diff --git a/jass_preprocessing/__main__.py b/jass_preprocessing/__main__.py
index 46943b83500480753a4898623f6e22447fe7fbe1..a4a9a56d832ba513bdcfe5741452fe73cc782614 100644
--- a/jass_preprocessing/__main__.py
+++ b/jass_preprocessing/__main__.py
@@ -13,7 +13,7 @@ import argparse
#| variable name | description | current default value|
#|---------------|-------------|----------------------|
#| netPath | Main project folder, must end by "/" | /mnt/atlas/ |
-#| GWAS_labels* | Path to the file describing the format of the individual GWASs files | netPath+'PCMA/1._DATA/RAW.GWAS/GWAS_labels.csv' |
+#| args.gwas_info* | Path to the file describing the format of the individual GWASs files | netPath+'PCMA/1._DATA/RAW.GWAS/args.gwas_info.csv' |
#| GWAS_path* | Path to the folder containing the GWASs summ stat files, must end by "/" | netPath+'PCMA/1._DATA/RAW.GWAS/'|
#| diagnostic_folder | folder for histograms of sample size distribution among SNPs | /mnt/atlas/PCMA/1._DATA/sample_size_distribution/ |
#| ldscore_format | data formated to use LDscore, 1 file per study | /mnt/atlas/PCMA/1._DATA/ldscore_data/ |
@@ -27,55 +27,56 @@ def launch_preprocessing(args):
"""
Preprocessing GWAS dataset
"""
- gwas_map = pd.read_csv(GWAS_labels, sep="\t", index_col=0)
+ gwas_map = pd.read_csv(args.gwas_info, sep="\t", index_col=0)
- tag = "{0}_{1}".format(gwas_map.loc[GWAS_filename, 'consortia'],
- gwas_map.loc[GWAS_filename, 'outcome'])
+ tag = "{0}_{1}".format(gwas_map.loc[args.gwas_filename, 'consortia'],
+ gwas_map.loc[args.gwas_filename, 'outcome'])
print('processing GWAS: {}'.format(tag))
start = time.time()
- gwas = jp.map_gwas.gwas_internal_link(GWAS_table, GWAS_path)
- GWAS_link = jp.map_gwas.walkfs(GWAS_path, GWAS_filename)[2]
- mapgw = jp.map_gwas.map_columns_position(GWAS_link, GWAS_labels)
+ gwas = jp.map_gwas.gwas_internal_link(GWAS_table, args.gwas_folder)
+ GWAS_link = jp.map_gwas.walkfs(args.gwas_folder, args.gwas_filename)[2]
+ mapgw = jp.map_gwas.map_columns_position(GWAS_link, args.gwas_info)
print(mapgw)
gw_df = jp.map_gwas.read_gwas(GWAS_link, mapgw)
- ref = pd.read_csv(REF_filename, header=None, sep= "\t",
+ ref = pd.read_csv(args.ref_path, header=None, sep= "\t",
names =['chr', "pos", "snp_id", "ref", "alt", "MAF"],
index_col="snp_id")
mgwas = jp.map_reference.map_on_ref_panel(gw_df, ref)
mgwas = jp.map_reference.compute_snp_alignement(mgwas)
mgwas = jp.compute_score.compute_z_score(mgwas)
- mgwas = jp.compute_score.compute_sample_size(mgwas, diagnostic_folder, tag)
+ mgwas = jp.compute_score.compute_sample_size(mgwas, args.diagnostic_folder, tag, args.percent_sample_size)
+
end = time.time()
print("Preprocessing of {0} in {1}s".format(tag, end-start))
+ jp.save_output.save_output_by_chromosome(mgwas, args.output_folder, tag)
- jp.save_output.save_output_by_chromosome(mgwas, ImpG_output_Folder, tag)
- jp.save_output.save_output(mgwas, ldscore_format, tag)
+ if(args.output_folder_1_file):
+ jp.save_output.save_output(mgwas, args.output_folder_1_file, tag)
def add_preprocessing_argument():
parser = argparse.ArgumentParser()
- parser.add_argument('--percent-sample-size', required=True, help= "the proportion of the 90th percentile of the sample size used to filter the SNPs")
-
parser.add_argument('--gwas-info', required=True, help= "Path to the file describing the format of the individual GWASs files")
- parser.add_argument('--ref-folder', required=True, help= "reference panel location (used to determine which snp to impute)")
- parser.add_argument('--gwas-folder', required=True, help= " Path to the folder containing the GWASs summ stat files, must end by '/'")
+ parser.add_argument('--gwas-filename', required=True, help= "Name of the raw GWAS file to standardize")
+ parser.add_argument('--ref-path', required=True, help= "reference panel location (used to determine which snp to impute)")
+ parser.add_argument('--gwas-folder', required=True, help= "Path to the folder containing the GWASs summ stat files, must end by '/'")
+ parser.add_argument('--diagnostic-folder', required=True, help= "Path to the reporting information on the PreProcessing such as the SNPs sample size distribution")
parser.add_argument('--output-folder', required=True, help= "Location of main ouput folder for preprocessed GWAS files (splitted by chromosome)")
parser.add_argument('--output-folder-1-file', required=False, help= "optional location to store the preprocessing in one tabular file with one chromosome columns")
-
+ parser.add_argument('--percent-sample-size', required=False, help= "the proportion (between 0 and 1) of the 90th percentile of the sample size used to filter the SNPs", default=0.7)
parser.set_defaults(func=launch_preprocessing)
return parser
def main():
-
parser = add_preprocessing_argument()
args = parser.parse_args()
args.func(args)
diff --git a/jass_preprocessing/compute_score.py b/jass_preprocessing/compute_score.py
index fd29ff24ac0d1c198a0e7812d8f75b1dddf11a4c..db0e3240631d31046c7fdaa057aa0666282a9f9d 100644
--- a/jass_preprocessing/compute_score.py
+++ b/jass_preprocessing/compute_score.py
@@ -6,7 +6,7 @@ import scipy.stats as ss
import seaborn as sns
import matplotlib.pyplot as plt
-perSS = 0.7
+
def compute_z_score(mgwas):
"""
@@ -27,7 +27,7 @@ def compute_z_score(mgwas):
return mgwas
-def compute_sample_size(mgwas, diagnostic_folder, trait):
+def compute_sample_size(mgwas, diagnostic_folder, trait, perSS = 0.7):
if 'n' in mgwas.columns:
myN = mgwas.n
diff --git a/setup.py b/setup.py
index aac8ae5c7bea9c9a9daf22e7b2bafb10adca3c77..b0413ec481929d2bc96b9d3d0c8c75f84868bf96 100644
--- a/setup.py
+++ b/setup.py
@@ -5,7 +5,7 @@ setup(name='jass_preprocessing',
description='Preprocess and standardize heterogeneous GWAS summary statistic for JASS',
url='http:https://gitlab.pasteur.fr/statistical-genetics/JASS_Pre-processing',
author='Hugues Aschard, Hanna Julienne, Vincent Laville',
- author_email='hugues.aschard@pasteur.fr',
+ author_email='hanna.julienne@pasteur.fr',
license='MIT',
#package_dir = {'': 'jass_preprocessing'},
packages= ['jass_preprocessing'],