def getContigStats(vcf,window_size,outfile,subpops):
#load data
vcf=allel.read_vcf(vcf)
snps=allel.GenotypeArray(vcf['calldata/GT'])
positions=vcf['variants/POS']
sample_indices=dict()
for i in range(len(vcf['samples'])): sample_indices[vcf['samples'][i]]=i
#prep output file
outfile=open(str(outfile),'w')
outfile.write('chrom\tchromStart\tchromEnd\tnumSites\tfst\ttajD1\ttajD2\tthetaW1\tthetaW2\tdxy_bw\tpi\tdfd\n')
outfile.close()
#get window bounds
window_bounds=getSubWinBounds(window_size,max(positions))
window_bound_indices=getSnpIndicesInSubWins(window_bounds,positions)
nwindows=max(positions)//window_size - 1
#loop over windows and print summary stats to file
for i in range(nwindows):
if(len(window_bound_indices[i])<10): #if <n snps in the window
outfile=open(str(outfile),'a')
sumstats=[vcf['variants/CHROM'][0],str(window_bounds[i][0]),str(window_bounds[i][1]),str(0),
"NA","NA","NA","NA","NA","NA","NA","NA"]
sumstats='\t'.join(sumstats)+'\n'
outfile.write(sumstats)
outfile.close()
else:
window_snp_positions=positions[window_bound_indices[i]]
window_snps=snps.subset(window_bound_indices[i])
window_ac_all=window_snps.count_alleles()
window_ac_subpop=window_snps.count_alleles_subpops(subpops=subpops)
window_ac_per_ind=window_snps.to_allele_counts()
#summary stats
a,b,c=allel.stats.fst.weir_cockerham_fst(window_snps,[subpops['rufus'],subpops['sasin']])
fst=np.sum(a) / (np.sum(a) + np.sum(b) + np.sum(c))
tajD1=allel.stats.diversity.tajima_d(window_ac_subpop['rufus'])
tajD2=allel.stats.diversity.tajima_d(window_ac_subpop['sasin'])
thetaW1=allel.stats.diversity.watterson_theta(window_snp_positions,window_ac_subpop['rufus'])
thetaW2=allel.stats.diversity.watterson_theta(window_snp_positions,window_ac_subpop['sasin'])
dxy_bw=allel.stats.diversity.sequence_divergence(window_snp_positions,window_ac_subpop['rufus'],window_ac_subpop['sasin'])
pi=allel.stats.diversity.sequence_diversity(window_snp_positions,window_ac_all)
dfd=allel.stats.diversity.windowed_df(window_snp_positions,window_ac_subpop['rufus'],window_ac_subpop['sasin'],size=window_size)[0][0]
# pdxy=allel.stats.distance.pairwise_dxy(window_snp_positions,window_ac_per_ind)
# dmax=pdxy.max()
# dmin=pdxy.min()
# f2=allel.stats.admixture.patterson_f2(window_ac_subpop['rufus'],window_ac_subpop['sasin']) #need to drop non-biallelic sites for this
#write a vector of summary stats to file
outfile=open(str(outfile),'a')
sumstats=[vcf['variants/CHROM'][0],str(window_bounds[i][0]),str(window_bounds[i][1]),str(window_snps.shape[0]),
str(round(fst,6)),str(round(tajD1,6)),str(round(tajD2,6)),
str(round(thetaW1,6)),str(round(thetaW2,6)),str(round(dxy_bw,6)),
str(round(pi,6)),str(round(dfd,6))]
sumstats='\t'.join(sumstats)+'\n'
outfile.write(sumstats)
outfile.close()
def read_vcf_founderliab(path):
"""
Read whole vcf and return ONLY founder matrix
"""
geno_dosage = allel.GenotypeArray(allel.read_vcf(path, fields=['calldata/GT'])['calldata/GT']).to_n_alt().T
return geno_dosage
def read_vcf_allel(file_vcf):
'''
Use scikit allel to read vcf file. Organise variant information into summary pandas df.
