def run_QTL_analysis(pheno_filename,
anno_filename,
geno_prefix,
plinkGenotype,
output_dir,
window_size=250000,
min_maf=0.05,
min_hwe_P=0.001,
min_call_rate=0.95,
blocksize=1000,
cis_mode=True,
skipAutosomeFiltering=False,
gaussianize_method=None,
minimum_test_samples=10,
seed=np.random.randint(40000),
n_perm=0,
write_permutations=False,
relatedness_score=0.95,
feature_variant_covariate_filename=None,
snps_filename=None,
feature_filename=None,
snp_feature_filename=None,
genetic_range='all',
covariates_filename=None,
kinship_filename=None,
sample_mapping_filename=None,
extended_anno_filename=None,
regressCovariatesUpfront=False):
fill_NaN = Imputer(missing_values=np.nan,
strategy='mean',
axis=0,
copy=False)
print('Running QTL analysis.')
lik = 'normal'
minimumProbabilityStep = 0.1
'''Core function to take input and run QTL tests on a given chromosome.'''
if relatedness_score is not None:
relatedness_score = float(relatedness_score)
[phenotype_df, kinship_df, covariate_df, sample2individual_df,complete_annotation_df, annotation_df, snp_filter_df, snp_feature_filter_df, geneticaly_unique_individuals, minimum_test_samples, feature_list, bim, fam, bed, bgen, chromosome, selectionStart, selectionEnd, feature_variant_covariate_df]=\
utils.run_QTL_analysis_load_intersect_phenotype_covariates_kinship_sample_mapping(pheno_filename=pheno_filename, anno_filename=anno_filename, geno_prefix=geno_prefix, plinkGenotype=plinkGenotype, cis_mode=cis_mode, skipAutosomeFiltering = skipAutosomeFiltering,
minimum_test_samples= minimum_test_samples, relatedness_score=relatedness_score, snps_filename=snps_filename, feature_filename=feature_filename, snp_feature_filename=snp_feature_filename, selection=genetic_range,
covariates_filename=covariates_filename, kinship_filename=kinship_filename, sample_mapping_filename=sample_mapping_filename, extended_anno_filename=extended_anno_filename, feature_variant_covariate_filename=feature_variant_covariate_filename)
mixed = kinship_df is not None
if (kinship_df is None) or (relatedness_score is None):
geneticaly_unique_individuals = sample2individual_df['iid'].values
QS = None
if (feature_list == None or len(feature_list) == 0):
print('No features to be tested.')
sys.exit()
#Open output files
qtl_loader_utils.ensure_dir(output_dir)
if not selectionStart is None:
output_writer = qtl_output.hdf5_writer(
output_dir + '/qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
else:
output_writer = qtl_output.hdf5_writer(
output_dir + '/qtl_results_{}.h5'.format(chromosome))
if (write_permutations):
if not selectionStart is None:
permutation_writer = qtl_output.hdf5_permutations_writer(
output_dir + '/perm_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd), n_perm)
else:
permutation_writer = qtl_output.hdf5_permutations_writer(
output_dir + '/perm_results_{}.h5'.format(chromosome), n_perm)
#Arrays to store indices of snps tested and pass and fail QC SNPs for features without missingness.
tested_snp_ids = []
pass_qc_snps_all = []
fail_qc_snps_all = []
fail_qc_features = []
alpha_params = []
beta_params = []
n_samples = []
n_e_samples = []
na_containing_features = 0
currentFeatureNumber = 0
snpQcInfoMain = None
for feature_id in feature_list:
snpQcInfo = None
currentFeatureNumber += 1
if (len(phenotype_df.loc[feature_id, :])) < minimum_test_samples:
print("Feature: " + feature_id +
" not tested not enough samples do QTL test.")
fail_qc_features.append(feature_id)
geneticaly_unique_individuals = tmp_unique_individuals
continue
data_written = False
contains_missing_samples = False
snpQuery = utils.do_snp_selection(feature_id, complete_annotation_df,
bim, cis_mode, window_size,
skipAutosomeFiltering)
snp_cov_df = None
if (feature_variant_covariate_df is not None):
if (feature_id in feature_variant_covariate_df['feature'].values):
covariateSnp = feature_variant_covariate_df['snp_id'].values[
feature_variant_covariate_df['feature'] == feature_id]
if (any(i in bim['snp'].values for i in covariateSnp)):
snpQuery_cov = bim.loc[
bim['snp'].map(lambda x: x in list(covariateSnp)), :]
if (plinkGenotype):
snp_cov_df = pd.DataFrame(
data=bed[snpQuery_cov['i'].values, :].compute().
transpose(),
index=fam.index,
columns=snpQuery_cov['snp'],
)
else:
##Here we make some assumptions on the SNPs. They are expected to be ploidy 2!
##Also we don't use a minimal quality to assure a value is present for all samples.
print(
'Warning, during the regression of SNPs we assume ploidy 2.'
)
snp_cov_df_t = pd.DataFrame(columns=fam.index)
rowNumber = 0
for snpId in snpQuery_cov['i']:
geno = bgen["genotype"][snpId].compute()
if (geno["phased"]):
snp_df_dosage_t = geno["probs"][:, [0, 2]].sum(
1).astype(float)
snp_df_dosage_t[(
np.amax(geno["probs"][:, :2], 1) +
np.amax(geno["probs"][:, 2:4], 1)) < (
1 +
minimumProbabilityStep)] = float('NaN')
else:
snp_df_dosage_t = (geno["probs"][:, 0] *
2) + geno["probs"][:, 1]
snp_df_dosage_t[
np.amax(geno["probs"][:, :3], 1) < (
(1 / 3) +
minimumProbabilityStep)] = float('NaN')
snp_df_dosage_t = pd.Series(snp_df_dosage_t,
index=fam.index)
snp_df_dosage_t.name = snpId
snp_cov_df_t = snp_cov_df_t.append(snp_df_dosage_t)
rowNumber = rowNumber + 1
snp_cov_df_t = snp_cov_df_t.transpose()
if (len(snpQuery) != 0) and (snp_filter_df is not None):
toSelect = set(snp_filter_df.index).intersection(
set(snpQuery['snp']))
snpQuery = snpQuery.loc[snpQuery['snp'].isin(toSelect)]
if (len(snpQuery) != 0) and (snp_feature_filter_df is not None):
toSelect = set(
np.unique(snp_feature_filter_df['snp_id'].loc[
snp_feature_filter_df['feature'] ==
feature_id])).intersection(set(snpQuery['snp']))
snpQuery = snpQuery.loc[snpQuery['snp'].isin(toSelect)]
if len(snpQuery) == 0:
print("Feature: " + feature_id +
" not tested. No SNPS passed QC for phenotype.")
fail_qc_features.append(feature_id)
continue
else:
phenotype_ds = phenotype_df.loc[feature_id]
contains_missing_samples = any(~np.isfinite(phenotype_ds))
if (contains_missing_samples):
print('Feature: ' + feature_id + ' contains missing data.')
phenotype_ds.dropna(inplace=True)
na_containing_features = na_containing_features + 1
'''select indices for relevant individuals in genotype matrix
These are not unique. NOT to be used to access phenotype/covariates data
'''
individual_ids = sample2individual_df.loc[phenotype_ds.index,
'iid'].values
sample2individual_feature = sample2individual_df.loc[
phenotype_ds.index]
if (contains_missing_samples):
tmp_unique_individuals = geneticaly_unique_individuals
if (kinship_df is not None) and (relatedness_score
is not None):
geneticaly_unique_individuals = utils.get_unique_genetic_samples(
kinship_df.loc[individual_ids, individual_ids],
relatedness_score)
else:
geneticaly_unique_individuals = individual_ids
else:
#If no missing samples we can use the previous SNP Qc information before actually loading data.
#This allows for more efficient blocking and retrieving of data
snpQuery = snpQuery.loc[snpQuery['snp'].map(
lambda x: x not in list(map(str, fail_qc_snps_all)))]
if phenotype_ds.empty or len(
geneticaly_unique_individuals) < minimum_test_samples:
print("Feature: " + feature_id +
" not tested not enough samples do QTL test.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
elif np.var(phenotype_ds.values) == 0:
print("Feature: " + feature_id +
" has no variance in selected individuals.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
print('For feature: ' + str(currentFeatureNumber) + '/' +
str(len(feature_list)) + ' (' + feature_id + '): ' +
str(snpQuery.shape[0]) +
' SNPs need to be tested.\n Please stand by.')
if (n_perm != 0):
bestPermutationPval = np.ones((n_perm), dtype=np.float)
#Here we need to start preparing the LMM, can use the fam for sample IDS in SNP matrix.
#test if the covariates, kinship, snp and phenotype are in the same order
if ((all(kinship_df.loc[individual_ids,individual_ids].index==sample2individual_feature.loc[phenotype_ds.index]['iid']) if kinship_df is not None else True) &\
(all(phenotype_ds.index==covariate_df.loc[sample2individual_feature['sample'],:].index)if covariate_df is not None else True)):
'''
if all lines are in order put in arrays the correct genotype and phenotype
x=a if cond1 else b <---> equivalent to if cond1: x=a else x=b; better readability of the code
'''
if kinship_df is not None:
kinship_mat = kinship_df.loc[individual_ids,
individual_ids].values
kinship_mat = kinship_mat.astype(float)
##GOWER normalization of Kinship matrix.
kinship_mat *= (kinship_mat.shape[0] - 1) / (
kinship_mat.trace() - kinship_mat.mean(0).sum())
## This needs to go with the subselection stuff.
if (QS is None and not contains_missing_samples):
QS = economic_qs(kinship_mat)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(kinship_mat)
if kinship_df is None:
K = np.eye(len(phenotype_ds.index))
if (QS is None and not contains_missing_samples):
QS = economic_qs(K)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(K)
cov_matrix = covariate_df.loc[sample2individual_feature[
'sample'], :].values if covariate_df is not None else None
if covariate_df is None:
cov_matrix = np.ones((len(individual_ids), 1))
if snp_cov_df is not None:
snp_cov_df_tmp = snp_cov_df.loc[individual_ids, :]
snp_cov_df_tmp.index = sample2individual_feature['sample']
snp_cov_df = pd.DataFrame(
fill_NaN.fit_transform(snp_cov_df_tmp))
snp_cov_df.index = snp_cov_df_tmp.index
snp_cov_df.columns = snp_cov_df_tmp.columns
cov_matrix = np.concatenate(
(cov_matrix, snp_cov_df.values), 1)
snp_cov_df_tmp = None
snp_cov_df = None
cov_matrix = cov_matrix.astype(float)
else:
print(
'There is an issue in mapping phenotypes vs covariates and/or kinship'
)
sys.exit()
phenotype = utils.force_normal_distribution(
phenotype_ds.values, method=gaussianize_method
) if gaussianize_method is not None else phenotype_ds.values
#Prepare LMM
phenotype = phenotype.astype(float)
##Mixed and test.
