/usr/lib/python3/dist-packages/csb/bio/sequence/alignment.py is in python3-csb 1.2.2+dfsg-2ubuntu1.
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 | """
Collection of sequence alignment algorithms.
@note: The classes in this module have been optimized for performance.
Think twice before switching a field to a generally nicer property
access, because it turns out that these things often add significant
constants to the running time of a dynamic programming algorithm.
"""
from csb.bio.sequence import AbstractSequence, SequenceAlignment, RichSequence, ResidueInfo
from abc import ABCMeta, abstractmethod
class ResidueNotFoundError(KeyError):
pass
class AbstractScoringMatrix(object):
"""
Defines a pairwise sequence alignment scoring function.
"""
__metaclass__ = ABCMeta
@abstractmethod
def score(self, x, y):
"""
Return the pairwise score of residues C{x} and C{y}.
C{x} and C{y} must be comparable (e.g. implement __eq__ and __hash__).
@param x: first residue
@type x: object
@param y: second residue
@type y: object
@rtype: float
@raise ResidueNotFoundError: if C{x} or C{y} cannot be handled by this
scoring matrix
"""
pass
class IdentityMatrix(AbstractScoringMatrix):
"""
Simple identity-based scoring matrix.
@param match: score for a match
@type match: float
@param mismatch: score for a mismatch
@type mismatch: float
"""
def __init__(self, match=1, mismatch=-1):
self._match = float(match)
self._mismatch = float(mismatch)
@property
def match(self):
"""
Score for a match
@rtype: float
"""
return self._match
@property
def mismatch(self):
"""
Score for a mismatch
@rtype: float
"""
return self._mismatch
def score(self, x, y):
if x == y:
return self._match
else:
return self._mismatch
class SimilarityMatrix(AbstractScoringMatrix):
"""
Similarity scoring matrix.
@param matrix:
"""
BLOSUM62 = {
'A': { 'A': 4.0, 'R':-1.0, 'N':-2.0, 'D':-2.0, 'C': 0.0, 'Q':-1.0, 'E':-1.0, 'G': 0.0, 'H':-2.0, 'I':-1.0, 'L':-1.0, 'K':-1.0, 'M':-1.0, 'F':-2.0, 'P':-1.0, 'S': 1.0, 'T': 0.0, 'W':-3.0, 'Y':-2.0, 'V': 0.0, 'B':-2.0, 'Z':-1.0, 'X': 0.0, '*':-4.0 },
'R': { 'A':-1.0, 'R': 5.0, 'N': 0.0, 'D':-2.0, 'C':-3.0, 'Q': 1.0, 'E': 0.0, 'G':-2.0, 'H': 0.0, 'I':-3.0, 'L':-2.0, 'K': 2.0, 'M':-1.0, 'F':-3.0, 'P':-2.0, 'S':-1.0, 'T':-1.0, 'W':-3.0, 'Y':-2.0, 'V':-3.0, 'B':-1.0, 'Z': 0.0, 'X':-1.0, '*':-4.0 },
