forked from jrhendrix/xRange
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathxRange.py
247 lines (179 loc) · 6.03 KB
/
xRange.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
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
'''
FILE: xRange.py
AUTHOR: J.R. Hendrix
URL: http://stronglab.org
DESC: This script extracts a range of nucleotides
from a fasta sequence file
'''
# IMPORT FROM PYTHON STANDARD LIBRARY
import argparse
import os
import sys
from Bio import SeqIO # Source: https://biopython.org/wiki/SeqIO
from Bio.Seq import Seq
from Bio.SeqRecord import SeqRecord
class File:
""" Base class for all file-types """
def __init__(self, path, file_type=None):
self._path = None
self.path = path
self.file_type = file_type
@property
def path(self):
return self._path
@path.setter
def path(self, value):
if not os.path.isabs(value):
value = os.path.join(os.getcwd(), value)
if os.path.isfile(value):
self._path = value
else:
raise FileNotFoundError(value)
@property
def filename(self):
return os.path.basename(self.path)
@property
def file_prefix(self):
return self.filename.split(".")[0]
@property
def extension(self):
return self.filename.split(".")[-1]
class Dir:
""" Base class for system directories """
def __init__(self, path):
self._path = None
self.path = path
@property
def path(self):
return self._path
@path.setter
def path(self, value):
if not os.path.isabs(value):
value = os.path.join(os.getcwd(), value)
if os.path.isdir(value):
self._path = value
else:
raise NotADirectoryError(value)
def modify_index(start, stop):
# INDEX MODIFIER
## Note: Input will be position. Translate to index
start = start - 1
stop = stop - 1
# FIX OUT OF BOUNDS CASES
if start < 0:
start = 0
if stop < 0:
stop = 0
# CHECK THAT 'STOP' COMES AFTER 'START'
if stop < start: # flip indecies
print('Start index is larger than stop index. Inverting...\n')
iStart = start
start = stop
stop = iStart
return(start, stop)
def extract_range(args, start, stop, outdir):
'''Find a range of indexes and write bases to file'''
start, stop = modify_index(start, stop)
outname = ''.join((args.savename, '.fasta'))
outfile = '/'.join((outdir.path, outname))
f2 = open(outfile, 'w')
# LOOP THROUGH SEQUENCE FILE
records = []
f1 = open(args.fasta, 'r')
for record in SeqIO.parse(f1, 'fasta'):
# Restrict extraction to a specific node
if args.id != None and args.id != record.id:
continue
max_index = len(record.seq)
# INDEX MODIFIER
if stop > max_index:
stop = max_index
print('xRange uses an inclusive range')
print(f'Exporting sequence at positions: {start+1} - {stop+1}')
print(f'\t(i.e. index: {start} - {stop})\n')
fragment = record.seq[start:stop+1]
extract_length = len(fragment)
print(f'Extract length: {extract_length}')
xTract = '-'.join((str(start+1), str(stop+1)))
xTract = ''.join(('extract:', xTract))
if args.outID == None:
newID = ' '.join((record.id, xTract))
else:
newID = ' '.join((args.outID, xTract))
# TAKE REVERSE COMPLIMENT
if args.reverse_complement:
fragment = fragment.reverse_complement()
newID = ' '.join((newID, 'reverse_complement'))
new_record = SeqRecord(fragment, newID, '', '')
records.append(new_record)
break
# WRITE RECORD(S) TO OUTPUT
SeqIO.write(records, f2, "fasta")
f1.close()
f2.close()
def check_input(args):
# CHECK IF FILE EXISTS
try:
f = File(args.fasta)
except IOError:
print("ERROR: Could not find file")
return 1
# CHECK THAT FILE IS FASTA FORMAT
extensions = ('fasta', 'fa', 'fna', 'faa')
if f.extension not in extensions:
print("ERROR: Input file was not in FASTA format.")
return 2
return 0
def make_output(args):
# CHECK THAT OUTPUT DIRECTORY EXISTS
d = Dir(args.p)
outpath = '/'.join((args.p, args.output_directory))
if os.path.isdir(outpath):
outdir = Dir(outpath)
else:
os.makedirs(outpath)
outdir = Dir(outpath)
return outdir
def main(program):
cwd = os.getcwd()
# PARSER : ROOT
parent_parser = argparse.ArgumentParser(prog='xRange', add_help=False)
parent_parser.add_argument('-f', '--fasta', help="FASTA file containing sequences")
parent_parser.add_argument('--id', default=None, help='Match sequence ID')
parent_parser.add_argument('-o', '--output_directory', default='xSequences', help='Prefix of output directory', type=str)
parent_parser.add_argument('--outID', default=None, help='ID for output sequence', type=str)
parent_parser.add_argument('-p', default=cwd, help='Path to output', type=str)
parent_parser.add_argument('-r', '--reverse_complement', default=False, action='store_true', help='Gets the reverse compliment')
parent_parser.add_argument('-s', '--savename', default='xSeq', help='Prefix for output file')
subparsers = parent_parser.add_subparsers(help='sub-command help')
# PARSER : DEFINED
def_parser = subparsers.add_parser('define', help='Define the range by index', parents=[parent_parser])
def_parser.add_argument('--start', default=None, help='First index in range', type=int, required=True)
def_parser.add_argument('--stop', default=None, help='Last index in range. Must be larger than start', type=int, required=True)
# PARSER : ADD
a_parser = subparsers.add_parser('add', help='Define the range by first index', parents=[parent_parser])
a_parser.add_argument('--add', default=None, help='Length of extract', type=int, required=True)
a_parser.add_argument('--start', default=None, help='First index in range', type=int, required=True)
# PARSER : SUBTRACT
s_parser = subparsers.add_parser('subtract', help='Define the range by last index', parents=[parent_parser])
s_parser.add_argument('--stop', default=None, help='Last index in range', type=int, required=True)
s_parser.add_argument('--sub', default=None, help='Length of extract', type=int, required=True)
args = parent_parser.parse_args()
# CHECK FOR VALID INPUT
check = check_input(args)
if check != 0:
print('Check input returned non-zero result. Abort.')
exit()
outdir = make_output(args)
if program == 'define':
start = args.start
stop = args.stop
if program == 'add':
start = args.start
stop = start + args.add
if program == 'subtract':
stop = args.stop
start = stop - args.sub
extract_range(args, start, stop, outdir)
if __name__ == "__main__":
main(sys.argv[1])