##This is a future change so we don't need to decompose the COVs every time.
##Like QS this needs to happen when genetic unique individuals is the same.
#svd_cov = economic_svd(cov_matrix)
#lmm = LMM(phenotype, cov_matrix, QS, SVD=svd_cov)
#These steps need to happen only once per phenotype.
#print(QS)
lmm = LMM(phenotype, cov_matrix, QS)
if not mixed:
lmm.delta = 1
lmm.fix('delta')
#Prepare null model.
lmm.fit(verbose=False)
if regressCovariatesUpfront:
phenotype_corrected = phenotype - cov_matrix[:, 1:].dot(
lmm.beta[1:])
cov_matrix_corrected = cov_matrix[:, 0]
lmm = LMM(phenotype_corrected, cov_matrix_corrected, QS)
lmm.fit(verbose=False)
null_lml = lmm.lml()
flmm = lmm.get_fast_scanner()
countChunker = 0
for snpGroup in utils.chunker(snpQuery, blocksize):
countChunker = countChunker + 1
#print(countChunker)
#Fix seed at the start of the first chunker so all permutations are based on the same random first split.
np.random.seed(seed)
#print(snpGroup)
snp_idxs = snpGroup['i'].values
snp_names = snpGroup['snp'].values
tested_snp_ids.extend(snp_names)
#subset genotype matrix, we cannot subselect at the same time, do in two steps.
if (plinkGenotype):
snp_df = pd.DataFrame(
data=bed[snp_idxs, :].compute().transpose(),
index=fam.index,
columns=snp_names)
else:
snp_df_dosage = pd.DataFrame(np.nan,
index=fam.index,
columns=snp_names)
snp_df = pd.DataFrame(np.nan,
index=fam.index,
columns=snp_names)
rowNumber = 0
for snpId in snp_idxs:
geno = bgen["genotype"][snpId].compute()
if (geno["ploidy"].min() > 1 & geno["ploidy"].max() <
3):
if (geno["phased"]):
snp_df_dosage_t = geno["probs"][:, [0, 2]].sum(
1).astype(float)
snp_df_t = (np.abs(
np.argmax(geno["probs"][:, :2], axis=1) - 1
) + np.abs(
np.argmax(geno["probs"][:, 2:4], axis=1) -
1)).astype(float)
naId = (np.amax(geno["probs"][:, :2], 1) +
np.amax(geno["probs"][:, 2:4], 1)) < (
1 + minimumProbabilityStep)
snp_df_dosage_t[naId] = float('NaN')
snp_df_t[naId] = float('NaN')
else:
snp_df_dosage_t = (
(geno["probs"][:, 0] * 2) +
geno["probs"][:, 1]).astype(float)
snp_df_t = (np.abs(
np.argmax(geno["probs"][:, :3], axis=1) -
2)).astype(float)
naId = np.amax(geno["probs"][:, :3], 1) < (
(1 / 3) + minimumProbabilityStep)
snp_df_dosage_t[naId] = float('NaN')
snp_df_t[naId] = float('NaN')
snp_df_dosage.loc[:, snp_names[
rowNumber]] = snp_df_dosage_t
snp_df.loc[:, snp_names[rowNumber]] = snp_df_t
rowNumber = rowNumber + 1
snp_df_dosage = snp_df_dosage.loc[individual_ids, :]
snp_df = snp_df.loc[individual_ids, :]
snp_df = snp_df.loc[:,
np.unique(snp_df.columns)[
np.unique(snp_df.columns,
return_counts=1)[1] == 1]]
#SNP QC.
if not contains_missing_samples:
#remove SNPs from snp_df if they have previously failed QC
snp_df = snp_df.loc[:,
snp_df.columns[~snp_df.columns.
isin(fail_qc_snps_all)]]
if snp_df.shape[1] == 0:
continue
snps_to_test_df = snp_df.loc[:, snp_df.columns[
~snp_df.columns.isin(pass_qc_snps_all)]]
if snps_to_test_df.shape[1] > 0:
#Only do QC on relevant SNPs. join pre-QCed list and new QCed list.
if kinship_df is not None:
passed_snp_names, failed_snp_names, call_rate, maf, hweP = do_snp_qc(
snps_to_test_df.iloc[np.unique(
snps_to_test_df.index,
return_index=1)[1]].loc[
geneticaly_unique_individuals, :],
min_call_rate, min_maf, min_hwe_P)
else:
passed_snp_names, failed_snp_names, call_rate, maf, hweP = do_snp_qc(
snps_to_test_df, min_call_rate, min_maf,
min_hwe_P)
snps_to_test_df = None
#append snp_names and failed_snp_names
pass_qc_snps_all.extend(passed_snp_names)
fail_qc_snps_all.extend(failed_snp_names)
snp_df = snp_df.loc[:,
snp_df.columns[snp_df.columns.
isin(pass_qc_snps_all)]]
else:
#Do snp QC for relevant section.
#Get relevant slice from: phenotype_ds
if kinship_df is not None:
passed_snp_names, failed_snp_names, call_rate, maf, hweP = do_snp_qc(
snp_df.iloc[np.unique(
snp_df.index, return_index=1)[1]].loc[
geneticaly_unique_individuals, :],
min_call_rate, min_maf, min_hwe_P)
else:
passed_snp_names, failed_snp_names, call_rate, maf, hweP = do_snp_qc(
snp_df, min_call_rate, min_maf, min_hwe_P)
snp_df = snp_df.loc[:,
snp_df.columns[snp_df.columns.
isin(passed_snp_names)]]
snpQcInfo_t = None
if call_rate is not None:
snpQcInfo_t = call_rate
if maf is not None:
snpQcInfo_t = pd.concat(
[snpQcInfo_t,
maf.reindex(snpQcInfo_t.index)],
axis=1)
if hweP is not None:
snpQcInfo_t = pd.concat(
[snpQcInfo_t,
hweP.reindex(snpQcInfo_t.index)],
axis=1)
call_rate = None
maf = None
hweP = None
if snpQcInfo is None and snpQcInfo_t is not None:
snpQcInfo = snpQcInfo_t
elif snpQcInfo_t is not None:
snpQcInfo = pd.concat([snpQcInfo, snpQcInfo_t],
axis=0,
sort=False)
##First process SNPQc than check if we can continue.
if len(snp_df.columns) == 0:
continue
elif (not plinkGenotype):
snp_df_dosage = snp_df_dosage.loc[:,
np.unique(snp_df.columns
)]
#We could make use of relatedness when imputing. And impute only based on genetically unique individuals.
snp_df = pd.DataFrame(fill_NaN.fit_transform(snp_df),
index=snp_df.index,
columns=snp_df.columns)
if (not plinkGenotype):
snp_df_dosage = pd.DataFrame(
fill_NaN.fit_transform(snp_df_dosage),
index=snp_df_dosage.index,
columns=snp_df_dosage.columns)
##No more snp_matrix_DF > snp_df
# test if the covariates, kinship, snp and phenotype are in the same order
if (len(snp_df.index) != len(sample2individual_feature.loc[
phenotype_ds.index]['iid'])
or not all(snp_df.index == sample2individual_feature.
loc[phenotype_ds.index]['iid'])):
print(
'There is an issue in mapping phenotypes and genotypes'
)
sys.exit()
G = snp_df.values
if (not plinkGenotype):
G = snp_df_dosage.values
G = G.astype(float)
G_index = snp_df.columns
alt_lmls, effsizes = flmm.fast_scan(G, verbose=False)
var_pvalues = lrt_pvalues(null_lml, alt_lmls)
var_effsizes_se = effsizes_se(effsizes, var_pvalues)
#add these results to qtl_results
temp_df = pd.DataFrame(index=range(len(G_index)),
columns=[
'feature_id', 'snp_id', 'p_value',
'beta', 'beta_se',
'empirical_feature_p_value'
])
temp_df['snp_id'] = G_index
temp_df['feature_id'] = feature_id
temp_df['beta'] = np.asarray(effsizes)
temp_df['p_value'] = np.asarray(var_pvalues)
temp_df['beta_se'] = np.asarray(var_effsizes_se)
#insert default dummy value
temp_df['empirical_feature_p_value'] = -1.0
if (n_perm != 0):
pValueBuffer = []
totalSnpsToBeTested = (G.shape[1] * n_perm)
permutationStepSize = np.floor(
n_perm / (totalSnpsToBeTested / blocksize))
if (permutationStepSize > n_perm):
permutationStepSize = n_perm
elif (permutationStepSize < 1):
permutationStepSize = 1
if (write_permutations):
perm_df = pd.DataFrame(
index=range(len(G_index)),
columns=['snp_id'] +
['permutation_' + str(x) for x in range(n_perm)])
perm_df['snp_id'] = G_index
for currentNperm in utils.chunker(
list(range(1, n_perm + 1)), permutationStepSize):
if (kinship_df is not None) and (relatedness_score
is not None):
if (plinkGenotype):
temp = utils.get_shuffeld_genotypes_preserving_kinship(
geneticaly_unique_individuals,
relatedness_score, snp_df,
kinship_df.loc[individual_ids,
individual_ids],
len(currentNperm))
else:
temp = utils.get_shuffeld_genotypes_preserving_kinship(
geneticaly_unique_individuals,
relatedness_score, snp_df_dosage,
kinship_df.loc[individual_ids,
individual_ids],
len(currentNperm))
else:
if (plinkGenotype):
temp = utils.get_shuffeld_genotypes(
snp_df, len(currentNperm))
else:
temp = utils.get_shuffeld_genotypes(
snp_df_dosage, len(currentNperm))
temp = temp.astype(float)
alt_lmls_p, effsizes_p = flmm.fast_scan(temp,
verbose=False)
var_pvalues_p = lrt_pvalues(null_lml, alt_lmls_p)
pValueBuffer.extend(np.asarray(var_pvalues_p))
if (not (len(pValueBuffer) == totalSnpsToBeTested)):
#print(len(pValueBuffer))
#print(pValueBuffer)
#print(totalSnpsToBeTested)
print('Error in blocking logic for permutations.')
sys.exit()
perm = 0
for relevantOutput in utils.chunker(
pValueBuffer, G.shape[1]):
if (write_permutations):
perm_df['permutation_' +
str(perm)] = relevantOutput
if (bestPermutationPval[perm] > min(relevantOutput)):
bestPermutationPval[perm] = min(relevantOutput)
perm = perm + 1
#print(relevantOutput)
#print('permutation_'+str(perm))
if not temp_df.empty:
data_written = True
output_writer.add_result_df(temp_df)
if (write_permutations):
permutation_writer.add_permutation_results_df(
perm_df, feature_id)
#This we need to change in the written file.