'N': { 'A':-2.0, 'R': 0.0, 'N': 6.0, 'D': 1.0, 'C':-3.0, 'Q': 0.0, 'E': 0.0, 'G': 0.0, 'H': 1.0, 'I':-3.0, 'L':-3.0, 'K': 0.0, 'M':-2.0, 'F':-3.0, 'P':-2.0, 'S': 1.0, 'T': 0.0, 'W':-4.0, 'Y':-2.0, 'V':-3.0, 'B': 3.0, 'Z': 0.0, 'X':-1.0, '*':-4.0 },
'D': { 'A':-2.0, 'R':-2.0, 'N': 1.0, 'D': 6.0, 'C':-3.0, 'Q': 0.0, 'E': 2.0, 'G':-1.0, 'H':-1.0, 'I':-3.0, 'L':-4.0, 'K':-1.0, 'M':-3.0, 'F':-3.0, 'P':-1.0, 'S': 0.0, 'T':-1.0, 'W':-4.0, 'Y':-3.0, 'V':-3.0, 'B': 4.0, 'Z': 1.0, 'X':-1.0, '*':-4.0 },
'C': { 'A': 0.0, 'R':-3.0, 'N':-3.0, 'D':-3.0, 'C': 9.0, 'Q':-3.0, 'E':-4.0, 'G':-3.0, 'H':-3.0, 'I':-1.0, 'L':-1.0, 'K':-3.0, 'M':-1.0, 'F':-2.0, 'P':-3.0, 'S':-1.0, 'T':-1.0, 'W':-2.0, 'Y':-2.0, 'V':-1.0, 'B':-3.0, 'Z':-3.0, 'X':-2.0, '*':-4.0 },
'Q': { 'A':-1.0, 'R': 1.0, 'N': 0.0, 'D': 0.0, 'C':-3.0, 'Q': 5.0, 'E': 2.0, 'G':-2.0, 'H': 0.0, 'I':-3.0, 'L':-2.0, 'K': 1.0, 'M': 0.0, 'F':-3.0, 'P':-1.0, 'S': 0.0, 'T':-1.0, 'W':-2.0, 'Y':-1.0, 'V':-2.0, 'B': 0.0, 'Z': 3.0, 'X':-1.0, '*':-4.0 },
'E': { 'A':-1.0, 'R': 0.0, 'N': 0.0, 'D': 2.0, 'C':-4.0, 'Q': 2.0, 'E': 5.0, 'G':-2.0, 'H': 0.0, 'I':-3.0, 'L':-3.0, 'K': 1.0, 'M':-2.0, 'F':-3.0, 'P':-1.0, 'S': 0.0, 'T':-1.0, 'W':-3.0, 'Y':-2.0, 'V':-2.0, 'B': 1.0, 'Z': 4.0, 'X':-1.0, '*':-4.0 },
'G': { 'A': 0.0, 'R':-2.0, 'N': 0.0, 'D':-1.0, 'C':-3.0, 'Q':-2.0, 'E':-2.0, 'G': 6.0, 'H':-2.0, 'I':-4.0, 'L':-4.0, 'K':-2.0, 'M':-3.0, 'F':-3.0, 'P':-2.0, 'S': 0.0, 'T':-2.0, 'W':-2.0, 'Y':-3.0, 'V':-3.0, 'B':-1.0, 'Z':-2.0, 'X':-1.0, '*':-4.0 },
'H': { 'A':-2.0, 'R': 0.0, 'N': 1.0, 'D':-1.0, 'C':-3.0, 'Q': 0.0, 'E': 0.0, 'G':-2.0, 'H': 8.0, 'I':-3.0, 'L':-3.0, 'K':-1.0, 'M':-2.0, 'F':-1.0, 'P':-2.0, 'S':-1.0, 'T':-2.0, 'W':-2.0, 'Y': 2.0, 'V':-3.0, 'B': 0.0, 'Z': 0.0, 'X':-1.0, '*':-4.0 },
'I': { 'A':-1.0, 'R':-3.0, 'N':-3.0, 'D':-3.0, 'C':-1.0, 'Q':-3.0, 'E':-3.0, 'G':-4.0, 'H':-3.0, 'I': 4.0, 'L': 2.0, 'K':-3.0, 'M': 1.0, 'F': 0.0, 'P':-3.0, 'S':-2.0, 'T':-1.0, 'W':-3.0, 'Y':-1.0, 'V': 3.0, 'B':-3.0, 'Z':-3.0, 'X':-1.0, '*':-4.0 },
'L': { 'A':-1.0, 'R':-2.0, 'N':-3.0, 'D':-4.0, 'C':-1.0, 'Q':-2.0, 'E':-3.0, 'G':-4.0, 'H':-3.0, 'I': 2.0, 'L': 4.0, 'K':-2.0, 'M': 2.0, 'F': 0.0, 'P':-3.0, 'S':-2.0, 'T':-1.0, 'W':-2.0, 'Y':-1.0, 'V': 1.0, 'B':-4.0, 'Z':-3.0, 'X':-1.0, '*':-4.0 },
'K': { 'A':-1.0, 'R': 2.0, 'N': 0.0, 'D':-1.0, 'C':-3.0, 'Q': 1.0, 'E': 1.0, 'G':-2.0, 'H':-1.0, 'I':-3.0, 'L':-2.0, 'K': 5.0, 'M':-1.0, 'F':-3.0, 'P':-1.0, 'S': 0.0, 'T':-1.0, 'W':-3.0, 'Y':-2.0, 'V':-2.0, 'B': 0.0, 'Z': 1.0, 'X':-1.0, '*':-4.0 },
