Mercurial > repos > proteore > proteore_data_manager

annotate data_manager/resource_building.py @ 0:9e31ea9fc7ea draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
author proteore
date Wed, 13 Mar 2019 06:30:42 -0400
parents
children f3507260b30f
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
1 # -*- coding: utf-8 -*-
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
2 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
3 The purpose of this script is to create source files from different databases to be used in other proteore tools
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
4 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
5
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
6 import os, sys, argparse, requests, time, csv, re, json, shutil, zipfile
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
7 from io import BytesIO
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
8 from zipfile import ZipFile
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
9 from galaxy.util.json import from_json_string, to_json_string
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
10
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
11 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
12 # General functions
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
13 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
14 def unzip(url, output_file):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
15 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
16 Get a zip file content from a link and unzip
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
17 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
18 content = requests.get(url)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
19 zipfile = ZipFile(BytesIO(content.content))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
20 output_content = ""
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
21 output_content += zipfile.open(zipfile.namelist()[0]).read()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
22 output = open(output_file, "w")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
23 output.write(output_content)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
24 output.close()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
25
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
26 def _add_data_table_entry(data_manager_dict, data_table_entry,data_table):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
27 data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
28 data_manager_dict['data_tables'][data_table] = data_manager_dict['data_tables'].get(data_table, [])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
29 data_manager_dict['data_tables'][data_table].append(data_table_entry)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
30 return data_manager_dict
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
31
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
32 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
33 # 1. Human Protein Atlas
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
34 # - Normal tissue
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
35 # - Pathology
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
36 # - Full Atlas
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
37 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
38 def HPA_sources(data_manager_dict, tissue, target_directory):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
39 if tissue == "HPA_normal_tissue":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
40 tissue_name = "HPA normal tissue"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
41 url = "https://www.proteinatlas.org/download/normal_tissue.tsv.zip"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
42 table = "proteore_protein_atlas_normal_tissue"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
43 elif tissue == "HPA_pathology":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
44 tissue_name = "HPA pathology"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
45 url = "https://www.proteinatlas.org/download/pathology.tsv.zip"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
46 table = "proteore_protein_atlas_tumor_tissue"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
47 elif tissue == "HPA_full_atlas":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
48 tissue_name = "HPA full atlas"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
49 url = "https://www.proteinatlas.org/download/proteinatlas.tsv.zip"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
50 table = "proteore_protein_full_atlas"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
51
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
52 output_file = tissue +"_"+ time.strftime("%d-%m-%Y") + ".tsv"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
53 path = os.path.join(target_directory, output_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
54 unzip(url, path) #download and save file
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
55 tissue_name = tissue_name + " " + time.strftime("%d/%m/%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
56 tissue_id = tissue_name.replace(" ","_").replace("/","-")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
57
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
58
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
59 data_table_entry = dict(id=tissue_id, name = tissue_name, tissue = tissue, value = path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
60 _add_data_table_entry(data_manager_dict, data_table_entry, table)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
61
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
62
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
63 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
64 # 2. Peptide Atlas
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
65 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
66 def peptide_atlas_sources(data_manager_dict, tissue, date, target_directory):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
67 # Define organism_id (here Human) - to be upraded when other organism added to the project
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
68 organism_id = "2"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
69 # Extract sample_category_id and output filename
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
70 tissue=tissue.split(".")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
71 sample_category_id = tissue[0]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
72 tissue_name = tissue[1]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
73 output_file = tissue_name+"_"+date + ".tsv"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
74
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
75 query="https://db.systemsbiology.net/sbeams/cgi/PeptideAtlas/GetProteins?&atlas_build_id="+ \
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
76 sample_category_id+"&display_options=ShowAbundances&organism_id="+organism_id+ \
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
77 "&redundancy_constraint=4&presence_level_constraint=1%2C2&gene_annotation_level_constraint=leaf\
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
78 &QUERY_NAME=AT_GetProteins&action=QUERY&output_mode=tsv&apply_action=QUERY"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
79
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
80 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
81 download = s.get(query)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
82 decoded_content = download.content.decode('utf-8')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
83 cr = csv.reader(decoded_content.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
84
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
85 uni_dict = build_dictionary(cr)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
86
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
87 #columns of data table peptide_atlas
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
88 tissue_id = tissue_name+"_"+date
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
