# loops over genes
for gene in genes:
print '.. Analyzing gene %s' % gene
gene_group = fout.create_group(gene)
print ' .. Importing data'
try:
Xc, info = data.getGenotypes(gene, return_info=True)
except:
print 'Error: no SNPs found in cis'
continue
Y = data.getPhenotypes(gene, peer=opt.peer, gauss=True)
o = gene_group.create_group('snp_info')
smartDumpDictHdf5(info, o)
if opt.perm:
if opt.seed is not None:
sp.random.seed(opt.seed)
idxs = sp.random.permutation(Xc.shape[0])
Xc = Xc[idxs, :]
if 1:
print " .. single trait analysis"
lmm = QTL.test_lmm(Xc, Y, K=K)
pv = lmm.getPv()
RV = {}
RV['pv'] = pv
RV['qv'] = FDR.qvalues(pv)
RV['beta'] = lmm.getBetaSNP()
except:
print geneID, 'failed'
continue
#append the temp table into the big table
for key in temp.keys():
smartAppend(table, key, temp[key])
f.close()
for key in table.keys():
table[key] = sp.array(table[key])
print '.. correct for multiple testing'
table['pv_bonf'][table['pv_bonf'] > 1] = 1.
table['qv_all'] = FDR.qvalues(table['pv_bonf'])
print 'no eQTLs at FDR 0.10:', (table['qv_all'] < 0.10).sum()
print 'no genes:', table['qv_all'].shape[0]
fout = h5py.File(out_file, 'w')
smartDumpDictHdf5(table, fout)
fout.close()
else:
f = h5py.File(out_file, 'r')
R = {}
for key in f.keys():
R[key] = f[key][:]
f.close()
pdb.set_trace()
Mloc = sp.loadtxt(f_geneloc, dtype=object, delimiter='\t')
assert (Mloc[1:, 0] == M[1:, 0]).all(), 'gene id do not match'
# filtering genes of the following criteria:
# 1. on autosomal chromosome
# 2. expressed in at least half of the samples
# (where expressed means more than 5 counts)
chrom = Mloc[1:, 1]
Iaut = sp.array([(chrom[i] not in ['M', 'X', 'Y'])
for i in range(chrom.shape[0])])
expr = M[1:][:, 1:].astype(float).T
Iexpr = ((expr > cut1).mean(0) > cut2)
Igene = sp.logical_and(Iaut, Iexpr)
# export data
RV = {}
RV['matrix'] = expr[:, Igene]
RV['col_header'] = {}
RV['col_header']['gene_ID'] = M[1:, 0][Igene]
RV['col_header']['gene_chrom'] = chrom[Igene].astype(float)
RV['col_header']['gene_start'] = Mloc[1:, 2][Igene].astype(float)
RV['col_header']['gene_end'] = Mloc[1:, 3][Igene].astype(float)
RV['row_header'] = {}
RV['row_header']['sample_ID'] = M[0, 1:]
#pdb.set_trace()
fout = h5py.File(out_file, 'w')
smartDumpDictHdf5(RV, fout)
fout.close()
fout = h5py.File(out_file, 'w')
genoGroup = fout.create_group('genotypes')
RV = {}
n_chroms = 22
for chrom_i in range(1, n_chroms+1):
print '.. copying chromosome %d'%chrom_i
# load genotype
in_file = os.path.join(in_dir, 'chrom%d.h5' % chrom_i)
fin = h5py.File(in_file, 'r')
chromGroup = genoGroup.create_group('chrom%d' % chrom_i)
chromGroup.create_dataset('matrix',data=fin['genotypes']['matrix'][:].T)
chromGroup.create_dataset('RRM',data=fin['RRM'][:])
h5py.h5o.copy(fin['genotypes'].id, 'col_headers', chromGroup.id, 'col_headers')
h5py.h5o.copy(fin['genotypes'].id, 'row_headers', chromGroup.id, 'row_headers')
# summing up Kpop
if 'RRM' not in RV.keys():
RV['RRM'] = fin['RRM'][:]
else:
RV['RRM'] += fin['RRM'][:]
fin.close()
smartDumpDictHdf5(RV, genoGroup)
fout.close()