'M': { 'A':-1.0, 'R':-1.0, 'N':-2.0, 'D':-3.0, 'C':-1.0, 'Q': 0.0, 'E':-2.0, 'G':-3.0, 'H':-2.0, 'I': 1.0, 'L': 2.0, 'K':-1.0, 'M': 5.0, 'F': 0.0, 'P':-2.0, 'S':-1.0, 'T':-1.0, 'W':-1.0, 'Y':-1.0, 'V': 1.0, 'B':-3.0, 'Z':-1.0, 'X':-1.0, '*':-4.0 },
'F': { 'A':-2.0, 'R':-3.0, 'N':-3.0, 'D':-3.0, 'C':-2.0, 'Q':-3.0, 'E':-3.0, 'G':-3.0, 'H':-1.0, 'I': 0.0, 'L': 0.0, 'K':-3.0, 'M': 0.0, 'F': 6.0, 'P':-4.0, 'S':-2.0, 'T':-2.0, 'W': 1.0, 'Y': 3.0, 'V':-1.0, 'B':-3.0, 'Z':-3.0, 'X':-1.0, '*':-4.0 },
'P': { 'A':-1.0, 'R':-2.0, 'N':-2.0, 'D':-1.0, 'C':-3.0, 'Q':-1.0, 'E':-1.0, 'G':-2.0, 'H':-2.0, 'I':-3.0, 'L':-3.0, 'K':-1.0, 'M':-2.0, 'F':-4.0, 'P': 7.0, 'S':-1.0, 'T':-1.0, 'W':-4.0, 'Y':-3.0, 'V':-2.0, 'B':-2.0, 'Z':-1.0, 'X':-2.0, '*':-4.0 },
'S': { 'A': 1.0, 'R':-1.0, 'N': 1.0, 'D': 0.0, 'C':-1.0, 'Q': 0.0, 'E': 0.0, 'G': 0.0, 'H':-1.0, 'I':-2.0, 'L':-2.0, 'K': 0.0, 'M':-1.0, 'F':-2.0, 'P':-1.0, 'S': 4.0, 'T': 1.0, 'W':-3.0, 'Y':-2.0, 'V':-2.0, 'B': 0.0, 'Z': 0.0, 'X': 0.0, '*':-4.0 },
'T': { 'A': 0.0, 'R':-1.0, 'N': 0.0, 'D':-1.0, 'C':-1.0, 'Q':-1.0, 'E':-1.0, 'G':-2.0, 'H':-2.0, 'I':-1.0, 'L':-1.0, 'K':-1.0, 'M':-1.0, 'F':-2.0, 'P':-1.0, 'S': 1.0, 'T': 5.0, 'W':-2.0, 'Y':-2.0, 'V': 0.0, 'B':-1.0, 'Z':-1.0, 'X': 0.0, '*':-4.0 },
'W': { 'A':-3.0, 'R':-3.0, 'N':-4.0, 'D':-4.0, 'C':-2.0, 'Q':-2.0, 'E':-3.0, 'G':-2.0, 'H':-2.0, 'I':-3.0, 'L':-2.0, 'K':-3.0, 'M':-1.0, 'F': 1.0, 'P':-4.0, 'S':-3.0, 'T':-2.0, 'W': 11.0,'Y': 2.0, 'V':-3.0, 'B':-4.0, 'Z':-3.0, 'X':-2.0, '*':-4.0 },
'Y': { 'A':-2.0, 'R':-2.0, 'N':-2.0, 'D':-3.0, 'C':-2.0, 'Q':-1.0, 'E':-2.0, 'G':-3.0, 'H': 2.0, 'I':-1.0, 'L':-1.0, 'K':-2.0, 'M':-1.0, 'F': 3.0, 'P':-3.0, 'S':-2.0, 'T':-2.0, 'W': 2.0, 'Y': 7.0, 'V':-1.0, 'B':-3.0, 'Z':-2.0, 'X':-1.0, '*':-4.0 },
'V': { 'A': 0.0, 'R':-3.0, 'N':-3.0, 'D':-3.0, 'C':-1.0, 'Q':-2.0, 'E':-2.0, 'G':-3.0, 'H':-3.0, 'I': 3.0, 'L': 1.0, 'K':-2.0, 'M': 1.0, 'F':-1.0, 'P':-2.0, 'S':-2.0, 'T': 0.0, 'W':-3.0, 'Y':-1.0, 'V': 4.0, 'B':-3.0, 'Z':-2.0, 'X':-1.0, '*':-4.0 },
'B': { 'A':-2.0, 'R':-1.0, 'N': 3.0, 'D': 4.0, 'C':-3.0, 'Q': 0.0, 'E': 1.0, 'G':-1.0, 'H': 0.0, 'I':-3.0, 'L':-4.0, 'K': 0.0, 'M':-3.0, 'F':-3.0, 'P':-2.0, 'S': 0.0, 'T':-1.0, 'W':-4.0, 'Y':-3.0, 'V':-3.0, 'B': 4.0, 'Z': 1.0, 'X':-1.0, '*':-4.0 },
'Z': { 'A':-1.0, 'R': 0.0, 'N': 0.0, 'D': 1.0, 'C':-3.0, 'Q': 3.0, 'E': 4.0, 'G':-2.0, 'H': 0.0, 'I':-3.0, 'L':-3.0, 'K': 1.0, 'M':-1.0, 'F':-3.0, 'P':-1.0, 'S': 0.0, 'T':-1.0, 'W':-3.0, 'Y':-2.0, 'V':-2.0, 'B': 1.0, 'Z': 4.0, 'X':-1.0, '*':-4.0 },