'''
print(file_vcf)
vcf_ori= allel.read_vcf(file_vcf)
if not vcf_ori:
print('empty vcf.')
return {}, {}, {}
print(vcf_ori.keys())
### get genotype array
geno= vcf_ori['calldata/GT']
mult_alt= [x for x in range(geno.shape[0]) if vcf_ori['variants/ALT'][x][1]] #len(vcf_ori['variants/REF'][x]) > 1
indel= [x for x in range(geno.shape[0]) if len(vcf_ori['variants/REF'][x]) == 1 and len(vcf_ori['variants/ALT'][x][0]) == 1]
## eliminate +1 segregating mutations.
for mult in mult_alt:
gen_t= geno[mult]
gen_t[gen_t > 1] = 0
geno[mult]= gen_t
geno= allel.GenotypeArray(geno)
geno= geno.to_n_alt().T
## setup summary
column_names= ['CHROM','POS','ID','REF','ALT','QUAL','FILTER']
alts= [vcf_ori['variants/ALT'][x][0] for x in range(geno.shape[1])]
PASS= [['.','PASS'][int(vcf_ori['variants/FILTER_PASS'][x])] for x in range(geno.shape[1])]
summary= [
vcf_ori['variants/CHROM'],
vcf_ori['variants/POS'],
vcf_ori['variants/ID'],
vcf_ori['variants/REF'],
alts,
vcf_ori['variants/QUAL'],
PASS,
]
summary= np.array(summary).T
if len(indel):
print('mutliple ref loci: {}'.format(geno.shape[1] - len(indel)))
geno= geno[:,indel]
summary= summary[indel,:]
summary= pd.DataFrame(summary,columns= column_names)
return geno, summary, vcf_ori['samples']
def __get_variants_from_vcf(cls, vcf: str) -> Optional[Dict[str, Any]]:
# variants is None precisely when filtered vcf file has no variants
try:
variants = allel.read_vcf(vcf,
fields=cls.FIELD_NAMES,
transformers=allel.ANNTransformer())
except IOError:
raise FileNotFoundError("File " + vcf +
" not found or cannot be opened.")
return variants
def get_ann_from_output_snpeff(temp_out_name):
callset = allel.read_vcf(temp_out_name, fields='ANN', transformers=allel.ANNTransformer(), \
numbers={'ANN': num_ann_max})
df1 = pd.DataFrame(data=callset['variants/ANN_Allele'])
df2 = pd.DataFrame(data=callset['variants/ANN_Annotation'])
df3 = pd.concat((df1, df2), axis=1)
df3.columns = range(0, df3.shape[1])
return df3
def main(vcffile, pop1, pop2, binwidth, stepsize, outprefix):
"""
计算pop1和pop2之间的Fst
using the method of Hudson (1992) elaborated by Bhatia et al. (2013).
"""
pop1 = [x.strip() for x in open(pop1)]
pop2 = [x.strip() for x in open(pop2)]
callset = allel.read_vcf(vcffile)
allsamples = callset['samples']
genotypes = allel.GenotypeChunkedArray(callset['calldata/GT'])
variant_selection = np.full((genotypes.shape[0] + 1), True) # 选择vcf中的全部位点
sample_selection = [True if x in pop1 else False for x in allsamples]
ac1 = getAC(genotypes, variant_selection, sample_selection)
sample_selection = [True if x in pop2 else False for x in allsamples]
ac2 = getAC(genotypes, variant_selection, sample_selection)
num, den = allel.hudson_fst(ac1, ac2)
fst = num / den
meanFst = np.sum(num) / np.sum(den)
print('meanFst: %s' % meanFst)
chrom = callset['variants/CHROM']
pos = callset['variants/POS']
df = pd.DataFrame({'chrom': chrom, 'pos': pos, 'hudson_Fst': fst})
df.to_csv(f'{outprefix}_persite.tsv.gz',
sep='\t',
index=False,
na_rep='nan',
compression='gzip')
df['num'] = num
df['den'] = den
# sliding bins
bdf = []
for offset in range(0, binwidth, stepsize):
df['bin_index'] = ((df['pos'].values - 1) - offset) // binwidth
for group_name, gdf in df.groupby(by=['chrom', 'bin_index']):
chrom, bin_index = group_name
start = bin_index * binwidth + offset + 1
if start < 0: # 开头几个窗口长度不足的就直接跳过
continue
end = start + binwidth - 1
n_snp = gdf.shape[0]
sum_num = gdf['num'].sum()
sum_den = gdf['den'].sum()
if sum_den > 0:
meanFst = sum_num / sum_den
else:
meanFst = np.nan
bdf.append([chrom, start, end, n_snp, meanFst])
bdf = pd.DataFrame(bdf,
columns=['chrom', 'start', 'end', 'n_snp',
'meanFst']).sort_values(by=['chrom', 'start'])
bdf.to_csv(f'{outprefix}_meanFst.tsv.gz',
index=False,
compression='gzip',
sep='\t',
float_format='%.3f')
def import_data(callset_path):
'''Read in the VCF in the appropriate format.'''
