Skip to content

B
binfpy
Commit ac6c5d6b authored by Mikael Boden's avatar Mikael Boden
Browse files
Options

python3_5

parent 934c2bff
Expand all Hide whitespace changes
Inline Side-by-side
Showing with 860 additions and 1533 deletions
binomial.py
View file @ ac6c5d6b
......@@ -95,8 +95,8 @@ def betacf(a, b, x):
h *= delta
if (abs(delta-1.0) < EPS): break
if (m > MAXIT): print >> sys.stderr, ("a or b too big or MAXIT too small "
"in betacf")
if (m > MAXIT): print(("a or b too big or MAXIT too small "
"in betacf"), file=sys.stderr)
return h
......@@ -118,5 +118,5 @@ def gammaln(x):
def die(string):
print >> sys.stderr, string
print(string, file=sys.stderr)
genome.py
View file @ ac6c5d6b
......@@ -105,7 +105,7 @@ class GeneExpression:
{'G2': array([ 4.1, -0.9]), 'G3': array([ 2.1, -2.1])}
"""
if names == None:
return self.genes.keys()
return list(self.genes.keys())
elif isinstance(names, str):
return self.matrix[self.genes[names],:]
else:
......@@ -148,7 +148,7 @@ class GeneExpression:
except:
index = samples
mygenes = {}
for (name, ndx) in self.genes.items():
for (name, ndx) in list(self.genes.items()):
mygenes[name] = self.matrix[ndx, index]
return mygenes
......@@ -165,7 +165,7 @@ class GeneExpression:
sort_ndx = np.nan_to_num(self.matrix[:,index]).argsort()
except:
sort_ndx = np.nan_to_num(self.matrix[:,sample]).argsort()
name_tuples = sorted(self.genes.items(), key=lambda v: v[1]) # put all gene names in order of the matrix of profiles
name_tuples = sorted(list(self.genes.items()), key=lambda v: v[1]) # put all gene names in order of the matrix of profiles
names = []
if descending:
for (name, index) in [name_tuples[index] for index in sort_ndx[::-1]]: # reverse the order
......@@ -199,7 +199,7 @@ class GeneExpression:
Creates and returns a gene dictionary with the corresponding ratios. """
mygenes = {}
mdiv = self.matrix[:, index1] / self.matrix[:, index2]
for (name, ndx) in self.genes.items():
for (name, ndx) in list(self.genes.items()):
mygenes[name] = mdiv[ndx]
return mygenes
......@@ -208,7 +208,7 @@ class GeneExpression:
Creates and returns a gene dictionary with the corresponding log-ratios. """
mygenes = {}
mlr = np.log2(self.matrix[:, index1] / self.matrix[:, index2])
for (name, ndx) in self.genes.items():
for (name, ndx) in list(self.genes.items()):
mygenes[name] = mlr[ndx]
return mygenes
......@@ -218,7 +218,7 @@ class GeneExpression:
index = self.genes[probeID]
profile = self.matrix[index, :]
mygenes = {}
for (name, ndx) in self.genes.items():
for (name, ndx) in list(self.genes.items()):
other = self.matrix[ndx, :]
mygenes[name] = pearson(profile, other)
return mygenes
......@@ -252,7 +252,7 @@ class GeneExpression:
# Calculate Z-score for the given column for each gene
zscore = (self.matrix[:, index] - mu) / sd
mygenes = {}
for (name, ndx) in self.genes.items():
for (name, ndx) in list(self.genes.items()):
try:
mygenes[name] = zscore[ndx, :]
except IndexError:
......@@ -331,9 +331,9 @@ def readGEOFile(filename, id_column=0):
genes[name] = values
if len(genes) == 0:
raise RuntimeError('No data in file')
print 'Data set %s contains %d entries' % (dataset, len(genes))
print('Data set %s contains %d genes' % (dataset, len(genes)))
if cnt_null > 0:
print 'Data set has %d null-values' % (cnt_null)
print('Data set has %d null-values' % (cnt_null))