if (n_perm > 1 and data_written):
#updated_permuted_p_in_hdf5(bestPermutationPval, feature_id);
alpha_para, beta_para = output_writer.apply_pval_correction(
feature_id, bestPermutationPval, cis_mode)
#np.savetxt(output_dir+"/Permutation.pValues."+feature_id+".txt",bestPermutationPval)
alpha_params.append(alpha_para)
beta_params.append(beta_para)
if not data_written:
fail_qc_features.append(feature_id)
else:
n_samples.append(phenotype_ds.size)
n_e_samples.append(len(geneticaly_unique_individuals))
if contains_missing_samples:
QS = QS_tmp
geneticaly_unique_individuals = tmp_unique_individuals
del QS_tmp
del tmp_unique_individuals
if snpQcInfo is not None:
snpQcInfo.index.name = "snp_id"
snpQcInfo.to_csv(
output_dir +
'/snp_qc_metrics_naContaining_feature_{}.txt'.format(
feature_id),
sep='\t')
else:
if (snpQcInfo is not None and snpQcInfoMain is not None):
snpQcInfoMain = pd.concat([snpQcInfoMain, snpQcInfo],
axis=0,
sort=False)
elif snpQcInfo is not None:
snpQcInfoMain = snpQcInfo.copy(deep=True)
#if snpQcInfo is not None:
#snpQcInfo2 = snpQcInfo.copy().transpose()
#snpQcInfo2.to_csv(output_dir+'/snp_qc_metrics_feature_{}.txt'.format(feature_id),sep='\t')
#print('step 5')
output_writer.close()
if (write_permutations):
permutation_writer.close()
fail_qc_features = np.unique(fail_qc_features)
if ((len(feature_list) - len(fail_qc_features)) == 0):
time.sleep(15)
#Safety timer to make sure the file is unlocked.
print("Trying to remove the h5 file. Nothing has been tested.")
print(output_dir + 'qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
if not selectionStart is None:
os.remove(output_dir + 'qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
else:
os.remove(output_dir + 'qtl_results_{}.h5'.format(chromosome))
sys.exit()
#gather unique indexes of tested SNPs
tested_snp_ids = list(set(tested_snp_ids))
#write annotation and snp data to file
snp_df = pd.DataFrame()
snp_df['snp_id'] = bim['snp']
snp_df['chromosome'] = bim['chrom']
snp_df['position'] = bim['pos']
snp_df['assessed_allele'] = bim['a1']
snp_df.index = snp_df['snp_id']
snp_df = snp_df.drop_duplicates()
snp_df = snp_df.reindex(tested_snp_ids)
snp_df = snp_df.drop_duplicates()
if snpQcInfoMain is not None:
snpQcInfoMain['index'] = snpQcInfoMain.index
snpQcInfoMain = snpQcInfoMain.drop_duplicates()
del snpQcInfoMain['index']
snp_df = pd.concat(
[snp_df, snpQcInfoMain.reindex(snp_df.index)], axis=1)
if (snp_df.shape[1] == 5):
snp_df.columns = [
'snp_id', 'chromosome', 'position', 'assessed_allele',
'call_rate'
]
elif (snp_df.shape[1] == 6):
snp_df.columns = [
'snp_id', 'chromosome', 'position', 'assessed_allele',
'call_rate', 'maf'
]
else:
snp_df.columns = [
'snp_id', 'chromosome', 'position', 'assessed_allele',
'call_rate', 'maf', 'hwe_p'
]
feature_list = list(set(feature_list) - set(fail_qc_features))
annotation_df = annotation_df.reindex(feature_list)
annotation_df['n_samples'] = n_samples
annotation_df['n_e_samples'] = n_e_samples
if (n_perm > 1):
annotation_df['alpha_param'] = alpha_params
annotation_df['beta_param'] = beta_params
if not selectionStart is None:
snp_df.to_csv(output_dir + '/snp_metadata_{}_{}_{}.txt'.format(
chromosome, selectionStart, selectionEnd),
sep='\t',
index=False)
annotation_df.to_csv(output_dir +
'/feature_metadata_{}_{}_{}.txt'.format(
chromosome, selectionStart, selectionEnd),
sep='\t')
else:
snp_df.to_csv(output_dir + '/snp_metadata_{}.txt'.format(chromosome),
sep='\t',
index=False)
annotation_df.to_csv(output_dir +
'/feature_metadata_{}.txt'.format(chromosome),
sep='\t')
def run_plots(plinkGenotype, geno_prefix, annotation_filename, phenotype_filename,
covariate_filename, top_qtl_results_filename, output_directory,
sample_mapping_filename,randomeff_filename):
# # Loading Files
# phenotype_filename = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Expression/Geuvadis_CEU_YRI_Expr.txt"
# annotation_filename = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Expression/Geuvadis_CEU_Annot.txt"
# covariate_filename = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Expression/Geuvadis_CEU_YRI_covariates.txt"
# sample_mapping_filename = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Geuvadis_CEU_gte.txt"
# geno_prefix = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Genotypes/Geuvadis"
# output_directory = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Output"
# top_qtl_results_filename = "/Users/chaaya/dhonveli_dkfz/limix_qtl/limix_qtl-master/Limix_QTL/test_data/Output/top_qtl_results_all_FDR0.05.txt"
# plinkGenotype = True
[phenotype_df, kinship_df, readdepth_df, covariate_df, sample2individual_df,complete_annotation_df, annotation_df, snp_filter_df,
snp_feature_filter_df, geneticaly_unique_individuals, minimum_test_samples, feature_list, bim, fam, bed, bgen,
chromosome, selectionStart, selectionEnd, feature_variant_covariate_df]=\
utils.run_QTL_analysis_load_intersect_phenotype_covariates_kinship_sample_mapping(pheno_filename=phenotype_filename,
anno_filename=annotation_filename, geno_prefix=geno_prefix, plinkGenotype=plinkGenotype, cis_mode=True,
skipAutosomeFiltering = False, minimum_test_samples= 10,
relatedness_score=None, snps_filename=None, feature_filename=None,
snp_feature_filename=None, selection='all',covariates_filename=covariate_filename,
randomeff_filename=randomeff_filename, sample_mapping_filename=sample_mapping_filename,
extended_anno_filename=None, feature_variant_covariate_filename=None)
# results
top_qtl_results_df = qtl_loader_utils.get_top_qtl_results(top_qtl_results_filename)
for row in top_qtl_results_df.iterrows():
# feature specific parameters for QS mixing
rho1 = [0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
Sigma = {}
Sigma_qs = {}
best = {}
snpQcInfo = None
currentFeatureNumber+= 1
phenotype_ds = phenotype_df.loc[row[1]["feature_id"]]
individual_ids = sample2individual_df.loc[phenotype_ds.index, 'iid'].values
sample2individual_feature = sample2individual_df.loc[phenotype_ds.index]
if kinship_df is not None and readdepth_df is None:
kinship_mat = kinship_df.loc[individual_ids,individual_ids].values
kinship_mat = kinship_mat.astype(float)
##GOWER normalization of Kinship matrix.
kinship_mat *= (kinship_mat.shape[0] - 1) / (kinship_mat.trace() - kinship_mat.mean(0).sum())
## This needs to go with the subselection stuff.
if(QS is None and not contains_missing_samples):
QS = economic_qs(kinship_mat)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(kinship_mat)
randomeff_mix = False
# combining the two matrices
if kinship_df is not None and readdepth_df is not None:
randomeff_mix = True
kinship_mat = kinship_df.loc[individual_ids,individual_ids].values
kinship_mat = kinship_mat.astype(float)
##GOWER normalization of Kinship matrix.
kinship_mat *= (kinship_mat.shape[0] - 1) / (kinship_mat.trace() - kinship_mat.mean(0).sum())
for rho in rho1:
Sigma[rho] = rho * kinship_df + (1 - rho) * readdepth_df
Sigma_qs[rho] = economic_qs(Sigma[rho])
# creating a fake QS if none random effect is present or use the read depth one
if kinship_df is None:
if readdepth_df is None:
K = np.eye(len(phenotype_ds.index))
if(QS is None and not contains_missing_samples):
QS = economic_qs(K)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(K)
else:
if(QS is None and not contains_missing_samples):
QS = economic_qs(readdepth_df)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(readdepth_df)
# covariance matrix
cov_matrix = covariate_df.loc[sample2individual_feature['sample'], :].values if covariate_df is not None else None
if covariate_df is None:
cov_matrix = np.ones((len(individual_ids), 1))
cov_matrix = cov_matrix.astype(float)
phenotype = utils.force_normal_distribution(phenotype_ds.values,method="gaussnorm")
# Prepare LMM
phenotype = phenotype.astype(float)
if randomeff_mix:
# initialize best to minus infinite
best["lml"] = - math.inf
best["lmm"] = - math.inf
best["rho1"] = - math.inf
for rho, QS in Sigma_qs.items():
lmm = LMM(phenotype, cov_matrix, QS)
if not mixed:
lmm.delta = 1
lmm.fix('delta')
lmm.fit(verbose=False)
lml = lmm.lml()
if lml > best["lml"]:
best["lml"] = lml
best["lmm"] = lmm
best["rho1"] = rho
lmm = best["lmm"]
print(best["rho1"])
if best["rho1"] != 0:
rho_log[(feature_id)] = best["rho1"]
print("Read depth has actually an effect!")