callset = allel.read_vcf(callset_path,
fields=[
'samples', 'calldata/GT', 'variants/CHROM',
'variants/FILTER', 'variants/POS',
'variants/REF', 'variants/ALT'
])
return callset
def _load_calldata(self):
callset = allel.read_vcf(self.data, fields=["samples", "GT"])
self.samples_vcforder = callset["samples"]
gt = allel.GenotypeArray(callset['calldata/GT'])
## All this is for removing multi-allelic snps, and biallelic singletons
ac = gt.count_alleles()
flt = (ac.max_allele() == 1) & (ac[:, :2].min(axis=1) > 1)
self.genotypes = gt.compress(flt, axis=0)
def vcf2ped( args ):
""" create a ped and map file based on vcf and metafile, suitable for isoRelate """
# open group file
group_parser = grpparser.GroupParser( args )
# open VCF file
cerr('[I: reading VCF...]')
start_time = time.monotonic()
vcfset = allel.read_vcf(args.infile,
fields = ['samples', 'variants/CHROM', 'variants/POS', 'calldata/GT'])
cerr('[I: read %s site, %s samples in %d secs]' % (len(vcfset['variants/CHROM']),
len(vcfset['samples']), time.monotonic() - start_time))
# assign groups
samples = vcfset['samples']
group_parser.assign_groups(samples)
groups = group_parser.group_keys
#import IPython; IPython.embed()
# write to PED
with open(args.outprefix + '.ped', 'w') as outf:
for i in range(len(samples)):
outf.write('%s\t%s\t0\t0\t1\t0\t' % (groups[i], samples[i]))
alleles = []
for gt in vcfset['calldata/GT'][:,i]:
allele_1, allele_2 = gt
#print(allele_1, allele_2)
if allele_1 == allele_2:
if allele_1 == -1:
alleles += [0, 0]
elif allele_1 == 0:
alleles += [1, 1]
elif allele_1 == 1:
alleles += [2, 2]
else:
alleles += [1, 1]
else:
alleles += [1, 2]
outf.write('\t'.join( str(i) for i in alleles))
outf.write('\n')
#import IPython; IPython.embed()
# write to MAP
with open(args.outprefix + '.map', 'w') as outf:
last_pos = 0
curr_chr = None
for (chrom, pos) in zip( vcfset['variants/CHROM'], vcfset['variants/POS'] ):
if curr_chr != chrom:
curr_chr = chrom
last_pos = 0
dist = (pos - last_pos) * 1e-6
last_pos = pos
outf.write('%s\t%s:%d\t%8.6f\t%d\n' % (chrom, chrom, pos, dist, pos))
def sample_genotype_array(self, sample, part):
"""Get a genotype array for the specified individual"""
file = self._sample_genotype_path(sample, part)
if not self._check_local(file):
cmd = f'bcftools view -s {sample} -v snps -m2 -M2 -Oz -o {file} {self._chr_path} {self._query(part)}'
subprocess.call(cmd, shell=True, stdout=subprocess.PIPE)
gt = allel.read_vcf(file, fields=['GT', 'POS'])
return pd.Series(allel.GenotypeArray(gt['calldata/GT'])[:, 0],
index=gt['variants/POS'])
def vcf2npy(vcffile, samples):
callset = allel.read_vcf(vcffile, samples=samples)
haplotypes_1 = callset['calldata/GT'][:, :, 0]
haplotypes_2 = callset['calldata/GT'][:, :, 1]
m, n = haplotypes_1.shape
mat_haplo = np.empty((2 * n, m))
mat_haplo[::2] = haplotypes_1.T
mat_haplo[1::2] = haplotypes_2.T
return mat_haplo.astype(np.uint8)
def load_vcf_wrapper(path, seqid, samples):
callset = allel.read_vcf(path,
region=seqid,
fields=['variants/POS', 'calldata/GT', 'samples'],
tabix="tabix",
samples=samples)
p = allel.SortedIndex(callset["variants/POS"])
g = allel.GenotypeArray(callset['calldata/GT'])
