janxkoci

SAM and BAM filtering one-liners

@author: David Fredman, david.fredmanAAAAAA@gmail.com (sans poly-A tail)
@dependencies: http://sourceforge.net/projects/bamtools/ and http://samtools.sourceforge.net/

Please extend with additional/faster/better solutions via a pull request!

BWA mapping (using piping for minimal disk I/O)

janxkoci

#!/usr/bin/awk -f

function usage()
{
	print "Convert legofit model with estimates to slendr simulation script." > "/dev/stderr"
	print "usage: estlgo2slendr.awk model.lgo" > "/dev/stderr"
	err_exit = 1
	exit 1
}

janxkoci

#!/bin/bash
#PBS -l select=1:ncpus=64:mem=1gb,walltime=24:00:00

## GO TO WORKDIR
cd $PBS_O_WORKDIR || exit

## EXPORT PATH
export PATH="/storage/brno2/home/jena/bin:$PATH"
export PATH="/storage/brno2/home/jena/miniconda3/bin:$PATH"

janxkoci

# julia shebang here

# mean fasta length
# non-fasta input may lead to division by zero !!
# use at your own risk

# add global constants for vars in loop below
# actually - requires julia v1.8+
nseq::Int = 0
len::Int = 0

janxkoci

#!/bin/bash

## bash vcf2hetfa.sh input.vcf.gz

VCF=$1
OUT=$(basename -s .vcf.gz $VCF).hetfa.fa
TMP=${OUT}.tmp

rm $OUT # output build by appending, so remove old versions first

janxkoci

#!/usr/bin/awk -f

BEGIN {
	OFS = "\t"
	print "chrom_pos", "ref", "alt", "aa", "da", "Altai", "Denisova3", "Chagyrskaya", "Vindija", "Africa"
}

$4 == $5 {		# chimp matches gorilla
	
	## concatenate African genotypes to a string (columns 10..NF)

janxkoci

#!/usr/bin/env Rscript

# library(seqinr)

## ARGS
args <- commandArgs(trailingOnly=TRUE)
if (length(args) != 2) stop("Two input files must be supplied.", call.=FALSE)

## INPUT
fastafile <- grep(".fa", args, val=T) # args[1] # "mez1_chr21-22.fa"

janxkoci

// R keyboard shortcuts for jupyterlab
{
          "command": "notebook:replace-selection",
          "selector": ".jp-Notebook",
          "keys": ["Ctrl Shift M"],
          "args": {"text": " %>% "}
        },
        {
          "command": "notebook:replace-selection",
          "selector": ".jp-Notebook",

janxkoci

#!/bin/bash

## PLINK CLUSTERING (plink1.9)
## takes input (any path) and creates clustering reports in working dir (to not mix data and results)

## OUTPUT PREFIX
prefix=$1

## MDS DIMENSIONS (optional, default = 2)
dims=${2:-2}

janxkoci

#!/usr/bin/awk -f

## USAGE
## awk -f est2lgo.awk model_est.txt model.lgo

BEGIN {OFS="\t"}

# read EST file and save param values into array
# note: array includes also header, but that won't match, so nobody cares
NR==FNR {a[$1]=$2; next}