def testUnique(seqs, Ws, prefixes=('ACA',)):
"""Check we count the unique W-mers correctly by counting them in
an independent way."""
import seqan
import numpy as npy
from jemima.wmers import countWmersMulti
index = seqan.IndexStringDNA5SetESA(seqs)
counts = npy.zeros((2*len(index), len(Ws)), dtype=int)
numunique = countWmersMulti(
index.topdownhistory(), Ws, counts, countunique=True)
unique = _countUnique(seqs, Ws)
if (npy.array([len(unique[W]) for W in Ws]) != numunique).all():
raise ValueError('Counts did not match.')
for prefix in prefixes:
it = index.topdownhistory()
if not it.goDown(prefix):
raise ValueError('Prefix "%s" does not exist in text' % prefix)
for Widx, W in enumerate(Ws):
count1 = len(filter(
lambda wmer: wmer.startswith(prefix), unique[W]))
count2 = counts[it.value.id, Widx]
if count1 != count2:
raise ValueError(
'Counts for "%s" did not match: %s != %s' % (
prefix, count1, count2))
def testUnique(seqs, Ws, prefixes=('ACA', )):
"""Check we count the unique W-mers correctly by counting them in
an independent way."""
import seqan
import numpy as npy
from jemima.wmers import countWmersMulti
index = seqan.IndexStringDNA5SetESA(seqs)
counts = npy.zeros((2 * len(index), len(Ws)), dtype=int)
numunique = countWmersMulti(index.topdownhistory(),
Ws,
counts,
countunique=True)
unique = _countUnique(seqs, Ws)
if (npy.array([len(unique[W]) for W in Ws]) != numunique).all():
raise ValueError('Counts did not match.')
for prefix in prefixes:
it = index.topdownhistory()
if not it.goDown(prefix):
raise ValueError('Prefix "%s" does not exist in text' % prefix)
for Widx, W in enumerate(Ws):
count1 = len(
filter(lambda wmer: wmer.startswith(prefix), unique[W]))
count2 = counts[it.value.id, Widx]
if count1 != count2:
raise ValueError('Counts for "%s" did not match: %s != %s' %
(prefix, count1, count2))
def _countWmers(index, Ws, countunique):
counts = npy.zeros((2*len(index), len(Ws)), dtype=npy.uint)
rootcounts = wmers.countWmersMulti(
index.topdownhistory(), Ws, counts, countunique=countunique)
# Count how many W-mers are represented by the children
# of each node
childfreqs = npy.zeros((2*len(index), len(Ws), jem.SIGMA))
wmers.countChildren(
index.topdownhistory(), Ws, counts, childfreqs)
childfreqs = jem.normalisearray(childfreqs)
return rootcounts, counts, childfreqs
def _countWmers(index, Ws, countunique):
counts = npy.zeros((2 * len(index), len(Ws)), dtype=npy.uint)
rootcounts = wmers.countWmersMulti(index.topdownhistory(),
Ws,
counts,
countunique=countunique)
# Count how many W-mers are represented by the children
# of each node
childfreqs = npy.zeros((2 * len(index), len(Ws), jem.SIGMA))
wmers.countChildren(index.topdownhistory(), Ws, counts, childfreqs)
childfreqs = jem.normalisearray(childfreqs)
return rootcounts, counts, childfreqs
def countWmersMulti(it, Ws, counts, countunique=True):
"""Count all the :math:`W`-mer occurrences (or unique W-mers)
below the iterator for multiple widths, Ws.
Arguments:
- *it*: The iterator below which to count occurrences.
- *Ws*: The widths to count for.
- *counts*: The counts array of shape
(2*len(index), len(Ws))
- *countunique*: If true, count the number of unique W-mers below
each vertex for each width. Otherwise count the number of
occurrences.
