pgx-main from prod added

pgx-main/tests/config/nat2.config

@@ -0,0 +1,90 @@
+
+
+
+params {
+    gene = "nat2"
+}
+
+
+process {
+
+    // ALL PROCESSES
+    cache = true
+    stageInMode = 'symlink'
+    stageOutMode = 'rsync'
+   // scratch = "$HOME/tmp"  // clean this regularly
+
+    // Containers
+
+    // Singularity
+
+//    withLabel: phase {
+//    singularity.enabled	= false
+    //container = "$PWD/containers/whatshap.sif" // this can be generated from docker://pacificbiosciences/whatshap
+//    }
+
+    withName: call_snvs1 {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: call_snvs2 {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: call_sv_del {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: call_sv_dup {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: get_depth {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: format_snvs {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: get_core_var {
+    singularity.enabled	= true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: analyse_1 {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: analyse_2 {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: analyse_3 {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: analyse_4 {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    withName: call_stars {
+    singularity.enabled = true
+    container = "$PWD/containers/stellarpgx-dev.sif"
+    }
+
+    
+    // Docker
+    // container = "twesigomwedavid/stellarpgx-dev:latest" // Note that this Docker build needs to be pulled from Do
+
+}

pgx-main/tests/config/test.config

@@ -0,0 +1,23 @@
+
+
+params {
+// User-defined parameters
+
+   // reference genome
+   ref_file = "$PWD/tests/reference/hg38/chr22_hg38.fasta"
+
+
+   // BAM/CRAM file(s) and respective indexes 
+   in_bam = "$PWD/tests/samples/hg38/HG03130*{bam,bai}" 
+
+
+   // Output directoy (Default is $PWD/results)
+   out_dir = "$PWD/results"
+
+
+   // DO NOT modify these lines  
+   gene = "cyp2d6"
+   res_init = "$PWD/tests/resources"
+
+}
+

pgx-main/tests/reference/hg38/chr22_hg38.fasta.fai

@@ -0,0 +1 @@
+chr22	50818468	7	70	71

pgx-main/tests/resources/cyp2d6/res_hg38/test3.bed

@@ -0,0 +1,11 @@
+chr22	42126300	42126800
+chr22	42127750	42130000
+chr22	42126000	42137500
+chr22	42149880	42155020
+chr22	42139000	42142455
+chr22	42142465	42144575
+chr22	42139500	42140600
+chr22	42140600	42142500
+chr22	42149883	42155000
+chr22	42140600	42143600
+chr22	42143600	42144575

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()