return GeneExpression(dataset, headers[2:], genes)
......@@ -357,40 +357,29 @@ def pearson(X, Y):
return 0
return (sum - n * (Xmu * Ymu)) / (n * math.sqrt(Xvar) * math.sqrt(Yvar))
# ------------------- Example ---------------------
# ------------------- Example (basically exercise 7 in prac 9)---------------------
ge3716 = readGEOFile('/Users/mikael/workspace/COSC2000/GDS3716.soft')
if __name__=='__main__':
ratio = GeneExpression('GDS3716_ratio')
ratio.addSamples('S1_ER+/Healthy', ge3716.getRatio( 33, 0))
ratio.addSamples('S2_ER+/Healthy', ge3716.getRatio( 34, 1))
ratio.addSamples('S3_ER+/Healthy', ge3716.getRatio( 35, 2))
ratio.addSamples('S4_ER+/Healthy', ge3716.getRatio( 36, 3))
ratio.addSamples('S5_ER+/Healthy', ge3716.getRatio( 37, 4))
ratio.addSamples('S6_ER+/Healthy', ge3716.getRatio( 38, 5))
ratio.addSamples('S7_ER+/Healthy', ge3716.getRatio( 39, 6))
ratio.addSamples('S8_ER+/Healthy', ge3716.getRatio( 40, 7))
ratio.addSamples('S9_ER+/Healthy', ge3716.getRatio( 41, 8))
ratio.addSamples('S1_ER-/Healthy', ge3716.getRatio( 24, 9))
ratio.addSamples('S2_ER-/Healthy', ge3716.getRatio( 25, 10))
ratio.addSamples('S3_ER-/Healthy', ge3716.getRatio( 26, 11))
ratio.addSamples('S4_ER-/Healthy', ge3716.getRatio( 27, 12))
ratio.addSamples('S5_ER-/Healthy', ge3716.getRatio( 28, 13))
ratio.addSamples('S6_ER-/Healthy', ge3716.getRatio( 29, 14))
ratio.addSamples('S7_ER-/Healthy', ge3716.getRatio( 30, 15))
ratio.addSamples('S8_ER-/Healthy', ge3716.getRatio( 31, 16))
ratio.addSamples('S9_ER-/Healthy', ge3716.getRatio( 32, 17))
ratio.writeGEOFile('/Users/mikael/workspace/COSC2000/GDS3716_ratios.soft')
print ge3716.getHeaders()
z = ratio.getZScore(0) # NOT recommended! Ratios are NOT normally distributed! Use log-ratios instead.
ge38 = readGEOFile('/Users/mikael/workspace/COSC2000/GDS38.soft', id_column = 1)
cln2_profile = ge38.getGenes('CLN2')
pcorr = ge38.getPearson('CLN2')
gp = GeneExpression('Ex3', 'PC_CLN2', pcorr)
sorted = gp.sort('PC_CLN2', True)
print sorted[0], ge38.getGenes(sorted[0])
print sorted[1], ge38.getGenes(sorted[1])
g = readGEOFile('GDS3198.soft', id_column = 1)
meanfold = {}
for gene in g.genes:
profile = g.getGenes(gene)
meanfold[gene] = (np.log2(profile[0] / profile[3]) + np.log2(profile[1] / profile[4]) + np.log2(profile[2] / profile[5])) / 3
import matplotlib.pyplot as plt
scores = [y for y in list(meanfold.values()) if not np.isnan(y)]
hist, bins = np.histogram(scores, bins=50)
width = 0.7 * (bins[1] - bins[0])
center = (bins[:-1] + bins[1:]) / 2
plt.bar(center, hist, align='center', width=width)
plt.show()
result = sorted(list(meanfold.items()), key=lambda v: v[1])
print('========== Wildtype may down-regulate ==========')
for r in result[0:100]:
print(r[0], r[1])
print('========== Wildtype may up-regulate ==========')
for r in result[-1:-100:-1]:
print(r[0], r[1])
gibbs.py
View file @ ac6c5d6b
......@@ -138,7 +138,7 @@ class GibbsMotif():
LL += math.log(Qk / Pk)
except ZeroDivisionError:
pass
print "LL @ %5d=\t%5.2f" % (round, LL)
print("LL @ %5d=\t%5.2f" % (round, LL))
# end main for-loop
self.q = q
......@@ -312,7 +312,7 @@ class GibbsAlign():
LL += math.log(Qk / Pk)
except ZeroDivisionError:
pass
print "LL @ %5d=\t%5.2f" % (round, LL)
print("LL @ %5d=\t%5.2f" % (round, LL))
# end main for-loop
self.q = q
......
