/usr/share/pyshared/Bio/Sequencing/Ace.py is in python-biopython 1.58-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 | # Copyright 2004 by Frank Kauff and Cymon J. Cox. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""
Parser for ACE files output by PHRAP.
Written by Frank Kauff (fkauff@duke.edu) and
Cymon J. Cox (cymon@duke.edu)
Uses the Biopython Parser interface: ParserSupport.py
Usage:
There are two ways of reading an ace file:
1) The function 'read' reads the whole file at once;
2) The function 'parse' reads the file contig after contig.
1) Parse whole ace file at once:
from Bio.Sequencing import Ace
acefilerecord=Ace.read(open('my_ace_file.ace'))
This gives you:
acefilerecord.ncontigs (the number of contigs in the ace file)
acefilerecord.nreads (the number of reads in the ace file)
acefilerecord.contigs[] (one instance of the Contig class for each contig)
The Contig class holds the info of the CO tag, CT and WA tags, and all the reads used
for this contig in a list of instances of the Read class, e.g.:
contig3=acefilerecord.contigs[2]
read4=contig3.reads[3]
RD_of_read4=read4.rd
DS_of_read4=read4.ds
CT, WA, RT tags from the end of the file can appear anywhere are automatically
sorted into the right place.
see _RecordConsumer for details.
2) Or you can iterate over the contigs of an ace file one by one in the ususal way:
from Bio.Sequencing import Ace
contigs=Ace.parse(open('my_ace_file.ace'))
for contig in contigs:
print contig.name
...
Please note that for memory efficiency, when using the iterator approach, only one
contig is kept in memory at once. However, there can be a footer to the ACE file
containing WA, CT, RT or WR tags which contain additional meta-data on the contigs.
Because the parser doesn't see this data until the final record, it cannot be added to
the appropriate records. Instead these tags will be returned with the last contig record.
Thus an ace file does not entirerly suit the concept of iterating. If WA, CT, RT, WR tags
are needed, the 'read' function rather than the 'parse' function might be more appropriate.
"""
class rd(object):
"""RD (reads), store a read with its name, sequence etc.
The location and strand each read is mapped to is held in the AF lines.
"""
def __init__(self):
self.name=''
self.padded_bases=None
self.info_items=None
self.read_tags=None
self.sequence=''
class qa(object):
"""QA (read quality), including which part if any was used as the consensus."""
def __init__(self, line=None):
self.qual_clipping_start=None
self.qual_clipping_end=None
self.align_clipping_start=None
self.align_clipping_end=None
if line:
header=map(eval,line.split()[1:])
self.qual_clipping_start=header[0]
self.qual_clipping_end=header[1]
self.align_clipping_start=header[2]
self.align_clipping_end=header[3]
class ds(object):
"""DS lines, include file name of a read's chromatogram file."""
def __init__(self, line=None):
self.chromat_file=''
self.phd_file=''
self.time=''
self.chem=''
self.dye=''
self.template=''
self.direction=''
if line:
tags=['CHROMAT_FILE','PHD_FILE','TIME','CHEM','DYE','TEMPLATE','DIRECTION']
poss=map(line.find,tags)
tagpos=dict(zip(poss,tags))
if -1 in tagpos:
del tagpos[-1]
ps=tagpos.keys()
ps.sort()
for (p1,p2) in zip(ps,ps[1:]+[len(line)+1]):
setattr(self,tagpos[p1].lower(),line[p1+len(tagpos[p1])+1:p2].strip())
class af(object):
"""AF lines, define the location of the read within the contig.
Note attribute coru is short for complemented (C) or uncomplemented (U),
since the strand information is stored in an ACE file using either the
C or U character.
"""
def __init__(self, line=None):
self.name=''
self.coru=None
self.padded_start=None
if line:
header = line.split()
self.name = header[1]
self.coru = header[2]
self.padded_start = int(header[3])
class bs(object):
""""BS (base segment), which read was chosen as the consensus at each position."""
def __init__(self, line=None):
self.name=''
self.padded_start=None
self.padded_end=None
if line:
header = line.split()
self.padded_start = int(header[1])
self.padded_end = int(header[2])
self.name = header[3]
class rt(object):
"""RT (transient read tags), generated by crossmatch and phrap."""
def __init__(self, line=None):
self.name=''
self.tag_type=''
self.program=''
self.padded_start=None
self.padded_end=None
self.date=''
self.comment=[]
if line:
header=line.split()
self.name=header[0]
self.tag_type=header[1]
self.program=header[2]
self.padded_start=int(header[3])
self.padded_end=int(header[4])
self.date=header[5]
class ct(object):
"""CT (consensus tags)."""