89 name = tissue_id.replace("-","/").replace("_"," ")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
90 path = os.path.join(target_directory,output_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
91
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
92 with open(path,"w") as out :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
93 w = csv.writer(out,delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
94 w.writerow(["Uniprot_AC","nb_obs"])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
95 w.writerows(uni_dict.items())
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
96
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
97 data_table_entry = dict(id=tissue_id, name=name, value = path, tissue = tissue_name)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
98 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_peptide_atlas")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
99
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
100 #function to count the number of observations by uniprot id
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
101 def build_dictionary (csv) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
102 uni_dict = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
103 for line in csv :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
104 if "-" not in line[0] and check_uniprot_access(line[0]) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
105 if line[0] in uni_dict :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
106 uni_dict[line[0]] += int(line[5])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
107 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
108 uni_dict[line[0]] = int(line[5])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
109
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
110 return uni_dict
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
111
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
112 #function to check if an id is an uniprot accession number : return True or False-
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
113 def check_uniprot_access (id) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
114 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}")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
115 if uniprot_pattern.match(id) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
116 return True
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
117 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
118 return False
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
119
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
120 def check_entrez_geneid (id) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
121 entrez_pattern = re.compile("[0-9]+|[A-Z]{1,2}_[0-9]+|[A-Z]{1,2}_[A-Z]{1,4}[0-9]+")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
122 if entrez_pattern.match(id) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
123 return True
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
124 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
125 return False
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
126
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
127 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
128 # 3. ID mapping file
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
129 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
130 import ftplib, gzip
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
131 csv.field_size_limit(sys.maxsize) # to handle big files
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
132
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
133 def id_mapping_sources (data_manager_dict, species, target_directory) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
134
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
135 human = species == "Human"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
136 species_dict = { "Human" : "HUMAN_9606", "Mouse" : "MOUSE_10090", "Rat" : "RAT_10116" }
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
137 files=["idmapping_selected.tab.gz","idmapping.dat.gz"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
138
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
139 #header
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
140 if human : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","neXtProt","BioGrid","STRING","KEGG"]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
141 else : tab = [["UniProt-AC","UniProt-ID","GeneID","RefSeq","GI","PDB","GO","PIR","MIM","UniGene","Ensembl_Gene","Ensembl_Transcript","Ensembl_Protein","BioGrid","STRING","KEGG"]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
142
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
143 #print("header ok")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
144
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
145 #get selected.tab and keep only ids of interest
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
146 selected_tab_file=species_dict[species]+"_"+files[0]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
147 tab_path = download_from_uniprot_ftp(selected_tab_file,target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
148 with gzip.open(tab_path,"rt") as select :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
149 tab_reader = csv.reader(select,delimiter="\t")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
150 for line in tab_reader :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
151 tab.append([line[i] for i in [0,1,2,3,4,5,6,11,13,14,18,19,20]])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
152 os.remove(tab_path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
153
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
154 #print("selected_tab ok")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
155
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
156 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
157 Supplementary ID to get from HUMAN_9606_idmapping.dat :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
158 -NextProt,BioGrid,STRING,KEGG
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
159 """
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
160
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
161 #there's more id type for human
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
162 if human : ids = ['neXtProt','BioGrid','STRING','KEGG' ] #ids to get from dat_file
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
163 else : ids = ['BioGrid','STRING','KEGG' ]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
164 unidict = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
165
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
166 #keep only ids of interest in dictionaries
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
167 dat_file=species_dict[species]+"_"+files[1]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
168 dat_path = download_from_uniprot_ftp(dat_file,target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
169 with gzip.open(dat_path,"rt") as dat :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
170 dat_reader = csv.reader(dat,delimiter="\t")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
171 for line in dat_reader :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
172 uniprotID=line[0] #UniProtID as key
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
173 id_type=line[1] #ID type of corresponding id, key of sub-dictionnary
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
174 cor_id=line[2] #corresponding id
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
175 if "-" not in id_type : #we don't keep isoform
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
176 if id_type in ids and uniprotID in unidict :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
177 if id_type in unidict[uniprotID] :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
178 unidict[uniprotID][id_type]= ";".join([unidict[uniprotID][id_type],cor_id]) #if there is already a value in the dictionnary
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
179 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
180 unidict[uniprotID].update({ id_type : cor_id })