godata.py
View file @ ac6c5d6b
This diff is collapsed.
guide.py
View file @ ac6c5d6b
This diff is collapsed.
ml.py
View file @ ac6c5d6b
......@@ -21,7 +21,7 @@ class NN():
self.b_hid = numpy.random.randn(nHidden) # biases hidden layer
self.w_out = numpy.random.randn(nOutput, nHidden) # weights hid -> out
self.b_out = numpy.random.randn(nOutput) # biases output layer
print "Constructed NN with %d inputs, %d hidden and %d output nodes." % (self.ninput, len(self.hidden), len(self.output))
print("Constructed NN with %d inputs, %d hidden and %d output nodes." % (self.ninput, len(self.hidden), len(self.output)))
def writeFile(self, filename):
""" Save NN to a file. """
......@@ -110,7 +110,7 @@ class NN():
multi_targ = [ target ]
for i in range(niter):
mse = 0.0
entries = range(len(multi_input))
entries = list(range(len(multi_input)))
if shuffle:
random.shuffle(entries)
for p in entries:
......
phylo.py
View file @ ac6c5d6b
......@@ -2,7 +2,7 @@
Module with methods and classes for phylogeny.
@author: mikael
'''
##import sequence
import sequence
class PhyloTree:
""" Rooted, binary (bifurcating) tree for representing phylogenetic relationships.
......@@ -140,7 +140,19 @@ class PhyloNode:
return left+','
elif self.left and self.right:
return '(' + left + ',' + right + ')' + dist
def __le__(self, other):
""" Returns indication of less than other node. """
return other and self.__hash__() <= other.__hash__()
def __eq__(self, other):
""" Returns indication of equivalence to other node. """
return other and self.__hash__() == other.__hash__()
def __hash__(self):
""" Returns hash of object. """
return hash((self.label, self.dist, self.sequence))
def _printSequences(self, start, end):
""" Returns string with node (incl descendants) in a Newick style. """
left = right = label = dist = ''
......@@ -352,12 +364,12 @@ def runUPGMA(aln, measure, absoluteDistances = False):
find the *closest* pair of clusters, and
merge that pair into a new cluster (to replace the two that merged).
In each case, the new cluster is represented by the (phylo)node that is formed. """
while len(N) > 1: # N will contain all "live" clusters, to be reduced to a signle below
while len(N) > 1: # N will contain all "live" clusters, to be reduced to a single below
closest_pair = (None, None) # The two nodes that are closest to one another according to supplied metric
closest_dist = None # The distance between them
for pair in D: # check all pairs which should be merged
dist = D[pair]
if dist < closest_dist or closest_dist == None:
if closest_dist == None or dist < closest_dist:
closest_dist = dist
closest_pair = pair
# So we know the closest, now we need to merge...
......@@ -365,8 +377,10 @@ def runUPGMA(aln, measure, absoluteDistances = False):
y = closest_pair[1]
z = PhyloNode() # create a new node for the cluster z
z.dist = D.pop(_getkey(x, y)) / 2.0 # assign the absolute distance, travelled so far, note: this will change to relative distance later
Nx = N.pop(x) # find number of sequences in x, remove the cluster from list N
Ny = N.pop(y) # find number of sequences in y, remove the cluster from list N
Nx = N.pop(x, None) # find number of sequences in x, remove the cluster from list N
Ny = N.pop(y, None) # find number of sequences in y, remove the cluster from list N
if Nx == None or Ny == None:
continue
dz = {} # new distances to cluster z
for w in N: # for each node w ...
