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
|
"""
Data structure for performing intersect queries on a set of intervals which
preserves all information about the intervals (unlike bitset projection methods).
:Authors: James Taylor (james@jamestaylor.org),
Ian Schenk (ian.schenck@gmail.com),
Brent Pedersen (bpederse@gmail.com)
"""
# Historical note:
# This module original contained an implementation based on sorted endpoints
# and a binary search, using an idea from Scott Schwartz and Piotr Berman.
# Later an interval tree implementation was implemented by Ian for Galaxy's
# join tool (see `bx.intervals.operations.quicksect.py`). This was then
# converted to Cython by Brent, who also added support for
# upstream/downstream/neighbor queries. This was modified by James to
# handle half-open intervals strictly, to maintain sort order, and to
# implement the same interface as the original Intersecter.
#cython: cdivision=True
import operator
cdef extern from "stdlib.h":
int ceil(float f)
float log(float f)
int RAND_MAX
int rand()
int strlen(char *)
int iabs(int)
cdef inline int imax2(int a, int b):
if b > a: return b
return a
cdef inline int imax3(int a, int b, int c):
if b > a:
if c > b:
return c
return b
if a > c:
return a
return c
cdef inline int imin3(int a, int b, int c):
if b < a:
if c < b:
return c
return b
if a < c:
return a
return c
cdef inline int imin2(int a, int b):
if b < a: return b
return a
cdef float nlog = -1.0 / log(0.5)
cdef class IntervalNode:
"""
A single node of an `IntervalTree`.
NOTE: Unless you really know what you are doing, you probably should us
`IntervalTree` rather than using this directly.
"""
cdef float priority
cdef public object interval
cdef public int start, end
cdef int minend, maxend, minstart
cdef IntervalNode cleft, cright, croot
property left_node:
def __get__(self):
return self.cleft if self.cleft is not EmptyNode else None
property right_node:
def __get__(self):
return self.cright if self.cright is not EmptyNode else None
property root_node:
def __get__(self):
return self.croot if self.croot is not EmptyNode else None
def __repr__(self):
return "IntervalNode(%i, %i)" % (self.start, self.end)
def __cinit__(IntervalNode self, int start, int end, object interval):
# Python lacks the binomial distribution, so we convert a
# uniform into a binomial because it naturally scales with
# tree size. Also, python's uniform is perfect since the
# upper limit is not inclusive, which gives us undefined here.
self.priority = ceil(nlog * log(-1.0/(1.0 * rand()/RAND_MAX - 1)))
self.start = start
self.end = end
self.interval = interval
self.maxend = end
self.minstart = start
self.minend = end
self.cleft = EmptyNode
self.cright = EmptyNode
self.croot = EmptyNode
cpdef IntervalNode insert(IntervalNode self, int start, int end, object interval):
"""
Insert a new IntervalNode into the tree of which this node is
currently the root. The return value is the new root of the tree (which
may or may not be this node!)
"""
cdef IntervalNode croot = self
# If starts are the same, decide which to add interval to based on
# end, thus maintaining sortedness relative to start/end
cdef int decision_endpoint = start
if start == self.start:
decision_endpoint = end
if decision_endpoint > self.start:
# insert to cright tree
if self.cright is not EmptyNode:
self.cright = self.cright.insert( start, end, interval )
else:
self.cright = IntervalNode( start, end, interval )
# rebalance tree
if self.priority < self.cright.priority:
croot = self.rotate_left()
else:
# insert to cleft tree
if self.cleft is not EmptyNode:
self.cleft = self.cleft.insert( start, end, interval)
else:
self.cleft = IntervalNode( start, end, interval)
# rebalance tree
if self.priority < self.cleft.priority:
croot = self.rotate_right()
croot.set_ends()
self.cleft.croot = croot
self.cright.croot = croot
return croot
cdef IntervalNode rotate_right(IntervalNode self):
cdef IntervalNode croot = self.cleft
self.cleft = self.cleft.cright
croot.cright = self
self.set_ends()
return croot
cdef IntervalNode rotate_left(IntervalNode self):
cdef IntervalNode croot = self.cright
self.cright = self.cright.cleft
croot.cleft = self
self.set_ends()
return croot
cdef inline void set_ends(IntervalNode self):
if self.cright is not EmptyNode and self.cleft is not EmptyNode:
self.maxend = imax3(self.end, self.cright.maxend, self.cleft.maxend)
self.minend = imin3(self.end, self.cright.minend, self.cleft.minend)
self.minstart = imin3(self.start, self.cright.minstart, self.cleft.minstart)
elif self.cright is not EmptyNode:
self.maxend = imax2(self.end, self.cright.maxend)
self.minend = imin2(self.end, self.cright.minend)
self.minstart = imin2(self.start, self.cright.minstart)
elif self.cleft is not EmptyNode:
self.maxend = imax2(self.end, self.cleft.maxend)
self.minend = imin2(self.end, self.cleft.minend)
self.minstart = imin2(self.start, self.cleft.minstart)
def intersect( self, int start, int end, sort=True ):
"""
given a start and a end, return a list of features
falling within that range
"""
cdef list results = []
self._intersect( start, end, results )
return results
find = intersect
cdef void _intersect( IntervalNode self, int start, int end, list results):
# Left subtree
if self.cleft is not EmptyNode and self.cleft.maxend > start:
self.cleft._intersect( start, end, results )
# This interval
if ( self.end > start ) and ( self.start < end ):
results.append( self.interval )
# Right subtree
if self.cright is not EmptyNode and self.start < end:
self.cright._intersect( start, end, results )
cdef void _seek_left(IntervalNode self, int position, list results, int n, int max_dist):
