def getNBPValue(mean0, var0, mean1, lower=False, log=False):
"""
Use negative binomial to calculate p-value
Reference:
http://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.nbinom.html#scipy.stats.nbinom
"""
from scipy.stats import nbinom
n = len(mean0)
nb_p = [mean0[i] / var0[i] for i in range(n)]
# consisitent with R
nb_n0 = [mean0[i] * mean0[i] / (var0[i] - mean0[i]) for i in range(n)]
nb_n = [(lambda t: t if t >= 1 else 1)(x) for x in nb_n0]
#
if lower == True:
if log == False:
nb_p_low = nbinom.cdf(mean1, nb_n, nb_p)
else:
nb_p_low = nbinom.logcdf(mean1, nb_n, nb_p)
return list(nb_p_low)
else:
if log == False:
nb_p_low = nbinom.sf(mean1, nb_n, nb_p)
else:
nb_p_low = nbinom.logsf(mean1, nb_n, nb_p)
return list(nb_p_low)
def nbinom_logsf(x, mu, dispersion):
# for zero mus this will be assigned to -100
res = -100.0 * np.ones(mu.shape, dtype=np.float64)
p = dispersion / (dispersion + mu)
res[mu > 0.0] = nbinom.logsf(x[mu > 0.0], dispersion, p[mu > 0.0])
return res
def getNBPValue(mean0,var0,mean1, lower=False,log=False):
"""
Use negative binomial to calculate p-value
Reference:
http://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.nbinom.html#scipy.stats.nbinom
"""
from scipy.stats import nbinom
n=len(mean0)
nb_p=[mean0[i]/var0[i] for i in range(n)]; # consisitent with R
nb_n0=[mean0[i]*mean0[i]/(var0[i]-mean0[i]) for i in range(n)]
nb_n=[ (lambda t: t if t>=1 else 1)(x) for x in nb_n0]
#
if lower==True:
if log==False:
nb_p_low=nbinom.cdf(mean1,nb_n,nb_p)
else:
nb_p_low=nbinom.logcdf(mean1,nb_n,nb_p)
return list(nb_p_low)
else:
if log==False:
nb_p_low=nbinom.sf(mean1,nb_n,nb_p)
else:
nb_p_low=nbinom.logsf(mean1,nb_n,nb_p)
return list(nb_p_low)
def GetSitesForGene(data):
'''
This function determines for each gene the score of the sites
'''
#Computing the probabilities for the current gene
Sites, gene, nr_of_genes, gene_nr, seq_file, bck_file, EmissionParameters, TransitionParameters, TransitionTypeFirst, fg_state, merge_neighbouring_sites, minimal_site_length = data
#Turn the Sequence and Bacground objects into dictionaries again such that the subsequent methods for using these do not need to be modified
if len(Sites) == 0:
return gene, []
NrOfStates = EmissionParameters['NrOfStates']
Sites = dict([(gene, Sites)])
Sequences = h5py.File(EmissionParameters['DataOutFile_seq'], 'r')
Background = h5py.File(EmissionParameters['DataOutFile_bck'], 'r')
Sequences_per_gene = PreloadSequencesForGene(Sequences, gene)
Background_per_gene = PreloadSequencesForGene(Background, gene)
Ix = GetModelIx(Sequences_per_gene, Type='all')
if np.sum(Ix) == 0:
return gene, []
if EmissionParameters['FilterSNPs']:
Ix = GetModelIx(Sequences_per_gene, Type='no_snps_conv', snps_thresh=EmissionParameters['SnpRatio'], snps_min_cov=EmissionParameters['SnpAbs'], Background=Background_per_gene)
else:
Ix = GetModelIx(Sequences_per_gene, Type='Conv')
#Only compute the emission probability for regions where a site is
ix_sites = np.zeros_like(Ix)
ix_sites_len = Ix.shape[0]
for currsite in Sites[gene]:
ix_sites[max(0, currsite[0] - 1) : min(ix_sites_len, currsite[1] + 1)] = 1
ix_sites = ix_sites == 1
#2) Compute the probabilities for both states
EmmisionProbGene = np.log(np.ones((NrOfStates, Ix.shape[0])) * (1 / np.float64(NrOfStates)))
CurrStackSum = StackData(Sequences_per_gene)
