/usr/lib/python3/dist-packages/csb/bio/io/fasta.py is in python3-csb 1.2.3+dfsg-3.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 | """
FASTA format sequence I/O.
This module provides parsers and writers for sequences and alignments in
FASTA format. The most basic usage is:
>>> parser = SequenceParser()
>>> parser.parse_file('sequences.fa')
<SequenceCollection> # collection of L{AbstractSequence}s
This will load all sequences in memory. If you are parsing a huge file,
then you could efficiently read the file sequence by sequence:
>>> for seq in parser.read('sequences.fa'):
... # seq is an L{AbstractSequence}
L{BaseSequenceParser} is the central class in this module, which defines a
common infrastructure for all sequence readers. L{SequenceParser} is a standard
implementation, and L{PDBSequenceParser} is specialized to read FASTA sequences
with PDB headers.
For parsing alignments, have a look at L{SequenceAlignmentReader} and
L{StructureAlignmentFactory}.
Finally, this module provides a number of L{OutputBuilder}s, which know how to
write L{AbstractSequence} and L{AbstractAlignment} objects to FASTA files:
>>> with open('file.fa', 'w') as out:
builder = OutputBuilder.create(AlignmentFormats.FASTA, out)
builder.add_alignment(alignment)
builder.add_sequence(sequence)
...
or you could instantiate any of the L{OutputBuilder}s directly.
"""
import csb.io
import csb.core
from abc import ABCMeta, abstractmethod
from csb.bio.sequence import SequenceTypes, SequenceAlphabets, AlignmentFormats, SequenceError
from csb.bio.sequence import SequenceAlignment, StructureAlignment, A3MAlignment
from csb.bio.sequence import SequenceCollection, AbstractSequence, Sequence, RichSequence, ChainSequence
class SequenceFormatError(ValueError):
pass
class BaseSequenceParser(object):
"""
FASTA parser template. Subclasses must implement the way FASTA strings are
handled by overriding C{BaseSequenceParser.read_sequence}.
@param product: sequence product factory (an L{AbstractSequence} subclass)
@type product: type
@param product_type: default L{SequenceTypes} member for the products
@type product_type: L{EnumItem}
"""
__metaclass__ = ABCMeta
def __init__(self, product=Sequence, product_type=SequenceTypes.Protein):
self._product = None
if not issubclass(product, AbstractSequence):
raise TypeError(product)
if not product_type.enum is SequenceTypes:
raise TypeError(product_type)
self._product = product
self._type = product_type
@property
def product_factory(self):
"""
Factory used to build sequence products
@rtype: class
"""
return self._product
@property
def product_type(self):
"""
Default sequence type of the products - a member of L{SequenceTypes}
@rtype: enum item
"""
return self._type
@abstractmethod
def read_sequence(self, string):
"""
Parse a single FASTA string
@return: a new sequence, created with L{BaseSequenceParser.product_factory}
@rtype: L{AbstractSequence}
@raise SequenceFormatError: on parse error
"""
pass
def parse_string(self, fasta_string):
"""
Read FASTA sequences from an (m)FASTA-formatted string
@param fasta_string: FASTA string to parse
@type fasta_string: str
@return: a list of L{Sequence}s
@rtype: L{SequenceCollection}
@raise SequenceFormatError: on parse error
"""
stream = csb.io.MemoryStream()
stream.write(fasta_string)
return self.parse_file(stream)
def parse_file(self, fasta_file):
"""
Read FASTA sequences from a (m)FASTA file
@param fasta_file: input FASTA file name or opened stream
@type fasta_file: str, file
@return: a list of L{Sequence}s
@rtype: L{SequenceCollection}
@raise SequenceFormatError: on parse error
"""
if isinstance(fasta_file, csb.core.string):
stream = open(fasta_file)
else:
stream = fasta_file
seqs = []
reader = csb.io.EntryReader(stream, AbstractSequence.DELIMITER, None)
for entry in reader.entries():
seqs.append(self.read_sequence(entry))
return SequenceCollection(seqs)
def read(self, fasta_file):
"""
Read FASTA sequences from an (m)FASTA file.
@param fasta_file: input FASTA file name or opened stream
@type fasta_file: str, file
@return: efficient cursor over all L{Sequence}s (parse on demand)
@rtype: iterator
@raise SequenceFormatError: on parse error
"""
if isinstance(fasta_file, csb.core.string):
stream = open(fasta_file)
else:
stream = fasta_file
reader = csb.io.EntryReader(stream, AbstractSequence.DELIMITER, None)
for entry in reader.entries():
yield self.read_sequence(entry)
class SequenceParser(BaseSequenceParser):
"""
Standard FASTA parser. See L{BaseSequenceParser} for details.
