comparison data_manager/resource_building.py @ 20:d2af5a5053fd draft

planemo upload commit 8040003119a3d54866ec6ee9b9f659f2af554817-dirty

19:85532a48e4e4

# -*- coding: utf-8 -*-
"""
The purpose of this script is to create source files from different databases to be used in other proteore tools
"""

import os, sys, argparse, requests, time, csv, re, json, zipfile, shutil
from io import BytesIO
from zipfile import ZipFile
from galaxy.util.json import from_json_string, to_json_string

#######################################################################################################

        #delete tmp_BioGRID directory
        os.remove("BioGRID.zip")
        shutil.rmtree("tmp_BioGRID", ignore_errors=True) 

        #download NCBI2Reactome.txt file and build dictionary
        download = requests.get('https://www.reactome.org/download/current/NCBI2Reactome.txt')
        decoded_content = download.content.decode('utf-8')
        tab_file = csv.reader(decoded_content.splitlines(), delimiter='\t')
        dico_nodes = {}
        GeneID_index=0
        pathway_description_index=3
        species_index=5
        for line in tab_file :

        dico['nodes']=dico_nodes

    ##Bioplex
    elif interactome=="bioplex":

        download = requests.get("http://bioplex.hms.harvard.edu/data/BioPlex_interactionList_v4a.tsv")
        decoded_content = download.content.decode('utf-8')
        bioplex = csv.reader(decoded_content.splitlines(), delimiter='\t')
        dico_network = {}
        dico_network["GeneID"]={}
        network_geneid_cols=[0,1,4,5,8]
        dico_network["UniProt-AC"]={}
        network_uniprot_cols=[2,3,4,5,8]

        for line in bioplex :
            dico_network["GeneID"][line[0]]=[line[i] for i in network_geneid_cols]
            dico_network["UniProt-AC"][line[2]]=[line[i] for i in network_uniprot_cols]
            dico_GeneID_to_UniProt[line[0]]=line[2]

        download = requests.get("https://reactome.org/download/current/UniProt2Reactome.txt")
        decoded_content = download.content.decode('utf-8')
        tab_file = csv.reader(decoded_content.splitlines(), delimiter='\t')
        dico_nodes = {}
        uniProt_index=0
        pathway_description_index=3
        species_index=5
        for line in tab_file :

20:d2af5a5053fd

# -*- coding: utf-8 -*-
"""
The purpose of this script is to create source files from different databases to be used in other proteore tools
"""

import os, sys, argparse, requests, time, csv, re, json, shutil
from io import BytesIO
from zipfile import ZipFile
from galaxy.util.json import from_json_string, to_json_string

#######################################################################################################

        #delete tmp_BioGRID directory
        os.remove("BioGRID.zip")
        shutil.rmtree("tmp_BioGRID", ignore_errors=True) 

        #download NCBI2Reactome.txt file and build dictionary
        r = requests.get('https://www.reactome.org/download/current/NCBI2Reactome.txt')
        r.encoding ="utf-8"
        tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
        dico_nodes = {}
        GeneID_index=0
        pathway_description_index=3
        species_index=5
        for line in tab_file :

        dico['nodes']=dico_nodes

    ##Bioplex
    elif interactome=="bioplex":

        r = requests.get("http://bioplex.hms.harvard.edu/data/BioPlex_interactionList_v4a.tsv")
        r.encoding ="utf-8"
        bioplex = csv.reader(r.content.splitlines(), delimiter='\t')
        dico_network = {}
        dico_network["GeneID"]={}
        network_geneid_cols=[0,1,4,5,8]
        dico_network["UniProt-AC"]={}
        network_uniprot_cols=[2,3,4,5,8]

        for line in bioplex :
            dico_network["GeneID"][line[0]]=[line[i] for i in network_geneid_cols]
            dico_network["UniProt-AC"][line[2]]=[line[i] for i in network_uniprot_cols]
            dico_GeneID_to_UniProt[line[0]]=line[2]

        r = requests.get("https://reactome.org/download/current/UniProt2Reactome.txt")
        r.encoding ="utf-8"
        tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
        dico_nodes = {}
        uniProt_index=0
        pathway_description_index=3
        species_index=5
        for line in tab_file :