return p, g
def main() -> None:
file_path1 = sys.argv[1]
file_path2 = sys.argv[2]
if len(sys.argv) == 5:
population1 = sys.argv[3]
population2 = sys.argv[4]
callset1 = allel.read_vcf(file_path1, fields=VCF_FIELDS)
callset2 = allel.read_vcf(file_path2, fields=VCF_FIELDS)
genotypes1, positions1, _, _ = biallelic_variant_filter(callset1)
genotypes2, positions2, _, _ = biallelic_variant_filter(callset2)
shared_position_indices1, shared_position_indices2 = joint_position_indices(positions1, positions2)
positions1 = positions1[shared_position_indices1]
positions2 = positions2[shared_position_indices2]
genotypes1 = genotypes1[shared_position_indices1]
genotypes2 = genotypes2[shared_position_indices2]
genotypes1[genotypes1 < 0] = 0
genotypes2[genotypes2 < 0] = 0
#
# allele_counts1 = genotypes1.reshape(genotypes1.shape[0], -1).sum(1)
# allele_counts2 = genotypes2.reshape(genotypes2.shape[0], -1).sum(1)
# sfs1 = allel.sfs(allele_counts1, np.product(genotypes1.shape[1:]))
# sfs2 = allel.sfs(allele_counts2, np.product(genotypes2.shape[1:]))
# plt.title('real vs synthetic PGP site frequency spectrum')
# ax = plt.gca()
# ax = allel.plot_sfs(sfs1, ax=ax, label=population1, plot_kwargs=dict([('c','b')]))
# ax = allel.plot_sfs(sfs2, ax=ax, label=population2, plot_kwargs=dict([('c','g')]))
# ax.legend()
# plt.savefig(os.path.join(FIGURES_DIR, 'synthetic_PGP.PGP.sfs.png'))
# plt.clf()
#
# sfs1 = site_frequency_spectrum(genotypes1, population1)
# sfs2 = site_frequency_spectrum(genotypes2, population2)
joint_site_frequency_spectrum(genotypes1, genotypes2, population1, population2)
def mutect2(inputs, normal_name) -> dict:
# chrom: pos: normal_genotype
chrom_pos_gt = dict()
cnt = 0
cnt_het_hom = 0
for ifile in inputs:
# ["variants/CHROM", "variants/POS", "variants/REF", "variants/ALT", "calldata/GT"]
in_vcf = allel.read_vcf(ifile, fields='*')
idx_normal = np.argwhere(in_vcf["samples"] == normal_name)[0][0]
zipped = zip(
in_vcf["variants/CHROM"][in_vcf["variants/is_snp"]],
in_vcf["variants/POS"][in_vcf["variants/is_snp"]],
in_vcf["variants/REF"][in_vcf["variants/is_snp"]],
in_vcf["variants/ALT"][in_vcf["variants/is_snp"]],
in_vcf["calldata/GT"][in_vcf["variants/is_snp"]],
in_vcf["variants/FILTER_PASS"][in_vcf["variants/is_snp"]],
in_vcf["variants/FILTER_artifact_in_normal"][
in_vcf["variants/is_snp"]])
for chrom, pos, ref, alt, gt, is_pass, is_artifact in zipped:
if is_artifact:
continue
chrom = str(chrom)
pos = int(pos)
num_pass = int(is_pass)
alt = alt[0]
ref_alt = ref + alt
normal = ref_alt[gt[idx_normal][0]] + ref_alt[gt[idx_normal][1]]
if gt[idx_normal][0] != 0 or gt[idx_normal][1] != 0:
cnt_het_hom += 1
if chrom in chrom_pos_gt:
if pos in chrom_pos_gt[chrom]:
chrom_pos_gt[chrom][pos]["num_pass"] += num_pass
if chrom_pos_gt[chrom][pos]["gt"][0] == chrom_pos_gt[
chrom][pos]["gt"][1] and normal[0] != normal[1]:
cnt += 1
chrom_pos_gt[chrom][pos]["gt"] = normal
else:
chrom_pos_gt[chrom][pos] = {
"gt": normal,
"num_pass": num_pass
}
else:
chrom_pos_gt[chrom] = {
pos: {
"gt": normal,
"num_pass": num_pass
}
}
print(f"Disagreement on normal: {cnt} times.")
print(f"Not ref: {cnt_het_hom} times.")
