def collect_data(regions, pcode='p1'):
'''Get the trees in JSON'''
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'first')
fn_data = foldername+'data/'
print fn_data
data = []
for region in regions:
fn = fn_data+'haplotype_tree_'+pcode+'_'+region+'.json'
data.append({'region': region,
'pcode': pcode,
'tree': tree_from_json(fn)})
return data
def collect_data(regions, pcode='p1'):
'''Get the trees in JSON'''
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'first')
fn_data = foldername + 'data/'
print fn_data
data = []
for region in regions:
fn = fn_data + 'haplotype_tree_' + pcode + '_' + region + '.json'
data.append({
'region': region,
'pcode': pcode,
'tree': tree_from_json(fn)
})
return data
for frac, total, num_std, denom_std in zip(fraction, rev_div.loc[:,'divergence'],reversion_std, total_div_std):
print frac, '+/-', np.sqrt(num_std**2/total**2 + denom_std**2*frac**2/total**2)
#print reversion_std,total_div_std
print "Consensus!=Founder:",np.mean(data[subtype]['consensus_distance'].values())
if __name__=="__main__":
import argparse
import matplotlib.pyplot as plt
import pandas as pd
parser = argparse.ArgumentParser(description="make figure")
parser.add_argument('--redo', action = 'store_true', help = 'recalculate data')
params=parser.parse_args()
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'first')
fn_data = foldername+'data/'
fn_data = fn_data + 'to_away.pickle'
if not os.path.isfile(fn_data) or params.redo:
#patients = ['p1', 'p6'] # other subtypes
patients = ['p1', 'p2', 'p3','p5', 'p6', 'p8', 'p9','p10', 'p11'] # all subtypes
regions = ['genomewide']
#regions = ['gag', 'pol', 'nef'] #, 'env']
#regions = ['p24', 'p17'] #, 'RT1', 'RT2', 'RT3', 'RT4', 'PR',
# 'IN1', 'IN2', 'IN3','p15', 'vif', 'nef','gp41','gp1201']
cov_min = 1000
Sbins = np.array([0,0.03, 0.08, 0.25, 2])
Sbinc = 0.5*(Sbins[1:]+Sbins[:-1])
data = {}
# Script
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser(description="make figure for SNP correlations")
parser.add_argument('--redo', action='store_true', help='recalculate data')
params = parser.parse_args()
VERBOSE = 2
pname = 'p11'
n_time = 4
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'controls')
fn_data = foldername+'data/'
fn_data = fn_data + 'allele_frequency_overlap.pickle'
if not os.path.isfile(fn_data) or params.redo:
patient = Patient.load(pname)
samples = patient.samples[n_time]
data = get_allele_frequency_overlap(sample, overlaps, cov_min=cov_min,
VERBOSE=VERBOSE, qual_min=qual_min)
estimate_templates_overlaps(sample, data)
store_data(data, fn_data)
else:
data = load_data(fn_data)
# Script
if __name__ == '__main__':
import argparse
parser = argparse.ArgumentParser(
description="make figure for SNP correlations")
parser.add_argument('--redo', action='store_true', help='recalculate data')
params = parser.parse_args()
VERBOSE = 2
pname = 'p11'
n_time = 4
username = os.path.split(os.getenv('HOME'))[-1]
foldername = get_figure_folder(username, 'controls')
fn_data = foldername + 'data/'
fn_data = fn_data + 'allele_frequency_overlap.pickle'
if not os.path.isfile(fn_data) or params.redo:
patient = Patient.load(pname)
samples = patient.samples[n_time]
data = get_allele_frequency_overlap(sample,
overlaps,
cov_min=cov_min,
VERBOSE=VERBOSE,
qual_min=qual_min)
estimate_templates_overlaps(sample, data)
store_data(data, fn_data)