"""
nodecounts = counts[it.value.id]
maxW = Ws[-1]
firstunknown = findfirstparentunknown(it, maxW)
# Do we have to descend any further? Is our representative as long as
# largest W? Did we find an unknown base?
if firstunknown == it.repLength and it.repLength < maxW:
# Yes we should descend so go down and add up counts from child nodes
if it.goDown():
while True:
nodecounts += countWmersMulti(it, Ws, counts, countunique)
if not it.goRight():
break
it.goUp()
# Determine which Ws our representative is longer than
longestWidx = bisect.bisect(Ws, firstunknown)
# Determine which Ws our parent representative is longer than
parentWidx = not it.isRoot and bisect.bisect(
Ws[:longestWidx],
it.repLength - it.parentEdgeLength) or 0
# Set those counts to number of occurrences
if countunique:
nodecounts[parentWidx:longestWidx] = 1
else:
nodecounts[parentWidx:longestWidx] = it.numOccurrences
return nodecounts
def countWmersMulti(it, Ws, counts, countunique=True):
"""Count all the :math:`W`-mer occurrences (or unique W-mers)
below the iterator for multiple widths, Ws.
Arguments:
- *it*: The iterator below which to count occurrences.
- *Ws*: The widths to count for.
- *counts*: The counts array of shape
(2*len(index), len(Ws))
- *countunique*: If true, count the number of unique W-mers below
each vertex for each width. Otherwise count the number of
occurrences.
"""
nodecounts = counts[it.value.id]
maxW = Ws[-1]
firstunknown = findfirstparentunknown(it, maxW)
# Do we have to descend any further? Is our representative as long as
# largest W? Did we find an unknown base?
if firstunknown == it.repLength and it.repLength < maxW:
# Yes we should descend so go down and add up counts from child nodes
if it.goDown():
while True:
nodecounts += countWmersMulti(it, Ws, counts, countunique)
if not it.goRight():
break
it.goUp()
# Determine which Ws our representative is longer than
longestWidx = bisect.bisect(Ws, firstunknown)
# Determine which Ws our parent representative is longer than
parentWidx = not it.isRoot and bisect.bisect(
Ws[:longestWidx], it.repLength - it.parentEdgeLength) or 0
# Set those counts to number of occurrences
if countunique:
nodecounts[parentWidx:longestWidx] = 1
else:
nodecounts[parentWidx:longestWidx] = it.numOccurrences
return nodecounts
# jem.logo(runx1pwm, 'runx1')
# jem.logo(runx1withpc, 'runx1-pc')
logging.info('Loading sequences')
# seqs = seqan.StringDNASet(('AAAAAAAA', 'ACGTACGT', 'TATATATA'))
numbases, seqs, ids = seqan.readFastaDNA('T00759-small.fa')
logging.info('Loaded %d bases from %d sequences', numbases, len(seqs))
lambda_ = len(seqs) / float(numbases)
logging.info('Building index')
index = seqan.IndexStringDNASetESA(seqs)
logging.info('Counting W-mers')
Ws = [W]
Wmercounts = npy.zeros((2*len(index), len(Ws)), dtype=npy.uint)
numWmers = wmers.countWmersMulti(index.topdownhistory(), Ws, Wmercounts)[0]
logging.info('Got %d %d-mers', numWmers, W)
childWmerfreqs = npy.zeros((2*len(index), len(Ws), jem.SIGMA))
wmers.countWmerChildren(index.topdownhistory(), W, Wmercounts, childWmerfreqs)
childWmerfreqs = jem.normalisearray(childWmerfreqs)
sumestimator = jis.makesumestimator(numWmers)
logging.info('Importance sampling using background model to find one seed')
rdm.seed(2)
memocb = jis.importancesample(
index, W, childWmerfreqs[:, 0], jis.UniformImportanceWeight(),
numsamples=1, callback=jis.ISCbMemo())
pwm = jem.pwmfromWmer(memocb.Xns[0], numseedsites, 1.)
jem.logo(pwm, 'seed')
numsamples = 3000