CurrStackVar = StackData(Sequences_per_gene, add = 'no')
CurrStackSumBck = StackData(Background_per_gene, add = 'only_cov')
CurrStackVarSumm = StackData(Sequences_per_gene, add = 'only_var_summed')
EmmisionProbGeneDir = np.zeros_like(EmmisionProbGene)
if EmissionParameters['glm_weight'] < 0.0:
weight1 = 1.0
weight2 = 1.0
elif EmissionParameters['glm_weight'] == 0.0:
weight1 = 0.0000001
weight2 = 1.0 - weight1
elif EmissionParameters['glm_weight'] == 1.0:
weight1 = 0.9999999
weight2 = 1.0 - weight1
else:
weight1 = EmissionParameters['glm_weight']
weight2 = (1.0 - EmissionParameters['glm_weight'])
for State in range(NrOfStates):
EmmisionProbGene[State, ix_sites] = np.log(weight1) + emission_prob.predict_expression_log_likelihood_for_gene(CurrStackSum[:, ix_sites], State, nr_of_genes, gene_nr, EmissionParameters)
if EmissionParameters['BckType'] == 'Coverage':
EmmisionProbGene[State, ix_sites] += np.log(weight1) + emission_prob.predict_expression_log_likelihood_for_gene(CurrStackSumBck[:, ix_sites], State, nr_of_genes, gene_nr, EmissionParameters, 'bg')
if EmissionParameters['BckType'] == 'Coverage_bck':
EmmisionProbGene[State, ix_sites] += np.log(weight1) + emission_prob.predict_expression_log_likelihood_for_gene(CurrStackSumBck[:, ix_sites], State, nr_of_genes, gene_nr, EmissionParameters, 'bg')
EmmisionProbGeneDir[State, Ix] = np.log(weight2) + diag_event_model.pred_log_lik(CurrStackVar[:, Ix], State, EmissionParameters)
EmmisionProbGene[State, Ix] += np.log(weight2) + EmmisionProbGeneDir[State, Ix]
Counts = StackData(Sequences_per_gene, add = 'all')
Score = EmmisionProbGene
CurrStack = CurrStackVar
#Compute the scores when staying in the same state
#RowIx = list(range(16)) + list(range(17, 38)) + list(range(39,44))
strand = Sequences_per_gene['strand']
#Get the coverages for the froeground and background
CountsSeq = StackData(Sequences_per_gene, add = 'only_cov')
CountsBck = StackData(Background_per_gene, add = 'only_cov')
if strand == 0:
strand = -1
#Since we the transition probabilty is the same for all States we do not need to compute it for the bayes factor
#this list contains the returned sites
sites = []
for currsite in Sites[gene]:
mean_mat_fg, var_mat_fg, mean_mat_bg, var_mat_bg, counts_fg, counts_bg = ComputeStatsForSite(CountsSeq, CountsBck, currsite, fg_state, nr_of_genes, gene_nr, EmissionParameters)
site = {}
site['Start'] = currsite[0]
site['Stop'] = currsite[1]
site['Strand'] = strand
site['SiteScore'] = EvaluateSite(Score, currsite, fg_state)
site['Coverage'] = np.sum(np.sum(Counts[:, site['Start'] : site['Stop']], axis=0))
site['Variants'] = np.sum(CurrStackVarSumm[:, site['Start'] : site['Stop']], axis=1)
site['mean_mat_fg'] = mean_mat_fg
site['var_mat_fg'] = var_mat_fg
site['mean_mat_bg'] = mean_mat_bg
site['var_mat_bg'] = var_mat_bg
site['counts_fg'] = counts_fg
site['counts_bg'] = counts_bg
p = mean_mat_fg / var_mat_fg
n = (mean_mat_fg ** 2) / (var_mat_fg - mean_mat_fg)
site['pv'] = nbinom.logsf(counts_fg, n, p)
site['max_pos'] = get_max_position(Score, currsite, fg_state, strand)
site['dir_score'] = EvaluateSite(EmmisionProbGeneDir, currsite, fg_state)
if site['SiteScore'] < 0.0:
continue
sites.append(site)
Sequences.close()
Background.close()
return gene, sites
def np_nbinom_logsf(x, mu, dispersion):
p = dispersion / (dispersion + mu)
return nbinom.logsf(x, dispersion, p)
