comparison data_manager/resource_building.py @ 6:8f33a6e6e36c draft

"planemo upload commit 4747fc3ca8e24e0f6c0cfcde0992780c6d4ef4ff-dirty"

5:b05fa99ddda2

        return False

#######################################################################################################
# 3. ID mapping file
#######################################################################################################
import ftplib, gzip
csv.field_size_limit(sys.maxsize) # to handle big files

def id_mapping_sources (data_manager_dict, species, target_directory, tool_data_path) :

    human = species == "Human"

    #print ("tab ok")

    #add missing nextprot ID for human or replace old ones
    if human : 
        #build next_dict
        nextprot_path = id_list_from_nextprot_ftp("nextprot_ac_list_all.txt",target_directory)
        with open(nextprot_path,'r') as nextprot_ids :
            nextprot_ids = nextprot_ids.read().splitlines()
        if os.path.exists(os.path.join(archive,nextprot_path.split("/")[-1])) : os.remove(os.path.join(archive,nextprot_path.split("/")[-1]))
        shutil.move(nextprot_path,archive)
        next_dict = {}

    ftp.cwd(ftp_dir)
    ftp.retrbinary("RETR " + file, open(path, 'wb').write)
    ftp.quit()
    return (path)

def id_list_from_nextprot_ftp(file,target_directory) :
    ftp_dir = "pub/current_release/ac_lists/"
    path = os.path.join(target_directory, file)
    ftp = ftplib.FTP("ftp.nextprot.org")
    ftp.login("anonymous", "anonymous") 
    ftp.cwd(ftp_dir)
    ftp.retrbinary("RETR " + file, open(path, 'wb').write)
    ftp.quit()

    return (path)

#return '' if there's no value in a dictionary, avoid error
def access_dictionary (dico,key1,key2) :
    if key1 in dico :
        if key2 in dico[key1] :

        
    nextprot_file=[["NextprotID","MW","SeqLength","IsoPoint","Chr","SubcellLocations","Diseases","TMDomains","ProteinExistence"]]
    writer.writerows(nextprot_file)
    
    for id in ids :
        #print (id)
        query="https://api.nextprot.org/entry/"+id+".json"
        resp = requests.get(url=query)
        data = resp.json()

        #get info from json dictionary
        mass_mol = data["entry"]["isoforms"][0]["massAsString"]
        seq_length = data['entry']["isoforms"][0]["sequenceLength"]

6:8f33a6e6e36c

        return False

#######################################################################################################
# 3. ID mapping file
#######################################################################################################
import ftplib,  gzip
from io import StringIO
csv.field_size_limit(sys.maxsize) # to handle big files

def id_mapping_sources (data_manager_dict, species, target_directory, tool_data_path) :

    human = species == "Human"

    #print ("tab ok")

    #add missing nextprot ID for human or replace old ones
    if human : 
        #build next_dict
        nextprot_path = download_from_nextprot_ftp("nextprot_ac_list_all.txt",target_directory)
        with open(nextprot_path,'r') as nextprot_ids :
            nextprot_ids = nextprot_ids.read().splitlines()
        if os.path.exists(os.path.join(archive,nextprot_path.split("/")[-1])) : os.remove(os.path.join(archive,nextprot_path.split("/")[-1]))
        shutil.move(nextprot_path,archive)
        next_dict = {}

    ftp.cwd(ftp_dir)
    ftp.retrbinary("RETR " + file, open(path, 'wb').write)
    ftp.quit()
    return (path)

def download_from_nextprot_ftp(file,target_directory) :
    ftp_dir = "pub/current_release/ac_lists/"
    path = os.path.join(target_directory, file)
    ftp = ftplib.FTP("ftp.nextprot.org")
    ftp.login("anonymous", "anonymous") 
    ftp.cwd(ftp_dir)
    ftp.retrbinary("RETR " + file, open(path, 'wb').write)
    ftp.quit()
    return (path)

def id_list_from_nextprot_ftp(file,target_directory) :
    ftp_dir = "pub/current_release/ac_lists/"
    path = os.path.join(target_directory, file)
    ftp = ftplib.FTP("ftp.nextprot.org")
    ftp.login("anonymous", "anonymous") 
    ftp.cwd(ftp_dir)
    ftp.retrbinary("RETR " + file, open(path, 'wb').write)
    ftp.quit()
    with open(path,'r') as nextprot_ids :
        nextprot_ids = nextprot_ids.read().splitlines()
    return (nextprot_ids)

#return '' if there's no value in a dictionary, avoid error
def access_dictionary (dico,key1,key2) :
    if key1 in dico :
        if key2 in dico[key1] :

        
    nextprot_file=[["NextprotID","MW","SeqLength","IsoPoint","Chr","SubcellLocations","Diseases","TMDomains","ProteinExistence"]]
    writer.writerows(nextprot_file)
    
    for id in ids :
        query="https://api.nextprot.org/entry/"+id+".json"
        try:
            resp = requests.get(url=query)
        except :
            print ("wainting 1 hour before trying again")
            time.sleep(3600)
            resp = requests.get(url=query)
        data = resp.json()

        #get info from json dictionary
        mass_mol = data["entry"]["isoforms"][0]["massAsString"]
        seq_length = data['entry']["isoforms"][0]["sequenceLength"]