'X': { 'A': 0.0, 'R':-1.0, 'N':-1.0, 'D':-1.0, 'C':-2.0, 'Q':-1.0, 'E':-1.0, 'G':-1.0, 'H':-1.0, 'I':-1.0, 'L':-1.0, 'K':-1.0, 'M':-1.0, 'F':-1.0, 'P':-2.0, 'S': 0.0, 'T': 0.0, 'W':-2.0, 'Y':-1.0, 'V':-1.0, 'B':-1.0, 'Z':-1.0, 'X':-1.0, '*':-4.0 },
'*': { 'A':-4.0, 'R':-4.0, 'N':-4.0, 'D':-4.0, 'C':-4.0, 'Q':-4.0, 'E':-4.0, 'G':-4.0, 'H':-4.0, 'I':-4.0, 'L':-4.0, 'K':-4.0, 'M':-4.0, 'F':-4.0, 'P':-4.0, 'S':-4.0, 'T':-4.0, 'W':-4.0, 'Y':-4.0, 'V':-4.0, 'B':-4.0, 'Z':-4.0, 'X':-4.0, '*': 1.0 }
}
def __init__(self, matrix=BLOSUM62):
self._matrix = matrix
def score(self, x, y):
try:
return self._matrix[x][y]
except KeyError as ke:
raise ResidueNotFoundError(ke.message)
@staticmethod
def parse(string):
"""
Parse a standard scoring matrix file, where the first row and
column are residue labels.
@param string: scoring matrix string
@type string: str
@rtype: L{SimilarityMatrix}
"""
residues = {}
matrix = {}
for line in string.splitlines():
if not line.strip() or line.startswith("#"):
continue
if not residues:
residues = line.split()
else:
items = line.split()
if len(items) != len(residues) + 1:
raise ValueError("{0} scoring columns expected".format(len(residues)))
try:
aa, scores = items[0], map(float, items[1:])
matrix[aa] = dict((residues[i], s) for i, s in enumerate(scores))
except (KeyError, ValueError):
raise ValueError("Corrupt scoring matrix")
return SimilarityMatrix(matrix)
class AbstractAlignmentAlgorithm(object):
"""
Base class for all sequence alignment algorithms.
This class was designed with simple sequence alignment algorithms in mind.
Implementors have full control over the behavior of the scoring function and
the dynamic programming matrix, but implementing things that require
additional matrices (such as affine gap penalties) might be trickier.
@param scoring: scoring matrix
@type scoring: L{AbstractScoringMatrix}
@param gap: simple gap penalty
@type gap: float
"""
__metaclass__ = ABCMeta
def __init__(self, scoring=IdentityMatrix(), gap=0):
if not isinstance(scoring, AbstractScoringMatrix):
raise TypeError(scoring)
self._gap = float(gap)
self._scoring = scoring
@property
def gap(self):
"""
Simple gap penalty
@rtype: float
"""
return self._gap
@property
def scoring_matrix(self):
"""
Scoring matrix
@rtype: L{AbstractScoringMatrix}
"""
return self._scoring
def align(self, query, subject):
"""
Align two sequences and return the optimal alignment.
