def test_large_sizes(self):
#Previous test failed on exterme coverage, testing that here
#result = peaks.shuffle(1000, 5, 0, .05, [48] * 5000)
#print "foo"
#print result
#self.assertEqual(sum(result), 5)
#lets try a different example
result = shuffle(136, 5, 0, .05, [48] * 2003)
#print "bar"
#print result
self.assertEqual(sum(result), 5)
def test_large_sizes(self):
#Previous test failed on exterme coverage, testing that here
#result = peaks.shuffle(1000, 5, 0, .05, [48] * 5000)
#print "foo"
#print result
#self.assertEqual(sum(result), 5)
#lets try a different example
result = shuffle(136, 5, 0, .05, [48] * 2003)
#print "bar"
#print result
self.assertEqual(sum(result), 5)
def test_shuffle(self):
#Case: fail on null inputs
self.assertRaises(TypeError, shuffle, (None, 1, 0, .05, [2, 3, 4]))
self.assertRaises(TypeError, shuffle, (1, None, 0, .05, [2, 3, 4]))
self.assertRaises(TypeError, shuffle, (1, 1, None, .05, [2, 3, 4]))
self.assertRaises(TypeError, shuffle, (1, 1, 0, None, [2, 3, 4]))
self.assertRaises(TypeError, shuffle, (1, 1, 0, .05, None))
#Case: fail on zero input for [] for the reads
self.assertRaises(TypeError, shuffle, (1, 1, 0, .05, []))
#case fail on zero input for either length or #iterations
self.assertRaises(TypeError, shuffle, (0, 1, 0, .05, [2, 3, 4]))
self.assertRaises(TypeError, shuffle, (1, 0, 0, .05, [2, 3, 4]))
#case succede and check results (need to figure how to lock down random for testing
result = shuffle(100, 3, 0, .05, [5] * 50)
self.assertEqual(sum(result), 3)
#reads longer than gene
self.assertEqual([0] * 100, shuffle(1, 1, 0, .05, [2, 3, 4]))
def test_shuffle(self):
#Case: fail on null inputs
self.assertRaises(TypeError, shuffle, (None, 1, 0, .05, [2,3,4]))
self.assertRaises(TypeError, shuffle, (1, None, 0, .05, [2,3,4]))
self.assertRaises(TypeError, shuffle, (1, 1, None, .05, [2,3,4]))
self.assertRaises(TypeError, shuffle, (1, 1, 0, None, [2,3,4]))
self.assertRaises(TypeError, shuffle, (1, 1, 0, .05, None))
#Case: fail on zero input for [] for the reads
self.assertRaises(TypeError, shuffle, (1,1,0,.05, []))
#case fail on zero input for either length or #iterations
self.assertRaises(TypeError, shuffle, (0, 1, 0, .05, [2,3,4]))
self.assertRaises(TypeError, shuffle, (1, 0, 0, .05, [2,3,4]))
#case succede and check results (need to figure how to lock down random for testing
result = shuffle(100, 3, 0,.05, [5] * 50 )
self.assertEqual(sum(result), 3)
#reads longer than gene
self.assertEqual([0] * 100, shuffle(1, 1, 0, .05, [2,3,4]))
def get_FDR_cutoff_mean(readlengths,
genelength,
iterations=100,
mincut=2,
alpha=0.05):
"""
Find randomized method, as in FOX2ES NSMB paper.
MEAN, not MODE
scatter reads, calcaluate number of reads to pass fdr threshold, takes average observed cutoff
readlengths -- list of lengths of aligned portions of reads
genelength -- effective gene length (unalignable regions aren't counted)
interations -- number of times to repeat FDR thresholding calculation
mincut -- min threshold possible to return
alpha -- FDR alpha
Returns an int, the number of reads needed to meet the FDR cutoff
TODO: Allow the minimum cutoff to be paramaritizied
TODO: double check math on this
"""
#if you have very few reads on a gene, don't waste time
#trying to find a cutoff
if len(readlengths) < 20:
return mincut
results = shuffle(int(genelength), int(iterations), 0, .05, readlengths)
total = 0
#parses results from peaks script, calculates mean from peaks results
#should document peaks function call return value somewhere around here
for cut, n_observed in enumerate(results):
total += (cut * n_observed)
#logic for min cutoffs
cutoff = total / iterations
if cutoff < mincut:
cutoff = mincut
return int(round(cutoff, 0))
def get_FDR_cutoff_mean(readlengths,
genelength,
iterations=100,
mincut=2,
alpha=0.05):
"""
Find randomized method, as in FOX2ES NSMB paper.
MEAN, not MODE
scatter reads, calcaluate number of reads to pass fdr threshold, takes average observed cutoff
readlengths -- list of lengths of aligned portions of reads
genelength -- effective gene length (unalignable regions aren't counted)
interations -- number of times to repeat FDR thresholding calculation
mincut -- min threshold possible to return
alpha -- FDR alpha
Returns an int, the number of reads needed to meet the FDR cutoff
TODO: Allow the minimum cutoff to be paramaritizied
TODO: double check math on this
"""
#if you have very few reads on a gene, don't waste time
#trying to find a cutoff
if len(readlengths) < 20:
return mincut
results = shuffle(int(genelength), int(iterations), 0, .05, readlengths)
total = 0
#parses results from peaks script, calculates mean from peaks results
#should document peaks function call return value somewhere around here
for cut, n_observed in enumerate(results):
total += (cut * n_observed)
#logic for min cutoffs
cutoff = total / iterations
if cutoff < mincut:
cutoff = mincut
return int(round(cutoff, 0))
def get_FDR_cutoff_mean(readlengths,
genelength,
iterations=100,
mincut=2,
alpha=0.05):
"""
Returns an int, the number of reads needed to meet the FDR cutoff by randomized method
TODO: Allow the minimum cutoff to be paramaritizied
TODO: double check math on this
:param readlengths: list, list of lengths of aligned portions of reads
:param genelength: int, effective gene length (unalignable regions aren't counted)
:param iterations: int, default 100
:param mincut: int, default 2, min threshold possible to return
:param alpha: float, default 0.05, FDR alpha
:return: int, min number of reads per position to read FDR
"""
# if you have very few reads on a gene, don't waste time
# trying to find a cutoff
if len(readlengths) < 20:
return mincut
results = shuffle(int(genelength), int(iterations), 0, .05, readlengths)
total = 0
# parses results from peaks script, calculates mean from peaks results
# should document peaks function call return value somewhere around here
for cut, n_observed in enumerate(results):
total += (cut * n_observed)
# logic for min cutoffs
cutoff = total / iterations
if cutoff < mincut:
cutoff = mincut
return int(round(cutoff, 0))
def test_small_sizes(self):
#makes sure it works on edge cases
result = shuffle(100, 3, 0, .05, [2, 3, 4])
print result
def test_super_large_sizes(self):
result = shuffle(4434885, 5, 0, .05, [48] * 2003)
#print "bar"
#print result
self.assertEqual(sum(result), 5)
def test_small_sizes(self):
#makes sure it works on edge cases
result = shuffle(100, 3, 0, .05, [2,3,4])
print result
def test_super_large_sizes(self):
result = shuffle(4434885, 5, 0, .05, [48] * 2003)
#print "bar"
#print result
self.assertEqual(sum(result), 5)