Spaces:
No application file
No application file
File size: 11,860 Bytes
b7731cd |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 |
# Copyright 2010 by Tiago Antao. All rights reserved.
#
# This file is part of the Biopython distribution and governed by your
# choice of the "Biopython License Agreement" or the "BSD 3-Clause License".
# Please see the LICENSE file that should have been included as part of this
# package.
"""Code to parse BIG GenePop files.
The difference between this class and the standard Bio.PopGen.GenePop.Record
class is that this one does not read the whole file to memory.
It provides an iterator interface, slower but consuming much mess memory.
Should be used with big files (Thousands of markers and individuals).
See http://wbiomed.curtin.edu.au/genepop/ , the format is documented
here: http://wbiomed.curtin.edu.au/genepop/help_input.html .
Classes:
- FileRecord Holds GenePop data.
Functions:
"""
from Bio.PopGen.GenePop import get_indiv
def read(fname):
"""Parse a file containing a GenePop file.
fname is a file name that contains a GenePop record.
"""
record = FileRecord(fname)
return record
class FileRecord:
"""Hold information from a GenePop record.
Attributes:
- marker_len The marker length (2 or 3 digit code per allele).
- comment_line Comment line.
- loci_list List of loci names.
Methods:
- get_individual Returns the next individual of the current population.
- skip_population Skips the current population.
skip_population skips the individuals of the current population, returns
True if there are more populations.
get_individual returns an individual of the current population (or None
if the list ended).
Each individual is a pair composed by individual name and a list of alleles
(2 per marker or 1 for haploid data). Examples::
('Ind1', [(1,2), (3,3), (200,201)]
('Ind2', [(2,None), (3,3), (None,None)]
('Other1', [(1,1), (4,3), (200,200)]
"""
def __init__(self, fname):
"""Initialize the class."""
self.comment_line = ""
self.loci_list = []
self.fname = fname
self.start_read()
def __str__(self):
"""Return (reconstructs) a GenePop textual representation.
This might take a lot of memory.
Marker length will be 3.
"""
marker_len = 3
rep = [self.comment_line + "\n"]
rep.append("\n".join(self.loci_list) + "\n")
current_pop = self.current_pop
current_ind = self.current_ind
self._handle.seek(0)
self.skip_header()
rep.append("Pop\n")
more = True
while more:
res = self.get_individual()
if res is True:
rep.append("Pop\n")
elif res is False:
more = False
else:
name, markers = res
rep.append(name)
rep.append(",")
for marker in markers:
rep.append(" ")
for al in marker:
if al is None:
al = "0"
aStr = str(al)
while len(aStr) < marker_len:
aStr = "".join(["0", aStr])
rep.append(aStr)
rep.append("\n")
self.seek_position(current_pop, current_ind)
return "".join(rep)
def start_read(self):
"""Start parsing a file containing a GenePop file."""
self._handle = open(self.fname)
self.comment_line = self._handle.readline().rstrip()
# We can now have one loci per line or all loci in a single line
# separated by either space or comma+space...
# We will remove all commas on loci... that should not be a problem
sample_loci_line = self._handle.readline().rstrip().replace(",", "")
all_loci = sample_loci_line.split(" ")
self.loci_list.extend(all_loci)
for line in self._handle:
line = line.rstrip()
if line.upper() == "POP":
break
self.loci_list.append(line)
else:
raise ValueError(
"No population data found, file probably not GenePop related"
)
# self._after_pop = True
self.current_pop = 0
self.current_ind = 0
def skip_header(self):
"""Skip the Header. To be done after a re-open."""
self.current_pop = 0
self.current_ind = 0
for line in self._handle:
if line.rstrip().upper() == "POP":
return
def seek_position(self, pop, indiv):
"""Seek a certain position in the file.
Arguments:
- pop - pop position (0 is first)
- indiv - individual in pop
"""
self._handle.seek(0)
self.skip_header()
while pop > 0:
self.skip_population()
pop -= 1
while indiv > 0:
self.get_individual()
indiv -= 1
def skip_population(self):
"""Skip the current population. Returns true if there is another pop."""
for line in self._handle:
if line == "":
return False
line = line.rstrip()
if line.upper() == "POP":
self.current_pop += 1
self.current_ind = 0
return True
def get_individual(self):
"""Get the next individual.