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
181 elif id_type in ids :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
182 unidict[uniprotID]={id_type : cor_id}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
183 os.remove(dat_path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
184
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
185 #print("dat_file ok")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
186
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
187 #add ids from idmapping.dat to the final tab
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
188 for line in tab[1:] :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
189 uniprotID=line[0]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
190 if human :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
191 if uniprotID in unidict :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
192 nextprot = access_dictionary(unidict,uniprotID,'neXtProt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
193 if nextprot != '' : nextprot = clean_nextprot_id(nextprot,line[0])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
194 line.extend([nextprot,access_dictionary(unidict,uniprotID,'BioGrid'),access_dictionary(unidict,uniprotID,'STRING'),
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
195 access_dictionary(unidict,uniprotID,'KEGG')])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
196 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
197 line.extend(["","","",""])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
198 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
199 if uniprotID in unidict :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
200 line.extend([access_dictionary(unidict,uniprotID,'BioGrid'),access_dictionary(unidict,uniprotID,'STRING'),
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
201 access_dictionary(unidict,uniprotID,'KEGG')])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
202 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
203 line.extend(["","",""])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
204
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
205 #print ("tab ok")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
206
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
207 #add missing nextprot ID for human
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
208 if human :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
209 #build next_dict
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
210 nextprot_ids = id_list_from_nextprot_ftp("nextprot_ac_list_all.txt",target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
211 next_dict = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
212 for nextid in nextprot_ids :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
213 next_dict[nextid.replace("NX_","")] = nextid
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
214 os.remove(os.path.join(target_directory,"nextprot_ac_list_all.txt"))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
215
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
216 #add missing nextprot ID
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
217 for line in tab[1:] :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
218 uniprotID=line[0]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
219 nextprotID=line[13]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
220 if nextprotID == '' and uniprotID in next_dict :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
221 line[13]=next_dict[uniprotID]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
222
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
223 output_file = species+"_id_mapping_"+ time.strftime("%d-%m-%Y") + ".tsv"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
224 path = os.path.join(target_directory,output_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
225
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
226 with open(path,"w") as out :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
227 w = csv.writer(out,delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
228 w.writerows(tab)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
229
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
230 name_dict={"Human" : "Homo sapiens", "Mouse" : "Mus musculus", "Rat" : "Rattus norvegicus"}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
231 name = species +" (" + name_dict[species]+" "+time.strftime("%d/%m/%Y")+")"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
232 id = species+"_id_mapping_"+ time.strftime("%d-%m-%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
233
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
234 data_table_entry = dict(id=id, name = name, species = species, value = path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
235 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_id_mapping_"+species)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
236
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
237 def download_from_uniprot_ftp(file,target_directory) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
238 ftp_dir = "pub/databases/uniprot/current_release/knowledgebase/idmapping/by_organism/"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
239 path = os.path.join(target_directory, file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
240 ftp = ftplib.FTP("ftp.uniprot.org")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
241 ftp.login("anonymous", "anonymous")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
242 ftp.cwd(ftp_dir)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
243 ftp.retrbinary("RETR " + file, open(path, 'wb').write)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
244 ftp.quit()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
245 return (path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
246
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
247 def id_list_from_nextprot_ftp(file,target_directory) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
248 ftp_dir = "pub/current_release/ac_lists/"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
249 path = os.path.join(target_directory, file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
250 ftp = ftplib.FTP("ftp.nextprot.org")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
251 ftp.login("anonymous", "anonymous")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
252 ftp.cwd(ftp_dir)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
253 ftp.retrbinary("RETR " + file, open(path, 'wb').write)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
254 ftp.quit()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
255 with open(path,'r') as nextprot_ids :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
256 nextprot_ids = nextprot_ids.read().splitlines()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
257 return (nextprot_ids)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
258
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
259 #return '' if there's no value in a dictionary, avoid error
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
260 def access_dictionary (dico,key1,key2) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
261 if key1 in dico :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
262 if key2 in dico[key1] :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
263 return (dico[key1][key2])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
264 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
265 return ("")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
266 #print (key2,"not in ",dico,"[",key1,"]")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
267 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
268 return ('')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
269
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
270 #if there are several nextprot ID for one uniprotID, return the uniprot like ID
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
271 def clean_nextprot_id (next_id,uniprotAc) :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
272 if len(next_id.split(";")) > 1 :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