@param query: first sequence
@type query: L{AbstractSequence}
@param subject: second sequence
@type subject: L{AbstractSequence}
@rtype: L{AlignmentResult}
"""
if query.length == 0 or subject.length == 0:
raise ValueError("Can't align zero length sequence")
# working with string sequences results in a massive speed-up
qseq = ["*"] + self._sequence(query)
sseq = ["*"] + self._sequence(subject)
# 1. create a dynamic programming matrix
matrix = []
rows, cols = len(query), len(subject)
for i in range(rows + 1):
matrix.append([])
for j in range(cols + 1):
matrix[i].append(None)
# 2. initialize the first row and column
self._initialize(matrix)
# fill
for i in range(1, rows + 1):
for j in range(1, cols + 1):
score = self._score(qseq[i], sseq[j])
self._fill(matrix, i, j, score)
# 3. compute alignment
return self._traceback(matrix, query, subject)
def _sequence(self, s):
"""
Extract and return the string sequence of {s}.
@param s: sequence object
@type s: L{AbstractSequence}
@rtype: list of str
"""
return list(s.sequence)
@abstractmethod
def _initialize(self, matrix):
"""
Initialize (typically the first row and column) of the dynamic
programming matrix.
@param matrix: list (2D)
@type matrix: list
"""
pass
def _score(self, residue1, residue2):
"""
Retrieve the pairwise score of two residues using the current
scoring matrix.
@rtype: float
"""
return self._scoring.score(residue1, residue2)
def _fill(self, matrix, i, j, score):
"""
Compute and set the best score that leads to cell i,j in the dynamic
programming matrix: right, down or diagonal.
See also L{AbstractAlignmentAlgorithm._max}.
@param score: pairwise score at matrix[i][j]
@type score: float
@return: the best score
@rtype: float
"""
match = matrix[i-1][j-1] + score
insertion = matrix[i][j-1] + self._gap
deletion = matrix[i-1][j] + self._gap
best = self._max(match, insertion, deletion)
matrix[i][j] = best
return best
@abstractmethod
def _max(self, match, insertion, deletion):
"""
Choose the best score among all given possibilities:
scores for match, insertion and deletion. This will determine
the direction taken at each step while building the dynamic programming
matrix (diagonal, down or right).
This is an expected notable point of divergence for most sequence
alignment algorithms.
"""
pass
def _traceback(self, m, seq1, seq2):
"""
Trace back and return the optimal alignment.
"""
query = []
subject = []
# working with string sequences results in a massive speed-up
qseq = ["*"] + self._sequence(seq1)
sseq = ["*"] + self._sequence(seq2)
i, j = self._terminus(m)
qstart, start = i, j
qend, end = i, j
score = m[i][j]
while self._expandable(m, i, j):
if i > 0 and j > 0 and m[i][j] == (m[i-1][j-1] + self._score(qseq[i], sseq[j])):
query.append(seq1.residues[i])
subject.append(seq2.residues[j])
qstart, start = i, j
i, j = i - 1, j - 1
elif i > 0 and m[i][j] == (m[i-1][j] + self._gap):
query.append(seq1.residues[i])
subject.append(ResidueInfo(-1, seq2.alphabet.GAP))
qstart = i
i = i - 1
elif j > 0 and m[i][j] == (m[i][j-1] + self._gap):
query.append(ResidueInfo(-1, seq1.alphabet.GAP))
subject.append(seq2.residues[j])
start = j
j = j - 1
else:
assert False
query.reverse()
subject.reverse()
aligned_query = RichSequence(seq1.id, seq1.header, query, seq1.type)
aligned_subject = RichSequence(seq2.id, seq2.header, subject, seq2.type)
return AlignmentResult(score, aligned_query, aligned_subject, qstart, qend, start, end)
@abstractmethod
def _terminus(self, matrix):
"""
Find the coordinates of the optimal alignment's right endpoint in the
dynamic programming matrix. This is the starting point of a traceback.
@param matrix: the complete dynamic programming matrix
@type matrix: 2D list
@rtype: 2-tuple (i, j)
"""
pass
@abstractmethod
def _expandable(self, i, j):
"""
Return True if the traceback procedure must not terminate at
position C{i,j} in the dynamic programming matrix.
@rtype: bool
"""
pass
class GlobalAlignmentAlgorithm(AbstractAlignmentAlgorithm):
"""
Needleman-Wunsch global sequence alignment.
"""
def __init__(self, scoring=IdentityMatrix(), gap=0):
super(GlobalAlignmentAlgorithm, self).__init__(scoring, gap)
def _initialize(self, matrix):
for i in range(len(matrix)):
matrix[i][0] = self._gap * i
for j in range(len(matrix[0])):
matrix[0][j] = self._gap * j
def _max(self, match, insertion, deletion):
return max(match, insertion, deletion)
def _terminus(self, matrix):
i = len(matrix) - 1
j = len(matrix[0]) - 1
return (i, j)
def _expandable(self, matrix, i, j):
return i > 0 or j > 0
class LocalAlignmentAlgorithm(AbstractAlignmentAlgorithm):
"""
Smith-Waterman local sequence alignment.