# we know we can bail in these 2 cases.
if self.maxend + max_dist < position:
return
if self.minstart > position:
return
# the ordering of these 3 blocks makes it so the results are
# ordered nearest to farest from the query position
if self.cright is not EmptyNode:
self.cright._seek_left(position, results, n, max_dist)
if -1 < position - self.end < max_dist:
results.append(self.interval)
# TODO: can these conditionals be more stringent?
if self.cleft is not EmptyNode:
self.cleft._seek_left(position, results, n, max_dist)
cdef void _seek_right(IntervalNode self, int position, list results, int n, int max_dist):
# we know we can bail in these 2 cases.
if self.maxend < position: return
if self.minstart - max_dist > position: return
#print "SEEK_RIGHT:",self, self.cleft, self.maxend, self.minstart, position
# the ordering of these 3 blocks makes it so the results are
# ordered nearest to farest from the query position
if self.cleft is not EmptyNode:
self.cleft._seek_right(position, results, n, max_dist)
if -1 < self.start - position < max_dist:
results.append(self.interval)
if self.cright is not EmptyNode:
self.cright._seek_right(position, results, n, max_dist)
cpdef left(self, position, int n=1, int max_dist=2500):
"""
find n features with a start > than `position`
f: a Interval object (or anything with an `end` attribute)
n: the number of features to return
max_dist: the maximum distance to look before giving up.
"""
cdef list results = []
# use start - 1 becuase .left() assumes strictly left-of
self._seek_left( position - 1, results, n, max_dist )
if len(results) == n: return results
r = results
r.sort(key=operator.attrgetter('end'), reverse=True)
return r[:n]
cpdef right(self, position, int n=1, int max_dist=2500):
"""
find n features with a end < than position
f: a Interval object (or anything with a `start` attribute)
n: the number of features to return
max_dist: the maximum distance to look before giving up.
"""
cdef list results = []
# use end + 1 becuase .right() assumes strictly right-of
self._seek_right(position + 1, results, n, max_dist)
if len(results) == n: return results
r = results
r.sort(key=operator.attrgetter('start'))
return r[:n]
def traverse(self, func):
self._traverse(func)
cdef void _traverse(IntervalNode self, object func):
if self.cleft is not EmptyNode: self.cleft._traverse(func)
func(self)
if self.cright is not EmptyNode: self.cright._traverse(func)
cdef IntervalNode EmptyNode = IntervalNode( 0, 0, Interval(0, 0))
## ---- Wrappers that retain the old interface -------------------------------
cdef class Interval:
"""
Basic feature, with required integer start and end properties.
Also accepts optional strand as +1 or -1 (used for up/downstream queries),
a name, and any arbitrary data is sent in on the info keyword argument
>>> from bx.intervals.intersection import Interval
>>> from collections import OrderedDict
>>> f1 = Interval(23, 36)
>>> f2 = Interval(34, 48, value=OrderedDict([('chr', 12), ('anno', 'transposon')]))
"""
cdef public int start, end
cdef public object value, chrom, strand
def __init__(self, int start, int end, object value=None, object chrom=None, object strand=None ):
assert start <= end, "start must be less than end"
self.start = start
self.end = end
self.value = value
self.chrom = chrom
self.strand = strand
def __repr__(self):
fstr = "Interval(%d, %d" % (self.start, self.end)
if not self.value is None:
fstr += ", value=" + str(self.value)
fstr += ")"
return fstr
def __richcmp__(self, other, op):
if op == 0:
# <
return self.start < other.start or self.end < other.end
elif op == 1:
# <=
return self == other or self < other
elif op == 2:
# ==
return self.start == other.start and self.end == other.end
elif op == 3:
# !=
return self.start != other.start or self.end != other.end
elif op == 4:
# >
return self.start > other.start or self.end > other.end
elif op == 5:
# >=
return self == other or self > other
cdef class IntervalTree:
"""
Data structure for performing window intersect queries on a set of
of possibly overlapping 1d intervals.