"""
def read_sequence(self, string):
lines = string.strip().splitlines()
if not lines[0].startswith(AbstractSequence.DELIMITER):
lines = [''] + lines
if len(lines) < 2:
raise SequenceFormatError('Empty FASTA entry')
header = lines[0]
id = header[1:].split()[0]
sequence = ''.join(lines[1:])
return self.product_factory(id, header, sequence, self.product_type)
class PDBSequenceParser(SequenceParser):
"""
PDB FASTA parser. Reads the PDB ID and sequence type from the header.
See L{BaseSequenceParser} for more details.
"""
def read_sequence(self, string):
seq = super(PDBSequenceParser, self).read_sequence(string)
if not (seq.header and seq.id) or not (len(seq.id) in(5, 6) and seq.header.find('mol:') != -1):
raise SequenceFormatError('Does not look like a PDB header: {0}'.format(seq.header))
seq.id = seq.id.replace('_', '')
stype = seq.header.partition('mol:')[2].partition(' ')[0]
try:
seq.type = csb.core.Enum.parse(SequenceTypes, stype)
except csb.core.EnumValueError:
seq.type = SequenceTypes.Unknown
return seq
class A3MSequenceIterator(object):
def __init__(self, sequences, insertion):
self._temp = []
self._insertion = insertion
for sequence in sequences:
row = list(sequence.sequence)
row.reverse()
self._temp.append(row)
def next(self):
sequences = self._temp
column = [ ]
has_insertion = False
for sequence in sequences:
if len(sequence) > 0 and sequence[-1].islower():
has_insertion = True
for sequence in sequences:
try:
if has_insertion and not sequence[-1].islower():
column.append(self._insertion)
else:
column.append(sequence.pop())
except IndexError:
column.append('')
if not any(column):
raise StopIteration()
return column
def __iter__(self):
return self
def __next__(self):
return self.next()
class SequenceAlignmentReader(object):
"""
Sequence alignment parser.
@param product_type: default L{SequenceTypes} member for the sequence products
@type product_type: L{EnumItem}
@param strict: if True, raise exception on duplicate sequence identifiers.
See L{csb.bio.sequence.AbstractAlignment} for details
@type strict: bool
"""
def __init__(self, product_type=SequenceTypes.Protein, strict=True):
if not product_type.enum is SequenceTypes:
raise TypeError(product_type)
self._type = product_type
self._strict = bool(strict)
@property
def product_type(self):
"""
Default sequence type of the alignment entries - a member of L{SequenceTypes}
@rtype: enum item
"""
return self._type
@property
def strict(self):
"""
True if strict mode is enabled
@rtype: bool
"""
return self._strict
def read_fasta(self, string):
"""
Parse an alignment in multi-FASTA format.
@param string: alignment string
@type string: str
@rtype: L{SequenceAlignment}
"""
parser = SequenceParser(RichSequence, self.product_type)
sequences = parser.parse_string(string)
return SequenceAlignment(sequences, strict=self.strict)
def read_a3m(self, string):
"""
Parse an alignment in A3M format.
@param string: alignment string
@type string: str
@rtype: L{A3MAlignment}
"""
alphabet = SequenceAlphabets.get(self.product_type)
# parse all "mis-aligned" sequences as case-sensitive strings
parser = SequenceParser(Sequence, self.product_type)
sequences = parser.parse_string(string)
# storage for expanded sequences
s = []
for dummy in sequences:
s.append([])
# expand all sequences with insertion characters and make them equal length
for column in A3MSequenceIterator(sequences, str(alphabet.INSERTION)):
for sn, char in enumerate(column):
s[sn].append(char)
# build normal sequence objects from the equalized sequence strings
aligned_seqs = []
for sn, seq in enumerate(sequences):
sequence = RichSequence(seq.id, seq.header, s[sn], self.product_type)
aligned_seqs.append(sequence)
return A3MAlignment(aligned_seqs, strict=self.strict)
class StructureAlignmentFactory(object):
"""
Protein structure alignment parser.
In order to construct the structural alignment, this factory needs a PDB
structure provider: an object, whose C{provider.get} method returns a
L{csb.bio.structute.Structure} for a given sequence identifier. Sequence
identifiers on the other hand need to be split into 'accession number'
and 'chain ID'. By default this is done using a standard PDB Entry ID
factory, but clients are free to provide custom factories. An C{id_factory}
must be a callable, which accepts a single string identifier and returns
an EntryID object.
@param provider: data source for all structures found in the alignment
@type provider: L{csb.bio.io.wwpdb.StructureProvider}
@param id_factory: callable factory, which transforms a sequence ID into
a L{csb.bio.io.wwpdb.EntryID} object. By default
this is L{csb.bio.io.wwpdb.EntryID.create}.
