Skip to content
Snippets Groups Projects
Select Git revision
  • a40f95cfe66b3968877d368af66bf6148d502a52
  • master default protected
  • P_value_too_small
  • new_sample_size_filter
  • 2.3
  • 2.2
  • 2.1
  • 2.0.1
  • 1.0
9 results

main_preprocessing.py

Blame
    • main_preprocessing.py 1.98 KiB
    1
    2
    3
    4
    5
    6
    7
    8
    9
    10
    11
    12
    13
    14
    15
    16
    17
    18
    19
    20
    21
    22
    23
    24
    25
    26
    27
    28
    29
    30
    31
    32
    33
    34
    35
    36
    37
    38
    39
    40
    41
    42
    43
    44
    45
    46
    47
    48
    49
    50
    51
    52
    53
    54
    55
    56
    57
    58
    59
    60
    61
    62
    63
    64
    65
    66 
    

    

    

    """
Read raw GWAS summary statistics, filter and format
Write clean GWAS
"""
__updated__ = '2018-19-02'

import numpy as np
import scipy.stats as ss
import sys
import math
import os
import pandas as pd
import matplotlib.pyplot as plt
import jass_preprocessing as jp
import pandas as pd


perSS = 0.7
netPath = "/mnt/atlas/"  # '/home/genstat/ATLAS/'
#netPath       = '/pasteur/projets/policy01/'
GWAS_labels = netPath+'PCMA/1._DATA/RAW.GWAS/GWAS_LABELS_MAP.txt'
GWAS_path = netPath+'PCMA/1._DATA/RAW.GWAS/'
REF_filename = netPath+'PCMA/0._REF/1KGENOME/summary_genome_Filter_part2.out'
pathOUT = netPath+'PCMA/1._DATA/RAW.summary/'

outFileName = netPath+'PCMA/1._DATA/ZSCORE_merged_ALL_NO_strand_ambiguous.hdf5'
def_missing = ['', '#N/A', '#N/A', 'N/A', '#NA', '-1.#IND', '-1.#QNAN', '-NaN',
               '-nan', '1.#IND', '1.#QNAN', 'N/A', 'NA', 'NULL', 'NaN', 'nan', 'na', '.']
out_summary = "summary_GWAS.csv"
ImpG_output_Folder = netPath+ 'PCMA/1._DATA/ImpG_zfiles/'


GWAS_table = ['GIANT_HEIGHT_Wood_et_al_2014_publicrelease_HapMapCeuFreq.txt',
              'SNP_gwas_mc_merge_nogc.tbl.uniq',
              'GIANT_2015_HIP_COMBINED_EUR.txt',
              'GIANT_2015_WC_COMBINED_EUR.txt',
              'GIANT_2015_WHR_COMBINED_EUR.txt']


gwas = jp.map_gwas.gwas_internal_link(GWAS_table, GWAS_path)


column_dict = pd.read_csv(GWAS_labels, sep='\t', na_values='na')

column_dict.iloc[:2]
gwas.iloc[0,1].split('/')[-1]


column_dict['filename']
my_labels = column_dict[column_dict['filename'] == gwas.iloc[0,0]]
target_lab = my_labels.values.tolist()[0]
len(target_lab)

    # READ GWAS
GWAS_filename = GWAS_table[0]
GWAS_filename

GWAS_link = jp.map_gwas.walkfs(GWAS_path, GWAS_filename)[2]
GWAS_link
mapgw = jp.map_gwas.map_columns_position(GWAS_link, GWAS_labels)
gw_df = jp.map_gwas.read_gwas(GWAS_link, mapgw)
ref = pd.read_csv(REF_filename, header=None, sep= "\t", names =['chr', "pos", "snp_id", "ref", "alt", "MAF"], index_col="snp_id")

dir(jp.map_gwas)
mgwas = jp.map_gwas.map_on_ref_panel(gw_df, ref)