273 tmp = next_id.split(";")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
274 if "NX_"+uniprotAc in tmp :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
275 return ("NX_"+uniprotAc)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
276 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
277 return (tmp[1])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
278 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
279 return (next_id)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
280
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
281
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
282 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
283 # 4. Build protein interaction maps files
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
284 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
285
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
286 def get_interactant_name(line,dico):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
287
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
288 if line[0] in dico :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
289 interactant_A = dico[line[0]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
290 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
291 interactant_A = "NA"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
292
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
293 if line[1] in dico :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
294 interactant_B = dico[line[1]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
295 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
296 interactant_B = "NA"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
297
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
298 return interactant_A, interactant_B
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
299
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
300 def PPI_ref_files(data_manager_dict, species, interactome, target_directory):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
301
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
302 species_dict={'Human':'Homo sapiens',"Mouse":"Mus musculus","Rat":"Rattus norvegicus"}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
303
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
304 ##BioGRID
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
305 if interactome=="biogrid":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
306
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
307 tab2_link="https://downloads.thebiogrid.org/Download/BioGRID/Release-Archive/BIOGRID-3.5.167/BIOGRID-ORGANISM-3.5.167.tab2.zip"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
308
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
309 #download zip file
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
310 r = requests.get(tab2_link)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
311 with open("BioGRID.zip", "wb") as code:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
312 code.write(r.content)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
313
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
314 #unzip files
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
315 with zipfile.ZipFile("BioGRID.zip", 'r') as zip_ref:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
316 if not os.path.exists("tmp_BioGRID"): os.makedirs("tmp_BioGRID")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
317 zip_ref.extractall("tmp_BioGRID")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
318
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
319 #import file of interest and build dictionary
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
320 file_path="tmp_BioGRID/BIOGRID-ORGANISM-"+species_dict[species].replace(" ","_")+"-3.5.167.tab2.txt"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
321 with open(file_path,"r") as handle :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
322 tab_file = csv.reader(handle,delimiter="\t")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
323 dico_network = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
324 GeneID_index=1
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
325 network_cols=[1,2,7,8,11,12,14,18,20]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
326 for line in tab_file :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
327 if line[GeneID_index] not in dico_network:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
328 dico_network[line[GeneID_index]]=[[line[i] for i in network_cols]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
329 else:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
330 dico_network[line[GeneID_index]].append([line[i] for i in network_cols])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
331
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
332 #delete tmp_BioGRID directory
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
333 os.remove("BioGRID.zip")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
334 shutil.rmtree("tmp_BioGRID", ignore_errors=True)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
335
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
336 #download NCBI2Reactome.txt file and build dictionary
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
337 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
338 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
339 r.encoding ="utf-8"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
340 tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
341
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
342 dico_nodes = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
343 geneid_index=0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
344 pathway_description_index=3
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
345 species_index=5
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
346 for line in tab_file :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
347 if line[species_index]==species_dict[species]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
348 if line[geneid_index] in dico_nodes :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
349 dico_nodes[line[geneid_index]].append(line[pathway_description_index])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
350 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
351 dico_nodes[line[geneid_index]] = [line[pathway_description_index]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
352
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
353 dico={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
354 dico['network']=dico_network
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
355 dico['nodes']=dico_nodes
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
356
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
357 ##Bioplex
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
358 elif interactome=="bioplex":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
359
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
360 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
361 r = s.get('http://bioplex.hms.harvard.edu/data/BioPlex_interactionList_v4a.tsv')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
362 r = r.content.decode('utf-8')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
363 bioplex = csv.reader(r.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
364
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
365 dico_network = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
366 dico_network["GeneID"]={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
367 network_geneid_cols=[0,1,4,5,8]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
368 dico_network["UniProt-AC"]={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
369 network_uniprot_cols=[2,3,4,5,8]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
370 dico_GeneID_to_UniProt = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
371 for line in bioplex :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
372 if line[0] not in dico_network["GeneID"]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