return chrom_pos_gt
def fit_em_smm(
variants_vcf: str,
n_iterations: int,
K: int,
seed: int,
logsum_approx: bool,
) -> Tuple[np.ndarray, np.ndarray, np.ndarray]:
variants = (
allel.vcf_to_dataframe(variants_vcf, fields=[
'POS', 'REF', 'ALT'
]).drop(['ALT_2', 'ALT_3'], axis=1) # ALT_2, ALT_3 are always empty
)
genotypes = allel.read_vcf(variants_vcf, fields=['calldata/GT'])
genotypes = genotypes['calldata/GT']
# scikit-allel reads missing values as -1
genotypes = np.where(genotypes == -1, 0, genotypes)
haplo_1 = genotypes[:, :, 0]
haplo_2 = genotypes[:, :, 1]
haplos = np.hstack((haplo_1, haplo_2)).T
n_variants_pos = (
variants # find number of variants by position
.groupby('POS'
) # add 1 to account for fact that we always have a reference
.count()['REF'].values) + 1
max_n_variants = np.sort(n_variants_pos)[-1]
n_loci = len(variants['POS'].unique())
n_samples = haplos.shape[0]
haplos = _encode_haplotypes(variants['POS'].values, haplos, n_samples,
n_loci)
# em initialization
rng = np.random.default_rng(seed)
group_e_ini = rng.random(size=(n_samples, K))
group_e = group_e_ini / np.sum(group_e_ini, axis=1, keepdims=1)
group_probs = np.full(6, 1 / K) # make this a probability vector
variant_ini = rng.random(size=(K, n_loci, max_n_variants))
variant_probs = variant_ini / np.sum(variant_ini, axis=2, keepdims=1)
# TODO: add step filtering this to correct number of variants
return _em_loop(
n_iterations,
K,
n_samples,
n_loci,
n_variants_pos,
group_e,
group_probs,
variant_probs,
haplos,
logsum_approx,
)
def load_genotypes():
if args.zarr is not None:
print("reading zarr")
callset = zarr.open_group(args.zarr, mode='r')
gt = callset['calldata/GT']
genotypes = allel.GenotypeArray(gt[:])
samples = callset['samples'][:]
elif args.vcf is not None:
print("reading VCF")
vcf = allel.read_vcf(args.vcf, log=sys.stderr)
genotypes = allel.GenotypeArray(vcf['calldata/GT'])
samples = vcf['samples']
return genotypes, samples
def generate_vcf_classes(vcfs):
print("Parsing VCFs")
parsed_vcf_bodies = list(map(lambda x: allel.read_vcf(x, fields="*"),
vcfs))
parsed_vcf_bodies = list(filter(None, parsed_vcf_bodies))
deque(
map(
lambda x: x.update(samples=numpy.char.upper(x['samples'].tolist())
), parsed_vcf_bodies))
deque(map(lambda x, y: x.update(FILE=y), parsed_vcf_bodies, vcfs))
add_headers = lambda x, y: x.update(header=allel.read_vcf_headers(y))
deque(map(add_headers, parsed_vcf_bodies, vcfs))
return parsed_vcf_bodies
def vcf2npy(
vcfpath
): #converts a .vcf file to a numpy matrix w/ values 0, 1, and 2; https://github.com/bcm-uga/Loter/blob/master/python-package/Local_Ancestry_Example.ipynb
callset = allel.read_vcf(vcfpath)
haplotypes_1 = callset['calldata/GT'][:, :, 0]
haplotypes_2 = callset['calldata/GT'][:, :, 1]
m, n = haplotypes_1.shape
mat_haplo = np.empty((2 * n, m))
mat_haplo[::2] = haplotypes_1.T
mat_haplo[1::2] = haplotypes_2.T
return mat_haplo.astype(np.uint8)
def vcf2npy(vcffile, samples):
callset = allel.read_vcf(vcffile, samples=samples,
fields=['samples', 'variants/CHROM', 'variants/POS', 'calldata/GT'])
haplotypes_1 = callset['calldata/GT'][:,:,0]
haplotypes_2 = callset['calldata/GT'][:,:,1]
m, n = haplotypes_1.shape
mat_haplo = np.empty((2*n, m))
mat_haplo[::2] = haplotypes_1.T
mat_haplo[1::2] = haplotypes_2.T
keep_samples = callset['samples']
return mat_haplo.astype(np.uint8), keep_samples, callset['variants/CHROM'], callset['variants/POS']
def test_few_chrom_small_region_num(self):
self.data_holder.filename = VCF_DATA_FEW_CHR
self.region_len = 500000
chromosomes = create_bed_files_and_extract_chromosomes(
data_holder=self.data_holder,
output_dir=self.output_dir,
region_len=self.region_len,
)
vcf_data = allel.read_vcf(self.data_holder.filename)
self.assertEqual(len(set(vcf_data['variants/CHROM'])),
len(chromosomes))
regions_num = len(listdir(self.output_dir))
self.assertEqual(regions_num, 16)
def loadvcf(vcfFile):
"""Reads VCF using scikit-allel, object is stored as pandas DF
"""
print("loading vcf file...")
