forked from shpakoo/YAP
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathClusterRename.py
201 lines (161 loc) · 6.38 KB
/
ClusterRename.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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
########################################################################################
## This file is a part of YAP package of scripts. https://github.com/shpakoo/YAP
## Distributed under the MIT license: http://www.opensource.org/licenses/mit-license.php
## Copyright (c) 2011-2013 Sebastian Szpakowski
########################################################################################
#################################################
## rename anything with "uncultured" with a species that is most abundant in a cluster
#################################################
import sys
from optparse import OptionParser
from collections import defaultdict
_author="Sebastian Szpakowski"
_date="2012/03/30"
_version="Version 1"
#################################################
## Classes
##
class FastaLikeParser:
def __init__ (self, x):
self.filename = x
self.fp = open(x, "r")
self.currline = ""
self.currentFastaName = ""
self.currentFastaSequence = ""
self.lastitem=False
def __iter__(self):
return(self)
#####
def next(self):
for self.currline in self.fp:
if self.currline.startswith(">"):
self.currline = self.currline[1:]
if self.currentFastaName == "":
self.currentFastaName = self.currline
else:
otpt = (self.currentFastaName.strip(), self.currentFastaSequence.strip())
self.currentFastaName = self.currline
self.currentFastaSequence = ""
self.previoustell = self.fp.tell()
return (otpt)
else:
self.addSequence(self.currline)
if not self.lastitem:
self.lastitem=True
return (self.currentFastaName.strip(), self.currentFastaSequence.strip())
else:
raise StopIteration
def addSequence(self, x):
self.currentFastaSequence = "%s\n%s" % (self.currentFastaSequence, x.strip())
def __str__():
return ("reading file: %s" %self.filename)
#################################################
### Iterator over input fata file.
### Only reading when requested
### Useful for very large FASTA files
### with many sequences
class FastaParser:
def __init__ (self, x, quals=False):
self.filename = x
self.fp = open(x, "r")
self.currline = ""
self.currentFastaName = ""
self.currentFastaSequence = ""
self.lastitem=False
if quals:
self.linesep=" "
else:
self.linesep=""
def __iter__(self):
return(self)
#####
def next(self):
for self.currline in self.fp:
if self.currline.startswith(">"):
self.currline = self.currline[1:]
if self.currentFastaName == "":
self.currentFastaName = self.currline
else:
otpt = (self.currentFastaName.strip(), self.currentFastaSequence.strip())
self.currentFastaName = self.currline
self.currentFastaSequence = ""
self.previoustell = self.fp.tell()
return (otpt)
else:
self.addSequence(self.currline)
if not self.lastitem:
self.lastitem=True
return (self.currentFastaName.strip(), self.currentFastaSequence.strip())
else:
raise StopIteration
def addSequence(self, x):
self.currentFastaSequence = "%s%s%s" % (self.currentFastaSequence,self.linesep, x.strip())
def __str__():
return ("reading file: %s" %self.filename)
#################################################
## Functions
##
def findName(names):
tmp = defaultdict(int)
for n in names:
if n.lower().find("uncultured")==-1 and n.lower().find("associated")==-1:
n = "_".join(n.split("_")[1:])
n = "%s" % (n)
tmp[n]+=1
if len(tmp.keys())>0:
otpt = defaultdict(list)
for n,count in tmp.items():
otpt[count].append(n)
keys = otpt.keys()
keys.sort()
keys.reverse()
newname = otpt[keys[0]]
return newname
else:
return list()
#################################################
## Arguments
##
parser = OptionParser()
parser.add_option("-c", "--clusters", dest="fn_clstr",
help="clustering from CDHIT", metavar="FILE")
parser.add_option("-s", "--sequences", dest="fn_seqs", default ="",
help="names from CDHIT", metavar="FILE")
parser.add_option("-o", "--output", dest="fn_out", default ="",
help="names from CDHIT", metavar="FILE")
(options, args) = parser.parse_args()
#################################################
## Begin
##
names = defaultdict(set)
clusters = defaultdict(set)
remapping = defaultdict(list)
## parse clusters
for clusterid, contents in FastaLikeParser(options.fn_clstr):
representative= ""
descendants = set()
for line in contents.strip().split("\n"):
id = line.split(">")[1].split("...")[0]
if line.endswith("*"):
representative = id
### self is always a descendant of itself!
descendants.add(id)
[descendants.add(x) for x in names[id]]
clusters[representative] = descendants
### find new names
for K in clusters:
if K.lower().find("uncultured")>-1 or K.lower().find("associated")>-1:
remapping[K] = findName(clusters[K])
## rename fasta
otptfile = open(options.fn_out, "w")
for head, seq in FastaParser(options.fn_seqs):
if len(remapping[head])>0:
newname = "%s_%s" % (head.split("_")[0], remapping[head][0])
print head, "->" , newname, remapping[head]
else:
newname = head
otptfile.write(">%s\n%s\n" % (newname, seq))
otptfile.close
#################################################
## Finish
#################################################