comparison data_manager/resource_building.py @ 34:0c0586ac3e29 draft

planemo upload commit c89c5deac442c0c2aa52b24f2c5af4b290773fc0-dirty

33:cdeffb3670c3

#######################################################################################################
def peptide_atlas_sources(data_manager_dict, tissue, target_directory):
    # Define organism_id (here Human) - to be upraded when other organism added to the project
    organism_id = "2"
    # 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"

    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)
    _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_peptide_atlas")

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

34:0c0586ac3e29

#######################################################################################################
def peptide_atlas_sources(data_manager_dict, tissue, target_directory):
    # Define organism_id (here Human) - to be upraded when other organism added to the project
    organism_id = "2"
    # Extract sample_category_id and output filename
    tissue=tissue.split(".")
    sample_category_id = tissue[0]
    tissue_name = tissue[1]
    output_file = tissue_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"

    uni_dict = build_dictionary(cr)

    #columns of data table peptide_atlas
    date = time.strftime("%d-%m-%Y")
    tissue_id = tissue_name+"_"+date
    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=name, value = path, tissue = tissue_name)
    _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_peptide_atlas")

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