def __init__(self, line=None):
self.name=''
self.tag_type=''
self.program=''
self.padded_start=None
self.padded_end=None
self.date=''
self.notrans=''
self.info=[]
self.comment=[]
if line:
header=line.split()
self.name = header[0]
self.tag_type = header[1]
self.program = header[2]
self.padded_start = int(header[3])
self.padded_end = int(header[4])
self.date = header[5]
if len(header)==7:
self.notrans = header[6]
class wa(object):
"""WA (whole assembly tag), holds the assembly program name, version, etc."""
def __init__(self, line=None):
self.tag_type=''
self.program=''
self.date=''
self.info=[]
if line:
header = line.split()
self.tag_type = header[0]
self.program = header[1]
self.date = header[2]
class wr(object):
"""WR lines."""
def __init__(self, line=None):
self.name=''
self.aligned=''
self.program=''
self.date=[]
if line:
header = line.split()
self.name = header[0]
self.aligned = header[1]
self.program = header[2]
self.date = header[3]
class Reads(object):
"""Holds information about a read supporting an ACE contig."""
def __init__(self, line=None):
self.rd=None # one per read
self.qa=None # one per read
self.ds=None # none or one per read
self.rt=None # none or many per read
self.wr=None # none or many per read
if line:
self.rd = rd()
header = line.split()
self.rd.name = header[1]
self.rd.padded_bases = int(header[2])
self.rd.info_items = int(header[3])
self.rd.read_tags = int(header[4])
class Contig(object):
"""Holds information about a contig from an ACE record."""
def __init__(self, line=None):
self.name = ''
self.nbases=None
self.nreads=None
self.nsegments=None
self.uorc=None
self.sequence=""
self.quality=[]
self.af=[]
self.bs=[]
self.reads=[]
self.ct=None # none or many
self.wa=None # none or many
if line:
header = line.split()
self.name = header[1]
self.nbases = int(header[2])
self.nreads = int(header[3])
self.nsegments = int(header[4])
self.uorc = header[5]
def parse(handle):
"""parse(handle)
where handle is a file-like object.
This function returns an iterator that allows you to iterate
over the ACE file record by record:
records = parse(handle)
for record in records:
# do something with the record
where each record is a Contig object.
"""
handle = iter(handle)
line = ""
while True:
# at beginning, skip the AS and look for first CO command
try:
while True:
if line.startswith('CO'):
break
line = handle.next()
except StopIteration:
return
record = Contig(line)
for line in handle:
line = line.strip()
if not line:
break
record.sequence+=line
for line in handle:
if line.strip():
break
if not line.startswith("BQ"):
raise ValueError("Failed to find BQ line")
for line in handle:
if not line.strip():
break
record.quality.extend(map(int,line.split()))
for line in handle:
if line.strip():
break
while True:
if not line.startswith("AF "):
break
record.af.append(af(line))
try:
line = handle.next()
except StopIteration:
raise ValueError("Unexpected end of AF block")
while True:
if line.strip():
break
try:
line = handle.next()
except StopIteration:
raise ValueError("Unexpected end of file")
while True:
if not line.startswith("BS "):
break
record.bs.append(bs(line))
try:
line = handle.next()
except StopIteration:
raise ValueError("Failed to find end of BS block")
# now read all the read data
# it starts with a 'RD', and then a mandatory QA
# then follows an optional DS
# CT,RT,WA,WR may or may not be there in unlimited quantity. They might refer to the actual read or contig,
# or, if encountered at the end of file, to any previous read or contig. the sort() method deals
# with that later.
while True:
# each read must have a rd and qa
try:
while True:
# If I've met the condition, then stop reading the line.
if line.startswith("RD "):
break
line = handle.next()
except StopIteration:
raise ValueError("Failed to find RD line")
record.reads.append(Reads(line))
for line in handle:
line = line.strip()
if not line:
break
record.reads[-1].rd.sequence+=line
for line in handle:
if line.strip():
break
if not line.startswith("QA "):
raise ValueError("Failed to find QA line")
record.reads[-1].qa = qa(line)
# now one ds can follow
for line in handle:
if line.strip():
break
else:
break
if line.startswith("DS "):
record.reads[-1].ds = ds(line)
line = ""
# the file could just end, or there's some more stuff. In ace files, anything can happen.
# the following tags are interspersed between reads and can appear multiple times.
while True:
# something left
try:
while True:
if line.strip():
break
line = handle.next()
except StopIteration:
# file ends here
break
if line.startswith("RT{"):