print("using scitkit allele version:", allel.__version__)
h5 = "{}h5".format(vcfFile.strip("vcf"))
if os.path.isfile(h5):
callset = h5py.File(h5, 'r')
else:
callset = allel.read_vcf(vcfFile)
print("creating h5 for faster loading")
allel.vcf_to_hdf5(vcfFile, h5)
return(callset)
def loadvcf(vcfFile):
"""Reads VCF using scikit-allel, object is stored as pandas DF
"""
print("loading vcf file...")
print("using scitkit allele version:", allel.__version__)
h5 = "{}h5".format(vcfFile.strip("vcf"))
if os.path.isfile(h5):
callset = h5py.File(h5, 'r')
else:
callset = allel.read_vcf(vcfFile)
print("creating h5 for faster loading")
allel.vcf_to_hdf5(vcfFile, h5)
return (callset)
def simulate(reference_file_bcf, sample_file, idx_to_pop_map, genetic_map_file,
generations, num_out, sim_output_path, chm, use_phase_shift):
# path to RFMix/simulate binary
rfmix_sim_path = "./Admixture/simulate"
# NOTE: If running from a different directory than XGMIX/, this needs to
# be updated.
# assume everyone in the sample map is founder
print("Creating founders.bcf.gz for {}".format(sample_file))
write_founders_bcf(reference_file_bcf, sample_file, sim_output_path)
for gen in generations:
print("-"*80)
print("Simulation for generation {} from {}".format(gen,sample_file))
# generation simulation output path
gen_path = join_paths(sim_output_path, "gen_"+str(gen))
out_basename = gen_path+'/admix'
# Simulating the individuals via rfmix simulation
print("simulating ...")
rfmix_sim_cmd = rfmix_sim_path + " -f %s/founders.bcf.gz -m %s/founders.map -g %s -o %s --growth-rate=1.5 --maximum-size=2000 --n-output=%d -c %s -G %d -p %f --random-seed=%d %s"
rfmix_sim = rfmix_sim_cmd % (sim_output_path, sim_output_path, genetic_map_file, out_basename, num_out, chm, gen, 0.0, 123, "--dephase" if use_phase_shift else "")
try:
run_shell_cmd(rfmix_sim, verb=True)
except:
print("something went wrong using rfmix/simulate ...", end=" ")
print("trying -c chr"+chm+" insted of -c "+chm+" ...")
rfmix_sim = rfmix_sim_cmd % (sim_output_path, sim_output_path, genetic_map_file, out_basename, num_out, "chr"+chm, gen, 0.0, 123, "--dephase" if use_phase_shift else "")
run_shell_cmd(rfmix_sim, verb=True)
# reading .vcf output of simulation and converting to npy matricies
print('reading .vcf output of simulation and converting to npy matricies ...')
vcf_data = allel.read_vcf(out_basename+".query.vcf")
chm_len, nout, _ = vcf_data["calldata/GT"].shape
mat_vcf_2d = vcf_data["calldata/GT"].reshape(chm_len,nout*2).T
np.save(gen_path+"/mat_vcf_2d.npy", mat_vcf_2d)
# reading .map output of simulation and converting to npy matricies
print('reading .map output of simulation and converting to npy matricies ...')
map_path = out_basename + ".result"
matrix = sample_map_to_matrix(map_path)
# Finally map them to original labels (which can be further mapped to coordinates) and saving
matrix = np.vectorize(idx_to_pop_map.get)(matrix)
np.save(gen_path+"/mat_map.npy",matrix)
print("-"*80)
print("Finishing up ...")
def import_data(callset_path):
'''Read in the VCF in the appropriate format.'''
