forked from lamdv/PyRice
-
Notifications
You must be signed in to change notification settings - Fork 2
/
test.py
76 lines (72 loc) · 2.78 KB
/
test.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
# #!/usr/bin/env python3
import query
print("Oryzabase Query: ")
for iter in query.query("oryzabase", ["Os03g0149100"]):
print(iter)
# print("\nRapDB Query")
# for iter in query.query("rapdb", ["Os01g0102700"]):
# print(iter)
# print("\nGramene Query")
# for iter in query.query("Gramene", ["Os03g0149100"]):
# print(iter)
# # print("\nic4r Query")
# # for iter in query.query("ic4r", ["Os03g0149100"]):
# # print(iter)
# print("\nplntfdb Query")
# for iter in query.query("plntfdb", ["321718"]):
# print(iter)
# # print("\nSNP-Seek Query")
# # for iter in query.query("snpseek", ["chr01", "1", "43270923", "rap"]):
# # print(iter)
# print("\nfunricegene Query")
# for iter in query.query("funricegene_genekeywords", ["","LOC_Os07g39750"]):
# print(iter)
# print("\nfunricegene Query")
# for iter in query.query("funricegene_geneinfo", ["","LOC_Os07g39750"]):
# print(iter)
# print("\nfunricegene Query")
# for iter in query.query("funricegene_faminfo", ["","LOC_Os07g39750"]):
# print(iter)
# print("\nMSU Query")
# for iter in query.query("msu", ["LOC_Os10g01006"]):
# print(iter)
# import os
# import sys
# sys.path.append('inst/python')
# import helper
# import query
# import csv
# from multiprocessing import Pool
# from multiprocessing.dummy import Pool as ThreadPool
#
# # Configuration:
# num_of_thread = 2
# path = '/storage/bio/coffee/input/'
# set = ['G1_clustered_genes_annotations.tab','G2_clustered_genes_annotations.tab','G5_clustered_genes_annotations.tab','G6_ clustered_genes_annotations.tab']
# #set = ['Control-1-NT_25628_clustered_genes_annotations.tab', 'Curcuma-longa-N0-L_25630_clustered_genes_annotations.tab',' Curcuma-longa-N350-H_25629_clustered_genes_annotations.tab']
#
# # Support functions:
# def get_kegg_id(key):
# try:
# return {'KEGG_id': key, 'Definition':query.query('kegg', [key])[0]['Definition']}
# except:
# print(key)
# return None
# # Get a list of unique gene
# unique_gene_list = []
# for data in set:
# with open(path + data, newline='') as input_file:
# dictReader = csv.DictReader(input_file, delimiter = "\t")
# for line in dictReader:
# for kegg_id in line['KEGG_ko'].split('|'):
# if not(kegg_id in unique_gene_list): unique_gene_list.append(kegg_id)
# for kegg_id in line['KEGG_module'].split('|'):
# if not(kegg_id in unique_gene_list): unique_gene_list.append(kegg_id)
# for kegg_id in line['KEGG_pathway'].split('|'):
# if not(kegg_id in unique_gene_list): unique_gene_list.append(kegg_id)
#
# print('Querying')
# # Query from unique list
# # Using multiple (4) threads
# pool = ThreadPool(num_of_thread)
# unique_return = pool.map(get_kegg_id, unique_gene_list)