else:
lmm = LMM(phenotype, cov_matrix, QS)
if not mixed:
lmm.delta = 1
lmm.fix('delta')
lmm.fit(verbose=False)
# create phenotype_corrected_df for plotting
phenotype_corrected = phenotype - cov_matrix[:, 1:].dot(lmm.beta[1:])
phenotype_corrected_ds = pd.Series(data = phenotype_corrected, index = phenotype_ds.index, name="exp")
qtl_plots(row, phenotype_ds, phenotype_corrected_ds, plinkGenotype, bim, fam, bed, annotation_df, sample2individual_df)
def _test_lmm(random, y, X, G, mvn, restricted):
c = X.shape[1]
QS = economic_qs_linear(G)
lmm = LMM(y, X, QS, restricted=restricted)
beta = lmm.beta
v0 = lmm.v0
v1 = lmm.v1
K0 = G @ G.T
assert_allclose(lmm.lml(), mvn(beta, v0, v1, y, X, K0))
beta = random.randn(c)
lmm.beta = beta
assert_allclose(lmm.lml(), mvn(beta, v0, v1, y, X, K0))
delta = random.rand(1).item()
lmm.delta = delta
v0 = lmm.v0
v1 = lmm.v1
assert_allclose(lmm.lml(), mvn(beta, v0, v1, y, X, K0))
scale = random.rand(1).item()
lmm.scale = scale
v0 = lmm.v0
v1 = lmm.v1
assert_allclose(lmm.lml(), mvn(beta, v0, v1, y, X, K0))
def fun(x):
beta = x[:c]
v0 = exp(x[c])
v1 = exp(x[c + 1])
return -mvn(beta, v0, v1, y, X, K0)
res = minimize(fun, [0] * c + [0, 0])
lmm.fit(verbose=False)
assert_allclose(lmm.lml(), -res.fun, rtol=1e-3, atol=1e-6)
assert_allclose(lmm.beta, res.x[:c], rtol=1e-3, atol=1e-6)
assert_allclose(lmm.v0, exp(res.x[c]), rtol=1e-3, atol=1e-6)
assert_allclose(lmm.v1, exp(res.x[c + 1]), rtol=1e-3, atol=1e-6)
lmm = LMM(y, X, QS, restricted=restricted)
beta = random.randn(c)
lmm.beta = beta
lmm.delta = random.rand(1).item()
lmm.scale = random.rand(1).item()
lmm.fix("beta")
def fun(x):
v0 = exp(x[0])
v1 = exp(x[1])
return -mvn(beta, v0, v1, y, X, K0)
res = minimize(fun, [0, 0])
lmm.fit(verbose=False)
assert_allclose(lmm.lml(), -res.fun, rtol=1e-3, atol=1e-6)
assert_allclose(lmm.v0, exp(res.x[0]), rtol=1e-3, atol=1e-6)
assert_allclose(lmm.v1, exp(res.x[1]), rtol=1e-3, atol=1e-6)
lmm = LMM(y, X, QS, restricted=restricted)
lmm.beta = random.randn(c)
delta = random.rand(1).item()
lmm.delta = delta
lmm.scale = random.rand(1).item()
lmm.fix("delta")
def fun(x):
beta = x[:c]
scale = exp(x[c])
v0 = scale * (1 - delta)
v1 = scale * delta
return -mvn(beta, v0, v1, y, X, K0)
res = minimize(fun, [0] * c + [0])
lmm.fit(verbose=False)
assert_allclose(lmm.lml(), -res.fun, rtol=1e-5, atol=1e-6)
assert_allclose(lmm.beta, res.x[:c], rtol=1e-5, atol=1e-6)
assert_allclose(lmm.scale, exp(res.x[c]), rtol=1e-5, atol=1e-6)
lmm = LMM(y, X, QS, restricted=restricted)
lmm.beta = random.randn(c)
lmm.delta = random.rand(1).item()
scale = random.rand(1).item()
lmm.scale = scale
lmm.fix("scale")
def fun(x):
beta = x[:c]
delta = 1 / (1 + exp(-x[c]))
v0 = scale * (1 - delta)
v1 = scale * delta
return -mvn(beta, v0, v1, y, X, K0)
res = minimize(fun, [0] * c + [0])
lmm.fit(verbose=False)
assert_allclose(lmm.lml(), -res.fun, rtol=1e-5, atol=1e-6)
assert_allclose(lmm.beta, res.x[:c], rtol=1e-3, atol=1e-6)
assert_allclose(lmm.delta, 1 / (1 + exp(-res.x[c])), rtol=1e-3, atol=1e-6)
def run_PrsQtl_analysis(pheno_filename,
anno_filename,
prsFile,
output_dir,
min_call_rate=0.95,
blocksize=1000,
skipAutosomeFiltering=False,
gaussianize_method=None,
minimum_test_samples=10,
seed=np.random.randint(40000),
n_perm=0,
write_permutations=False,
relatedness_score=None,
feature_variant_covariate_filename=None,
snps_filename=None,
feature_filename=None,
snp_feature_filename=None,
genetic_range='all',
covariates_filename=None,
kinship_filename=None,
sample_mapping_filename=None,
regressCovariatesUpfront=False):
fill_NaN = Imputer(missing_values=np.nan, strategy='mean', axis=0)
print('Running GRS QT analysis.')
lik = 'normal'
'''Core function to take input and run QTL tests on a given chromosome.'''
if relatedness_score is not None:
relatedness_score = float(relatedness_score)
[phenotype_df, kinship_df, covariate_df, sample2individual_df, annotation_df, snp_filter_df, snp_feature_filter_df, geneticaly_unique_individuals, minimum_test_samples, feature_list, risk_df, chromosome, selectionStart, selectionEnd, feature_variant_covariate_df]=\
utils.run_PrsQtl_analysis_load_intersect_phenotype_covariates_kinship_sample_mapping(pheno_filename=pheno_filename, anno_filename=anno_filename, prsFile=prsFile, skipAutosomeFiltering = skipAutosomeFiltering,
minimum_test_samples= minimum_test_samples, relatedness_score=relatedness_score, snps_filename=snps_filename, feature_filename=feature_filename, snp_feature_filename=snp_feature_filename, selection=genetic_range,
covariates_filename=covariates_filename, kinship_filename=kinship_filename, sample_mapping_filename=sample_mapping_filename, feature_variant_covariate_filename=feature_variant_covariate_filename)
mixed = kinship_df is not None
if (kinship_df is None) or (relatedness_score is None):
geneticaly_unique_individuals = sample2individual_df['iid'].values
QS = None
if (feature_list == None or len(feature_list) == 0):
print('No features to be tested.')
sys.exit()
#Open output files
qtl_loader_utils.ensure_dir(output_dir)
if not selectionStart is None:
output_writer = qtl_output.hdf5_writer(
output_dir + '/qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
else:
output_writer = qtl_output.hdf5_writer(
output_dir + '/qtl_results_{}.h5'.format(chromosome))
if (write_permutations):
if not selectionStart is None:
permutation_writer = qtl_output.hdf5_permutations_writer(
output_dir + '/perm_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd), n_perm)
else:
permutation_writer = qtl_output.hdf5_permutations_writer(
output_dir + '/perm_results_{}.h5'.format(chromosome), n_perm)
#Arrays to store indices of snps tested and pass and fail QC SNPs for features without missingness.
tested_snp_names = []
fail_qc_features = []
alpha_params = []
beta_params = []
n_samples = []
n_e_samples = []
na_containing_features = 0
currentFeatureNumber = 0
snpQcInfoMain = None
for feature_id in feature_list:
snpQcInfo = None
currentFeatureNumber += 1
if (len(phenotype_df.loc[feature_id, :])) < minimum_test_samples:
print("Feature: " + feature_id +
" not tested not enough samples do QTL test.")
fail_qc_features.append(feature_id)
geneticaly_unique_individuals = tmp_unique_individuals
continue
data_written = False
contains_missing_samples = False
snpQuery = risk_df.index.values
snp_cov_df = None
if (feature_variant_covariate_df is not None):
if (feature_id in feature_variant_covariate_df['feature'].values):
covariateSnp = feature_variant_covariate_df['snp_id'].values[
feature_variant_covariate_df['feature'] == feature_id]
if (any(i in risk_df.index.values for i in covariateSnp)):
snp_cov_df = risk_df.loc[risk_df.index.map(
lambda x: x in list(covariateSnp)), :].transpose()
if (len(snpQuery) != 0) and (snp_filter_df is not None):
snpQuery = list(
set(snp_filter_df.index).intersection(set(snpQuery)))
if (len(snpQuery) != 0) and (snp_feature_filter_df is not None):
snpQuery = list(
set(
np.unique(snp_feature_filter_df['snp_id'].loc[
snp_feature_filter_df['feature'] ==
feature_id])).intersection(set(snpQuery)))
if len(snpQuery) == 0:
print("Feature: " + feature_id +
" not tested. No SNPS passed QC for phenotype.")
fail_qc_features.append(feature_id)
continue
else:
phenotype_ds = phenotype_df.loc[feature_id]
contains_missing_samples = any(~np.isfinite(phenotype_ds))
if (contains_missing_samples):
#import pdb; pdb.set_trace()
print('Feature: ' + feature_id + ' contains missing data.')
phenotype_ds.dropna(inplace=True)
na_containing_features = na_containing_features + 1
'''select indices for relevant individuals in genotype matrix
These are not unique. NOT to be used to access phenotype/covariates data
'''
individual_ids = sample2individual_df.loc[phenotype_ds.index,
'iid'].values
sample2individual_feature = sample2individual_df.loc[
phenotype_ds.index]
if contains_missing_samples:
tmp_unique_individuals = geneticaly_unique_individuals
if (kinship_df is not None) and (relatedness_score
is not None):
geneticaly_unique_individuals = utils.get_unique_genetic_samples(
kinship_df.loc[individual_ids, individual_ids],
relatedness_score)
else:
geneticaly_unique_individuals = individual_ids
if phenotype_ds.empty or len(
geneticaly_unique_individuals) < minimum_test_samples:
print("Feature: " + feature_id +
" not tested not enough samples do QTL test.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
elif np.var(phenotype_ds.values) == 0:
print("Feature: " + feature_id +
" has no variance in selected individuals.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
print('For feature: ' + str(currentFeatureNumber) + '/' +
str(len(feature_list)) + ' (' + feature_id + '): ' +
str(len(snpQuery)) +
' risk scores will be tested.\n Please stand by.')
if (n_perm != 0):
bestPermutationPval = np.ones((n_perm), dtype=np.float)
#Here we need to start preparing the LMM, can use the fam for sample IDS in SNP matrix.
# test if the covariates, kinship, snp and phenotype are in the same order
if ((all(kinship_df.loc[individual_ids,individual_ids].index==sample2individual_feature.loc[phenotype_ds.index]['iid']) if kinship_df is not None else True) &\
(all(phenotype_ds.index==covariate_df.loc[sample2individual_feature['sample'],:].index)if covariate_df is not None else True)):
'''
if all lines are in order put in arrays the correct genotype and phenotype
x=a if cond1 else b <---> equivalent to if cond1: x=a else x=b; better readability of the code
'''
if kinship_df is not None:
kinship_mat = kinship_df.loc[individual_ids,
individual_ids].values
kinship_mat = kinship_mat.astype(float)
##GOWER normalization of Kinship matrix.
kinship_mat *= (kinship_mat.shape[0] - 1) / (
kinship_mat.trace() - kinship_mat.mean(0).sum())
## This needs to go with the subselection stuff.
if (QS is None and not contains_missing_samples):
QS = economic_qs(kinship_mat)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(kinship_mat)
if kinship_df is None:
K = np.eye(len(phenotype_ds.index))
if (QS is None and not contains_missing_samples):
QS = economic_qs(K)
elif (contains_missing_samples):
QS_tmp = QS
QS = economic_qs(K)
cov_matrix = covariate_df.loc[sample2individual_feature[
'sample'], :].values if covariate_df is not None else None
if covariate_df is None:
cov_matrix = np.ones((len(individual_ids), 1))
#pdb.set_trace()
if snp_cov_df is not None:
snp_cov_df_tmp = snp_cov_df.loc[individual_ids, :]
snp_cov_df = pd.DataFrame(
fill_NaN.fit_transform(snp_cov_df_tmp))
snp_cov_df.index = sample2individual_feature['sample']
snp_cov_df.columns = snp_cov_df_tmp.columns
cov_matrix = np.concatenate(
(cov_matrix, snp_cov_df.values), 1)
snp_cov_df_tmp = None
snp_cov_df = None
cov_matrix = cov_matrix.astype(float)
else:
print(
'There is an issue in mapping phenotypes vs covariates and/or kinship'
)
sys.exit()
phenotype = utils.force_normal_distribution(
phenotype_ds.values, method=gaussianize_method
) if gaussianize_method is not None else phenotype_ds.values
#Prepare LMM
phenotype = phenotype.astype(float)
##Mixed and test.
