comparison data_manager/resource_building.py @ 10:2f153b41b6fe draft

planemo upload commit e5e768b479ddc6b36270a1b5b0443a4c80d693bc-dirty

9:6c47b77d89d6

"""
The purpose of this script is to create source files from different databases to be used in other tools
"""

import os, sys, argparse, requests, time, csv, re
from io import BytesIO
from zipfile import ZipFile

        tissue_name = "HPA pathology"
        url = "https://www.proteinatlas.org/download/pathology.tsv.zip"
    elif tissue == "HPA_full_atlas":
        tissue_name = "HPA full atlas"
        url = "https://www.proteinatlas.org/download/proteinatlas.tsv.zip"
    output_file = tissue +"_"+ time.strftime("%d-%m-%Y") + ".tsv"
    path = os.path.join(target_directory, output_file)
    unzip(url, path)
    print(str(os.path.isfile(path)))
    tmp=open(path,"r").readlines()
    tissue_name = tissue_name + " " + time.strftime("%d/%m/%Y")
    data_table_entry = dict(value = tissue, name = tissue_name, path = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "protein_atlas")


#######################################################################################################
# 2. Peptide Atlas

    cr = csv.reader(decoded_content.splitlines(), delimiter='\t')

    #build dictionary by only keeping uniprot accession (not isoform) as key and sum of observations as value
    uni_dict = build_dictionary(cr)

    tissue_id = "_".join([atlas_build_id, organism_id, sample_category_id,time.strftime("%d-%m-%Y")])
    tissue_value = tissue.split("-")[1]
    tissue = tissue.split("-")[1] + "_" +time.strftime("%d-%m-%Y")
    tissue_name = " ".join(tissue_value.split("_")) + " " + time.strftime("%d/%m/%Y")
    path = os.path.join(target_directory,output_file)

    with open(path,"wb") as out :
        w = csv.writer(out,delimiter='\t')
        w.writerow(["Uniprot_AC","nb_obs"])
        w.writerows(uni_dict.items())
        
    data_table_entry = dict(value = path, name = tissue_name, tissue = tissue)
    _add_data_table_entry(data_manager_dict, data_table_entry, "peptide_atlas")

#function to count the number of observations by uniprot id
def build_dictionary (csv) :
    uni_dict = {} 

    with open(path,"w") as out :
        w = csv.writer(out,delimiter='\t')
        w.writerows(tab)

    name_dict={"human" : "Homo sapiens", "mouse" : "Mus musculus", "rat" : "Rattus norvegicus"}
    name = name_dict[species]+" ("+time.strftime("%d-%m-%Y")+")"

    data_table_entry = dict(value = species+"_id_mapping_"+ time.strftime("%d-%m-%Y"), name = name, path = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "id_mapping")

def download_from_uniprot_ftp(file,target_directory) :
    ftp_dir = "pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/"
    path = os.path.join(target_directory, file)

10:2f153b41b6fe

"""
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
from io import BytesIO
from zipfile import ZipFile

        tissue_name = "HPA pathology"
        url = "https://www.proteinatlas.org/download/pathology.tsv.zip"
    elif tissue == "HPA_full_atlas":
        tissue_name = "HPA full atlas"
        url = "https://www.proteinatlas.org/download/proteinatlas.tsv.zip"
    
    output_file = tissue +"_"+ time.strftime("%d-%m-%Y") + ".tsv"
    path = os.path.join(target_directory, output_file)
    unzip(url, path)    #download and save file
    tissue_name = tissue_name + " " + time.strftime("%d/%m/%Y")
    tissue_id = tissue_name.replace(" ","_").replace("/","-")

    data_table_entry = dict(id=tissue_id, name = tissue_name, value = tissue, path = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "protein_atlas")


#######################################################################################################
# 2. Peptide Atlas

    cr = csv.reader(decoded_content.splitlines(), delimiter='\t')

    #build dictionary by only keeping uniprot accession (not isoform) as key and sum of observations as value
    uni_dict = build_dictionary(cr)

    #columns of data table peptide_atlas
    date = time.strftime("%d-%m-%Y")
    tissue = tissue.split("-")[1]
    tissue_id = tissue+"_"+date
    tissue_name = tissue_id.replace("-","/").replace("_"," ")
    path = os.path.join(target_directory,output_file)

    with open(path,"wb") as out :
        w = csv.writer(out,delimiter='\t')
        w.writerow(["Uniprot_AC","nb_obs"])
        w.writerows(uni_dict.items())
        
    data_table_entry = dict(id=tissue_id, name=tissue_name, value = path, tissue = tissue)
    _add_data_table_entry(data_manager_dict, data_table_entry, "peptide_atlas")

#function to count the number of observations by uniprot id
def build_dictionary (csv) :
    uni_dict = {} 

    with open(path,"w") as out :
        w = csv.writer(out,delimiter='\t')
        w.writerows(tab)

    name_dict={"human" : "Homo sapiens", "mouse" : "Mus musculus", "rat" : "Rattus norvegicus"}
    name = name_dict[species]+" "+time.strftime("%d/%m/%Y")
    id = species+"_id_mapping_"+ time.strftime("%d-%m-%Y")

    data_table_entry = dict(id=id, name = name, value = species, path = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "id_mapping")

def download_from_uniprot_ftp(file,target_directory) :
    ftp_dir = "pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/"
    path = os.path.join(target_directory, file)