Mercurial > repos > dchristiany > data_manager_proteore

comparison data_manager/resource_building.py @ 29:871a7347ca24 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit c89c5deac442c0c2aa52b24f2c5af4b290773fc0-dirty
author dchristiany
date Mon, 28 Jan 2019 05:16:55 -0500
parents d235909789ca
children b8271b9a1049
comparison
equal deleted inserted replaced
28:d235909789ca 29:871a7347ca24
58 58
59 ####################################################################################################### 59 #######################################################################################################
60 # 2. Peptide Atlas 60 # 2. Peptide Atlas
61 ####################################################################################################### 61 #######################################################################################################
62 def peptide_atlas_sources(data_manager_dict, tissue, target_directory): 62 def peptide_atlas_sources(data_manager_dict, tissue, target_directory):
63 # Define PA Human build released number (here early 2018)
64 atlas_build_id = "472"
65 # Define organism_id (here Human) - to be upraded when other organism added to the project 63 # Define organism_id (here Human) - to be upraded when other organism added to the project
66 organism_id = "2" 64 organism_id = "2"
67 # Extract sample_category_id and output filename 65 # Extract sample_category_id and output filename
68 sample_category_id = tissue.split("-")[0] 66 tissue=tissue.split(".")
69 output_file = tissue.split("-")[1] +"_"+ time.strftime("%d-%m-%Y") + ".tsv" 67 sample_category_id = tissue[0]
70 query = "https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetPeptides?atlas_build_id=" + \ 68 name = tissue[1]
71 atlas_build_id + "&display_options=ShowMappings&organism_id= " + \ 69 output_file = name+"_"+time.strftime("%d-%m-%Y") + ".tsv"
72 organism_id + "&sample_category_id=" + sample_category_id + \ 70 query="https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetProteins?&atlas_build_id="+sample_category_id+ \
73 "&QUERY_NAME=AT_GetPeptides&output_mode=tsv&apply_action=QUERY" 71 "&display_options=ShowAbundances&organism_id="+organism_id+"&redundancy_constraint=4&presence_level_constraint=1%2C2"+ \
72 "&gene_annotation_level_constraint=leaf&QUERY_NAME=AT_GetProteins&action=QUERY&output_mode=tsv&apply_action=QUERY"
74 download = requests.get(query) 73 download = requests.get(query)
75 decoded_content = download.content.decode('utf-8') 74 decoded_content = download.content.decode('utf-8')
76 cr = csv.reader(decoded_content.splitlines(), delimiter='\t') 75 cr = csv.reader(decoded_content.splitlines(), delimiter='\t')
77 76
78 #build dictionary by only keeping uniprot accession (not isoform) as key and sum of observations as value 77 #build dictionary by only keeping uniprot accession (not isoform) as key and sum of observations as value