373 dico_network["GeneID"][line[0]]=[[line[i] for i in network_geneid_cols]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
374 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
375 dico_network["GeneID"][line[0]].append([line[i] for i in network_geneid_cols])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
376 if line[1] not in dico_network["UniProt-AC"]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
377 dico_network["UniProt-AC"][line[2]]=[[line[i] for i in network_uniprot_cols]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
378 else:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
379 dico_network["UniProt-AC"][line[2]].append([line[i] for i in network_uniprot_cols])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
380 dico_GeneID_to_UniProt[line[0]]=line[2]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
381
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
382 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
383 r = s.get('https://reactome.org/download/current/UniProt2Reactome.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
384 r.encoding ="utf-8"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
385 tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
386
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
387 dico_nodes_uniprot = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
388 uniProt_index=0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
389 pathway_description_index=3
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
390 species_index=5
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
391 for line in tab_file :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
392 if line[species_index]==species_dict[species]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
393 if line[uniProt_index] in dico_nodes_uniprot :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
394 dico_nodes_uniprot[line[uniProt_index]].append(line[pathway_description_index])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
395 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
396 dico_nodes_uniprot[line[uniProt_index]] = [line[pathway_description_index]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
397
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
398 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
399 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
400 r.encoding ="utf-8"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
401 tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
402
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
403 dico_nodes_geneid = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
404 geneid_index=0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
405 pathway_description_index=3
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
406 species_index=5
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
407 for line in tab_file :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
408 if line[species_index]==species_dict[species]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
409 if line[geneid_index] in dico_nodes_geneid :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
410 dico_nodes_geneid[line[geneid_index]].append(line[pathway_description_index])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
411 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
412 dico_nodes_geneid[line[geneid_index]] = [line[pathway_description_index]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
413
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
414 dico={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
415 dico_nodes={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
416 dico_nodes['GeneID']=dico_nodes_geneid
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
417 dico_nodes['UniProt-AC']=dico_nodes_uniprot
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
418 dico['network']=dico_network
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
419 dico['nodes']=dico_nodes
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
420 dico['convert']=dico_GeneID_to_UniProt
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
421
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
422 ##Humap
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
423 elif interactome=="humap":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
424
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
425 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
426 r = s.get('http://proteincomplexes.org/static/downloads/nodeTable.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
427 r = r.content.decode('utf-8')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
428 humap_nodes = csv.reader(r.splitlines(), delimiter=',')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
429
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
430 dico_geneid_to_gene_name={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
431 dico_protein_name={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
432 for line in humap_nodes :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
433 if check_entrez_geneid(line[4]):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
434 if line[4] not in dico_geneid_to_gene_name:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
435 dico_geneid_to_gene_name[line[4]]=line[3]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
436 if line[4] not in dico_protein_name:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
437 dico_protein_name[line[4]]=line[5]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
438
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
439 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
440 r = s.get('http://proteincomplexes.org/static/downloads/pairsWprob.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
441 r = r.content.decode('utf-8')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
442 humap = csv.reader(r.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
443
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
444 dico_network = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
445 for line in humap :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
446 if check_entrez_geneid(line[0]) and check_entrez_geneid(line[1]):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
447
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
448 interactant_A, interactant_B = get_interactant_name(line,dico_geneid_to_gene_name)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
449
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
450 #first interactant (first column)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
451 if line[0] not in dico_network:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
452 dico_network[line[0]]=[line[:2]+[interactant_A,interactant_B,line[2]]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
453 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
454 dico_network[line[0]].append(line[:2]+[interactant_A,interactant_B,line[2]])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
455
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
456 #second interactant (second column)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
457 if line[1] not in dico_network:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
458 dico_network[line[1]]=[[line[1],line[0],interactant_B,interactant_A,line[2]]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
459 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
460 dico_network[line[1]].append([line[1],line[0],interactant_B,interactant_A,line[2]])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
461
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
462 with requests.Session() as s:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
463 r = s.get('https://www.reactome.org/download/current/NCBI2Reactome.txt')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
464 r.encoding ="utf-8"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
465 tab_file = csv.reader(r.content.splitlines(), delimiter='\t')
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
466
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
467 dico_nodes = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
