PoisonAlien

PoisonAlien

---
title: "Sequencing run summary"
date: "Generated on: `r Sys.Date()`"
output: 
  html_document:
    toc: true
    toc_depth: 3
    toc_float: true
    self_contained: yes
    theme: sandstone

PoisonAlien

#!/usr/bin/env python3

#A simple script to predict gnomAD ancestry using PCA loadings trained on gnomAD V3 datasets
#See here for details: https://gnomad.broadinstitute.org/news/2021-09-using-the-gnomad-ancestry-principal-components-analysis-loadings-and-random-forest-classifier-on-your-dataset/
#Author: Anand Mayakonda

import sys
import os.path
import shutil
import argparse

PoisonAlien

#!/usr/bin/env bash

#Script to subset a bigWig file for user specific loci
#MIT License (Anand Mayakonda; [email protected])

function usage (){
   echo "Subset a bigWig file for genomic loci. 

Requires UCSC kentutils bigWigToBedGraph and bedGraphToBigWig to be installed
Binaries available from: https://hgdownload.soe.ucsc.edu/admin/exe/

PoisonAlien

pipeline_dir = "./"

echo "Downloading VEP cache.." 1>&2
mkdir -p ${pipeline_dir}/resources/vep_cache/
cd ${pipeline_dir}/resources/vep_cache/
curl -O https://ftp.ensembl.org/pub/release-107/variation/indexed_vep_cache/homo_sapiens_vep_107_GRCh38.tar.gz
tar -xzf homo_sapiens_vep_107_GRCh38.tar.gz -C ./

wget https://ftp.ensembl.org/pub/release-107/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz
gunzip -c Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz | bgzip > Homo_sapiens.GRCh38.dna.primary_assembly.fa.bgzip

PoisonAlien

#!/usr/bin/env bash

#A minimal project template structure that I use for my Bioinformatic projects
#MIT License (Anand Mayakonda; [email protected])

function usage() {
	echo "createproject.sh - Create a project template directory structure

Usage:         createproject.sh [option] <project_name>

PoisonAlien

#Wrapper around goseq 
#'@param assayedGenes total gene IDs that were measured
#'@param deGenes DE gene IDs
#'@param source_id Can be `ensGene` or `geneSymbol`
#'@param  hyperGeo Dfault TRUE. Set to FALSE for rna-seq data
goseq_wrapper = function(assayedGenes, deGenes, source_id = "ensGene", hyperGeo = TRUE){
  gene_vector = as.integer(assayedGenes %in% deGenes)
  names(gene_vector)= assayedGenes
  
  pwf = suppressWarnings(suppressMessages(goseq::nullp(DEgenes = gene_vector, genome = "hg19", id = source_id, plot.fit = FALSE)))

PoisonAlien

####################################################################################
#
# Best-practice 450k/EPIC QC and preprocessing workflow for the PPCG project
#
# creator: Pavlo Lutsik
#
# 30.01.2021
####################################################################################

library(RnBeads)

PoisonAlien

//A minimal program to extract nucelotide counts of selected genomic loci from the BAM file

//gcc -g -O3 -pthread ntcounts.c -lhts -Ihts -o ntcounts

//MIT License
//Copyright (c) 2021 Anand Mayakonda <[email protected]>


#include <unistd.h>
#include <stdio.h>

PoisonAlien

# Get the COSMIC variant file from here: https://cancer.sanger.ac.uk/cosmic/download (for. ex: CosmicCompleteTargetedScreensMutantExport.tsv.gz)
# You will have to register and sign in

# Readin only these selected columns: `Gene name	GENOMIC_MUTATION_ID	Mutation AA	Mutation Description	Mutation genome position	SNP	FATHMM prediction	HGVSG`

cosm = data.table::fread(cmd = "zcat CosmicCompleteTargetedScreensMutantExport.tsv.gz | cut -f 1,17,21,22,26,28,30,40 | sed 1d | sort -k1,2", header = FALSE)
csom = cosm[!V2 %in% ""]
csom = csom[!V4 %in% "Substitution - coding silent"] #Remove silent variants
csom = csom[!V4 %in% ""] #Remove vars with no sub. type variants
csom[, id := paste0(V2, ":", V3)]