pgx-main from prod added

pgx-main/tests/simulations/gen_dips.nf

@@ -0,0 +1,36 @@
+#!/usr/bin/env nextflow
+
+//haps1 = Channel.fromFilePairs(params.in_pgvcf, type: 'file') { file -> file.name.replaceAll(/.vcf.gz|.tbi$/,'') }
+
+haps1 = Channel.fromPath(params.in_hap1, type: 'file')
+haps2 = Channel.fromPath(params.in_hap2, type: 'file') 
+
+//haps2 = Channel.fromFilePairs(params.in_haplo, type: 'file') { file -> file.name.replaceAll(/.vcf.gz|.tbi$/,'') }
+
+haps1
+    .combine(haps2)
+    .set {data}
+//    .println()
+
+
+process make_diplo {
+//   maxForks 10
+//   errorStrategy 'ignore'
+//   tag "${name}" 
+//   label 'big_mem'
+   publishDir params.out_dir, mode: 'copy', overwrite: 'true'
+
+   input:
+      file(vcfs) from data   
+
+   output:	        
+      file("*_diplo.vcf.gz") into diplotypes_ch
+     
+   script:
+    """ 
+    tabix ${vcfs.get(0)}
+    tabix ${vcfs.get(1)}
+    bcftools merge ${vcfs.get(0)} ${vcfs.get(1)} | bgzip -c > ${vcfs.get(0).name.replace(/.vcf.gz/, "")}_${vcfs.get(1).name.replace(/.vcf.gz/, "")}_diplo.vcf.gz
+    """
+
+}

pgx-main/tests/simulations/nextflow.config

@@ -0,0 +1,32 @@
+params {
+  in_hap1 = "/path/to/haplotype_files/*.vcf.gz"
+  in_hap2 = "/path/to/haplotype_files/*.p.vcf.gz"
+  out_dir = "/path/to/output_directory"
+}
+
+
+
+process {
+    withLabel: big_mem {
+        cpus = 8
+        memory = 32.GB
+    }
+}
+
+
+
+
+profiles {
+
+    // For execution on a local machine, no containerization. -- Default
+    standard {
+        process.executor = 'local'
+    }
+
+
+    // For execution on a SLURM scheduler, no containerization.
+    slurm {
+        process.executor = 'slurm'
+        process.queue = 'batch'
+    }
+}

pgx-main/tests/simulations/sim_zygosity.py

@@ -0,0 +1,32 @@
+#!/usr/bin/env python
+
+
+# Script: sim_zygosity.py
+# Author: David Twesigomwe
+# Date modified: 15-Dec-2020
+# Purpose: This script simulates the zygosity of variants after concatenating 2 haplotype VCF files.
+# Usage: python3 sim_zygosity.py in_database.txt > output.txt
+
+import os
+import sys
+
+in_file = sys.argv[1]
+
+f = open (in_file, "r")
+
+
+for line in f:
+    list1 = line.strip().split(";")
+    new_list = []
+    for i in list1:
+        x = i + '~0/1'
+        y = i + '~1/1'
+        if x not in new_list:
+            new_list.append(x)
+            
+        else:
+            new_list = list(map(lambda st: str.replace(st, x, y), new_list))
+
+    print(";".join(new_list))
+
+f.close()