##This is a future change so we don't need to decompose the COVs every time.
##Like QS this needs to happen when genetic unique individuals is the same.
#svd_cov = economic_svd(cov_matrix)
#lmm = LMM(phenotype, cov_matrix, QS, SVD=svd_cov)
#These steps need to happen only once per phenotype.
#print(QS)
lmm = LMM(phenotype, cov_matrix, QS)
if not mixed:
lmm.delta = 1
lmm.fix('delta')
#Prepare null model.
lmm.fit(verbose=False)
if regressCovariatesUpfront:
phenotype_corrected = phenotype - cov_matrix[:, 1:].dot(
lmm.beta[1:])
cov_matrix_corrected = cov_matrix[:, 0]
lmm = LMM(phenotype_corrected, cov_matrix_corrected, QS)
lmm.fit(verbose=False)
null_lml = lmm.lml()
flmm = lmm.get_fast_scanner()
#pdb.set_trace();
for snpGroup in utils.chunker(snpQuery, blocksize):
#Fix seed at the start of the first chunker so all permutations are based on the same random first split.
np.random.seed(seed)
snp_names = snpGroup
tested_snp_names.extend(snp_names)
snp_matrix_DF = risk_df.loc[snp_names,
individual_ids].transpose()
##GRS var QC
snp_matrix_DF = snp_matrix_DF.loc[:,
snp_matrix_DF.isna().sum(
axis=0) != snp_matrix_DF.
shape[0], ]
snp_matrix_DF = snp_matrix_DF.loc[:, (
np.nanstd(snp_matrix_DF, axis=0) > 0)]
# test if the covariates, kinship, snp and phenotype are in the same order
if (len(snp_matrix_DF.index) != len(
sample2individual_feature.loc[phenotype_ds.index]
['iid']) or not all(
snp_matrix_DF.index == sample2individual_feature.loc[
phenotype_ds.index]['iid'])):
print(
'There is an issue in mapping phenotypes and genotypes'
)
sys.exit()
#Impute missingness
#pdb.set_trace()
call_rate = 1 - snp_matrix_DF.isnull().sum() / len(
snp_matrix_DF.index)
if snpQcInfo is None and call_rate is not None:
snpQcInfo = call_rate
elif call_rate is not None:
snpQcInfo = pd.concat([snpQcInfo, call_rate], axis=0)
selection = call_rate > min_call_rate
snp_matrix_DF = snp_matrix_DF.loc[:,
list(snp_matrix_DF.
columns[selection])]
if snp_matrix_DF.shape[1] == 0:
continue
snp_matrix_DF = pd.DataFrame(
fill_NaN.fit_transform(snp_matrix_DF),
index=snp_matrix_DF.index,
columns=snp_matrix_DF.columns)
#
G = snp_matrix_DF.values
G = G.astype(float)
G_index = snp_matrix_DF.columns
alt_lmls, effsizes = flmm.fast_scan(G, verbose=False)
var_pvalues = lrt_pvalues(null_lml, alt_lmls)
var_effsizes_se = effsizes_se(effsizes, var_pvalues)
#add these results to qtl_results
temp_df = pd.DataFrame(index=range(len(G_index)),
columns=[
'feature_id', 'snp_id', 'p_value',
'beta', 'beta_se',
'empirical_feature_p_value'
])
temp_df['snp_id'] = G_index
temp_df['feature_id'] = feature_id
temp_df['beta'] = np.asarray(effsizes)
temp_df['p_value'] = np.asarray(var_pvalues)
temp_df['beta_se'] = np.asarray(var_effsizes_se)
#insert default dummy value
temp_df['empirical_feature_p_value'] = -1.0
if (n_perm != 0):
pValueBuffer = []
totalSnpsToBeTested = (G.shape[1] * n_perm)
permutationStepSize = np.floor(
n_perm / (totalSnpsToBeTested / blocksize))
if (permutationStepSize > n_perm):
permutationStepSize = n_perm
elif (permutationStepSize < 1):
permutationStepSize = 1
if (write_permutations):
perm_df = pd.DataFrame(
index=range(len(G_index)),
columns=['snp_id'] +
['permutation_' + str(x) for x in range(n_perm)])
perm_df['snp_id'] = G_index
for currentNperm in utils.chunker(
list(range(1, n_perm + 1)), permutationStepSize):
if (kinship_df is not None) and (relatedness_score
is not None):
temp = utils.get_shuffeld_genotypes_preserving_kinship(
geneticaly_unique_individuals,
relatedness_score, snp_matrix_DF,
kinship_df.loc[individual_ids, individual_ids],
len(currentNperm))
else:
temp = utils.get_shuffeld_genotypes(
snp_matrix_DF, len(currentNperm))
temp = temp.astype(float)
alt_lmls_p, effsizes_p = flmm.fast_scan(temp,
verbose=False)
var_pvalues_p = lrt_pvalues(null_lml, alt_lmls_p)
pValueBuffer.extend(np.asarray(var_pvalues_p))
if (not (len(pValueBuffer) == totalSnpsToBeTested)):
#print(len(pValueBuffer))
#print(pValueBuffer)
#print(totalSnpsToBeTested)
print('Error in blocking logic for permutations.')
sys.exit()
perm = 0
for relevantOutput in utils.chunker(
pValueBuffer, G.shape[1]):
if (write_permutations):
perm_df['permutation_' +
str(perm)] = relevantOutput
if (bestPermutationPval[perm] > min(relevantOutput)):
bestPermutationPval[perm] = min(relevantOutput)
perm = perm + 1
#print(relevantOutput)
#print('permutation_'+str(perm))
if not temp_df.empty:
data_written = True
output_writer.add_result_df(temp_df)
if (write_permutations):
permutation_writer.add_permutation_results_df(
perm_df, feature_id)
#This we need to change in the written file.
if (n_perm > 1 and data_written):
#updated_permuted_p_in_hdf5(bestPermutationPval, feature_id);
alpha_para, beta_para = output_writer.apply_pval_correction(
feature_id, bestPermutationPval, False)
alpha_params.append(alpha_para)
beta_params.append(beta_para)
#pdb.set_trace();
if not data_written:
fail_qc_features.append(feature_id)
else:
n_samples.append(phenotype_ds.size)
n_e_samples.append(len(geneticaly_unique_individuals))
if contains_missing_samples:
QS = QS_tmp
geneticaly_unique_individuals = tmp_unique_individuals
snpQcInfo = snpQcInfo.to_frame(name="call_rate")
snpQcInfo.index.name = "snp_id"
snpQcInfo.to_csv(
output_dir +
'/snp_qc_metrics_naContaining_feature_{}.txt'.format(
feature_id),
sep='\t')
del QS_tmp
del tmp_unique_individuals
else:
if (snpQcInfo is not None and snpQcInfoMain is not None):
snpQcInfoMain = pd.concat([snpQcInfoMain, snpQcInfo],
axis=0)
elif snpQcInfo is not None:
snpQcInfoMain = snpQcInfo.copy(deep=True)
#print('step 5')
output_writer.close()
if (write_permutations):
permutation_writer.close()
fail_qc_features = np.unique(fail_qc_features)
if ((len(feature_list) - len(fail_qc_features)) == 0):
time.sleep(15)
#Safety timer to make sure the file is unlocked.
print("Trying to remove the h5 file. Nothing has been tested.")
print(output_dir + 'qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
if not selectionStart is None:
os.remove(output_dir + 'qtl_results_{}_{}_{}.h5'.format(
chromosome, selectionStart, selectionEnd))
else:
os.remove(output_dir + 'qtl_results_{}.h5'.format(chromosome))
sys.exit()
#gather unique indexes of tested snps
#write annotation and snp data to file
snp_df = pd.DataFrame()
snp_df['snp_id'] = np.unique(tested_snp_names)
snp_df.index = np.unique(tested_snp_names)
snp_df['chromosome'] = "NA"
snp_df['position'] = "NA"
if (snpQcInfoMain is not None):
snpQcInfoMain = snpQcInfoMain.to_frame(name="call_rate")
snpQcInfoMain['index'] = snpQcInfoMain.index
snpQcInfoMain = snpQcInfoMain.drop_duplicates()
del snpQcInfoMain['index']
snp_df = pd.concat(
[snp_df, snpQcInfoMain.reindex(snp_df.index)], axis=1)
feature_list = list(set(feature_list) - set(fail_qc_features))
annotation_df = annotation_df.reindex(feature_list)
annotation_df['n_samples'] = n_samples
annotation_df['n_e_samples'] = n_e_samples
if (n_perm > 1):
annotation_df['alpha_param'] = alpha_params
annotation_df['beta_param'] = beta_params
if not selectionStart is None:
snp_df.to_csv(output_dir + '/snp_metadata_{}_{}_{}.txt'.format(
chromosome, selectionStart, selectionEnd),
sep='\t',
index=False)
annotation_df.to_csv(output_dir +
'/feature_metadata_{}_{}_{}.txt'.format(
chromosome, selectionStart, selectionEnd),
sep='\t')
else:
snp_df.to_csv(output_dir + '/snp_metadata_{}.txt'.format(chromosome),
sep='\t',
index=False)
annotation_df.to_csv(output_dir +
'/feature_metadata_{}.txt'.format(chromosome),
sep='\t')
def run_QTL_analysis(pheno_filename, anno_filename, geno_prefix, plinkGenotype, output_dir, window_size=250000,
min_maf=0.05, min_hwe_P=0.001, min_call_rate=None, blocksize=1000, cis_mode=True,
skipAutosomeFiltering = False, gaussianize_method=None, minimum_test_samples= 10,
seed=np.random.randint(40000), n_perm=0, write_permutations = False, write_feature_top_permutations = False,
relatedness_score=0.95, feature_variant_covariate_filename = None, snps_filename=None, feature_filename=None,
snp_feature_filename=None, genetic_range='all', covariates_filename=None, randomeff_filename=None,
sample_mapping_filename=None, extended_anno_filename=None, regressCovariatesUpfront = False, debugger=False):
#Manual flag to set pearson (True), spearman (False). TODO add rank as an option to gaussnorm.
pearson=True
if regressCovariatesUpfront is not None:
#This implementation can only handle regression before the association test (correlation).
regressCovariatesUpfront= True
tot_time = 0
idx = 0
print(relatedness_score)
fill_NaN = Imputer(missing_values=np.nan, strategy='mean', axis=0, copy=False)
print('Running QTL analysis.')
lik = 'normal'
minimumProbabilityStep=0.1
'''Core function to take input and run QTL tests on a given chromosome.'''
