def het_check(self,
vcf_path,
plot=False,
ncpus=1,
min_depth=8,
sites=op.join(op.dirname(__file__), 'GRCH37.sites'),
**kwargs):
"""
kwargs is not used, but added here to allow same args as ped_check
"""
import cyvcf2
import numpy as np
if ncpus > 16:
ncpus = 16
sitesfile = sites
samps = [x.sample_id for x in self.samples()]
vcf = cyvcf2.VCF(vcf_path, gts012=True, samples=samps)
if sorted(vcf.samples) != sorted(samps):
log.warning(
"sample overlap issues\n\tin vcf, not in ped: %s\n\tin ped, not in vcf: %s"
% (",".join(set(vcf.samples) - set(samps)),
",".join(set(samps) - set(vcf.samples))))
if set(vcf.samples) - set(samps) == set(vcf.samples):
raise Exception("error: no samples from VCF found in ped")
samps = vcf.samples
sample_ranges, sites, gt_types = cyvcf2.par_het(vcf_path,
samps,
ncpus,
sites,
min_depth=min_depth)
call_rate = (gt_types != 3).mean(axis=1)
from .pca import pca
if plot:
pca_plot = plot.replace('het_', 'pca_').replace('het-', 'pca-')
if pca_plot == plot:
pca_plot, ext = pca_plot.rsplit(".", 1)
pca_plot = "%s.%s%s" % (pca_plot, "pca.", ext)
else:
pca_plot = False
pca_df, background_pca_df = pca(pca_plot, sitesfile, gt_types, sites)
# not find outliers.
depth = np.array([v['median_depth'] for v in sample_ranges.values()])
#ranges = np.array([d['range'] for d in sample_ranges.values()])
ratios = np.array([d['het_ratio'] for d in sample_ranges.values()])
bot = depth.mean() - 2 * depth.std()
# remove outliers and re-calc.
bot = depth[depth > bot].mean() - 5 * depth[depth > bot].std()
# care less if we have really high samples so make it 5.
top = depth.mean() + 8 * depth.std()
depth_outlier = ((depth < bot) | (depth > top))
for k, v in sample_ranges.items():
v['sample_id'] = k
for d, depth_o in zip(sample_ranges.values(), depth_outlier):
d['depth_outlier'] = depth_o
d['idr_baf'] = d.pop('range')
import pandas as pd
if sys.version_info[0] == 2:
df = pd.DataFrame(sample_ranges.values())
else:
df = pd.DataFrame(list(sample_ranges.values()))
cols = ['sample_id'] + sorted(
[x for x in df.columns if x != 'sample_id'])
df = df[cols]
df.index = df['sample_id']
l = {s: i for i, s in enumerate(samps)}
df['call_rate'] = [call_rate[l[s]] for s in df.index]
if pca_df is not None:
# merge the 2 dataframes.
pca_df.index = samps
df = pd.concat((df, pca_df), axis=1)
if not plot:
return df, background_pca_df
from matplotlib import pyplot as plt
import seaborn as sns
colors = sns.color_palette('Set1', 4)
cs = [
colors[1 - int(v['depth_outlier'])]
for v in sample_ranges.values()
]
ecs = ['none' for k in sample_ranges]
s = get_s(np.array([v['median_depth']
for v in sample_ranges.values()]))
plt.scatter(depth, ratios, c=cs, edgecolors=ecs, s=s)
for k, v in ((k, v) for k, v in sample_ranges.items()
if v['depth_outlier']):
plt.text(v['median_depth'],
v['het_ratio'],
k,
color=colors[1],
fontsize=7)
plt.xlabel('median depth')
plt.ylabel('proportion het calls')
plt.savefig(plot)
return df, background_pca_df
def het_check(self, vcf_path, plot=False, ncpus=1, min_depth=8,
sites=op.join(op.dirname(__file__), '1kg.sites'),
**kwargs):
"""
kwargs is not used, but added here to allow same args as ped_check
"""
import cyvcf2
import numpy as np
if ncpus > 16:
ncpus = 16
samps = [x.sample_id for x in self.samples()]
vcf = cyvcf2.VCF(vcf_path, gts012=True, samples=samps)
if sorted(vcf.samples) != sorted(samps):
print("warning: sample overlap issues\n\tin vcf, not in ped: %s\n\tin ped, not in vcf: %s" % (
",".join(set(vcf.samples) - set(samps)),
",".join(set(samps) - set(vcf.samples))), file=sys.stderr)
if set(vcf.samples) - set(samps) == set(vcf.samples):
raise Exception("error: no samples from VCF found in ped")
samps = vcf.samples
sample_ranges, sites, gt_types = cyvcf2.par_het(vcf_path, samps, ncpus,
sites, min_depth=min_depth)
call_rate = (gt_types != 3).mean(axis=1)
from .pca import pca
if plot:
pca_plot = plot.replace('het_', 'pca_').replace('het-', 'pca-')
if pca_plot == plot:
pca_plot, ext = pca_plot.rsplit(".", 1)
pca_plot = "%s.%s%s" % (pca_plot, "pca.", ext)
else:
pca_plot = False
pca_df, background_pca_df = pca(pca_plot, gt_types, sites)
# not find outliers.
depth = np.array([v['median_depth'] for v in sample_ranges.values()])
#ranges = np.array([d['range'] for d in sample_ranges.values()])
ratios = np.array([d['het_ratio'] for d in sample_ranges.values()])
ratios_outlier = ((ratios < 0.305) | (ratios > 0.41))
#ranges_outlier = ((ranges < 0.08) | (ranges > 0.31))
bot = depth.mean() - 2 * depth.std()
# remove outliers and re-calc.
bot = depth[depth > bot].mean() - 2 * depth[depth > bot].std()
# care less if we have really high samples so make it 5.
top = depth.mean() + 5 * depth.std()
depth_outlier = ((depth < bot) | (depth > top))
for k, v in sample_ranges.items():
v['sample_id'] = k
for d, depth_o, ratio_o in zip(sample_ranges.values(), depth_outlier,
ratios_outlier):
d['ratio_outlier'] = ratio_o
d['depth_outlier'] = depth_o
d['idr_baf'] = d.pop('range')
import pandas as pd
if sys.version_info[0] == 2:
df = pd.DataFrame(sample_ranges.values())
else:
df = pd.DataFrame(list(sample_ranges.values()))
cols = ['sample_id'] + sorted([x for x in df.columns if x != 'sample_id'])
df = df[cols]
df.index = df['sample_id']
l = {s: i for i, s in enumerate(samps)}
df['call_rate'] = [call_rate[l[s]] for s in df.index]
if pca_df is not None:
# merge the 2 dataframes.
pca_df.index = samps
df = pd.concat((df, pca_df), axis=1)
if not plot:
return df, background_pca_df
from matplotlib import pyplot as plt
import seaborn as sns
colors = sns.color_palette('Set1', 4)
cs = [colors[1 - int(v['depth_outlier'])] for v in sample_ranges.values()]
ecs = ['none' if not v['ratio_outlier'] else 'k' for v in sample_ranges.values()]
s = get_s(np.array([v['median_depth'] for v in sample_ranges.values()]))
plt.scatter(depth, ratios, c=cs, edgecolors=ecs, s=s)
for k, v in ((k, v) for k, v in sample_ranges.items()
if v['ratio_outlier'] or v['depth_outlier']):
plt.text(v['median_depth'], v['het_ratio'], k, color=colors[1], fontsize=7)
plt.xlabel('median depth')
plt.ylabel('proportion het calls')
plt.savefig(plot)
return df, background_pca_df