# we will merge x and y into a new cluster z, so need to consider w (which is not x or y)
......
prob.py
View file @ ac6c5d6b
......@@ -277,7 +277,7 @@ def _readDistrib(linelist):
if len(d) == 0:
return None
alpha = Alphabet(symstr)
if '*' in d.keys(): # tot provided
if '*' in list(d.keys()): # tot provided
for sym in d:
if sym != '*':
d[sym] = d[sym] * d['*']
......@@ -338,7 +338,7 @@ def _readMultiCount(linelist, format = 'JASPAR'):
ncol = len(counts)
if len(name) == 1: # proper symbol
symcount[name] = counts
alpha = Alphabet(''.join(symcount.keys()))
alpha = Alphabet(''.join(list(symcount.keys())))
distribs = []
for col in range(ncol):
d = dict([(sym, symcount[sym][col]) for sym in symcount])
......@@ -412,7 +412,7 @@ def readMultiCount(filename, format = 'JASPAR'):
"""
d = readMultiCounts(filename, format=format)
if len(d) > 0:
return d.values()[0]
return list(d.values())[0]
#################################################################################################
# Joint class
......@@ -628,12 +628,12 @@ class IndepJoint(Joint):
def displayMatrix(self, count = False):
""" Pretty-print matrix """
print " \t%s" % (''.join("\t%5d" % (i + 1) for i in range(len(self.alphas))))
print((" \t%s" % (''.join("\t%5d" % (i + 1) for i in range(len(self.alphas))))))
for a in self.alphas[0]:
if count:
print "%s\t%s" % (a, ''.join("\t%5d" % (y) for y in self.getRow(a, True)))
print(("%s\t%s" % (a, ''.join("\t%5d" % (y) for y in self.getRow(a, True)))))
else:
print "%s\t%s" % (a, ''.join("\t%5.3f" % (y) for y in self.getRow(a)))
print(("%s\t%s" % (a, ''.join("\t%5.3f" % (y) for y in self.getRow(a)))))
def __str__(self):
""" Text representation of the table. Note that size is an issue so big tables
......@@ -718,5 +718,3 @@ class NaiveBayes():
prob *= condprob[i][key[i]] or 0.0
out.observe(outsym, prob)
return out
sam.py
View file @ ac6c5d6b
This diff is collapsed.
seqdata.py
View file @ ac6c5d6b
This diff is collapsed.
sequence.py
View file @ ac6c5d6b
......@@ -55,10 +55,11 @@ class Sequence(object):
['A', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'K', 'L', 'M', 'N', 'P', 'Q',
'R', 'S', 'T', 'V', 'W', 'Y'] """
try: # convert sequence data into a compact array representation
self.sequence = array.array('c', ''.join([s.upper() for s in sequence]))
except TypeError:
raise RuntimeError('Sequence data is not specified correctly: must be iterable')
#try: # convert sequence data into a compact array representation
# self.sequence = sequence.encode("utf-8") #array.array('b', ''.join([s.upper() for s in sequence]))
#except TypeError:
# raise RuntimeError('S"""""""""""""""""""""""""""""""equence data is not specified correctly: must be iterable')
self.sequence = sequence
# Assign an alphabet
self.alphabet = None
......@@ -133,15 +134,15 @@ class Sequence(object):
Calling self.__getitem__(3) is equivalent to self[3]
"""
if type(ndx) is slice:
return self.sequence[ndx].tostring()
return ''.join(self.sequence[ndx])
else:
return self.sequence[ndx]
def writeFasta(self):
""" Write one sequence in FASTA format to a string and return it. """
fasta = '>' + self.name + ' ' + self.info + '\n'
data = self.sequence.tostring()
nlines = (len(self.sequence) - 1) / 60 + 1
data = ''.join(self.sequence)
nlines = int(math.ceil((len(self.sequence) - 1) / 60 + 1))
for i in range(nlines):
lineofseq = ''.join(data[i*60 : (i+1)*60]) + '\n'
fasta += lineofseq
......@@ -164,7 +165,7 @@ class Sequence(object):
def find(self, findme):
""" Find the position of the specified symbol or sub-sequence """
return self.sequence.tostring().find(findme)
return ''.join(self.sequence).find(findme)
"""
Below are some useful methods for loading data from strings and files.