468 geneid_index=0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
469 pathway_description_index=3
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
470 species_index=5
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
471 for line in tab_file :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
472 if line[species_index]==species_dict[species]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
473 #Fill dictionary with pathways
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
474 if line[geneid_index] in dico_nodes :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
475 dico_nodes[line[geneid_index]].append(line[pathway_description_index])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
476 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
477 dico_nodes[line[geneid_index]] = [line[pathway_description_index]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
478
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
479 dico={}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
480 dico['network']=dico_network
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
481 dico['nodes']=dico_nodes
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
482 dico['gene_name']=dico_geneid_to_gene_name
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
483 dico['protein_name']=dico_protein_name
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
484
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
485 #writing output
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
486 output_file = species+'_'+interactome+'_'+ time.strftime("%d-%m-%Y") + ".json"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
487 path = os.path.join(target_directory,output_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
488 name = species+" ("+species_dict[species]+") "+time.strftime("%d/%m/%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
489 id = species+"_"+interactome+"_"+ time.strftime("%d-%m-%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
490
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
491 with open(path, 'w') as handle:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
492 json.dump(dico, handle, sort_keys=True)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
493
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
494 data_table_entry = dict(id=id, name = name, species = species, value = path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
495 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_"+interactome+"_dictionaries")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
496
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
497 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
498 # 5. nextprot (add protein features)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
499 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
500
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
501 def Build_nextprot_ref_file(data_manager_dict,target_directory):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
502 nextprot_ids_file = "nextprot_ac_list_all.txt"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
503 ids = id_list_from_nextprot_ftp(nextprot_ids_file,target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
504
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
505 nextprot_file=[["NextprotID","MW","SeqLength","IsoPoint","Chr","SubcellLocations","Diseases","TMDomains","ProteinExistence"]]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
506 for id in ids :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
507 #print (id)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
508 query="https://api.nextprot.org/entry/"+id+".json"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
509 resp = requests.get(url=query)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
510 data = resp.json()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
511
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
512 #get info from json dictionary
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
513 mass_mol = data["entry"]["isoforms"][0]["massAsString"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
514 seq_length = data['entry']["isoforms"][0]["sequenceLength"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
515 iso_elec_point = data['entry']["isoforms"][0]["isoelectricPointAsString"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
516 chr_loc = data['entry']["chromosomalLocations"][0]["chromosome"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
517 protein_existence = "PE"+str(data['entry']["overview"]['proteinExistence']['level'])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
518
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
519 #put all subcell loc in a set
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
520 if "subcellular-location" in data['entry']["annotationsByCategory"].keys() :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
521 subcell_locs = data['entry']["annotationsByCategory"]["subcellular-location"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
522 all_subcell_locs = set()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
523 for loc in subcell_locs :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
524 all_subcell_locs.add(loc['cvTermName'])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
525 all_subcell_locs.discard("")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
526 all_subcell_locs = ";".join(all_subcell_locs)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
527 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
528 all_subcell_locs = "NA"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
529
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
530 #put all subcell loc in a set
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
531 if ('disease') in data['entry']['annotationsByCategory'].keys() :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
532 diseases = data['entry']['annotationsByCategory']['disease']
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
533 all_diseases = set()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
534 for disease in diseases :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
535 if (disease['cvTermName'] is not None and disease['cvTermName'] != ""):
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
536 all_diseases.add(disease['cvTermName'])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
537 if len(all_diseases) > 0 : all_diseases = ";".join(all_diseases)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
538 else : all_diseases="NA"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
539 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
540 all_diseases="NA"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
541
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
542 #get all tm domain
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
543 nb_domains = 0
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
544 if "domain" in data['entry']['annotationsByCategory'].keys():
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
545 tm_domains = data['entry']['annotationsByCategory']["domain"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
546 for tm_domain in tm_domains :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
547 if "properties" in tm_domain.keys() and tm_domain['properties']!=[]:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
548 domains = tm_domains["properties"]
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
549 for domain in domains :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
550 if domain["name"]=="region structure" and domain["value"]=="Helical" :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
551 nb_domains+=1
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
552
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
553
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
554 nextprot_file.append([id,mass_mol,str(seq_length),iso_elec_point,chr_loc,all_subcell_locs,all_diseases,str(nb_domains),protein_existence])
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
555
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
556 output_file = 'nextprot_ref_'+ time.strftime("%d-%m-%Y") + ".tsv"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
