Mercurial > repos > rliterman > csp2
diff CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/removecatdogmousehuman.sh @ 69:33d812a61356
planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author | jpayne |
---|---|
date | Tue, 18 Mar 2025 17:55:14 -0400 |
parents | |
children |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/removecatdogmousehuman.sh Tue Mar 18 17:55:14 2025 -0400 @@ -0,0 +1,76 @@ +#!/bin/bash + +usage(){ +echo " +Written by Brian Bushnell +Last modified December 22, 2021 +This script requires at least 52GB RAM. +It is designed for NERSC and uses hard-coded paths. + +Description: Removes all reads that map to the cat, dog, mouse, or human genome with at least 95% identity after quality trimming. +Removes approximately 98.6% of human 2x150bp reads, with zero false-positives to non-animals. +NOTE! This program uses hard-coded paths and will only run on Nersc systems. + +Usage: removecatdogmousehuman.sh in=<input file> outu=<clean output file> + +Input may be fasta or fastq, compressed or uncompressed. + +Parameters: +threads=auto (t) Set number of threads to use; default is number of logical processors. +overwrite=t (ow) Set to false to force the program to abort rather than overwrite an existing file. +interleaved=auto (int) If true, forces fastq input to be paired and interleaved. +trim=t Trim read ends to remove bases with quality below minq. + Values: t (trim both ends), f (neither end), r (right end only), l (left end only). +untrim=t Undo the trimming after mapping. +minq=4 Trim quality threshold. +ziplevel=2 (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster. +outm=<file> File to output the reads that mapped to human. + +***** All BBMap parameters can be used; run bbmap.sh for more details. ***** + +Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems. +" +} + +#This block allows symlinked shellscripts to correctly set classpath. +pushd . > /dev/null +DIR="${BASH_SOURCE[0]}" +while [ -h "$DIR" ]; do + cd "$(dirname "$DIR")" + DIR="$(readlink "$(basename "$DIR")")" +done +cd "$(dirname "$DIR")" +DIR="$(pwd)/" +popd > /dev/null + +#DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/" +CP="$DIR""current/" +JNI="-Djava.library.path=""$DIR""jni/" +JNI="" + +z="-Xmx50g" +z2="-Xms50g" +set=0 + +if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then + usage + exit +fi + +calcXmx () { + source "$DIR""/calcmem.sh" + setEnvironment + parseXmx "$@" + if [[ $set == 1 ]]; then + return + fi +} +calcXmx "$@" + +function removecatdogmousehuman() { + local CMD="java $EA $EOOM $z $z2 $JNI -cp $CP align2.BBMap minratio=0.9 maxindel=3 bwr=0.16 bw=12 quickmatch fast minhits=2 path=/global/cfs/cdirs/bbtools/mousecatdoghuman/ pigz unpigz zl=6 qtrim=r trimq=10 untrim idtag usemodulo printunmappedcount ztd=2 kfilter=25 maxsites=1 k=14 bloomfilter $@" + echo $CMD >&2 + eval $CMD +} + +removecatdogmousehuman "$@"