......@@ -438,8 +439,8 @@ class Alignment():
column index, entropy, number of gaps, and symbols in order of decreasing probability.
theta1 is the threshold for displaying symbols in upper case,
theta2 is the threshold for showing symbols at all, and in lower case. """
print "Alignment of %d sequences, with %d columns" % (len(self.seqs), self.alignlen)
print "Column\tEntropy\tGaps\tProb\tConserv\tSymbols (Up>=%.2f;Low>=%.2f)\n" % (theta1, theta2)
print(("Alignment of %d sequences, with %d columns" % (len(self.seqs), self.alignlen)))
print(("Column\tEntropy\tGaps\tProb\tConserv\tSymbols (Up>=%.2f;Low>=%.2f)\n" % (theta1, theta2)))
for col in range(self.alignlen):
d = Distrib(self.alphabet)
gaps = 0
......@@ -448,21 +449,21 @@ class Alignment():
d.observe(seq[col])
else:
gaps += 1
print (col + 1), "\t%5.3f" % d.entropy(), "\t%4d\t" % gaps,
print(((col + 1), "\t%5.3f" % d.entropy(), "\t%4d\t" % gaps,))
symprobs = d.getProbsort()
(_, maxprob) = symprobs[0]
if maxprob >= theta1:
print "%d\tTRUE\t" % int(maxprob * 100),
print(("%d\tTRUE\t" % int(maxprob * 100),))
else:
print "%d\t\t" % int(maxprob * 100),
print(("%d\t\t" % int(maxprob * 100),))
for (sym, prob) in symprobs:
if prob >= theta1:
print sym, "%d%%" % int(prob * 100),
print((sym, "%d%%" % int(prob * 100),))
elif prob >= theta2 and lowercase:
print sym.lower(), "%d%%" % int(prob * 100),
print((sym.lower(), "%d%%" % int(prob * 100),))
elif prob >= theta2:
print sym, "%d%%" % int(prob * 100),
print
print((sym, "%d%%" % int(prob * 100),))
print()
def saveConsensus(self, myseq, filename, theta1 = 0.2, theta2 = 0.05, lowercase = True, compact = False):
""" Display a table with rows for each alignment column, showing
......@@ -644,7 +645,7 @@ class Alignment():
return distmat
def writeHTML(self, filename=None):
""" Generate HTML that displays the alignment in color.
""" Generate HTML that displays the alignment in color.