Usage
=====
Create an empty IntervalTree
>>> from bx.intervals.intersection import Interval, IntervalTree
>>> intersecter = IntervalTree()
An interval is a start and end position and a value (possibly None).
You can add any object as an interval:
>>> intersecter.insert( 0, 10, "food" )
>>> intersecter.insert( 3, 7, dict(foo='bar') )
>>> intersecter.find( 2, 5 )
['food', {'foo': 'bar'}]
If the object has start and end attributes (like the Interval class) there
is are some shortcuts:
>>> intersecter = IntervalTree()
>>> intersecter.insert_interval( Interval( 0, 10 ) )
>>> intersecter.insert_interval( Interval( 3, 7 ) )
>>> intersecter.insert_interval( Interval( 3, 40 ) )
>>> intersecter.insert_interval( Interval( 13, 50 ) )
>>> intersecter.find( 30, 50 )
[Interval(3, 40), Interval(13, 50)]
>>> intersecter.find( 100, 200 )
[]
Before/after for intervals
>>> intersecter.before_interval( Interval( 10, 20 ) )
[Interval(3, 7)]
>>> intersecter.before_interval( Interval( 5, 20 ) )
[]
Upstream/downstream
>>> intersecter.upstream_of_interval(Interval(11, 12))
[Interval(0, 10)]
>>> intersecter.upstream_of_interval(Interval(11, 12, strand="-"))
[Interval(13, 50)]
>>> intersecter.upstream_of_interval(Interval(1, 2, strand="-"), num_intervals=3)
[Interval(3, 7), Interval(3, 40), Interval(13, 50)]
"""
cdef IntervalNode root
def __cinit__( self ):
root = None
# ---- Position based interfaces -----------------------------------------
def insert( self, int start, int end, object value=None ):
"""
Insert the interval [start,end) associated with value `value`.
"""
if self.root is None:
self.root = IntervalNode( start, end, value )
else:
self.root = self.root.insert( start, end, value )
add = insert
def find( self, start, end ):
"""
Return a sorted list of all intervals overlapping [start,end).
"""
if self.root is None:
return []
return self.root.find( start, end )
def before( self, position, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie before `position` and are no
further than `max_dist` positions away
"""
if self.root is None:
return []
return self.root.left( position, num_intervals, max_dist )
def after( self, position, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie after `position` and are no
further than `max_dist` positions away
"""
if self.root is None:
return []
return self.root.right( position, num_intervals, max_dist )
# ---- Interval-like object based interfaces -----------------------------
def insert_interval( self, interval ):
"""
Insert an "interval" like object (one with at least start and end
attributes)
"""
self.insert( interval.start, interval.end, interval )
add_interval = insert_interval
def before_interval( self, interval, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie completely before `interval`
and are no further than `max_dist` positions away
"""
if self.root is None:
return []
return self.root.left( interval.start, num_intervals, max_dist )
def after_interval( self, interval, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie completely after `interval` and
are no further than `max_dist` positions away
"""
if self.root is None:
return []
return self.root.right( interval.end, num_intervals, max_dist )
def upstream_of_interval( self, interval, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie completely upstream of
`interval` and are no further than `max_dist` positions away
"""
if self.root is None:
return []
if interval.strand == -1 or interval.strand == "-":
return self.root.right( interval.end, num_intervals, max_dist )
else:
return self.root.left( interval.start, num_intervals, max_dist )
def downstream_of_interval( self, interval, num_intervals=1, max_dist=2500 ):
"""
Find `num_intervals` intervals that lie completely downstream of
`interval` and are no further than `max_dist` positions away
"""
if self.root is None:
return []
if interval.strand == -1 or interval.strand == "-":
return self.root.left( interval.start, num_intervals, max_dist )
else:
return self.root.right( interval.end, num_intervals, max_dist )
def traverse(self, fn):
"""
call fn for each element in the tree
"""
if self.root is None:
return None
return self.root.traverse(fn)
# For backward compatibility
Intersecter = IntervalTree
|