# now if we're at the end of the file, this rt could
# belong to a previous read, not the actual one.
# we store it here were it appears, the user can sort later.
if record.reads[-1].rt is None:
record.reads[-1].rt=[]
for line in handle:
line=line.strip()
#if line=="COMMENT{":
if line.startswith("COMMENT{"):
if line[8:].strip():
#MIRA 3.0.5 would miss the new line out :(
record.reads[-1].rt[-1].comment.append(line[8:])
for line in handle:
line = line.strip()
if line.endswith("C}"):
break
record.reads[-1].rt[-1].comment.append(line)
elif line=='}':
break
else:
record.reads[-1].rt.append(rt(line))
line = ""
elif line.startswith("WR{"):
if record.reads[-1].wr is None:
record.reads[-1].wr=[]
for line in handle:
line=line.strip()
if line=='}': break
record.reads[-1].wr.append(wr(line))
line = ""
elif line.startswith("WA{"):
if record.wa is None:
record.wa=[]
try:
line = handle.next()
except StopIteration:
raise ValueError("Failed to read WA block")
record.wa.append(wa(line))
for line in handle:
line=line.strip()
if line=='}': break
record.wa[-1].info.append(line)
line = ""
elif line.startswith("CT{"):
if record.ct is None:
record.ct=[]
try:
line = handle.next()
except StopIteration:
raise ValueError("Failed to read CT block")
record.ct.append(ct(line))
for line in handle:
line=line.strip()
if line=="COMMENT{":
for line in handle:
line = line.strip()
if line.endswith("C}"):
break
record.ct[-1].comment.append(line)
elif line=='}':
break
else:
record.ct[-1].info.append(line)
line = ""
else:
break
if not line.startswith('RD'): # another read?
break
yield record
class ACEFileRecord(object):
"""Holds data of an ACE file.
"""
def __init__(self):
self.ncontigs=None
self.nreads=None
self.contigs=[]
self.wa=None # none or many
def sort(self):
"""Sorts wr, rt and ct tags into the appropriate contig / read instance, if possible. """
ct=[]
rt=[]
wr=[]
# search for tags that aren't in the right position
for i in range(len(self.contigs)):
c = self.contigs[i]
if c.wa:
if not self.wa:
self.wa=[]
self.wa.extend(c.wa)
if c.ct:
newcts=[ct_tag for ct_tag in c.ct if ct_tag.name!=c.name]
for x in newcts:
self.contigs[i].ct.remove(x)
ct.extend(newcts)
for j in range(len(c.reads)):
r = c.reads[j]
if r.rt:
newrts=[rt_tag for rt_tag in r.rt if rt_tag.name!=r.rd.name]
for x in newrts:
self.contigs[i].reads[j].rt.remove(x)
rt.extend(newrts)
if r.wr:
newwrs=[wr_tag for wr_tag in r.wr if wr_tag.name!=r.rd.name]
for x in newwrs:
self.contigs[i].reads[j].wr.remove(x)
wr.extend(newwrs)
# now sort them into their proper place
for i in range(len(self.contigs)):
c = self.contigs[i]
for ct_tag in ct:
if ct_tag.name==c.name:
if self.contigs[i].ct is None:
self.contigs[i].ct=[]
self.contigs[i].ct.append(ct_tag)
if rt or wr:
for j in range(len(c.reads)):
r = c.reads[j]
for rt_tag in rt:
if rt_tag.name==r.rd.name:
if self.contigs[i].reads[j].rt is None:
self.contigs[i].reads[j].rt=[]
self.contigs[i].reads[j].rt.append(rt_tag)
for wr_tag in wr:
if wr_tag.name==r.rd.name:
if self.contigs[i].reads[j].wr is None:
self.contigs[i].reads[j].wr=[]
self.contigs[i].reads[j].wr.append(wr_tag)
def read(handle):
"""Parses the full ACE file in list of contigs.
"""
handle = iter(handle)
record=ACEFileRecord()
try:
line = handle.next()
except StopIteration:
raise ValueError("Premature end of file")
# check if the file starts correctly
if not line.startswith('AS'):
raise ValueError("File does not start with 'AS'.")
words = line.split()
record.ncontigs, record.nreads = map(int, words[1:3])
# now read all the records
record.contigs = list(parse(handle))
# wa, ct, rt rags are usually at the end of the file, but not necessarily (correct?).
# If the iterator is used, the tags are returned with the contig or the read after which they appear,
# if all tags are at the end, they are read with the last contig. The concept of an
# iterator leaves no other choice. But if the user uses the ACEParser, we can check
# them and put them into the appropriate contig/read instance.
# Conclusion: An ACE file is not a filetype for which iteration is 100% suitable...
record.sort()
return record
|