# Check if relatedness_score is present as a measure of genotype similarity and hence, of sample similarity.
if relatedness_score is not None:
relatedness_score = float(relatedness_score)
# Intersect files together to list the amount of samples with enough files
if debugger:
fun_start = time.time()
[phenotype_df, kinship_df, randomeff_df, covariate_df, sample2individual_df,complete_annotation_df, annotation_df, snp_filter_df,
snp_feature_filter_df, geneticaly_unique_individuals, minimum_test_samples, feature_list, bim, fam, bed, bgen,
chromosome, selectionStart, selectionEnd, feature_variant_covariate_df]=\
utils.run_QTL_analysis_load_intersect_phenotype_covariates_kinship_sample_mapping(pheno_filename=pheno_filename,
anno_filename=anno_filename, geno_prefix=geno_prefix, plinkGenotype=plinkGenotype, cis_mode=cis_mode,
skipAutosomeFiltering = skipAutosomeFiltering, minimum_test_samples= minimum_test_samples,
relatedness_score=relatedness_score, snps_filename=snps_filename, feature_filename=feature_filename,
snp_feature_filename=snp_feature_filename, selection=genetic_range,covariates_filename=covariates_filename,
randomeff_filename=randomeff_filename, sample_mapping_filename=sample_mapping_filename,
extended_anno_filename=extended_anno_filename, feature_variant_covariate_filename=feature_variant_covariate_filename)
if debugger:
fun_end = time.time()
print(" Intersecting files took {}".format(fun_end-fun_start))
# Check if kinship matrix is present. The matrix of pairwise genotype similarity. If they are not present took genetically unique individuals based on IDs
mixed = kinship_df is not None
if (kinship_df is None) or (relatedness_score is None) :
geneticaly_unique_individuals = sample2individual_df['iid'].values
QS = None
# Check if feature list is empty (genes)
if(feature_list==None or len(feature_list)==0):
print ('No features to be tested.')
sys.exit()
#Open output files
if debugger:
fun_start = time.time()
qtl_loader_utils.ensure_dir(output_dir)
if not selectionStart is None :
output_writer = qtl_output.hdf5_writer(output_dir+'/qtl_results_{}_{}_{}.h5'.format(chromosome,selectionStart,selectionEnd))
else :
output_writer = qtl_output.hdf5_writer(output_dir+'/qtl_results_{}.h5'.format(chromosome))
if(write_permutations):
if not selectionStart is None :
permutation_writer = qtl_output.hdf5_permutations_writer(output_dir+'/perm_results_{}_{}_{}.h5'.format(chromosome,selectionStart,selectionEnd),n_perm)
else :
permutation_writer = qtl_output.hdf5_permutations_writer(output_dir+'/perm_results_{}.h5'.format(chromosome),n_perm)
if debugger:
fun_end = time.time()
print(" Opening writing files took {}".format(fun_end-fun_start))
#Arrays to store indices of snps tested and pass and fail QC SNPs for features without missingness.
tested_snp_ids = []
pass_qc_snps_all = []
fail_qc_snps_all = []
fail_qc_features = []
alpha_params = []
beta_params = []
n_samples = []
n_e_samples = []
random_eff_param = []
na_containing_features=0
currentFeatureNumber=0
snpQcInfoMain = None
random_eff_param = []
log = {}
rho1 = [0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1]
Sigma = {}
Sigma_qs = {}
randomeff_mix = False
#############################################################################################################################################################
# Per feature LMM fitting
#############################################################################################################################################################
# start per feature computations
for feature_id in feature_list:
gc.collect()
start_time = time.time()
# log file production for rho values storing and computation time
log[(feature_id)] = []
# feature specific parameters for QS mixing
mixingParameters = {}
feature_best_rho = -1
snpQcInfo = None
# counter
currentFeatureNumber+= 1
########################################################################################################################################################
# check if enough phenotype samples to test this gene
if (len(phenotype_df.loc[feature_id,:]))<minimum_test_samples:
print("Feature: "+feature_id+" not tested not enough samples do QTL test (n="+str(len(phenotype_df.loc[feature_id,:]))+").")
fail_qc_features.append(feature_id)
geneticaly_unique_individuals = tmp_unique_individuals
continue
data_written = False
contains_missing_samples = False
########################################################################################################################################################
########################################################################################################################################################
# SNP selection based on gene location and window size
if debugger:
fun_start = time.time()
snpQuery = utils.do_snp_selection(feature_id, complete_annotation_df, bim, cis_mode, window_size, skipAutosomeFiltering)
if debugger:
fun_end = time.time()
print("SNP querying took {}".format(fun_end-fun_start))
snp_cov_df = None
if debugger:
fun_start = time.time()
########################################################################################################################################################
#########################################################################################################################################################
# Check if a matrix of variant covariance is present. Like for example PCs covariates -- Understand better covariates to SNP
if(feature_variant_covariate_df is not None):
if(feature_id in feature_variant_covariate_df['feature_id'].values):
# array of covariates per SNP and feature
covariateSnp = feature_variant_covariate_df['snp_id'].values[feature_variant_covariate_df['feature_id']==feature_id]
if(any(i in bim['snp'].values for i in covariateSnp)):
snpQuery_cov = bim.loc[bim['snp'].map(lambda x: x in list(covariateSnp)),:]
if(plinkGenotype):
snp_cov_df = pd.DataFrame(data=bed[snpQuery_cov['i'].values,:].compute().transpose(),index=fam.index,columns=snpQuery_cov['snp'],)
else:
##Here we make some assumptions on the SNPs. They are expected to be ploidy 2!
##Also we don't use a minimal quality to assure a value is present for all samples.
print('Warning, during the regression of SNPs we assume ploidy 2.')
snp_cov_df_t = pd.DataFrame(columns=fam.index)
rowNumber = 0
for snpId in snpQuery_cov['i'] :
geno = bgen["genotype"][snpId].compute()
if(geno["phased"]):
snp_df_dosage_t = geno["probs"][:,[0,2]].sum(1).astype(float)
snp_df_dosage_t[(np.amax(geno["probs"][:,:2],1)+np.amax(geno["probs"][:,2:4],1))<(1+minimumProbabilityStep)] = float('NaN')
else :
snp_df_dosage_t = (geno["probs"][:,0]* 2)+geno["probs"][:,1]
snp_df_dosage_t[np.amax(geno["probs"][:,:3],1)<((1/3)+minimumProbabilityStep)] = float('NaN')
snp_df_dosage_t = pd.Series(snp_df_dosage_t, index= fam.index)
snp_df_dosage_t.name = snpId
snp_cov_df_t = snp_cov_df_t.append(snp_df_dosage_t)
rowNumber = rowNumber +1
snp_cov_df = snp_cov_df_t.transpose()
snp_cov_df_t = None
if debugger:
fun_end = time.time()
print(" Selecting feature variant covariate took {}".format(fun_end-fun_start))
########################################################################################################################################################
########################################################################################################################################################
# Check the number of SNP to be tested and look if there is some SNP or feature filtering requirement
if (len(snpQuery) != 0) and (snp_filter_df is not None):
toSelect = set(snp_filter_df.index).intersection(set(snpQuery['snp']))
snpQuery = snpQuery.loc[snpQuery['snp'].isin(toSelect)]
if (len(snpQuery) != 0) and (snp_feature_filter_df is not None):
toSelect = set(np.unique(snp_feature_filter_df['snp_id'].loc[snp_feature_filter_df['feature_id']==feature_id])).intersection(set(snpQuery['snp']))
snpQuery = snpQuery.loc[snpQuery['snp'].isin(toSelect)]
if len(snpQuery) == 0:
print("Feature: "+feature_id+" not tested. No SNPS passed QC for phenotype.")
fail_qc_features.append(feature_id)
continue
########################################################################################################################################################
else:
# selecting phenotype array
phenotype_ds = phenotype_df.loc[feature_id]
contains_missing_samples = any(~np.isfinite(phenotype_ds))
#####################################################################################################################################################
# check for missing samples according to specific feature otherwise use previous SNP QC information
if(contains_missing_samples):
print ('Feature: ' + feature_id + ' contains missing data.')
phenotype_ds.dropna(inplace=True)
na_containing_features = na_containing_features+1
'''select indices for relevant individuals in genotype matrix
These are not unique. NOT to be used to access phenotype/covariates data
'''
individual_ids = sample2individual_df.loc[phenotype_ds.index,'iid'].values
sample2individual_feature= sample2individual_df.loc[phenotype_ds.index]
if(contains_missing_samples):
tmp_unique_individuals = geneticaly_unique_individuals
if (kinship_df is not None) and (relatedness_score is not None):
geneticaly_unique_individuals = utils.get_unique_genetic_samples(kinship_df.loc[individual_ids,individual_ids], relatedness_score);
else:
geneticaly_unique_individuals = individual_ids
#####################################################################################################################################################
else:
#If no missing samples we can use the previous SNP QC information before actually loading data.
#This allows for more efficient blocking and retrieving of data
snpQuery = snpQuery.loc[snpQuery['snp'].map(lambda x: x not in list(map(str, fail_qc_snps_all)))]
#####################################################################################################################################################
# check for enough samples for QTL test
if phenotype_ds.empty or len(geneticaly_unique_individuals)<minimum_test_samples :
print("Feature: "+feature_id+" not tested not enough samples do QTL test.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
elif np.var(phenotype_ds.values) == 0:
print("Feature: "+feature_id+" has no variance in selected individuals.")
fail_qc_features.append(feature_id)
if contains_missing_samples:
geneticaly_unique_individuals = tmp_unique_individuals
continue
#####################################################################################################################################################
print ('For feature: ' +str(currentFeatureNumber)+ '/'+str(len(feature_list))+ ' (' + feature_id + '): ' + str(snpQuery.shape[0]) + ' SNPs need to be tested.\n Please stand by.')
##########################################################################################################################################################
# SNP TESTING
##########################################################################################################################################################
if(n_perm!=0):
bestPermutationPval = np.ones((n_perm), dtype=np.float)
#Here we need to start preparing the LMM, can use the fam for sample IDS in SNP matrix.