Requires that the alphabet is annotated with the label 'html-color' (see Sequence.annotateSym)
and that each symbol maps to a text string naming the color, e.g. 'blue'
"""
......@@ -681,10 +682,9 @@ class Alignment():
htmlstr += html
htmlstr += '<pre>'
if filename:
fh = open(filename, 'w')
fh.write(htmlstr)
fh.write('</body></html>\n')
fh.close()
with open(filename, 'w+') as fh:
fh.write(htmlstr)
fh.write('</body></html>\n')
else:
return htmlstr
......@@ -985,12 +985,12 @@ def readClustal(string, alphabet):
index = name.find('/')
if index >= 0:
name = name[0:index]
if seqs.has_key(name):
if name in seqs:
seqs[name] += seqstr
else:
seqs[name] = seqstr
sequences = []
for name, seqstr in seqs.items():
for name, seqstr in list(seqs.items()):
sequences.append(Sequence(seqstr, alphabet, name, gappy = True))
return Alignment(sequences)
......@@ -1180,12 +1180,12 @@ class PWM(object):
def display(self, format = 'COLUMN'):
if format == 'COLUMN':
print " \t%s" % (' '.join(" %5d" % (i + 1) for i in range(self.length)))
print((" \t%s" % (' '.join(" %5d" % (i + 1) for i in range(self.length)))))
for j in range(len(self.alphabet)):
print "%s\t%s" % (self.alphabet[j], ' '.join("%+6.2f" % (y) for y in self.m[j]))
print(("%s\t%s" % (self.alphabet[j], ' '.join("%+6.2f" % (y) for y in self.m[j]))))
elif format == 'JASPAR':
for j in range(len(self.alphabet)):
print "%s\t[%s]" % (self.alphabet[j], ' '.join("%+6.2f" % (y) for y in self.m[j]))
print(("%s\t[%s]" % (self.alphabet[j], ' '.join("%+6.2f" % (y) for y in self.m[j]))))
def search(self, sequence, lowerBound=0):
""" Find matches to the motif in a specified sequence. Returns a list
......@@ -1229,7 +1229,7 @@ def getSequence(id, database = 'uniprotkb', start=None, end=None):
""" Get the sequence identified by the given ID from the given database
(e.g. 'uniprotkb', 'refseqn' or 'refseqp'), and return it as a Sequence
object. An error is caused if the sequence ID is not found. If start and
end are given, then only that section of the sequence is returned.
end are given, then only that section of the sequence is returned.
Note: more flexible search options are supported by using webservice.fetch
directly."""
......@@ -1237,12 +1237,12 @@ def getSequence(id, database = 'uniprotkb', start=None, end=None):
for i in range(MAX_TRY):
try:
fastaData = fetch(id, database)
fastaData = fetch(id, database).decode("utf-8")
seq = readFasta(fastaData)[0]
break
except:
from time import sleep
print 'Failed on {i}th try for id {id}'.format(i=i, id=id)
print(('Failed on {i}th try for id {id}'.format(i=i, id=id)))
sleep(0.1)
try:
return Sequence(seq[start:end], seq.alphabet, seq.name, seq.info)
......@@ -1319,5 +1319,4 @@ def runBLAST(sequence, program='blastp', database='uniprotkb', exp='1e-1'):
if __name__ == '__main__':
seqs = readFastaFile('/Users/mikael/ASR/CYP11/CYP11_aln_full.fa', Protein_wX, gappy=True)
print 'Read', len(seqs), 'sequences'
print(('Read', len(seqs), 'sequences'))
spred.py
View file @ ac6c5d6b
......@@ -71,7 +71,7 @@ class SeqNN():
im[row, _onehotIndex(alpha, subseqs[k])] = 1
if targets: om[row, self.outp_alpha.index(subtarg[k])] = 1
row += 1
print "There are", row, "entries in data set"
print("There are", row, "entries in data set")
if targets:
return im, om
else:
......@@ -85,7 +85,7 @@ class SeqNN():
im, om = self._encodeseq(seqs, targets)
for i in range(niter): # train first NN
rmse = self.nn1.train(im, om, eta = eta, niter = 1)
print i, ":", rmse
print(i, ":", rmse)
if not self.cascade: # if there's no cascaded NN, finish here
return rmse
nn1seqs = [] # a list of new SS sequences ...
......@@ -95,7 +95,7 @@ class SeqNN():
im, om = self._encodeseq(nn1seqs, targets) # construct input/output patterns from SS sequences
for i in range(niter): # train cascaded NN
rmse = self.nn2.train(im, om, eta = eta, niter = 1)
print i, ":", rmse
print(i, ":", rmse)
return rmse
def testAll(self, seqs, targets):
......
sstruct.py
View file @ ac6c5d6b
......@@ -85,7 +85,7 @@ def extendDownstream(scores, calls, width = 4):
specified width average of 100.
