comparison data_manager/resource_building.py @ 30:b8271b9a1049 draft

planemo upload commit c89c5deac442c0c2aa52b24f2c5af4b290773fc0-dirty

29:871a7347ca24

    # Extract sample_category_id and output filename
    tissue=tissue.split(".")
    sample_category_id = tissue[0]
    name = tissue[1]
    output_file = name+"_"+time.strftime("%d-%m-%Y") + ".tsv"
    query="https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetProteins?&atlas_build_id="+sample_category_id+ \
        "&display_options=ShowAbundances&organism_id="+organism_id+"&redundancy_constraint=4&presence_level_constraint=1%2C2"+ \ 
        "&gene_annotation_level_constraint=leaf&QUERY_NAME=AT_GetProteins&action=QUERY&output_mode=tsv&apply_action=QUERY"
    download = requests.get(query)
    decoded_content = download.content.decode('utf-8')
    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)

#function to count the number of observations by uniprot id
def build_dictionary (csv) :
    uni_dict = {} 
    for line in csv :
        if "-" not in line[2] and check_uniprot_access(line[2]) :
            if line[2] in uni_dict :
                uni_dict[line[2]] += int(line[4])
            else : 
                uni_dict[line[2]] = int(line[4])

    return uni_dict

#function to check if an id is an uniprot accession number : return True or False-
def check_uniprot_access (id) :
    uniprot_pattern = re.compile("[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
    if uniprot_pattern.match(id) :
        return True
    else :
        return False



#######################################################################################################
# 3. ID mapping file
#######################################################################################################
import ftplib, gzip

30:b8271b9a1049

    # Extract sample_category_id and output filename
    tissue=tissue.split(".")
    sample_category_id = tissue[0]
    name = tissue[1]
    output_file = name+"_"+time.strftime("%d-%m-%Y") + ".tsv"

    query="https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetProteins?&atlas_build_id="+ \
    sample_category_id+"&display_options=ShowAbundances&organism_id="+organism_id+ \
    "&redundancy_constraint=4&presence_level_constraint=1%2C2&gene_annotation_level_constraint=leaf\
    &QUERY_NAME=AT_GetProteins&action=QUERY&output_mode=tsv&apply_action=QUERY"

    print (query)

    with requests.Session() as s:
        download = s.get(query)
        decoded_content = download.content.decode('utf-8')
        cr = csv.reader(decoded_content.splitlines(), delimiter='\t')
        #cr = list(cr)

    uni_dict = build_dictionary(cr)

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

    with open(path,"w") 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)

#function to count the number of observations by uniprot id
def build_dictionary (csv) :
    uni_dict = {} 
    for line in csv :
        if "-" not in line[0] and check_uniprot_access(line[0]) :
            if line[0] in uni_dict :
                uni_dict[line[0]] += int(line[5])
            else : 
                uni_dict[line[0]] = int(line[5])

    return uni_dict

#function to check if an id is an uniprot accession number : return True or False-
def check_uniprot_access (id) :
    uniprot_pattern = re.compile("[OPQ][0-9][A-Z0-9]{3}[0-9]|[A-NR-Z][0-9]([A-Z][A-Z0-9]{2}[0-9]){1,2}")
    if uniprot_pattern.match(id) :
        return True
    else :
        return False

#######################################################################################################
# 3. ID mapping file
#######################################################################################################
import ftplib, gzip