danielecook

# Source: https://lh3.github.io/2021/07/06/remapping-an-aligned-bam
samtools collate -Oun128 in.bam | samtools fastq -OT RG,BC - \
  | bwa mem -pt8 -CH <(samtools view -H in.bam|grep ^@RG) ref.fa - \
  | samtools sort -@4 -m4g -o out.bam -

danielecook

# get header from first file and drop it from other files
awk 'NR == FNR || FNR > 1' *.tsv > ${output_file}

# Add a column for filename and filename column
awk -v OFS='\t' 'NR == FNR { print \$0, 'filename' } FNR > 1 { print \$0, FILENAME }' 

danielecook

# This quick script will check for big differences in a bams index and creation date and perform indexing.
for i in *.bam; do
    bam=${i}
    bai=${i}.bai
    bam_date=$(stat -c %Y ${bam})
    bai_date=$(stat -c %Y ${bai})
    diff=`expr ${bam_date} - ${bai_date}`
    if [ ${diff} -gt 100000 ]; then
        echo "${bam} ${diff}";
        sbatch --job-name=${bam} --partition=cpu --time=3:00:00 --cpus-per-task=32 --wrap "samtools index -@ 32 ${bam}"

danielecook

function split_bed() {
# This function will split a bed file by chromosome and chunk_size=1000
# In other words, split files will only possess one chromosome max.
# File sizes may be variable.
awk -v chunk_size=1000 'NR == 1 { chrom=$1; iter=0; fname_iter=0; print chrom } 
    {
            if(chrom == $1 && iter <= chunk_size) {
                print > sprintf("x%04d_%s.segment.txt", fname_iter, $1);
                iter++; 
            } else {

danielecook

resolve-symbolic-link() {
  if [ -L $1 ]; then
      temp="$(readlink "$1")";
      rm -rf "$1";
      cp -rf "$temp" "$1";
  fi
}

danielecook

function node() {
    # Usage:
    # node ca015
    # ssh into node and go to current directory
    ssh -t ${1} "cd ${PWD}; bash"
}

danielecook

#!/usr/bin/bash
error() {
    >&2 echo -e "\n\t$(tput setaf 1)${1}$(tput sgr0)\n"
    exit 1
}

msg() {
    >&2 echo -e "$(tput setaf 3)${1}$(tput sgr0)"
}

danielecook

# ITEMS <- vectorize("
# a
# b
# c
# ")

vectorize <- function(x) {
    x <- strsplit(x, "\n")[[1]]
    x[!is.na(x) & x != ""]
}

danielecook

parse_format_column <- 
  df[, .(rbindlist(
              purrr::map2(
                strsplit(vcf_format, ":", fixed=TRUE),
                strsplit(vcf_gt, ":", fixed=TRUE),
                function(x, y) { names(y) <- x; data.table(t(y)) }
                )
              )
        ),
   ]

danielecook

docker stop $(docker ps -a -q)
docker rm $(docker ps -a -q)