"""
sum = 0.0
order = range(0, len(calls) - 1, +1) # we are extending calls downstream
order = list(range(0, len(calls) - 1, +1)) # we are extending calls downstream
cnt = 0
for i in order: # extend to the right
if calls[i]: # to extend a call is required in the first place
......@@ -105,7 +105,7 @@ def extendUpstream(scores, calls, width = 4):
AND extend this list upstream containing a specified width average of 100.
"""
sum = 0.0
order = range(len(calls) - 1, 0, -1) # we are extending calls upstream/to-the-left
order = list(range(len(calls) - 1, 0, -1)) # we are extending calls upstream/to-the-left
cnt = 0
for i in order: # extend to the right
if calls[i]: # a requirement to extend is to have a call in the first place
......
sym.py
View file @ ac6c5d6b
......@@ -291,7 +291,7 @@ class TupleEntries(object):
def __iter__(self):
return self
def next(self):
def __next__(self):
""" Step through sequence of entries, either
(if not sparse) with a step-size based on alphabet-sizes and what symbols are specified or
(if sparse) with calls to tuple store based on all possible symbol combinations."""
......
webservice.py
View file @ ac6c5d6b
This diff is collapsed.
wordcount.py
View file @ ac6c5d6b
......@@ -45,7 +45,7 @@ def countWordsReport(seqs, WordWidth = 8, PeakWidth = 100, PeakMargin = 100):
neg[word] = 1
logratio = RCDict() # DNA dictionary for storing the log-ration between pos and neg
for (word, cnt_pos) in pos.items():
for (word, cnt_pos) in list(pos.items()):
cnt_neg = 0.0001
try:
cnt_neg = neg[word]
......@@ -53,10 +53,10 @@ def countWordsReport(seqs, WordWidth = 8, PeakWidth = 100, PeakMargin = 100):
pass
logratio[word] = math.log(float(cnt_pos) / float(cnt_neg))
allpos = logratio.items() # extract all pairs of words:log-ratio
allpos = list(logratio.items()) # extract all pairs of words:log-ratio
sortpos = sorted(allpos, key=lambda v: v[1], reverse=True) # sort them
print "Enriched words (sorted by ln pos/neg)"
print "Word \tln pos/neg\tE-value"
print("Enriched words (sorted by ln pos/neg)")
print("Word \tln pos/neg\tE-value")
for (word, lgr) in sortpos[0:100]: # Look at the top-entries according to log-ratio, compute e-values
cnt_pos = int(pos[word])
try: cnt_neg = int(neg[word])
......@@ -65,7 +65,7 @@ def countWordsReport(seqs, WordWidth = 8, PeakWidth = 100, PeakMargin = 100):
pval = stats.getFETpval(cnt_pos, cnt_neg, len(seqs) * (PeakWidth - WordWidth + 1) - cnt_pos, len(seqs) * (len(seq) - (PeakMargin * 2 + PeakWidth) - (WordWidth - 1) * 2) - cnt_neg, False)
# Correct for multiple testing (very conservatively)
eval = pval * len(allpos)
print "%s\t%6.3f \t%e" % (word, lgr, eval)
print("%s\t%6.3f \t%e" % (word, lgr, eval))
def getReverse(distribs):
""" Construct a new list of probability distributions of DNA, by
......@@ -94,10 +94,10 @@ def scanMotifReport(seqs, motif, threshold=0, jaspar = 'JASPAR_matrices.txt'):
except KeyError:
usage(sys.argv[0], "Unknown motif %s" % motif)
return
print "Motif %s:" % motif
print("Motif %s:" % motif)
pwm1 = sequence.PWM(fg1, bg)
pwm1.display(format='JASPAR')
print "Motif %s (reverse complement):" % motif
print("Motif %s (reverse complement):" % motif)
pwm2 = sequence.PWM(fg2, bg)
