# -*- coding: utf-8 -*-
"""Constants for Bio2BEL Entrez."""
import os
from bio2bel import get_data_dir
MODULE_NAME = 'ncbigene'
DATA_DIR = get_data_dir(MODULE_NAME)
GENE_INFO_URL = 'ftp://ftp.ncbi.nlm.nih.gov/gene/DATA/gene_info.gz'
GENE2REFSEQ_URL = 'ftp://ftp.ncbi.nlm.nih.gov/gene/DATA/gene2refseq.gz'
GENE_INFO_DATA_PATH = os.path.join(DATA_DIR, 'gene_info.gz')
GENE2REFSEQ_DATA_PATH = os.path.join(DATA_DIR, 'gene2refseq.gz')
GENE2REFSEQ_HUMAN_DATA_PATH = os.path.join(DATA_DIR, 'gene2refseq.human')
GENE2REFSEQ_HUMAN_SLIM_DATA_PATH = os.path.join(DATA_DIR,
'gene2refseq.human.slim')
HOMOLOGENE_DATA_PATH = os.path.join(DATA_DIR, 'homologene.data')
#: Columns fro gene_info.gz that are used
GENE_INFO_COLUMNS = [
'#tax_id',
'GeneID',
'Symbol',
'dbXrefs',
'description',
'type_of_gene',
]
HOMOLOGENE_BUILD_URL = 'ftp://ftp.ncbi.nih.gov/pub/HomoloGene/current/RELEASE_NUMBER'
HOMOLOGENE_URL = 'ftp://ftp.ncbi.nih.gov/pub/HomoloGene/current/homologene.data'
"""This module contains all the constants used in the PathwayForte repo."""
import logging
import os
import time
from bio2bel import get_data_dir
logger = logging.getLogger(__name__)
dir_path = os.path.dirname(os.path.realpath(__file__))
SOURCE = os.path.join(os.path.abspath(os.path.join(dir_path, os.pardir)))
# Data folder where gene sets files are
DATA = os.path.join(os.path.abspath(os.path.join(SOURCE, os.pardir)), 'data')
BIO2BEL_DATA_DIR = get_data_dir('pathwayforte')
"""Cancer Data Sets"""
CANCER_DATA_SETS = {
'brca',
'lihc',
'kirc',
'prad',
'ov',
}
TCGA_DATASETS = os.path.join(DATA, 'tcga_datasets')
# Raw expression matrix from TCGA
EXPRESSION_MATRIX = os.path.join(TCGA_DATASETS, '{}',
'expression_matrix_full.txt')
# File with phenotype classes (e.g., tumor vs normal)
# -*- coding: utf-8 -*-
"""Constants for Bio2BEL ExCAPE-DB."""
import os
from bio2bel import get_data_dir
MODULE = 'excape'
DATA_DIR = get_data_dir(MODULE)
URL = 'https://zenodo.org/record/173258/files/pubchem.chembl.dataset4publication_inchi_smiles.tsv.xz?download=1'
PATH = os.path.join(DATA_DIR,
'pubchem.chembl.dataset4publication_inchi_smiles.tsv.xz')
HEADER = [
'Ambit_InchiKey', #hashkey
'Original_Entry_ID', #source database id
'pXC50', #measurement value (float)
'DB', #source database + version
'InChI', #Structual information
'SMILES', #Same thing
'Entrez_ID', #Identifer from the entrez database for the target
'Tax_ID', #Species
'Gene_Symbol', #pretty name for gene
'Ortholog_Group', #Gene group classifier
'Activity_Flag', #active / not active
'Original_Assay_ID' #Identifier of original assay
]