#test if the covariates, kinship, snp and phenotype are in the same order
if ((all(kinship_df.loc[sample2individual_df['iid'],sample2individual_df['iid']].index==sample2individual_feature.loc[phenotype_ds.index]['iid']) if kinship_df is not None else True) &\
(all(phenotype_ds.index==randomeff_df.loc[sample2individual_feature['sample'],sample2individual_feature['sample']].index) if randomeff_df is not None else True) &\
(all(phenotype_ds.index==covariate_df.loc[sample2individual_feature['sample'],:].index) if covariate_df is not None else True)):
'''
if all lines are in order put in arrays the correct genotype and phenotype
x=a if cond1 else b <---> equivalent to if cond1: x=a else x=b; better readability of the code
'''
#######################################################################################################################################################
# look if kinship or other random effect dataframe are present and QS computation !
if debugger:
fun_start = time.time()
if kinship_df is not None and randomeff_df is None:
kinship_mat = kinship_df.loc[individual_ids,individual_ids].values
kinship_mat = kinship_mat.astype(float)
##GOWER normalization of Kinship matrix.
kinship_mat *= (kinship_mat.shape[0] - 1) / (kinship_mat.trace() - kinship_mat.mean(0).sum())
## This needs to go with the subselection stuff.
if(QS is None and not contains_missing_samples):
QS = economic_qs(kinship_mat)
elif (contains_missing_samples):
QS = economic_qs(kinship_mat)
# combining the two matrices
if kinship_df is not None and randomeff_df is not None:
#Here we need to match names and make sure that the order is the same and the right samples get mixed.
randomeff_mix = True
if(not Sigma_qs and not contains_missing_samples):
kinship_mat = kinship_df.loc[individual_ids,individual_ids].values
kinship_mat = kinship_mat.astype(float)
randomeff_mat = randomeff_df.loc[sample2individual_feature['sample'],sample2individual_feature['sample']].values
randomeff_mat = randomeff_mat.astype(float)
for rho in rho1:
Sigma[rho] = rho * kinship_mat + (1 - rho) * randomeff_mat
Sigma[rho] *= (Sigma[rho].shape[0] - 1) / (Sigma[rho].trace() - Sigma[rho].mean(0).sum())
Sigma_qs[rho] = economic_qs(Sigma[rho])
elif (contains_missing_samples):
#To fix: this needs to be reset after running with missing samples. Now Missing!!
kinship_mat = kinship_df.loc[individual_ids,individual_ids].values
kinship_mat = kinship_mat.astype(float)
randomeff_mat = randomeff_df.loc[sample2individual_feature['sample'],sample2individual_feature['sample']].values
randomeff_mat = randomeff_mat.astype(float)
for rho in rho1:
Sigma[rho] = rho * kinship_mat + (1 - rho) * randomeff_mat
##GOWER normalization of Kinship matrix.
Sigma[rho] *= (Sigma[rho].shape[0] - 1) / (Sigma[rho].trace() - Sigma[rho].mean(0).sum())
Sigma_qs[rho] = economic_qs(Sigma[rho])
# if kinship_df is None and randomeff_df is not None:
# randomeff_mat = randomeff_df.loc[individual_ids,individual_ids].values
# randomeff_mat = randomeff_mat.astype(float)
# ##GOWER normalization of Kinship matrix.
# randomeff_mat *= (randomeff_mat.shape[0] - 1) / (randomeff_mat.trace() - randomeff_mat.mean(0).sum())
# ## This needs to go with the subselection stuff.
# if(QS is None and not contains_missing_samples):
# QS = economic_qs(randomeff_mat)
# elif (contains_missing_samples):
# QS = economic_qs(randomeff_mat)
# creating a fake QS if none random effect is present or use the read depth one
if kinship_df is None:
if randomeff_df is None:
K = np.eye(len(phenotype_ds.index))
if(QS is None and not contains_missing_samples):
QS = economic_qs(K)
elif (contains_missing_samples):
QS = economic_qs(K)
else:
if(QS is None and not contains_missing_samples):
QS = economic_qs(randomeff_df)
elif (contains_missing_samples):
QS = economic_qs(randomeff_df)
if debugger:
fun_end = time.time()
print(" Computing QS took {}".format(fun_end-fun_start))
#######################################################################################################################################################
#######################################################################################################################################################
# covariance matrix setting
cov_matrix = covariate_df.loc[sample2individual_feature['sample'],:].values if covariate_df is not None else None
if covariate_df is None:
cov_matrix = np.ones((len(individual_ids), 1))
if snp_cov_df is not None:
snp_cov_df_tmp = snp_cov_df.loc[individual_ids,:]
snp_cov_df_tmp.index=sample2individual_feature['sample']
snp_cov_df = pd.DataFrame(fill_NaN.fit_transform(snp_cov_df_tmp))
snp_cov_df.index=snp_cov_df_tmp.index
snp_cov_df.columns=snp_cov_df_tmp.columns
cov_matrix = np.concatenate((cov_matrix,snp_cov_df.values),1)
snp_cov_df_tmp = None
snp_cov_df = None
cov_matrix = cov_matrix.astype(float)
#######################################################################################################################################################
else:
print ('There is an issue in mapping phenotypes vs covariates and/or kinship')
sys.exit()
###########################################################################################################################################################
# force normal distribution of expression values
phenotype_ds = pd.Series(data= utils.force_normal_distribution(phenotype_ds.values,method=gaussianize_method) if gaussianize_method is not None else phenotype_ds.values,index=phenotype_ds.index,name=phenotype_ds.name)
###########################################################################################################################################################
##########################################################################################################################################################
# Regressing up covariates
if debugger:
fun_start = time.time()
if regressCovariatesUpfront:
phenotype = phenotype_ds.values
##Using LMM/LM to regress covariates up front.
# Computing Null Model
if debugger:
fun_start = time.time()
if randomeff_mix:
mixingParameters = utils.rhoTest(None, phenotype,cov_matrix,Sigma_qs,mixed, None)
lmm = mixingParameters["lmm"]
log[(feature_id)].append(mixingParameters["rho"])
feature_best_rho = mixingParameters["rho"]
if mixingParameters["rho"]!=0:
print("Random effect has influence, mixing parameter: "+str(mixingParameters["rho"]))
else :
print("Only kinship has effect.")
else:
lmm = LMM(phenotype, cov_matrix, QS)
if not mixed:
lmm.delta = 1
lmm.fix('delta')
lmm.fit(verbose=False)
if debugger:
fun_end = time.time()
print(" Computing Null model took {}".format(fun_end-fun_start))
#Replace phenotype with corrected phenotype:
phenotype_ds = pd.Series(data= (phenotype-cov_matrix[:,1:].dot(lmm.beta[1:])),index=phenotype_ds.index,name=phenotype_ds.name)
if debugger:
fun_end = time.time()
print(" Regressing Covariates took {}".format(fun_end-fun_start))
##########################################################################################################################################################
if debugger:
fun_start = time.time()
##########################################################################################################################################################
# Fast scanning - iterate according to a blocksize
countChunker = 0
for snpGroup in utils.chunker(snpQuery, blocksize):
countChunker=countChunker+1
#print(countChunker)
#Fix seed at the start of the first chunker so all permutations are based on the same random first split.
np.random.seed(seed)
#print(snpGroup)
snp_idxs = snpGroup['i'].values
snp_names = snpGroup['snp'].values
tested_snp_ids.extend(snp_names)
#subset genotype matrix, we cannot subselect at the same time, do in two steps.
if debugger:
fun_start = time.time()
##########################################################################################################################################################
# SNP dataframe creation
if(plinkGenotype):
snp_df = pd.DataFrame(data=bed[snp_idxs,:].compute().transpose(),index=fam.index,columns=snp_names)
else :
snp_df_dosage = pd.DataFrame(np.nan,index=fam.index, columns = snp_names)
snp_df = pd.DataFrame(np.nan,index=fam.index, columns = snp_names)
rowNumber = 0
for snpId in snp_idxs :
geno = bgen["genotype"][snpId].compute()
if (geno["ploidy"].min()>1 & geno["ploidy"].max()<3) :
if(geno["phased"]):
snp_df_dosage_t = geno["probs"][:,[0,2]].sum(1).astype(float)
snp_df_t = (np.abs(np.argmax(geno["probs"][:,:2], axis=1)-1)+np.abs(np.argmax(geno["probs"][:,2:4], axis=1)-1)).astype(float)
naId = (np.amax(geno["probs"][:,:2],1)+np.amax(geno["probs"][:,2:4],1))<(1+minimumProbabilityStep)
snp_df_dosage_t[naId] = float('NaN')
snp_df_t[naId] = float('NaN')
else :
snp_df_dosage_t = ((geno["probs"][:,0]* 2)+geno["probs"][:,1]).astype(float)
snp_df_t = (np.abs(np.argmax(geno["probs"][:,:3], axis=1)-2)).astype(float)
naId = np.amax(geno["probs"][:,:3],1)<((1/3)+minimumProbabilityStep)
snp_df_dosage_t[naId] = float('NaN')
snp_df_t[naId] = float('NaN')
snp_df_dosage.loc[:,snp_names[rowNumber]] = snp_df_dosage_t
snp_df.loc[:,snp_names[rowNumber]] = snp_df_t
rowNumber = rowNumber +1
snp_df_dosage = snp_df_dosage.loc[individual_ids,:]
snp_df = snp_df.loc[individual_ids,:]
snp_df = snp_df.loc[:,np.unique(snp_df.columns)[np.unique(snp_df.columns,return_counts=1)[1]==1]]
if debugger:
fun_end = time.time()
print(" Subsetting genotype matrix took {}".format(fun_end-fun_start))
##########################################################################################################################################################
#SNP QC.
if debugger:
fun_start = time.time()
if not contains_missing_samples:
#remove SNPs from snp_df if they have previously failed QC
snp_df = snp_df.loc[:,snp_df.columns[~snp_df.columns.isin(fail_qc_snps_all)]]
if snp_df.shape[1] == 0:
continue
snps_to_test_df = snp_df.loc[:,snp_df.columns[~snp_df.columns.isin(pass_qc_snps_all)]]
if snps_to_test_df.shape[1] > 0:
#Only do QC on relevant SNPs. join pre-QCed list and new QCed list.
if kinship_df is not None:
passed_snp_names,failed_snp_names,call_rate,maf,hweP = do_snp_qc(snps_to_test_df.iloc[np.unique(snps_to_test_df.index,return_index=1)[1]].loc[geneticaly_unique_individuals,:], min_call_rate, min_maf, min_hwe_P)
else:
passed_snp_names,failed_snp_names,call_rate,maf,hweP = do_snp_qc(snps_to_test_df, min_call_rate, min_maf, min_hwe_P)
snps_to_test_df = None
#append snp_names and failed_snp_names
pass_qc_snps_all.extend(passed_snp_names)
fail_qc_snps_all.extend(failed_snp_names)
snp_df = snp_df.loc[:,snp_df.columns[snp_df.columns.isin(pass_qc_snps_all)]]
else:
#Do snp QC for relevant section.
