Implement function to compute LD-matrices

impute_jass/impute_jass/ld_matrix.py

+"""
+    Function set to compute LD correlation from a reference panel
+    in predefined Region
+
+    LD matrix are then stored to the scipy sparse matrix format
+"""
+
+import scipy as sc
+import pandas as pd
+import subprocess as sub
+
+sub.check_output("pwd")
+
+LD_region = pd.read_csv('./impute_for_jass/Imputation_for_jass/impute_jass/data/Region_LD.csv')
+
+
+def launch_plink_ld(startpos, endpos, chr, reffile, folder):
+    """
+    launch plink ld
+    """
+
+    fo = "{0}/{1}_{2}_{3}".format(folder, chr, startpos, endpos)
+    cmd = "p-link --noweb --bfile {0} --r --ld-window-r2 0  --from-bp {1} --to-bp {2} --chr {3} --out {4}".format(reffile, startpos, endpos, chr, fo)
+    sub.check_output(cmd, shell=True)
+
+
+def generate_sparse_matrix(plink_ld, path_ld_mat):
+    """
+    read plink results create a sparse dataframe LD-matrix
+    then save it to a zipped pickle
+    """
+
+    plink_ld = pd.read_csv(plink_ld, sep = "\s+")
+    mat_ld = plink_ld.pivot(index='SNP_A', columns='SNP_B', values='R').to_sparse(fill_value=0)
+    mat_ld.to_pickle(path_ld_mat)
+
+def generate_genome_matrices(region_files, reffolder, folder_output):
+    """
+
+    """
+
+    regions = pd.read_csv(region_files)
+    for reg in region_files.iterrows():
+        print(reg[0])
+        # input reference panel file
+        fi_ref = "{0}/{1}.eur.1pct".format(reffolder, reg[1]['chr'])
+
+        # Compute the LD correlation with LD
+        launch_plink_ld(reg[1]['start'], reg[1]['stop'], reg[1]['chr'], fi_ref, folder_output)
+
+        fi_plink = "{0}/{1}_{2}_{3}.ld".format(folder_output, reg[1]['chr'], reg[1]['startpos'], reg[1]["endpos"])
+        fo_mat = "{0}/{1}_{2}_{3}.mat".format(folder_output, reg[1]['chr'], reg[1]['startpos'], reg[1]["endpos"])
+        #transform plink output to a compressed generate_sparse_matrix
+        generate_sparse_matrix(fi_plink, fo_mat)

impute_jass/setup.py

+from setuptools import setup, find_packages
+
+setup(name='jass_preprocessing',
+      version='0.1',
+      description='Preprocess GWAS summary statistic for JASS',
+      url='http:https://gitlab.pasteur.fr/statistical-genetics/JASS_Pre-processing',
+      author='Hanna Julienne',
+      author_email='hanna.julienne@pasteur.fr',
+      license='MIT',
+      #package_dir = {'': 'jass_preprocessing'},
+      packages= ['impute_jass'],
+      package_data = {'impute_jass':'data/*.csv'},
+      zip_safe=False)