557 path = os.path.join(target_directory,output_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
558 name = "neXtProt release "+time.strftime("%d-%m-%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
559 id = "nextprot_ref_"+time.strftime("%d-%m-%Y")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
560
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
561 with open(path, 'w') as output:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
562 writer = csv.writer(output,delimiter="\t")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
563 writer.writerows(nextprot_file)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
564
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
565 data_table_entry = dict(id=id, name = name, value = path)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
566 _add_data_table_entry(data_manager_dict, data_table_entry, "proteore_nextprot_ref")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
567
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
568 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
569 # Main function
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
570 #######################################################################################################
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
571 def main():
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
572 parser = argparse.ArgumentParser()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
573 parser.add_argument("--hpa", metavar = ("HPA_OPTION"))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
574 parser.add_argument("--peptideatlas", metavar=("SAMPLE_CATEGORY_ID"))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
575 parser.add_argument("--id_mapping", metavar = ("ID_MAPPING_SPECIES"))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
576 parser.add_argument("--interactome", metavar = ("PPI"))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
577 parser.add_argument("--species")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
578 parser.add_argument("--date")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
579 parser.add_argument("-o", "--output")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
580 parser.add_argument("--database")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
581 args = parser.parse_args()
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
582
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
583 data_manager_dict = {}
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
584 # Extract json file params
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
585 filename = args.output
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
586 params = from_json_string(open(filename).read())
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
587 target_directory = params[ 'output_data' ][0]['extra_files_path']
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
588 os.mkdir(target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
589
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
590 ## Download source files from HPA
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
591 try:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
592 hpa = args.hpa
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
593 except NameError:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
594 hpa = None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
595 if hpa is not None:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
596 #target_directory = "/projet/galaxydev/galaxy/tools/proteore/ProteoRE/tools/resources_building/test-data/"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
597 hpa = hpa.split(",")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
598 for hpa_tissue in hpa:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
599 HPA_sources(data_manager_dict, hpa_tissue, target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
600
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
601 ## Download source file from Peptide Atlas query
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
602 try:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
603 peptide_atlas = args.peptideatlas
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
604 date = args.date
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
605 except NameError:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
606 peptide_atlas = None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
607 if peptide_atlas is not None:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
608 #target_directory = "/projet/galaxydev/galaxy/tools/proteore/ProteoRE/tools/resources_building/test-data/"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
609 peptide_atlas = peptide_atlas.split(",")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
610 for pa_tissue in peptide_atlas:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
611 peptide_atlas_sources(data_manager_dict, pa_tissue, date, target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
612
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
613 ## Download ID_mapping source file from Uniprot
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
614 try:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
615 id_mapping=args.id_mapping
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
616 except NameError:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
617 id_mapping = None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
618 if id_mapping is not None:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
619 id_mapping = id_mapping .split(",")
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
620 for species in id_mapping :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
621 id_mapping_sources(data_manager_dict, species, target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
622
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
623 ## Download PPI ref files from biogrid/bioplex/humap
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
624 try:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
625 interactome=args.interactome
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
626 if interactome == "biogrid" :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
627 species=args.species
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
628 else :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
629 species="Human"
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
630 except NameError:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
631 interactome=None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
632 species=None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
633 if interactome is not None and species is not None:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
634 PPI_ref_files(data_manager_dict, species, interactome, target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
635
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
636 ## Build nextprot ref file for add protein features
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
637 try:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
638 database=args.database
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
639 except NameError:
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
640 database=None
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
641 if database is not None :
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
642 Build_nextprot_ref_file(data_manager_dict,target_directory)
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
643
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
644 #save info to json file
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
645 filename = args.output
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
646 open(filename, 'wb').write(to_json_string(data_manager_dict))
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
647
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
648 if __name__ == "__main__":
9e31ea9fc7ea planemo upload commit 567ba7934c0ca55529dfeb5e7ca0935ace260ad7-dirty
proteore
parents:
diff changeset
649 main()