def detect_differentially_abundant_features(seqGroup1, seqGroup2,
parentSeqGroup1, parentSeqGroup2,
coverage, B, preferences,
progress):
numFeatures = len(seqGroup1)
n1 = len(seqGroup1[0])
n2 = len(seqGroup2[0])
# convert to proportions
propGroup1 = []
for r in xrange(0, numFeatures):
row = []
for c in xrange(0, n1):
row.append(float(seqGroup1[r][c]) / parentSeqGroup1[r][c])
propGroup1.append(row)
propGroup2 = []
for r in xrange(0, numFeatures):
row = []
for c in xrange(0, n2):
row.append(float(seqGroup2[r][c]) / parentSeqGroup2[r][c])
propGroup2.append(row)
# calculate t-statistics for unpooled variances for each feature
T_statistics, effectSizes, notes = calc_twosample_ts(
propGroup1, propGroup2)
# generate statistics using non-parametric t-test based on permutations of the t-statistic
pValuesOneSided, pValuesTwoSided, lowerCIs, upperCIs = permuted_statistics(
propGroup1, propGroup2, seqGroup1, seqGroup2, T_statistics, coverage,
B, progress)
if progress != None and progress.wasCanceled():
return [], [], [], [], [], []
# generate p values for sparse data using fisher's exact test
fishers = Fishers(preferences)
diffBetweenProp = DiffBetweenPropAsymptoticCC(preferences)
for r in xrange(0, numFeatures):
if sum(seqGroup1[r]) < n1 and sum(seqGroup2[r]) < n2:
p1, p2, note = fishers.hypothesisTest(sum(seqGroup1[r]),
sum(seqGroup2[r]),
sum(parentSeqGroup1[r]),
sum(parentSeqGroup2[r]))
l, u, es, note = diffBetweenProp.run(sum(seqGroup1[r]),
sum(seqGroup2[r]),
sum(parentSeqGroup1[r]),
sum(parentSeqGroup2[r]),
coverage)
pValuesOneSided[r] = p1
pValuesTwoSided[r] = p2
lowerCIs[r] = l
upperCIs[r] = u
effectSizes[r] = es
notes[r] = "heuristic: statistics calculated with Fisher's test"
return pValuesOneSided, pValuesTwoSided, lowerCIs, upperCIs, effectSizes, notes
def testDiffBetweenPropAsymptoticCC(self): """Verify computation of Difference between proportions asymptotic CI method with continuity correction""" from stamp.plugins.samples.confidenceIntervalMethods.DiffBetweenPropAsymptoticCC import DiffBetweenPropAsymptoticCC diffBetweenPropAsymptoticCC = DiffBetweenPropAsymptoticCC(preferences) lowerCI, upperCI, effectSize, _ = diffBetweenPropAsymptoticCC.run(table1[0], table1[1], table1[2], table1[3], 0.95) self.assertAlmostEqual(lowerCI, -13.3167148125733) self.assertAlmostEqual(upperCI, 39.98338147924) self.assertAlmostEqual(effectSize, 13.333333333) lowerCI, upperCI, effectSize, _ = diffBetweenPropAsymptoticCC.run(table2[0], table2[1], table2[2], table2[3], 0.95) self.assertAlmostEqual(lowerCI, 0.271407084568653) self.assertAlmostEqual(upperCI, 0.328592915431347) self.assertAlmostEqual(effectSize, 0.3)
def detect_differentially_abundant_features(seqGroup1, seqGroup2, parentSeqGroup1, parentSeqGroup2, coverage, B, preferences, progress): numFeatures = len(seqGroup1) n1 = len(seqGroup1[0]) n2 = len(seqGroup2[0]) # convert to proportions propGroup1 = [] for r in xrange(0, numFeatures): row = [] for c in xrange(0, n1): row.append(float(seqGroup1[r][c]) / parentSeqGroup1[r][c]) propGroup1.append(row) propGroup2 = [] for r in xrange(0, numFeatures): row = [] for c in xrange(0, n2): row.append(float(seqGroup2[r][c]) / parentSeqGroup2[r][c]) propGroup2.append(row) # calculate t-statistics for unpooled variances for each feature T_statistics, effectSizes, notes = calc_twosample_ts(propGroup1, propGroup2) # generate statistics using non-parametric t-test based on permutations of the t-statistic pValuesOneSided, pValuesTwoSided, lowerCIs, upperCIs = permuted_statistics(propGroup1, propGroup2, seqGroup1, seqGroup2, T_statistics, coverage, B, progress) if progress != None and progress.wasCanceled(): return [], [], [], [], [], [] # generate p values for sparse data using fisher's exact test fishers = Fishers(preferences) diffBetweenProp = DiffBetweenPropAsymptoticCC(preferences) for r in xrange(0, numFeatures): if sum(seqGroup1[r]) < n1 and sum(seqGroup2[r]) < n2: p1, p2, note = fishers.hypothesisTest(sum(seqGroup1[r]), sum(seqGroup2[r]), sum(parentSeqGroup1[r]), sum(parentSeqGroup2[r])) l, u, es, note = diffBetweenProp.run(sum(seqGroup1[r]), sum(seqGroup2[r]), sum(parentSeqGroup1[r]), sum(parentSeqGroup2[r]), coverage) pValuesOneSided[r] = p1 pValuesTwoSided[r] = p2 lowerCIs[r] = l upperCIs[r] = u effectSizes[r] = es notes[r] = "heuristic: statistics calculated with Fisher's test" return pValuesOneSided, pValuesTwoSided, lowerCIs, upperCIs, effectSizes, notes