blacklistsTest/generateClusteredReference.py at master · samiscoding/blacklistsTest · GitHub

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
'''
@auther: Samaneh
The whole planned algorithm is implemented here:
'''

from Bio import SeqIO
import pandas as pd
import numpy as np
#import xlsxwriter
import re
import csv
import os
import json

#########################################################################

##@sam## 	Extracts all the uniprot IDs and corresponding clusters from eggNOG tsv file into a dictionary
def uniprotIdsExtraction(uniprotIdsFile):

	idsList = []
	idDesDic = dict()

	for line in uniprotIdsFile.readlines():
		if ">>" in line:
			ids = line.split("|")[0]
			ids = re.sub(">>","",ids).strip(" ")
			desc = line.split("|")[1].lstrip(" ")
			if ids not in idDesDic.keys():
				idDesDic.update({ids:desc})
			else:
				newDesc = idDesDic[ids] + " / " + desc
				idDesDic.update({ids:newDesc})

	return idDesDic


def referenceGenerator(idDesDic, sprotFile):

	reference = open("/home/samaneh/eggNOG/output/clstrd_ref_eggNOG_descs.fasta", "w")
	for record in SeqIO.parse(sprotFile, "fasta"):
		spId = record.id.split("|")[1]
		if spId in idDesDic.keys():
			newRecord = record
			newRecord.description = idDesDic[spId]
			SeqIO.write(newRecord, reference, "fasta")

	reference.close()


def handler():

	uniprotIdsFile = open("/home/samaneh/eggNOG/output/eggnogClusterDescriptions_onEggNOG.txt", "r")
	sprotFile = open("/home/samaneh/AHRD/data/db/uniprot_sprot.fasta", "r")

	idDesDic = uniprotIdsExtraction(uniprotIdsFile)
	referenceGenerator(idDesDic, sprotFile)


if __name__ == "__main__":
	handler()