Mercurial > repos > proteore > proteore_reactome

comparison reactome_analysis.py @ 8:a58dc5d4b8cd draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 4ba1ebe7b3f5e3fabf78b5fed7ed0b92e2cbf9e5-dirty
author proteore
date Fri, 28 Jun 2019 05:17:11 -0400
parents 9cc475dcd0f2
children 19195d1a4063
comparison
equal deleted inserted replaced
7:6c95f1b88627 8:a58dc5d4b8cd
1 import os 1 import os, re, json, argparse, csv
2 import re
3 import json
4 import argparse
5 2
6 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__)) 3 CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
7 4
8 def id_valid(identifiers): 5 def id_valid(identifiers):
9 """ 6 """
40 Submit IDs list to Reactome and return results in json format 37 Submit IDs list to Reactome and return results in json format
41 Return error in HTML format if web service is not available 38 Return error in HTML format if web service is not available
42 """ 39 """
43 trash = [] 40 trash = []
44 if identifiers[1] == "list": 41 if identifiers[1] == "list":
45 ids = "\n".join(id_valid(identifiers[0].split())[0]) 42 ids = identifiers[0].split()
43 ids = [x.split(";") for x in ids]
44 ids = [item.strip() for sublist in ids for item in sublist if item != '']
46 json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1" % ids).read() 45 json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1" % ids).read()
47 if len(id_valid(identifiers[0].split())[1]) > 0: 46 if len(id_valid(identifiers[0].split())[1]) > 0:
48 trash = id_valid(identifiers[0].split())[1] 47 trash = id_valid(identifiers[0].split())[1]
49 elif identifiers[1] == "file": 48 elif identifiers[1] == "file":
50 header = identifiers[2] 49 header = identifiers[2]
51 mq = open(identifiers[0]).readlines() 50 with open(identifiers[0],"r") as mq :
52 if isnumber("int", identifiers[3].replace("c", "")): 51 file_content = csv.reader(mq,delimiter="\t")
53 if header == "true": 52 file_content = list(file_content) #csv object to list
54 idens = [x.split("\t")[int(identifiers[3].replace("c", ""))-1] for x in mq[1:]] 53 ncol = identifiers[3]
55 else: 54 if isnumber("int", ncol.replace("c", "")):
56 idens = [x.split("\t")[int(identifiers[3].replace("c", ""))-1] for x in mq] 55 if header == "true":
57 ids = "\n".join(id_valid(idens)[0]) 56 idens = [x for x in [line[int(ncol.replace("c", ""))-1].split(";") for line in file_content[1:]]]
58 json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1 2> stderr" % ids).read() 57 else:
59 if len(id_valid(idens)[1]) > 0: 58 idens = [x for x in [line[int(ncol.replace("c", ""))-1].split(";") for line in file_content]]
60 trash = id_valid(idens)[1] 59
60 idens = [item.strip() for sublist in idens for item in sublist if item != ''] #flat list of list of lists, remove empty items
61 ids = "\n".join(id_valid(idens)[0])
62 json_string = os.popen("curl -H \"Content-Type: text/plain\" -d \"$(printf '%s')\" -X POST --url www.reactome.org/AnalysisService/identifiers/\?pageSize\=1\&page\=1 2> stderr" % ids).read()
63 if len(id_valid(idens)[1]) > 0:
64 trash = id_valid(idens)[1]
61 #print(json_string) 65 #print(json_string)
62 j = json.loads(json_string) 66 j = json.loads(json_string)
63 print ("Identifiers not found: " + str(j["identifiersNotFound"])) 67 print ("Identifiers not found: " + str(j["identifiersNotFound"]))
64 print ("Pathways found: " + str(j["pathwaysFound"])) 68 print ("Pathways found: " + str(j["pathwaysFound"]))
65 return json_string, trash 69 return json_string, trash