Returns individual information if there are more individuals
in the current population.
Returns True if there are no more individuals in the current
population, but there are more populations. Next read will
be of the following pop.
Returns False if at end of file.
"""
for line in self._handle:
line = line.rstrip()
if line.upper() == "POP":
self.current_pop += 1
self.current_ind = 0
return True
else:
self.current_ind += 1
indiv_name, allele_list, ignore = get_indiv(line)
return indiv_name, allele_list
return False
def remove_population(self, pos, fname):
"""Remove a population (by position).
Arguments:
- pos - position
- fname - file to be created with population removed
"""
old_rec = read(self.fname)
with open(fname, "w") as f:
f.write(self.comment_line + "\n")
for locus in old_rec.loci_list:
f.write(locus + "\n")
curr_pop = 0
l_parser = old_rec.get_individual()
start_pop = True
while l_parser:
if curr_pop == pos:
old_rec.skip_population()
curr_pop += 1
else:
if l_parser is True:
curr_pop += 1
start_pop = True
else:
if start_pop:
f.write("POP\n")
start_pop = False
name, markers = l_parser
f.write(name + ",")
for marker in markers:
f.write(" ")
for al in marker:
if al is None:
al = "0"
aStr = str(al)
while len(aStr) < 3:
aStr = "".join(["0", aStr])
f.write(aStr)
f.write("\n")
l_parser = old_rec.get_individual()
def remove_locus_by_position(self, pos, fname):
"""Remove a locus by position.
Arguments:
- pos - position
- fname - file to be created with locus removed
"""
old_rec = read(self.fname)
with open(fname, "w") as f:
f.write(self.comment_line + "\n")
loci_list = old_rec.loci_list
del loci_list[pos]
for locus in loci_list:
f.write(locus + "\n")
l_parser = old_rec.get_individual()
f.write("POP\n")
while l_parser:
if l_parser is True:
f.write("POP\n")
else:
name, markers = l_parser
f.write(name + ",")
marker_pos = 0
for marker in markers:
if marker_pos == pos:
marker_pos += 1
continue
marker_pos += 1
f.write(" ")
for al in marker:
if al is None:
al = "0"
aStr = str(al)
while len(aStr) < 3:
aStr = "".join(["0", aStr])
f.write(aStr)
f.write("\n")
l_parser = old_rec.get_individual()
def remove_loci_by_position(self, positions, fname):
"""Remove a set of loci by position.
Arguments:
- positions - positions
- fname - file to be created with locus removed
"""
old_rec = read(self.fname)
with open(fname, "w") as f:
f.write(self.comment_line + "\n")
loci_list = old_rec.loci_list
positions.sort()
positions.reverse()
posSet = set()
for pos in positions:
del loci_list[pos]
posSet.add(pos)
for locus in loci_list:
f.write(locus + "\n")
l_parser = old_rec.get_individual()
f.write("POP\n")
while l_parser:
if l_parser is True:
f.write("POP\n")
else:
name, markers = l_parser
f.write(name + ",")
marker_pos = 0
for marker in markers:
if marker_pos in posSet:
marker_pos += 1
continue
marker_pos += 1
f.write(" ")
for al in marker:
if al is None:
al = "0"
aStr = str(al)
while len(aStr) < 3:
aStr = "".join(["0", aStr])
f.write(aStr)
f.write("\n")
l_parser = old_rec.get_individual()
def remove_locus_by_name(self, name, fname):
"""Remove a locus by name.
Arguments:
- name - name
- fname - file to be created with locus removed
"""
for i, locus in enumerate(self.loci_list):
if locus == name:
self.remove_locus_by_position(i, fname)
return
# If here than locus not existent... Maybe raise exception?
# Although it should be Ok... Just a boolean return, maybe?
def remove_loci_by_name(self, names, fname):
"""Remove a loci list (by name).
Arguments:
- names - names
- fname - file to be created with loci removed
"""
positions = []
for i, locus in enumerate(self.loci_list):
if locus in names:
positions.append(i)
self.remove_loci_by_position(positions, fname)
# If here than locus not existent... Maybe raise exception?
# Although it should be Ok... Just a boolean return, maybe?
|