"""
START = 0
"""
Score for initiation of a new local alignment
"""
def __init__(self, scoring=IdentityMatrix(), gap=-1):
super(LocalAlignmentAlgorithm, self).__init__(scoring, gap)
def _initialize(self, matrix):
for i in range(len(matrix)):
matrix[i][0] = LocalAlignmentAlgorithm.START
for j in range(len(matrix[0])):
matrix[0][j] = LocalAlignmentAlgorithm.START
def _max(self, match, insertion, deletion):
return max(match, insertion, deletion, LocalAlignmentAlgorithm.START)
def _terminus(self, matrix):
maxi, maxj = 0, 0
for i in range(len(matrix)):
for j in range(len(matrix[i])):
if matrix[i][j] > matrix[maxi][maxj]:
maxi, maxj = i, j
return (maxi, maxj)
def _expandable(self, matrix, i, j):
return matrix[i][j] != LocalAlignmentAlgorithm.START
class AlignmentResult(object):
"""
Represents a pairwise sequence alignment result.
@param score: raw alignment score
@type score: float
@param query: aligned query sequence (with gaps)
@type query: L{AbstractSequence}
@param subject: aligned subject sequence (with gaps)
@type subject: L{AbstractSequence}
@param qstart: query start position
@type qstart: int
@param qend: query end position
@type qend: int
@param start: subject start position
@type start: int
@param end: subject end position
@type end: int
"""
def __init__(self, score, query, subject, qstart, qend, start, end):
if not isinstance(query, AbstractSequence):
raise TypeError(query)
if not isinstance(subject, AbstractSequence):
raise TypeError(query)
if not (len(query) == len(subject)):
raise ValueError("Corrupt alignment")
self._score = float(score)
self._query = query
self._subject = subject
self._qstart = int(qstart)
self._qend = int(qend)
self._start = int(start)
self._end = int(end)
self._identicals = 0
self._gaps = 0
self._length = 0
if query.length > 0 and subject.length > 0:
if not 1 <= qstart <= qend:
raise ValueError("Invalid query start/end positions")
if not 1 <= start <= end:
raise ValueError("Invalid subject start/end positions")
qgap = query.alphabet.GAP
sgap = subject.alphabet.GAP
for q, s in zip(query, subject):
if q.type == qgap or s.type == sgap:
self._gaps += 1
elif q.type == s.type:
self._identicals += 1
self._length = (self._gaps + (qend - qstart + 1) + (end - start + 1)) / 2
else:
if (score + qstart + qend + start + end) != 0:
raise ValueError("Corrupt alignment")
self._length = 0
def __str__(self):
string = "{0.qstart:5} {0.query.sequence:} {0.qend:<5}\n"
string += "{0.start:5} {0.subject.sequence:} {0.end:<5}"
return string.format(self)
@property
def is_empty(self):
"""
Return True if this is an empty alignment (i.e. no matches)
@rtype: bool
"""
return self.length == 0 or self.gaps == self.length
@property
def score(self):
"""
Raw alignment score
@rtype: float
"""
return self._score
@property
def query(self):
"""
Aligned query sequence (with gaps)
@rtype: L{AbstractSequence}
"""
return self._query
@property
def subject(self):
"""
Aligned subject sequence (with gaps)
@rtype: L{AbstractSequence}
"""
return self._subject
@property
def qstart(self):
"""
Query start position
@rtype: int
"""
return self._qstart
@property
def qend(self):
"""
Query end position
@rtype: int
"""
return self._qend
@property
def start(self):
"""
Subject start position
@rtype: int
"""
return self._start
@property
def end(self):
"""
Subject end position
@rtype: int
"""
return self._end
@property
def identicals(self):
"""
Number of identical residues
@rtype: int
"""
return self._identicals
@property
def identity(self):
"""
Percentage of identical residues
@rtype: int
"""
return float(self._identicals) / self._length
@property
def gaps(self):
"""
Total number of gaps (query + subject)
@rtype: int
"""
return self._gaps
@property
def length(self):
"""
Alignment length (query + subject + gaps / 2)
@rtype: int
"""
return self._length
def alignment(self):
"""
@return: as a sequence alignment object
@rtype: L{SequenceAlignment}
"""
return SequenceAlignment([self.query, self.subject])
|