@type id_factory: callable
@param strict: if True, raise exception on duplicate sequence identifiers.
See L{csb.bio.sequence.AbstractAlignment} for details
@type strict: bool
"""
def __init__(self, provider, id_factory=None, strict=True):
from csb.bio.io.wwpdb import EntryID
if id_factory is None:
id_factory = EntryID.create
if not hasattr(id_factory, '__call__'):
raise TypeError(id_factory)
if not hasattr(provider, 'get'):
raise TypeError(provider)
self._type = SequenceTypes.Protein
self._strict = bool(strict)
self._provider = provider
self._id_factory = id_factory
@property
def product_type(self):
"""
Default sequence type of the alignment rows - a member of L{SequenceTypes}
@rtype: enum item
"""
return self._type
@property
def provider(self):
"""
Current L{csb.bio.io.wwpdb.StructureProvider} instance in use
@rtype: L{StructureProvider}
"""
return self._provider
@property
def id_factory(self):
"""
Current L{csb.bio.io.wwpdb.EntryID} factory instance in use
@rtype: L{EntryID}
"""
return self._id_factory
@property
def strict(self):
"""
True if strict mode is enabled
@rtype: bool
"""
return self._strict
def make_alignment(self, string):
"""
Build a protein structure alignment given a multi-FASTA string
and the current structure C{provider}.
@param string: alignment string
@type string: str
@rtype: L{SequenceAlignment}
@raise SequenceError: when an aligned sequence is not a proper
subsequence of its respective source PDB chain
@raise StructureNotFoundError: if C{provider} can't provide a structure
for a given sequence ID
@raise InvalidEntryIDError: if a given sequence ID cannot be parsed
"""
entries = []
parser = SequenceParser(Sequence, self.product_type)
sequences = parser.parse_string(string)
for row in sequences:
id = self.id_factory(row.id)
chain = self.provider.get(id.accession).chains[id.chain]
entry = self.make_entry(row, chain)
entries.append(entry)
return StructureAlignment(entries, strict=self.strict)
def make_entry(self, row, chain):
"""
Build a protein structure alignment entry, given a sequence alignment
entry and its corresponding source PDB chain.
@param row: sequence alignment entry (sequence with gaps)
@type row: L{AbstractSequence}, L{SequenceAdapter}
@param chain: source PDB chain
@type chain: L{csb.bio.structure.Chain}
@return: gapped chain sequence, containing cloned residues from the
source chain (except for the gaps)
@rtype: L{ChainSequence}
@raise SequenceError: when C{row} is not a proper subsequence of C{chain}
"""
offset = 1
residues = []
sequence = row.strip().sequence.upper()
try:
start = chain.sequence.index(sequence) + 1
except ValueError:
raise SequenceError('{0}: not a subsequence of {1}'.format(row.id, chain.entry_id))
for rinfo in row.residues:
if rinfo.type == row.alphabet.GAP:
residues.append(rinfo)
continue
else:
rank = start + offset - 1
assert chain.residues[rank].type == rinfo.type
residues.append(chain.residues[rank].clone())
offset += 1
continue
return ChainSequence(row.id, row.header, residues, chain.type)
class OutputBuilder(object):
"""
Base sequence/alignment string format builder.
@param output: destination stream, where the product is written.
@type output: file
@param headers: if False, omit headers
@type headers: bool
@note: File builders are not guaranteed to check the correctness of the
product. It is assumed that the client of the builder knows what
it is doing.
"""
__metaclass__ = ABCMeta
_registry = {}
def __init__(self, output, headers=True):
if not hasattr(output, 'write'):
raise TypeError(output)
self._out = output
self._headers = bool(headers)
@staticmethod
def create(format, *a, **k):
"""
Create an output builder, which knows how to handle the specified
sequence/alignment C{format}. Additional arguments are passed to the
builder's constructor.
@param format: L{AlignmentFormats} member
@type format: L{EnumItem}
@rtype: L{OutputBuilder}
"""
if format not in OutputBuilder._registry:
raise ValueError('Unhandled format: {0}'.format(format))
klass = OutputBuilder._registry[format]
return klass(*a, **k)
@staticmethod
def register(format, klass):
"""
Register a new output builder.
@param format: L{AlignmentFormats} member
@type format: L{EnumItem}
@param klass: builder class (L{OutputBuilder} sub-class)
@type klass: type
"""
assert format not in OutputBuilder._registry
assert issubclass(klass, OutputBuilder)
OutputBuilder._registry[format] = klass
@property
def output(self):
"""
Destination stream
@rtype: stream
"""
return self._out
@property
def headers(self):
"""
True if sequence headers will be written to the destination
@rtype: bool
"""
return self._headers
def write(self, text):
"""
Write a chunk of C{text} to the output stream.