#Get relevant slice from: phenotype_ds
if kinship_df is not None:
passed_snp_names,failed_snp_names,call_rate,maf,hweP = do_snp_qc(snp_df.iloc[np.unique(snp_df.index,return_index=1)[1]].loc[geneticaly_unique_individuals,:], min_call_rate, min_maf, min_hwe_P)
else:
passed_snp_names,failed_snp_names,call_rate,maf,hweP = do_snp_qc(snp_df, min_call_rate, min_maf, min_hwe_P)
snp_df = snp_df.loc[:,snp_df.columns[snp_df.columns.isin(passed_snp_names)]]
snpQcInfo_t = None
if call_rate is not None:
snpQcInfo_t = call_rate
if maf is not None:
snpQcInfo_t = pd.concat([snpQcInfo_t,maf.reindex(snpQcInfo_t.index)],axis=1)
if hweP is not None:
snpQcInfo_t = pd.concat([snpQcInfo_t,hweP.reindex(snpQcInfo_t.index)],axis=1)
if debugger:
fun_end = time.time()
print(" SNP quality control took {}".format(fun_end-fun_start))
##########################################################################################################################################################
call_rate = None
maf = None
hweP = None
if snpQcInfo is None and snpQcInfo_t is not None:
snpQcInfo = snpQcInfo_t
elif snpQcInfo_t is not None:
snpQcInfo = pd.concat([snpQcInfo, snpQcInfo_t], axis=0, sort = False)
##First process SNPQc than check if si can continue.
if len(snp_df.columns) == 0:
continue
##If we use bgen we replace the genotypes here to only have the dosage matrix in mem. Trying to save some memory.
if (not plinkGenotype):
snp_df= snp_df_dosage.loc[:,np.unique(snp_df.columns)]
snp_df_dosage = None
#We could make use of relatedness when imputing. And impute only based on genetically unique individuals.
snp_df = pd.DataFrame(fill_NaN.fit_transform(snp_df),index=snp_df.index,columns=snp_df.columns)
##No more snp_matrix_DF > snp_df
# test if the covariates, kinship, snp and phenotype are in the same order
if (len(snp_df.index) != len(sample2individual_feature.loc[phenotype_ds.index]['iid']) or not all(snp_df.index==sample2individual_feature.loc[phenotype_ds.index]['iid'])):
print ('There is an issue in mapping phenotypes and genotypes')
sys.exit()
##########################################################################################################################################################
# SCANNING
if debugger:
fun_start = time.time()
rho = [None] * snp_df.shape[1]
pVal = [None] * snp_df.shape[1]
if pearson:
for snpPos in range(0, snp_df.shape[1]) :
rho[snpPos], pVal[snpPos] = sp.stats.pearsonr(snp_df.values[:,snpPos], phenotype_ds.values)
else:
for snpPos in range(0, snp_df.shape[1]) :
rho[snpPos], pVal[snpPos] = sp.stats.spearmanr(snp_df.values[:,snpPos], phenotype_ds.values)
if debugger:
fun_end = time.time()
print(" Actual scanning took {}".format(fun_end-fun_start))
#########################################################################################################################################################
#add these results to qtl_results
temp_df = pd.DataFrame(index = range(len(snp_df.columns)),columns=['feature_id','snp_id','p_value','beta','beta_se','empirical_feature_p_value'])
temp_df['snp_id'] = snp_df.columns
temp_df['feature_id'] = feature_id.replace("/","-")
temp_df['beta'] = np.asarray(rho)
temp_df['p_value'] = np.asarray(pVal)
#insert default dummy value
temp_df['beta_se'] = None
temp_df['empirical_feature_p_value'] = -1.0
##########################################################################################################################################################
# SCANNING
if debugger:
fun_start = time.time()
if(n_perm!=0):
pValueBuffer = []
totalSnpsToBeTested = (snp_df.shape[1]*n_perm)
permutationStepSize = np.floor(n_perm/(totalSnpsToBeTested/blocksize))
if(permutationStepSize>n_perm):
permutationStepSize=n_perm
elif(permutationStepSize<1):
permutationStepSize=1
if(write_permutations):
print("Not supported.")
#perm_df = pd.DataFrame(index = range(len(snp_df.columns)),columns=['snp_id'] + ['permutation_'+str(x) for x in range(n_perm)])
#perm_df['snp_id'] = snp_df.columns
for currentNperm in utils.chunker(list(range(1, n_perm+1)), permutationStepSize):
if (kinship_df is not None) and (relatedness_score is not None):
temp = utils.get_shuffeld_genotypes_preserving_kinship(geneticaly_unique_individuals, relatedness_score, snp_df,kinship_df.loc[individual_ids,individual_ids], len(currentNperm))
else:
temp = utils.get_shuffeld_genotypes(snp_df, len(currentNperm))
temp = temp.astype(float)
var_pvalues_p = [None] * temp.shape[1]
if pearson:
for snpPos in range(0, temp.shape[1]) :
rhoP, var_pvalues_p[snpPos] = sp.stats.pearsonr(temp[:,snpPos], phenotype_ds.values)
else :
for snpPos in range(0, temp.shape[1]) :
rhoP, var_pvalues_p[snpPos] = sp.stats.spearmanr(temp[:,snpPos], phenotype_ds.values)
pValueBuffer.extend(np.asarray(var_pvalues_p))
if(not(len(pValueBuffer)==totalSnpsToBeTested)):
print(len(pValueBuffer))
print(pValueBuffer)
print(totalSnpsToBeTested)
print('Error in blocking logic for permutations.')
sys.exit()
perm = 0
for relevantOutput in utils.chunker(pValueBuffer,snp_df.shape[1]) :
#if(write_permutations):
# perm_df['permutation_'+str(perm)] = relevantOutput
if(bestPermutationPval[perm] > min(relevantOutput)):
bestPermutationPval[perm] = min(relevantOutput)
perm = perm+1
#print(relevantOutput)
#print('permutation_'+str(perm))
if not temp_df.empty :
data_written = True
output_writer.add_result_df(temp_df)
#if(write_permutations):
# permutation_writer.add_permutation_results_df(perm_df,feature_id)
if debugger:
fun_end = time.time()
print(" Permutations took {}".format(fun_end-fun_start))
#This we need to change in the written file.
if debugger:
fun_start = time.time()
if not data_written :
fail_qc_features.append(feature_id)
else:
n_samples.append(phenotype_ds.size)
n_e_samples.append(len(geneticaly_unique_individuals))
if n_perm>1 :
#updated_permuted_p_in_hdf5(bestPermutationPval, feature_id);
alpha_para, beta_para = output_writer.apply_pval_correction(feature_id.replace("/","-"),bestPermutationPval, cis_mode)
if write_feature_top_permutations:
np.savetxt(output_dir+"/Permutation.pValues."+feature_id.replace("/","-")+".txt",bestPermutationPval)
alpha_params.append(alpha_para)
beta_params.append(beta_para)
if randomeff_mix :
random_eff_param.append(feature_best_rho)
if contains_missing_samples:
QS = None
Sigma_qs = None
geneticaly_unique_individuals = tmp_unique_individuals
del tmp_unique_individuals
if snpQcInfo is not None:
snpQcInfo.index.name = "snp_id"
snpQcInfo.to_csv(output_dir+'/snp_qc_metrics_naContaining_feature_{}.txt'.format(feature_id.replace("/","-")),sep='\t')
else:
if (snpQcInfo is not None and snpQcInfoMain is not None):
snpQcInfoMain = pd.concat([snpQcInfoMain, snpQcInfo], axis=0, sort=False)
elif snpQcInfo is not None :
snpQcInfoMain = snpQcInfo.copy(deep=True)
if debugger:
fun_end = time.time()
print(" Writing took {}".format(fun_end-fun_start))
#if snpQcInfo is not None:
#snpQcInfo2 = snpQcInfo.copy().transpose()
#snpQcInfo2.to_csv(output_dir+'/snp_qc_metrics_feature_{}.txt'.format(feature_id),sep='\t')
#print('step 5')
print("Time: --- %s seconds ---" % (time.time() - start_time))
tot_time += time.time() - start_time
idx += 1
print("Mean: --- %s seconds ---" % (tot_time/idx))
log[(feature_id)].append((time.time() - start_time))
log[(feature_id)].append(tot_time/idx)
output_writer.close()
if(write_permutations):
permutation_writer.close()
fail_qc_features = np.unique(fail_qc_features)
if((len(feature_list)-len(fail_qc_features))==0):
time.sleep(15)
#Safety timer to make sure the file is unlocked.
print("Trying to remove the h5 file. Nothing has been tested.")
print(output_dir+'qtl_results_{}_{}_{}.h5'.format(chromosome,selectionStart,selectionEnd))
if not selectionStart is None :
os.remove(output_dir+'qtl_results_{}_{}_{}.h5'.format(chromosome,selectionStart,selectionEnd))
else :
os.remove(output_dir+'qtl_results_{}.h5'.format(chromosome))
sys.exit()
#gather unique indexes of tested SNPs
tested_snp_ids = list(set(tested_snp_ids))
#write annotation and snp data to file
snp_df = pd.DataFrame()
snp_df['snp_id'] = bim['snp']
snp_df['chromosome'] = bim['chrom']
snp_df['position'] = bim['pos']
snp_df['assessed_allele'] = bim['a1']
snp_df.index = snp_df['snp_id']
snp_df = snp_df.drop_duplicates()
snp_df = snp_df.reindex(tested_snp_ids)
snp_df = snp_df.drop_duplicates()
if snpQcInfoMain is not None :
snpQcInfoMain['index']=snpQcInfoMain.index
snpQcInfoMain = snpQcInfoMain.drop_duplicates()
del snpQcInfoMain['index']
snp_df = pd.concat([snp_df, snpQcInfoMain.reindex(snp_df.index)], axis=1)
if(snp_df.shape[1]==5):
snp_df.columns = ['snp_id','chromosome','position','assessed_allele','call_rate']
elif(snp_df.shape[1]==6):
snp_df.columns = ['snp_id','chromosome','position','assessed_allele','call_rate','maf']
else :
snp_df.columns = ['snp_id','chromosome','position','assessed_allele','call_rate','maf','hwe_p']
feature_list = list(set(feature_list) - set(fail_qc_features))
annotation_df = annotation_df.reindex(feature_list)
annotation_df['n_samples'] = n_samples
annotation_df['n_e_samples'] = n_e_samples
if(n_perm>1):
annotation_df['alpha_param'] = alpha_params
annotation_df['beta_param'] = beta_params
if randomeff_mix:
annotation_df['rho'] = random_eff_param
if not selectionStart is None :
snp_df.to_csv(output_dir+'/snp_metadata_{}_{}_{}.txt'.format(chromosome,selectionStart,selectionEnd),sep='\t',index=False)
annotation_df.to_csv(output_dir+'/feature_metadata_{}_{}_{}.txt'.format(chromosome,selectionStart,selectionEnd),sep='\t')
else :
snp_df.to_csv(output_dir+'/snp_metadata_{}.txt'.format(chromosome),sep='\t',index=False)
annotation_df.to_csv(output_dir+'/feature_metadata_{}.txt'.format(chromosome),sep='\t')
if not selectionStart is None :
print("saving log!")
print(log)
#pd.DataFrame.from_dict(log, orient="index", columns=["rho","start","mean"]).to_csv(output_dir + "/" + str(chromosome) + "_" + str(selectionStart) + "_" + str(selectionEnd) + "_log_rho.txt", sep="\t")
else:
print("saving log!")
