comparison data_manager/resource_building.py @ 7:b8565596bb25 draft default tip

"planemo upload commit 7afd4b3ee25f024257ccbac6e51076d25b2a04e7"

6:8f33a6e6e36c

    output_file = 'nextprot_ref_'+ time.strftime("%d-%m-%Y") + ".tsv"
    path = os.path.join(target_directory,output_file)
    name = "neXtProt release "+time.strftime("%d-%m-%Y")
    release_id = "nextprot_ref_"+time.strftime("%d-%m-%Y")
    
    output = open(path, 'w')
    writer = csv.writer(output,delimiter="\t")
        
    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"]
        iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"]
        chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"]        
        protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level'])

        #put all subcell loc in a set
        if "subcellular-location" in data['entry']["annotationsByCategory"].keys() :
            subcell_locs = data['entry']["annotationsByCategory"]["subcellular-location"]
            all_subcell_locs = set()

            for tm in tm_domains :
                all_tm_domains.add(tm['cvTermName'])
                nb_domains+=1
                #print "nb domains ++"
                #print (nb_domains)
        nextprot_file[:] = [] 
        nextprot_file.append([id,mass_mol,str(seq_length),iso_elec_point,chr_loc,all_subcell_locs,all_diseases,str(nb_domains),protein_existence])
        writer.writerows(nextprot_file)

        id = str(10000000000 - int(time.strftime("%Y%m%d")))

    data_table_entry = dict(id=id, release=release_id, name = name, value = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref")

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

7:b8565596bb25

    output_file = 'nextprot_ref_'+ time.strftime("%d-%m-%Y") + ".tsv"
    path = os.path.join(target_directory,output_file)
    name = "neXtProt release "+time.strftime("%d-%m-%Y")
    release_id = "nextprot_ref_"+time.strftime("%d-%m-%Y")
    
    output = open('test.csv', 'w')
    writer = csv.writer(output,delimiter="\t")
        
    nextprot_file=[["NextprotID","ProteinName","SeqLength","MW","IsoPoint","TMDomains","SubcellLocations","Diseases","Function","PostTranslationalModifications","ProteinFamily","Pathway","ProteinExistence","Chr"]]
    writer.writerows(nextprot_file)
    
    for id in ids :
        query="https://api.nextprot.org/entry/"+id+".json"
        try:
            resp = requests.get(url=query)
        except :
            print ("waiting 15 minutes before trying again")
            time.sleep(900)
            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"]
        iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"]
        chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"]        
        protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level'])
        protein_name = data['entry']["overview"]['proteinNames'][0]['name']

        #get families description
        if 'families' in data['entry']["overview"] and len(data['entry']["overview"]['families']) > 0:
            families = data['entry']["overview"]['families']
            families = [entry['description'] for entry in families]
            protein_family = ";".join(families)
        else: 
            protein_family = 'NA'

        #get Protein function
        if 'function-info' in data['entry']['annotationsByCategory'].keys():
            function_info = data['entry']['annotationsByCategory']['function-info']
            function_info = [entry['description'] for entry in function_info if entry['qualityQualifier'] == 'GOLD']
            function = ';'.join(function_info)
        else : 
            function = 'NA'

        #Get ptm-info
        post_trans_mod = 'NA'
        if 'ptm-info' in data['entry']['annotationsByCategory'].keys():
            ptm_info = data['entry']['annotationsByCategory']['ptm-info']
            infos = [entry['description'] for entry in ptm_info if entry['qualityQualifier'] == 'GOLD']
            post_trans_mod = ";".join(infos)
        
        #Get pathway(s)
        if 'pathway' in data['entry']['annotationsByCategory'].keys():
            pathways = data['entry']['annotationsByCategory']['pathway']
            pathways = [entry['description'] for entry in pathways if entry['qualityQualifier'] == 'GOLD']
            pathway = ";".join(pathways)
        else : 
            pathway = 'NA'

        #put all subcell loc in a set
        if "subcellular-location" in data['entry']["annotationsByCategory"].keys() :
            subcell_locs = data['entry']["annotationsByCategory"]["subcellular-location"]
            all_subcell_locs = set()

            for tm in tm_domains :
                all_tm_domains.add(tm['cvTermName'])
                nb_domains+=1
                #print "nb domains ++"
                #print (nb_domains)

        nextprot_file[:] = [] 
        nextprot_file.append([id,protein_name,str(seq_length),mass_mol,iso_elec_point,str(nb_domains),all_subcell_locs,all_diseases,function,post_trans_mod,protein_family,pathway,protein_existence,chr_loc])
        writer.writerows(nextprot_file)

    id = str(10000000000 - int(time.strftime("%Y%m%d")))

    data_table_entry = dict(id=id, release=release_id, name = name, value = path)
    _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref")

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