adiamb

# ------------------
# from bgen to bed
# ------------------
plink2 --bgen myfile.bgen \
  # filter by chr or by snps names
  --chr 1 --extract {params.snps} \ 
  --make-bed --out myoutput
# 1. plink will create temporary/intermediate files such as *-temporary.{pgen,psam,pvar}
# 2. sample ids in .fam will be `ID1_ID1`

adiamb

import pandas as pd
import numpy as np
import keras 
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import OneHotEncoder
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix

adiamb

import re
import math
import sys
## Part 1
FileIn = 'D1_INPUT.txt'
CurFreq =0
with open(FileIn) as FreqIn:
	for line in FreqIn:
		FreqAdju = int(line.strip())
		CurFreq += FreqAdju

adiamb

import re
import subprocess
from subprocess import PIPE
import sys
import time
import numpy as np
import numpy


impute_file = sys.argv[1]

adiamb

from __future__ import print_function
import re
import subprocess
import sys

file_in = sys.argv[1]
#file_out = sys.argv[2]

### define functions
def num_ret(str=str):

adiamb

import sys
import time
import subprocess
from subprocess import PIPE
import re
from itertools import chain
import pandas as pd
import numpy as np
import copy
## import filenames as a list

adiamb

import re
import subprocess
from subprocess import PIPE
import pandas as pd
import numpy as np
import scipy.stats as stats
import glob
import scipy
############################ read in the DBID and TCR identifiers from ling's csv file

adiamb

import re
import subprocess
from subprocess import PIPE
import pandas as pd
import numpy as np
import scipy.stats as stats
import glob
import scipy

adiamb

import pandas as pd
import numpy as np


total_TCR = pd.read_excel('total done list 7-18-17.xlsx', sheetname='total file')
TCR_5merBC = pd.read_excel('early deep SEQ with 5 barcode.xlsx', sheetname='total file')

TCR_5mer_sub=TCR_5merBC.loc[:, ('DbID','cell type', 'Dx', '# to SEQ1', 'alpha', '# to SEQ2', 'beta')]
TCR_5mer_sub.groupby(['cell type', 'Dx']).size()

adiamb

import sys
clone_sum=0
validclones=0
outfile = open('HS115_clustered_low_rem.rcl', 'w')
with open('HS115_CLUSTERED.rcl') as rclfile:
	for rcl in rclfile:
		if rcl:
			parsedrcl= rcl.strip('\r\n').split(',')
			if int(parsedrcl[7]) > 2 :