pwm2.display(format='JASPAR')
......@@ -141,7 +141,7 @@ def scanMotifReport(seqs, motif, threshold=0, jaspar = 'JASPAR_matrices.txt'):
# plot the average score curve
# print >> sys.stderr, ""
x = range(-(seq_len/2), (seq_len/2)) # call center of sequence X=0
x = list(range(-(seq_len/2), (seq_len/2))) # call center of sequence X=0
lbl = "%s" % (motif)
plt.plot(x, avg_motif_score, label=lbl)
#plt.plot(x, smoothed_avg_motif_score, label=lbl)
......@@ -187,10 +187,10 @@ def scanMotifReport_new(seqs, motif, threshold=3.4567, jaspar = 'JASPAR_matrices
except KeyError:
usage(sys.argv[0], "Unknown motif %s" % motif)
return
print "Motif %s:" % motif
print("Motif %s:" % motif)
pwm1 = sequence.PWM(fg1, bg)
pwm1.display(format='JASPAR')
print "Motif %s (reverse complement):" % motif
print("Motif %s (reverse complement):" % motif)
pwm2 = sequence.PWM(fg2, bg)
pwm2.display(format='JASPAR')
......@@ -222,7 +222,7 @@ def scanMotifReport_new(seqs, motif, threshold=3.4567, jaspar = 'JASPAR_matrices
# divide number of sequences with hit by total number of hits
site_probability = [ (cnt/n_seqs_with_hits) for cnt in hit_count ]
print >> sys.stderr, "Number of sequences with hit (score >= %f): %d" % (threshold, n_seqs_with_hits)
print("Number of sequences with hit (score >= %f): %d" % (threshold, n_seqs_with_hits), file=sys.stderr)
# STATISTICS
# Get the cumulative hit counts in concentric windows
......@@ -250,7 +250,7 @@ def scanMotifReport_new(seqs, motif, threshold=3.4567, jaspar = 'JASPAR_matrices
for i in range(hw, seq_len-motif_width+1-hw):
smoothed_site_probability[i]=sum(site_probability[i-hw:i+hw+1])/(2*hw+1)
x = range(-(seq_len/2), (seq_len/2)) # call center of sequence X=0
x = list(range(-(seq_len/2), (seq_len/2))) # call center of sequence X=0
lbl = "%s, t=%.2f" % (motif, threshold)
#lbl = "%s, t=%.2f, w=%d, p=%.2e" % (motif, threshold, best_r, math.exp(best_log_pvalue))
plt.plot(x, smoothed_site_probability, label=lbl)
......@@ -263,20 +263,20 @@ def scanMotifReport_new(seqs, motif, threshold=3.4567, jaspar = 'JASPAR_matrices
def usage(name, errmsg = None):
if errmsg != None:
print "Error: %s" % errmsg
print """Usage: %s [options]
print("Error: %s" % errmsg)
print("""Usage: %s [options]
-f <fasta-filename> (required)
-d discover enriched words
-w <word width, default 8>
-p <peak width, default 100>
-m <peak margin, default 100>
-s <JASPAR-ID> scan for JASPAR motif
-h print this help""" % name
-h print this help""" % name)
if __name__ == '__main__':
try:
optlst, args = getopt.getopt(sys.argv[1:], 'f:hds:j:w:p:m:')
except getopt.GetoptError, err:
except getopt.GetoptError as err:
usage(sys.argv[0], str(err))
sys.exit(2)
FILENAME = None
......@@ -301,7 +301,7 @@ if __name__ == '__main__':
sys.exit(3)
seqs = sequence.readFastaFile(FILENAME, sym.DNA_Alphabet_wN)
if DISCOVER_MODE:
print "Discover (f=%s; w=%d; p=%d; m=%d)" % (FILENAME, WORD_WIDTH, PEAK_WIDTH, PEAK_MARGIN)
print("Discover (f=%s; w=%d; p=%d; m=%d)" % (FILENAME, WORD_WIDTH, PEAK_WIDTH, PEAK_MARGIN))
countWordsReport(seqs, WORD_WIDTH, PEAK_WIDTH, PEAK_MARGIN)
elif SCAN_MODE:
scanMotifReport(seqs, MOTIF_ID)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment