def main():
geno_in, norm_cov, cov_out_hdf5, cov_out_csv = sys.argv[1:]
logger = LoggerFactory.get_logger(cov_out_hdf5 + '.log')
LoggerFactory.log_command(logger, sys.argv[1:])
## Import genotype data
logger.info('Loading genotype from %s', geno_in)
geno_reader = gr.genotype_reader_tables(geno_in)
if (norm_cov == '1'):
logger.info('Normalizing')
norm = True
else:
logger.info('NOT normalizing')
norm = False
sample_relatedness = geno_reader.getCovariance(normalize=norm)
logger.info('Saving covariance to HDF5 file %s', cov_out_hdf5)
out_dict = {'Cov': sample_relatedness}
o = h5py.File(cov_out_hdf5, 'w')
util_functions.smartDumpDictHdf5(out_dict, o)
o.close()
logger.info('Saving covariance to CSV file %s', cov_out_csv)
save_cov_in_text_format(cov_out_csv, sample_relatedness,
geno_reader.sample_ID)
logger.info('Done!')
def main():
geno_in, scale_kinship, kinship_out_hdf5, kinship_out_csv = sys.argv[1:]
logger = LoggerFactory.get_logger(kinship_out_hdf5 + '.log')
LoggerFactory.log_command(logger, sys.argv[1:])
## Import genotype data
geno = genotype.load_hdf5_genotype_data(geno_in)
SNP_acc = geno.accessions
logger.info('Finished reading SNP from %s', geno_in)
logger.info('Start calculating kinship')
K = geno.get_ibs_kinship_matrix()
if (scale_kinship == '1'):
logger.info('Scaling')
K = kinship.scale_k(K)
else:
logger.info('NOT scaling')
logger.info('Saving kinship to HDF5 file %s', kinship_out_hdf5)
kinship.save_kinship_to_file(kinship_out_hdf5, K, geno.accessions,
geno.num_snps)
logger.info('Saving kinship to CSV file %s', kinship_out_csv)
save_kinship_in_text_format(kinship_out_csv, K, geno.accessions)
logger.info('Done!')
def main():
usage = "usage: %prog [options]"
parser = OptionParser(usage=usage)
parser.add_option("-O",
"--outfile",
action="store",
dest='outfile',
type=str,
help='The output hdf5 file wiht the resulting data',
default="example_out")
parser.add_option("-R",
"--dmr",
action="store",
dest='dmr',
help="Read DMR tsv file (filename)",
default=None)
parser.add_option("-S",
"--dms",
action="store",
dest='dms',
help="Read methylation site tsv file (filename)",
default=None)
(options, args) = parser.parse_args()
logger = LoggerFactory.get_logger(options.outfile + '.log')
LoggerFactory.log_command(logger, sys.argv)
hdf = h5py.File(options.outfile)
if options.dmr is not None:
logger.info('Converting DMR tsv %s and write to %s', options.dmr,
options.outfile)
convert_dmr_tsv(hdf,
options.dmr,
chrom=None,
start=None,
end=None,
sample_subset=None)
if options.dms is not None:
logger.info('Converting DMS tsv %s and write to %s', options.dms,
options.outfile)
convert_dms_tsv(hdf,
options.dms,
chrom=None,
start=None,
end=None,
sample_subset=None)
logger.info('Done!')
def main():
geno_in, acc_in, maf_lb, maf_ub, geno_out = sys.argv[1:]
logger = LoggerFactory.get_logger(geno_out + '.log')
LoggerFactory.log_command(logger, sys.argv[1:])
maf_lb, maf_ub = float(maf_lb), float(maf_ub)
## Import genotype data
geno = genotype.load_hdf5_genotype_data(geno_in)
SNP_acc = geno.accessions
logger.info('Finished reading SNP from %s', geno_in)
## accession subset
with open(acc_in, 'rb') as f:
reader = csv.reader(f)
file_acc = list(reader)
logger.info('Finished reading accession subset from %s', acc_in)
## get common accessions in the same order for genotype and accession subset
acc_common = [acc for acc in SNP_acc if acc in file_acc]
## filtering
logger.info(
'Start subsetting accessions and filtering SNPs by MAF >%f and <=%f',
maf_lb, maf_ub)
match = lambda a, b: [b.index(x) if x in b else None for x in a]
geno.filter_accessions_ix(match(acc_common, SNP_acc))
(num_snps, num_removed) = filter_maf_snps(geno, maf_lb, maf_ub)
logger.info('Removed %d from %d SNPs', num_removed, num_snps)
logger.info('Number of SNPs remaining %d', geno.num_snps)
logger.info('Start writing filtered genotype file to %s', geno_out)
geno.save_as_hdf5(geno_out)
logger.info('Finished')
logger.info('Done!')
def main():
geno_file, pheno_file, out_dir = sys.argv[1:]
#geno_file = '/gale/netapp/home/shhuang/data/1001_genomes/gmi_release_v3.1/1001genomes_snp-short-indel_only_ACGTN_1001tx_filter1.hdf5'
#pheno_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-01-03/ath1001_tx_norm_2016-01-03-filtered01_1001g_vst_cv0p05T.hdf5'
#out_dir = '.'
logger = LoggerFactory.get_logger(os.path.join(out_dir,
'get_geno_pos.log'))
LoggerFactory.log_command(logger, sys.argv[1:])
logger.info('Loading genotype from %s', geno_file)
geno_reader = gr.genotype_reader_tables(geno_file)
logger.info('Loading phenotype from %s', pheno_file)
pheno_reader = phr.pheno_reader_tables(pheno_file)
pheno_reader.sample_ID = strip_xvec(pheno_reader.sample_ID)
# the data object allows to query specific genotype or phenotype data
logger.info('Creating QTL dataset')
dataset = data.QTLData(geno_reader=geno_reader, pheno_reader=pheno_reader)
# getting genotypes
#snps = dataset.getGenotypes() #SNPS
position = dataset.getPos()
position, chromBounds = data_util.estCumPos(position=position,
offset=100000)
logger.info('Writing output to directory %s', out_dir)
position = position.astype(int)
chromBounds = chromBounds.astype(int)
position.to_csv(os.path.join(out_dir, 'position.txt'),
header=True,
index=False,
sep='\t')
np.savetxt(os.path.join(out_dir, 'chromBounds.txt'),
chromBounds,
delimiter=",")
def main():
geno_file,pheno_file,norm_mode,panama_file,RNA_start,RNA_end,out_dir = sys.argv[1:]
#geno_file = '/gale/netapp/home/shhuang/data/1001_genomes/gmi_release_v3.1/1001genomes_snp-short-indel_only_ACGTN_1001tx_filter1.hdf5'
#pheno_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-01-03/ath1001_tx_norm_2016-01-03-filtered01_1001g_vst_cv0p05T.hdf5'
#norm_mode = 'RIN'
#out_dir = '.'
#panama_file = '/gale/netapp/home/shhuang/projects/1001_genomes/calc_k_panama_2016-02-03/calc_k_panama_2016-02-03-_K10_dat.hdf5'
#RNA_start,RNA_end = 0,2
RNA_start,RNA_end = int(RNA_start),int(RNA_end)
make_sure_path_exists(out_dir)
log_dir = make_sure_path_exists(os.path.join(out_dir,'logs'))
logger = LoggerFactory.get_logger(os.path.join(log_dir,'%s-%s.log'%(RNA_start,RNA_end)),
file_level=logging.DEBUG,console_level=logging.DEBUG)
LoggerFactory.log_command(logger,sys.argv[1:])
logger.info('Output directory: %s',out_dir)
out_graphics_dir = make_sure_path_exists(os.path.join(out_dir,'graphics'))
out_results_dir = make_sure_path_exists(os.path.join(out_dir,'results'))
logger.info('Loading genotype from %s',geno_file)
geno_reader = gr.genotype_reader_tables(geno_file)
logger.info('Loading phenotype from %s',pheno_file)
pheno_reader = phr.pheno_reader_tables(pheno_file)
pheno_reader.sample_ID = strip_xvec(pheno_reader.sample_ID)
logger.info('Loading sample relatedness from %s',panama_file)
panama_f = h5py.File(panama_file,'r')
Ktot = panama_f['Ktot'][:]
# the data object allows to query specific genotype or phenotype data
logger.info('Creating QTL dataset')
dataset = data.QTLData(geno_reader=geno_reader,pheno_reader=pheno_reader)
# getting genotypes
snps = dataset.getGenotypes() #SNPS
position = dataset.getPos()
position,chromBounds = data_util.estCumPos(position=position,offset=100000)
logger.info('Subset phenotype to index %d-%d',RNA_start,RNA_end)
phenotype_ID = dataset.phenotype_ID[RNA_start:RNA_end]
phenotypes,sample_idx = dataset.getPhenotypes(phenotype_ID)
logger.info('Normalization: %s',norm_mode)
if norm_mode=='None':
phenotype_vals = phenotypes.values
elif norm_mode=='RIN':
phenotype_vals = preprocess.rankStandardizeNormal(phenotypes.values)
elif norm_mode=='boxcox':
phenotype_vals,maxlog = preprocess.boxcox(phenotypes.values)
else:
logger.info('Normalization mode %s is not recognized. Exit',norm_mode)
N = snps.shape[0] #number of individuals
S = snps.shape[1] #number of SNPs
P = phenotype_vals.shape[1]#number of phenotypes
logger.info('Number of individuals: %d; number of SNPs: %d; number of phenotypes: %d',
N,S,P)
logger.info('Plotting phenotype histograms')
phenohist_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'phenohist'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(phenohist_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[3,3])#create the figure
plot_normal(phenotype_vals[:,ip],alpha=0.8,figure=fig)
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
#logger.info('Start testing: LM')
#lm = qtl.test_lm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals.values,
# covs=cov,verbose=True)
#convert P-values to a DataFrame for nice output writing:
#pvalues_lm = pd.DataFrame(data=lm.pvalues.T,index=dataset.geno_ID,
# columns=phenotype_ID)
logger.info('Start testing: LMM')
#lmm = qtl.test_lmm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals.values,
# K=sample_relatedness,covs=cov,verbose=True)
lmm = qtl.test_lmm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals,
K=Ktot,covs=None,verbose=True)
pvalues_lmm = pd.DataFrame(data=lmm.pvalues.T,index=dataset.geno_ID,
columns=phenotype_ID)
logger.info('Saving P-values to text file')
#lm_pval_dir = make_sure_path_exists(os.path.join(out_results_dir,'lm_pval'))
lmm_pval_dir = make_sure_path_exists(os.path.join(out_results_dir,'lmm_pval'))
for ip,p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
#pvalues_lm[p_ID].to_csv(os.path.join(lm_pval_dir,'%s.txt'%p_ID),
# header=True,index=False)
pvalues_lmm[p_ID].to_csv(os.path.join(lmm_pval_dir,'%s.txt'%p_ID),
header=True,index=False)
# Genome-wide manhatton plots for one phenotype:
logger.info('Plotting Manhattan plots')
manh_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'manhattan'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(manh_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[12,8])
#subpl = plt.subplot(2,1,1)
#plot_manhattan(posCum=position['pos_cum'],pv=pvalues_lm[p_ID].values,chromBounds=chromBounds,thr_plotting=0.05)
#plt.title('%s, LM'%p_ID)
#subpl = plt.subplot(2,1,2)
plot_manhattan(posCum=position['pos_cum'],pv=pvalues_lmm[p_ID].values,chromBounds=chromBounds,thr_plotting=0.05)
plt.title('%s, LMM'%p_ID)
fig.savefig(out_file)
plt.close(fig)
# SNP vs. phenotype
logger.info('Plotting phenotype vs. SNP')
snp_pheno_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'snp_pheno'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(snp_pheno_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[3,3])#create the figure
#find maximum squared beta value
pheno_vals, s_idx = dataset.getPhenotypes([p_ID])
imax = lmm.pvalues[ip].argmin()
i_0 = snps[s_idx,imax]==0
#plot SNP vs. phenotype for max beta
plt.plot(snps[s_idx,imax]+0.05*np.random.randn(snps[s_idx,imax].shape[0]),pheno_vals.values,'.',alpha=0.5)
plt.xlabel("SNP")
plt.ylabel("phenotype")
plt.xlim([-0.5,2.5])
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P-value histgrams
logger.info('Plotting P-value histograms')
pval_hist_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'pval_hist'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(pval_hist_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[7,3])
#subpl = plt.subplot(1,2,1)
#plt.hist(pvalues_lm[p_ID].values,20,normed=True)
#plt.plot([0,1],[1,1],"r")
#plt.title("%s, LM" % p_ID)
#plt.xlabel("P-value")
#plt.ylabel("Frequency")
#subpl = plt.subplot(1,2,2)
plt.hist(pvalues_lmm[p_ID].values,20,normed=True)
plt.plot([0,1],[1,1],"r")
plt.title("%s, LMM" % p_ID)
plt.xlabel("P-value")
plt.ylabel("Frequency")
fig.savefig(out_file)
plt.close(fig)
# Quantile-Quantile plots
logger.info('Plotting Q-Q plots')
qqplot_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'qqplot'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(qqplot_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[7,3])
#subpl = plt.subplot(1,2,1)
#qqplot(pvalues_lm[p_ID].values)
#plt.title("%s, LM" % p_ID)
#subpl = plt.subplot(1,2,2)
qqplot(pvalues_lmm[p_ID].values)
plt.title("%s, LMM" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P value scatter plot
#logger.info('Plotting LM vs LMM P-values')
#pval_lmvslmm_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'pval_lmvslmm'))
#for ip,p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
# out_file = os.path.join(pval_lmvslmm_dir,'%s.png'%p_ID)
# fig = plt.figure(figsize=[3,3])
# plt.plot(-sp.log10(pvalues_lm[p_ID]),-sp.log10(pvalues_lmm[p_ID]),'.')
# ymax = max(plt.xlim()[1],plt.ylim()[1])
# plt.plot([0,ymax],[0,ymax],'k--')
# plt.xlabel('LM')
# plt.ylabel('LMM')
# plt.title(p_ID)
# fig.savefig(out_file)
# plt.close(fig)
logger.info('Done with all plots!')
logger.info('Done!')
def main():
parser = argparse.ArgumentParser(
description='Modified genome FASTA file by 5mC')
parser.add_argument('genome')
parser.add_argument('allc_h5')
parser.add_argument('genome_mod')
parser.add_argument('--zero',
help='whether the allc table is 0-index',
action='store_true')
args = parser.parse_args()
genome, allc_h5, genome_mod = args.genome, args.allc_h5, args.genome_mod
offset = 0 if args.zero else 1 # allc table positions are 1-based
logger = LoggerFactory.get_logger(genome_mod + '.log')
LoggerFactory.log_command(logger, sys.argv)
logger.info('Getting unmodified genome FASTA file from %s', genome)
coord_pat = re.compile('^(chr)?(.+)$')
fa_list = list(SeqIO.parse(genome, "fasta"))
fa_dict = dict((r.id, r.seq) for r in fa_list)
fa_key_by_chrom = dict()
for k in fa_dict.keys(): # '1' -> 'chr1' or '1' -> '1'
coord_mat = coord_pat.match(k)
chrom = coord_mat.group(2)
fa_key_by_chrom[chrom] = k
logger.info('Chromosomes: %s', fa_key_by_chrom.keys())
logger.info('Modifying FASTA by all_c %s', allc_h5)
fa_dict_out = dict()
for chrom, fa_key in fa_key_by_chrom.items():
logger.info('Reading allc table for chromosome %s from %s', chrom,
allc_h5)
hdf = read_hdf(allc_h5,
'allc_' + str(chrom),
where=['mcall==1'],
columns=['pos', 'strand', 'context'])
mc_pos, mc_strand, mc_type = hdf['pos'], hdf['strand'], hdf['context']
logger.info('Number of methylated C: %d', len(mc_pos))
seq = fa_dict[fa_key].tomutable()
for p, s, t in zip(mc_pos, mc_strand, mc_type):
p0 = p - offset
if (p0 > len(seq)):
logger.info('Index out of bound for %s: mc_pos %d, len %d',
fa_key, p0, len(seq))
continue
if s == '+':
if (seq[p0] == 'C' or seq[p0] == 'c'):
seq[p0] = 'm'
else:
logger.warn(
'Sequence %s: expected to see C/c (%s:%s) at %d, but saw %s',
fa_key, t, s, p0, seq[p0])
elif s == '-':
if (seq[p0] == 'G' or seq[p0] == 'g'):
seq[p0] = '1'
else:
logger.warn(
'Sequence %s: expected to see G/g (%s:%s) at %d, but saw %s',
fa_key, t, s, p0, seq[p0])
else:
logger.warn('Sequence %s: unrecognized strand %s at %d',
fa_key, s, p0)
fa_dict_out[fa_key] = seq
for r in fa_list:
r.seq = fa_dict_out[r.id]
with open(genome_mod, 'w') as ofa:
SeqIO.write(fa_list, ofa, 'fasta')
logger.info('Done!')
def main():
if 1:
geno_file, pheno_file, norm_mode, K_file, cov_file, RNA_start, RNA_end, out_dir = sys.argv[
1:]
if 0:
geno_file = '/gale/netapp/home/shhuang/data/1001_genomes/dmC_bins/dmC_filtered/dmC_filtered_methylation_4.hdf5'
pheno_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-02-06/ath1001_tx_norm_2016-02-06-UQ_gNorm_k4_vst2_cv0p05_UQCounts_1001gT.hdf5'
norm_mode = 'RIN'
out_dir = 'test_v8'
K_file = '/gale/netapp/home/shhuang/data/1001_genomes/gmi_release_v3.1/X1001tx_filter1/norm_cov_1001tx_filter1.csv'
cov_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-01-03/ath1001_tx_norm_2016-01-03-gNorm_W_k4.txt'
RNA_start, RNA_end = 0, 5
make_sure_path_exists(out_dir)
log_dir = make_sure_path_exists(os.path.join(out_dir, 'logs'))
logger = LoggerFactory.get_logger(os.path.join(
log_dir, '%s-%s.log' % (RNA_start, RNA_end)),
file_level=logging.DEBUG,
console_level=logging.DEBUG)
LoggerFactory.log_command(logger, sys.argv[1:])
logger.info('Output directory: %s', out_dir)
out_graphics_dir = make_sure_path_exists(os.path.join(out_dir, 'graphics'))
out_results_dir = make_sure_path_exists(os.path.join(out_dir, 'results'))
RNA_start, RNA_end = int(RNA_start), int(RNA_end)
logger.info('Loading genotype from %s', geno_file)
geno_reader = gr.genotype_reader_tables(geno_file)
logger.info('Loading phenotype from %s', pheno_file)
pheno_reader = phr.pheno_reader_tables(pheno_file)
pheno_reader.sample_ID = strip_xvec(pheno_reader.sample_ID)
# the data object allows to query specific genotype or phenotype data
logger.info('Creating QTL dataset')
dataset = data.QTLData(geno_reader=geno_reader, pheno_reader=pheno_reader)
# getting genotypes
snps = dataset.getGenotypes() #SNPS
position = dataset.getPos()
position, chromBounds = data_util.estCumPos(position=position,
offset=100000)
logger.info('Sample relatedness %s', K_file)
logger.info('Loading sample relatedness from %s', K_file)
if (K_file == 'None'):
sample_relatedness = None
else:
logger.info('Start loading covariance from %s', K_file)
K_df = pd.read_csv(K_file, sep='\t', header=None,
index_col=0) # accessions x accessions
K_df.index = ['%d' % i for i in K_df.index]
K_df.columns = K_df.index
sample_relatedness = K_df.loc[dataset.sample_ID,
dataset.sample_ID].as_matrix()
sample_relatedness_dir = make_sure_path_exists(
os.path.join(out_graphics_dir, 'sample_relatedness'))
pl.imshow(sample_relatedness, aspect='auto')
plt.savefig(os.path.join(sample_relatedness_dir, 'sample_relatedness.png'))
logger.info('Subset phenotype to index %d-%d', RNA_start, RNA_end)
phenotype_ID = dataset.phenotype_ID[RNA_start:RNA_end]
phenotypes,sample_idx = getPhenotypes(dataset.pheno_reader,phenotype_IDs=phenotype_ID,\
sample_idx=dataset.sample_idx['pheno'])
logger.info('Phenotype normalization: %s', norm_mode)
if norm_mode == 'None':
phenotype_vals = phenotypes.values
elif norm_mode == 'RIN':
phenotype_vals = preprocess.rankStandardizeNormal(phenotypes.values)
elif norm_mode == 'boxcox':
phenotype_vals, maxlog = preprocess.boxcox(phenotypes.values)
else:
logger.info('Normalization mode %s is not recognized. Use None',
norm_mode)
phenotype_vals = phenotypes.values
N = snps.shape[0] #number of individuals
S = snps.shape[1] #number of SNPs
P = phenotype_vals.shape[1] #number of phenotypes
logger.info(
'Number of individuals: %d; number of SNPs: %d; number of phenotypes: %d',
N, S, P)
logger.info('Plotting phenotype histograms')
phenohist_dir = make_sure_path_exists(
os.path.join(out_graphics_dir, 'phenohist'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(phenohist_dir, '%s.png' % p_ID)
fig = plt.figure(figsize=[3, 3]) #create the figure
plot_normal(phenotype_vals[:, ip], alpha=0.8, figure=fig)
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
logger.info('Sample covariance %s', cov_file)
if (cov_file == 'None'):
cov = None
else:
logger.info('Start loading covariance from %s', cov_file)
cov_df = pd.read_csv(cov_file, sep='\t', header=0,
index_col=0) # cov x accessions
cov = cov_df.ix[add_xvec(dataset.sample_ID)].as_matrix()
#logger.info('Start testing: LM')
#lm = qtl.test_lm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals,
# covs=cov,verbose=True)
#convert P-values to a DataFrame for nice output writing:
#pvalues_lm = pd.DataFrame(data=lm.pvalues.T,index=dataset.geno_ID,
# columns=phenotype_ID)
logger.info('Start testing: LMM')
lmm = qtl.test_lmm(snps=snps[sample_idx].astype('int'),
pheno=phenotype_vals,
K=sample_relatedness,
covs=cov,
verbose=True)
pvalues_lmm = pd.DataFrame(data=lmm.pvalues.T,
index=dataset.geno_ID,
columns=phenotype_ID)
#lm_pval_dir = make_sure_path_exists(os.path.join(out_results_dir,'lm_pval'))
lmm_pval_dir = make_sure_path_exists(
os.path.join(out_results_dir, 'lmm_pval'))
logger.info('Saving P-values to text file in %s', lmm_pval_dir)
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
#pvalues_lm[p_ID].to_csv(os.path.join(lm_pval_dir,'%s.txt'%p_ID),
# header=True,index=False)
pvalues_lmm[p_ID].to_csv(os.path.join(lmm_pval_dir, '%s.txt' % p_ID),
header=True,
index=False)
# Genome-wide manhatton plots for one phenotype:
manh_dir = make_sure_path_exists(
os.path.join(out_graphics_dir, 'manhattan'))
logger.info('Plotting Manhattan plots in %s', manh_dir)
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(manh_dir, '%s.png' % p_ID)
fig = plt.figure(figsize=[12, 8])
#subpl = plt.subplot(2,1,1)
#plot_manhattan(posCum=position['pos_cum'],pv=pvalues_lm[p_ID].values,chromBounds=chromBounds,thr_plotting=0.05)
#plt.title('%s, LM'%p_ID)
#subpl = plt.subplot(2,1,2)
plot_manhattan(posCum=position['pos_cum'],
pv=pvalues_lmm[p_ID].values,
chromBounds=chromBounds,
thr_plotting=0.05)
plt.title('%s, LMM' % p_ID)
fig.savefig(out_file)
plt.close(fig)
# SNP vs. phenotype
snp_pheno_dir = make_sure_path_exists(
os.path.join(out_graphics_dir, 'snp_pheno'))
logger.info('Plotting phenotype vs. SNP to %s', snp_pheno_dir)
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(snp_pheno_dir, '%s.png' % p_ID)
fig = plt.figure(figsize=[3, 3]) #create the figure
#find maximum squared beta value
pheno_vals, s_idx = getPhenotypes(dataset.pheno_reader,phenotype_IDs=[p_ID],\
sample_idx=dataset.sample_idx['pheno'])
imax = lmm.pvalues[ip].argmin()
i_0 = snps[s_idx, imax] == 0
#plot SNP vs. phenotype for max beta
plt.plot(snps[s_idx, imax] +
0.05 * np.random.randn(snps[s_idx, imax].shape[0]),
pheno_vals.values,
'.',
alpha=0.5)
plt.xlabel("SNP")
plt.ylabel("phenotype")
plt.xlim([-0.5, 2.5])
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P-value histgrams
pval_hist_dir = make_sure_path_exists(
os.path.join(out_graphics_dir, 'pval_hist'))
logger.info('Plotting P-value histograms to %s', pval_hist_dir)
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(pval_hist_dir, '%s.png' % p_ID)
fig = plt.figure(figsize=[7, 3])
#subpl = plt.subplot(1,2,1)
#plt.hist(pvalues_lm[p_ID].values,20,normed=True)
#plt.plot([0,1],[1,1],"r")
#plt.title("%s, LM" % p_ID)
#plt.xlabel("P-value")
#plt.ylabel("Frequency")
#subpl = plt.subplot(1,2,2)
plt.hist(pvalues_lmm[p_ID].values, 20, normed=True)
plt.plot([0, 1], [1, 1], "r")
plt.title("%s, LMM" % p_ID)
plt.xlabel("P-value")
plt.ylabel("Frequency")
fig.savefig(out_file)
plt.close(fig)
# Quantile-Quantile plots
qqplot_dir = make_sure_path_exists(os.path.join(out_graphics_dir,
'qqplot'))
logger.info('Plotting Q-Q plots to %s', qqplot_dir)
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(qqplot_dir, '%s.png' % p_ID)
fig = plt.figure(figsize=[7, 3])
#subpl = plt.subplot(1,2,1)
#qqplot(pvalues_lm[p_ID].values)
#plt.title("%s, LM" % p_ID)
#subpl = plt.subplot(1,2,2)
qqplot(pvalues_lmm[p_ID].values)
plt.title("%s, LMM" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P value scatter plot
# logger.info('Plotting LM vs LMM P-values')
# pval_lmvslmm_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'pval_lmvslmm'))
# for ip,p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
# out_file = os.path.join(pval_lmvslmm_dir,'%s.png'%p_ID)
# fig = plt.figure(figsize=[3,3])
# plt.plot(-sp.log10(pvalues_lm[p_ID]),-sp.log10(pvalues_lmm[p_ID]),'.')
# ymax = max(plt.xlim()[1],plt.ylim()[1])
# plt.plot([0,ymax],[0,ymax],'k--')
# plt.xlabel('LM')
# plt.ylabel('LMM')
# plt.title(p_ID)
# fig.savefig(out_file)
# plt.close(fig)
logger.info('Done with all plots!')
logger.info('Done!')
def main():
geno_file,pheno_file,cov_file,RNA_start,RNA_end,out_dir = sys.argv[1:]
make_sure_path_exists(out_dir)
log_dir = make_sure_path_exists(os.path.join(out_dir,'logs'))
logger = LoggerFactory.get_logger(os.path.join(log_dir,'%s-%s.log'%(RNA_start,RNA_end)),
file_level=logging.DEBUG,console_level=logging.DEBUG)
LoggerFactory.log_command(logger,sys.argv[1:])
logger.info('Output directory: %s',out_dir)
#geno_file = '/gale/netapp/home/shhuang/data/1001_genomes/gmi_release_v3.1/1001genomes_snp-short-indel_only_ACGTN_1001tx_filter1_2.hdf5'
#pheno_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-01-03/ath1001_tx_norm_2016-01-03-gNorm_normCounts_k4_1001g_vst2_cv0p05_rinT.hdf5'
#out_dir = '.'
#cov_file = '/gale/netapp/home/shhuang/projects/1001_genomes/ath1001_tx_norm_2016-01-03/ath1001_tx_norm_2016-01-03-gNorm_W_k4.txt'
#RNA_start,RNA_end = 0,5
RNA_start,RNA_end = int(RNA_start),int(RNA_end)
out_graphics_dir = make_sure_path_exists(os.path.join(out_dir,'graphics'))
out_results_dir = make_sure_path_exists(os.path.join(out_dir,'results'))
logger.info('Loading genotype from %s',geno_file)
geno_reader = gr.genotype_reader_tables(geno_file)
logger.info('Loading phenotype from %s',pheno_file)
pheno_reader = phr.pheno_reader_tables(pheno_file)
pheno_reader.sample_ID = strip_xvec(pheno_reader.sample_ID)
# the data object allows to query specific genotype or phenotype data
logger.info('Creating QTL dataset')
dataset = data.QTLData(geno_reader=geno_reader,pheno_reader=pheno_reader)
# getting genotypes
snps = dataset.getGenotypes() #SNPS
position = dataset.getPos()
position,chromBounds = data_util.estCumPos(position=position,offset=100000)
logger.info('Calculating sample relatedness')
# non-normalized and normalized sample relatedeness matrix
sample_relatedness_unnormalized = dataset.getCovariance(normalize=False)
sample_relatedness = sample_relatedness_unnormalized/sample_relatedness_unnormalized.diagonal().mean()
sample_relatedness_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'sample_relatedness'))
pl.imshow(sample_relatedness,aspect='auto')
plt.savefig(os.path.join(sample_relatedness_dir,'sample_relatedness_norm.png'))
logger.info('Subset phenotype to index %d-%d',RNA_start,RNA_end)
phenotype_ID = dataset.phenotype_ID[RNA_start:RNA_end]
phenotype_vals,sample_idx = dataset.getPhenotypes(phenotype_ID)
N = snps.shape[0] #number of individuals
S = snps.shape[1] #number of SNPs
P = phenotype_vals.shape[1]#number of phenotypes
logger.info('Number of individuals: %d; number of SNPs: %d; number of phenotypes: %d',
N,S,P)
logger.info('Plotting phenotype histograms')
phenohist_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'phenohist'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(phenohist_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[3,3])#create the figure
plot_normal(phenotype_vals.values[:,ip],alpha=0.8,figure=fig)
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
logger.info('Start loading covariance from %s',cov_file)
cov_df = pd.read_csv(cov_file,sep='\t',header=0,index_col=0) # cov x accessions
cov = cov_df.ix[add_xvec(dataset.sample_ID)].as_matrix()
logger.info('Finished')
logger.info('Start testing: LM')
lm = qtl.test_lm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals.values,
covs=cov,verbose=True)
#convert P-values to a DataFrame for nice output writing:
pvalues_lm = pd.DataFrame(data=lm.pvalues.T,index=dataset.geno_ID,
columns=phenotype_ID)
logger.info('Start testing: LMM')
lmm = qtl.test_lmm(snps=snps[sample_idx].astype('int'),pheno=phenotype_vals.values,
K=sample_relatedness,covs=cov,verbose=True)
pvalues_lmm = pd.DataFrame(data=lmm.pvalues.T,index=dataset.geno_ID,
columns=phenotype_ID)
logger.info('Saving P-values to text file')
lm_pval_dir = make_sure_path_exists(os.path.join(out_results_dir,'lm_pval'))
lmm_pval_dir = make_sure_path_exists(os.path.join(out_results_dir,'lmm_pval'))
for ip,p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
pvalues_lm[p_ID].to_csv(os.path.join(lm_pval_dir,'%s.txt'%p_ID),
header=True,index=False)
pvalues_lmm[p_ID].to_csv(os.path.join(lmm_pval_dir,'%s.txt'%p_ID),
header=True,index=False)
# Genome-wide manhatton plots for one phenotype:
logger.info('Plotting Manhattan plots')
manh_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'manhattan'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(manh_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[12,8])
subpl = plt.subplot(2,1,1)
plot_manhattan(posCum=position['pos_cum'],pv=pvalues_lm[p_ID].values,chromBounds=chromBounds,thr_plotting=0.05)
plt.title('%s, LM'%p_ID)
subpl = plt.subplot(2,1,2)
plot_manhattan(posCum=position['pos_cum'],pv=pvalues_lmm[p_ID].values,chromBounds=chromBounds,thr_plotting=0.05)
plt.title('%s, LMM'%p_ID)
fig.savefig(out_file)
plt.close(fig)
# SNP vs. phenotype
logger.info('Plotting phenotype vs. SNP')
snp_pheno_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'snp_pheno'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(snp_pheno_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[3,3])#create the figure
#find maximum squared beta value
pheno_vals, s_idx = dataset.getPhenotypes([p_ID])
imax = lm.pvalues[ip].argmin()
i_0 = snps[s_idx,imax]==0
#plot SNP vs. phenotype for max beta
plt.plot(snps[s_idx,imax]+0.05*np.random.randn(snps[s_idx,imax].shape[0]),pheno_vals.values,'.',alpha=0.5)
plt.xlabel("SNP")
plt.ylabel("phenotype")
plt.xlim([-0.5,2.5])
plt.title("%s" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P-value histgrams
logger.info('Plotting P-value histograms')
pval_hist_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'pval_hist'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(pval_hist_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[7,3])
subpl = plt.subplot(1,2,1)
plt.hist(pvalues_lm[p_ID].values,20,normed=True)
plt.plot([0,1],[1,1],"r")
plt.title("%s, LM" % p_ID)
plt.xlabel("P-value")
plt.ylabel("Frequency")
subpl = plt.subplot(1,2,2)
plt.hist(pvalues_lmm[p_ID].values,20,normed=True)
plt.plot([0,1],[1,1],"r")
plt.title("%s, LMM" % p_ID)
plt.xlabel("P-value")
plt.ylabel("Frequency")
fig.savefig(out_file)
plt.close(fig)
# Quantile-Quantile plots
logger.info('Plotting Q-Q plots')
qqplot_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'qqplot'))
for ip, p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(qqplot_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[7,3])
subpl = plt.subplot(1,2,1)
qqplot(pvalues_lm[p_ID].values)
plt.title("%s, LM" % p_ID)
subpl = plt.subplot(1,2,2)
qqplot(pvalues_lmm[p_ID].values)
plt.title("%s, LMM" % p_ID)
fig.savefig(out_file)
plt.close(fig)
# P value scatter plot
logger.info('Plotting LM vs LMM P-values')
pval_lmvslmm_dir = make_sure_path_exists(os.path.join(out_graphics_dir,'pval_lmvslmm'))
for ip,p_ID in enumerate(dataset.phenotype_ID[RNA_start:RNA_end]):
out_file = os.path.join(pval_lmvslmm_dir,'%s.png'%p_ID)
fig = plt.figure(figsize=[3,3])
plt.plot(-sp.log10(pvalues_lm[p_ID]),-sp.log10(pvalues_lmm[p_ID]),'.')
ymax = max(plt.xlim()[1],plt.ylim()[1])
plt.plot([0,ymax],[0,ymax],'k--')
plt.xlabel('LM')
plt.ylabel('LMM')
plt.title(p_ID)
fig.savefig(out_file)
plt.close(fig)
logger.info('Done with all plots!')
logger.info('Done!')
def main():
geno_hdf5, kinship_hdf5, RNA_csv, COV_file, RNA_start, RNA_end, out_file = sys.argv[
1:]
RNA_start, RNA_end = int(RNA_start), int(RNA_end)
logger = LoggerFactory.get_logger(out_file + '.log',
file_level=logging.DEBUG,
console_level=logging.DEBUG)
LoggerFactory.log_command(logger, sys.argv[1:])
step_list = [""]
## Import genotype data
logger.info('Start reading SNP from %s', geno_hdf5)
geno = genotype.load_hdf5_genotype_data(geno_hdf5)
SNP_accx = ['X' + acc for acc in geno.accessions]
logger.info('Finished reading SNP from %s', geno_hdf5)
## Import phenotype data
logger.info('Finished reading RNA from %s', RNA_csv)
RNA_df = pd.read_csv(RNA_csv, sep='\t', header=0,
index_col=0) # genes x accessions
RNA_accx = list(RNA_df.columns.values)
RNA_genes = list(RNA_df.index)
logger.info('Finished reading RNA from %s', RNA_csv)
## get common accessions in the same order for genotype, phenotype and phenotype covariates
logger.info('Consolidate accessions from genotype and RNA file')
accx_common = [accx for accx in SNP_accx if accx in RNA_accx]
RNA = RNA_df.as_matrix(columns=accx_common).T # accession x genes
match = lambda a, b: [b.index(x) if x in b else None for x in a]
geno.filter_accessions_ix(match(accx_common, SNP_accx))
logger.info(
'Number of accessions: genotype file %d, RNA file %d, common %d',
len(SNP_accx), len(RNA_accx), len(accx_common))
logger.info('Start building SNP matrix in memory')
snps = np.vstack(geno.get_snps_iterator(is_chunked=True))
snps = snps.T.astype(int)
logger.info('Finished')
logger.info('Start loading kinship matrix from %s', kinship_hdf5)
load_k = kinship.load_kinship_from_file(kinship_hdf5, scaled=False)
K0 = load_k['k'].astype(float)
K_accx = ['X' + acc for acc in load_k['accessions']]
K_accx_ix = np.ix_(match(accx_common, K_accx), match(accx_common, K_accx))
K = K0[K_accx_ix]
logger.info('Finished')
logger.info('Start loading covariance from %s', COV_file)
COV_df = pd.read_csv(COV_file, sep='\t', header=0,
index_col=0) # cov x accessions
COV = COV_df.ix[accx_common].as_matrix()
logger.info('Finished')
logger.info('Start association testing: RNA start %d, RNA end %d',
RNA_start, RNA_end)
run_lmm_chunk(snps, RNA, COV, RNA_start, RNA_end,
list(RNA_genes[RNA_start:RNA_end]), K, out_file)