numbers = get_numbers_dict(args.ploidy)
callset = allel.read_vcf(callset_path,
numbers=numbers,
fields=['samples', 'calldata/GT',
'variants/CHROM', 'variants/FILTER',
'variants/POS', 'variants/REF',
'variants/ALT'])
return callset
def load_data(self, genome_file, panel_file, population_file):
'''
Load files and create the population codes and description files
'''
self.genome_file = allel.read_vcf(genome_file)
self.panel_file = pd.read_csv(panel_file, sep='\t')
self.population_file = pd.read_csv(population_file, sep="\t")
#Basic Processing
self.panel_file['pop'] = self.panel_file['pop'].str.strip()
self.panel_pop = self.panel_file['pop'].values
self.df_code = self.population_file["Population Code"].dropna().values
self.df_desc = self.population_file["Population Description"].dropna(
).values[:-1]
def readVcf(inFile, logDebug):
log.info("reading the VCF file")
## We read only one sample from the VCF file
if logDebug:
vcf = allel.read_vcf(inFile, samples=[0], fields='*')
else:
import StringIO
import sys
sys.stderr = StringIO.StringIO()
vcf = allel.read_vcf(inFile, samples=[0], fields='*')
#vcf = vcfnp.variants(inFile, cache=False).view(np.recarray)
#vcfD = vcfnp.calldata_2d(inFile, cache=False).view(np.recarray)
sys.stderr = sys.__stderr__
(snpCHR, snpsREQ) = parseChrName(vcf['variants/CHROM'])
try:
snpGT = allel.GenotypeArray(vcf['calldata/GT']).to_gt()[snpsREQ, 0]
except AttributeError:
snpmatch.die("input VCF file doesnt have required GT field")
snpsREQ = snpsREQ[np.where(snpGT != './.')[0]]
snpGT = allel.GenotypeArray(vcf['calldata/GT']).to_gt()[snpsREQ, 0]
if 'calldata/PL' in sorted(vcf.keys()):
snpWEI = np.copy(vcf['calldata/PL'][snpsREQ, 0]).astype('float')
snpWEI = snpWEI / (-10)
snpWEI = np.exp(snpWEI)
else:
snpBinary = parseGT(snpGT)
snpWEI = np.ones((len(snpsREQ), 3)) ## for h**o and het
snpWEI[np.where(snpBinary != 0), 0] = 0
snpWEI[np.where(snpBinary != 1), 2] = 0
snpWEI[np.where(snpBinary != 2), 1] = 0
snpCHR = snpCHR[snpsREQ]
if 'calldata/DP' in sorted(vcf.keys()):
DPmean = np.mean(vcf['calldata/DP'][snpsREQ, 0])
else:
DPmean = "NA"
snpPOS = np.array(vcf['variants/POS'][snpsREQ])
return (DPmean, snpCHR, snpPOS, snpGT, snpWEI)
def read_haplotype_matrix_from_vcf(filepath):
""""
Read the vcf file into a haplotype matrix (numpy)
assume everything is phased,
"""
callset = allel.read_vcf(filepath)
gt = callset['calldata/GT']
hap0 = gt[:, :, 0].T
hap1 = gt[:, :, 1].T
haps = np.empty((hap0.shape[0]*2, hap0.shape[1]), dtype=hap0.dtype)
haps[0::2] = hap0
haps[1::2] = hap1
return haps
def process_vcf(vcf_file):
vcf = allel.read_vcf(vcf_file)
gt = vcf['calldata/GT']
n_variants, n_samples, ploidy = gt.shape
gt_matrix = gt.reshape(n_variants, n_samples * ploidy).astype(np.float32)
np.place(gt_matrix, gt_matrix < 0, np.nan)
IDs = vcf['variants/ID']
rs_IDs = [int(x[2:]) for x in IDs]
samples = vcf['samples']
ind_IDs = []
for sample in samples:
ind_IDs.append(sample + '_A')
ind_IDs.append(sample + '_B')
ind_IDs = np.array(ind_IDs)
positions = vcf['variants/POS'].tolist()
return gt_matrix, rs_IDs, ind_IDs, positions
def load_vcf_wrapper(path, seqid, samples, samples_path):
callset = allel.read_vcf(
path,
region=seqid,
fields=['variants/POS', 'calldata/GT', 'samples'],
tabix="tabix",
samples=samples)
assert "samples" in callset.keys(), "None of the samples provided in {0!r} are found in {1!r}".format(
samples_path, path)
p = allel.SortedIndex(callset["variants/POS"])
g = allel.GenotypeArray(callset['calldata/GT'])
return p, g
def load_vcf_wrapper(path, seqid, samples, samples_path):