"""
self._out.write(text)
def writeline(self, text):
"""
Write a chunk of C{text}, followed by a newline terminator.
"""
self._out.write(text)
self._out.write('\n')
@abstractmethod
def add_sequence(self, sequence):
"""
Format and append a new sequence to the product.
@type sequence: L{AbstractSequence}
"""
pass
def add_many(self, sequences):
"""
Format and append a collection of L{AbstractSequence}s to the product.
@type sequences: iterable of L{AbstractSequence}s
"""
for s in sequences:
self.add_sequence(s)
@abstractmethod
def add_alignment(self, alignment):
"""
Format and append an alignment to the product.
@type alignment: L{AbstractAlignment}
"""
pass
def add_separator(self, separator=''):
"""
Append a sequence separator to the product.
"""
self.writeline(separator)
def add_comment(self, text, comment='#', length=120):
"""
Append a comment line to the product.
@param text: comment text
@type text: str
@param comment: comment prefix
@type comment: str
@param length: maximal comment length
@type length: int
"""
for i in range(0, len(text), length):
self.write(comment)
self.write(' ')
self.write(text[i : i + length])
self.write('\n')
class FASTAOutputBuilder(OutputBuilder):
"""
Formats sequences as standard FASTA strings. See L{OutputBuilder}.
"""
FORMAT = AlignmentFormats.FASTA
def add_sequence(self, sequence):
if self.headers:
self.write(AbstractSequence.DELIMITER)
self.writeline(sequence.header)
insertion = str(sequence.alphabet.INSERTION)
gap = str(sequence.alphabet.GAP)
self.writeline(sequence.sequence.replace(insertion, gap))
def add_alignment(self, alignment):
self.add_many(alignment.rows)
class A3MOutputBuilder(OutputBuilder):
"""
Formats sequences as A3M strings. When appending an alignment, this builder
will write all insertion-containing columns in lower case. Also, gap symbols
are omitted if the respective columns contain insertions.
See L{OutputBuilder}.
"""
FORMAT = AlignmentFormats.A3M
def add_sequence(self, sequence):
if self.headers:
self.write(AbstractSequence.DELIMITER)
self.writeline(sequence.header)
self.writeline(sequence.sequence)
def add_alignment(self, alignment):
if isinstance(alignment, A3MAlignment):
self._add_a3m(alignment)
else:
self._add_proper(alignment)
def _add_a3m(self, alignment):
for s in alignment.rows:
if self.headers:
self.write(AbstractSequence.DELIMITER)
self.writeline(s.header)
sequence = []
for ci in s.columns:
if ci.residue.type != s.alphabet.INSERTION:
char = str(ci.residue.type)
if alignment.insertion_at(ci.column):
sequence.append(char.lower())
else:
sequence.append(char)
else:
continue
self.writeline(''.join(sequence))
def _add_proper(self, alignment):
for s in alignment.rows:
if self.headers:
self.write(AbstractSequence.DELIMITER)
self.writeline(s.header)
master = alignment.rows[1]
sequence = []
for ci in s.columns:
char = str(ci.residue.type)
if master.columns[ci.column].residue.type == master.alphabet.GAP:
if ci.residue.type == s.alphabet.GAP:
continue
else:
sequence.append(char.lower())
else:
sequence.append(char)
self.writeline(''.join(sequence))
class PIROutputBuilder(OutputBuilder):
"""
Formats sequences as PIR FASTA strings, recognized by Modeller.
See L{OutputBuilder} for general alignment documentation.
"""
FORMAT = AlignmentFormats.PIR
def add_sequence(self, sequence):
self._add(sequence, template=True)
def add_alignment(self, alignment):
for n, sequence in enumerate(alignment.rows, start=1):
if n == 1:
self.add_target(sequence)
else:
self.add_template(sequence)
def add_target(self, sequence):
self._add(sequence, template=False)
def add_template(self, sequence):
self._add(sequence, template=True)
def _add(self, sequence, template=True):
if self.headers:
if template:
type = 'structure'
else:
type = 'sequence'
id = sequence.id
start = end = '.'
if hasattr(sequence, 'start') and hasattr(sequence, 'end'):
start = sequence.start
end = sequence.end
header = 'P1;{0}\n{2}:{0}:{3}:{1}:{4}:{1}::::'.format(id[:-1], id[-1], type, start, end)
self.write(AbstractSequence.DELIMITER)
self.writeline(header)
insertion = str(sequence.alphabet.INSERTION)
gap = str(sequence.alphabet.GAP)
self.write(sequence.sequence.replace(insertion, gap))
self.writeline('*')
# register builders
for klass in OutputBuilder.__subclasses__():
OutputBuilder.register(klass.FORMAT, klass)
|