exact": 150}),
dataset_selector: DatasetSelector = None,
):
super().__init__(dataset_folder=dataset_folder, dataset_selector=dataset_selector)
self.__orphanetParser = OrphanetParser.get_orpha_base_for_vldb(join_paths(get_parent_path(
get_parent_path(dataset_folder)),
"supplementary_data"))
self.__algo = algo
self.__remove_useless_datasets()
self.__scoring_schemes = []
self.__consensus = {}
self.__scoring_schemes = scoring_schemes
self.__top_k_to_test = top_k_to_test
from corankco.experiments.orphanet_parser import OrphanetParser
from corankco.experiments.geneNcbiParser import GeneNcbiParser
from corankco.utils import join_paths
folder_input = input("folder path containing data NCBI and orphanet ?")
orphaParser = OrphanetParser(join_paths(folder_input, "en_product6.xml"))
geneNcbiParser = GeneNcbiParser(join_paths(folder_input, "dataGeneNCBI.txt"))
res = {}
cpt = 0
# print(str(geneNcbiParser.get_gene(285362)))
for geneOrpha in orphaParser.get_genes():
cpt += 1
res[geneOrpha] = []
for geneNCBI in geneNcbiParser.get_genes():
sim, nb_db_common = geneOrpha.similarity(geneNCBI)
if sim > 0:
res[geneOrpha].append((geneNCBI, sim, nb_db_common))
if len(res[geneOrpha]) > 1:
if geneOrpha.has_same_name(res[geneOrpha][0][0]):
if not geneOrpha.has_same_name(res[geneOrpha][1][0]):
res[geneOrpha] = [res[geneOrpha][0]]
elif geneOrpha.has_same_name(res[geneOrpha][1][0]):
res[geneOrpha] = [res[geneOrpha][1]]
mapping_final = open(folder_input + "mapping_genes_geneNCBI_orphanet.csv", "w")
for geneOrpha, mapping_ncbi in res.items():
ncbi_associated = res[geneOrpha][0][0]
def get_orpha_base_for_vldb(folder_data_files: str):
path_orphanet_base = join_paths(folder_data_files, "en_product6.xml")
path_mapping_ncbi = join_paths(folder_data_files, "mapping_genes_geneNCBI_orphanet.csv")
path_mapping_diseases = join_paths(folder_data_files, "mappingDiseaseID.csv")
return OrphanetParser.get_orpha_base(path_orphanet_base, path_mapping_ncbi, path_mapping_diseases)