callset = allel.read_vcf(path,
region=seqid,
fields=['variants/POS', 'calldata/GT', 'samples'],
tabix="tabix",
samples=samples)
assert "samples" in callset.keys(
), "None of the samples provided in {0!r} are found in {1!r}".format(
samples_path, path)
p = allel.SortedIndex(callset["variants/POS"])
g = allel.GenotypeArray(callset['calldata/GT'])
return p, g
def main(vcffile: str = typer.Argument(..., help="总vcf文件"),
groupfile: str = typer.Argument(..., help='样本分群信息，两列，一列vcf中的样本ID，一列对应的群体ID。不需要包含vcf中的全部个体。'),
outfile: str = typer.Argument(..., help='输出文件名(.ac.tsv.gz)'),
region: str = typer.Option(None, help='只使用指定区域chrom:start-end或者chrom')):
"""把vcf文件转换为treemix的输入格式，可以只转指定区域指定样本"""
group2samples = load_group(groupfile)
df = {}
for group, samples in group2samples.items():
callset = allel.read_vcf(vcffile, fields=['calldata/GT', 'samples'], numbers={'ALT': 1}, region=region)
samples_missed = set(samples) - set(callset['samples'])
if samples_missed:
print(f'{len(samples_missed)} / {len(samples)} samples missed in {group}:')
print(','.join(samples_missed))
df[group] = pd.DataFrame(allel.GenotypeArray(callset['calldata/GT']).count_alleles()).apply(lambda x: ','.join([str(x[0]), str(x[1])]), axis=1).values
df = pd.DataFrame(df)
df.to_csv(outfile, sep=' ', index=False, compression='gzip')
def load_vcf2array(vcffile, region: None, chrom2sites: None, samples,
outsamples: None):
callset = allel.read_vcf(vcffile,
region=region,
samples=samples,
fields=['samples', 'calldata/GT', 'variants/POS'])
gt_array = callset['calldata/GT'] # 三维array
samples_all = callset['samples']
pos_array = callset['variants/POS']
chrom = region.split(':')[0]
# 只保留sitefile中的位点
if chrom2sites:
selection_requiredsites = [
True if x in chrom2sites[chrom] else False for x in pos_array
]
gt_array = gt_array[selection_requiredsites, :, :]
pos_array = pos_array[selection_requiredsites]
print(
f'{np.sum(selection_requiredsites)} remained according to the sitefile.'
)
# 只保留双等位，因为对于多等位杂合后续没法区分，如0/2和 1/1加了之后都会转化为2
selection_biallelic = np.max(np.max(gt_array, axis=2), axis=1) < 2
gt_array = gt_array[selection_biallelic, :, :]
pos_array = pos_array[selection_biallelic]
n_sites, n_samples, n_hap = gt_array.shape
print(f'{n_sites} biallelic sites were remained.')
# 把outsamples中最高频率的allele设置为alt
if outsamples:
selection_outsamples = select_samples(samples_all, outsamples)
print(f'{np.sum(selection_outsamples)} outgroup samples in vcf file.')
gt_array_out = gt_array[:, selection_outsamples, :].reshape(
n_sites,
np.sum(selection_outsamples) * n_hap)
selection_swtich = np.sum(gt_array_out == 0, axis=1) > np.sum(
gt_array_out > 0, axis=1) # ref(0)的数量比非ref(!=0)但不是miss(-1)的数量多
print(f'Swtich REF and ALT in {np.sum(selection_swtich)} sites.')
assert gt_array.min() >= -1
assert gt_array.max() <= 1
gt_swtich = gt_array[selection_swtich, :, :]
gt_swtich[gt_swtich == 1] = 9
gt_swtich[gt_swtich == 0] = 1
gt_swtich[gt_swtich == 9] = 0
gt_array[selection_swtich, :, :] = gt_swtich
return gt_array, callset['samples'], pos_array
# import scikit-allel import allel import sys # Sys arguments in_vcf = sys.argv[1] out_file = sys.argv[2] callset = allel.read_vcf(in_vcf) # available keys in vcf file sorted(callset.keys()) # to get reference from vcf file callset['variants/REF'] # to get genotype/allel form vcf file callset['calldata/GT'] # to get genotype infomations in array form gt = allel.GenotypeArray(callset['calldata/GT']) # write the output to a file with open(out_file, 'w') as fh_out: fh_out.write(str(gt))
