Mercurial > repos > rliterman > csp2
comparison 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 |
comparison
equal
deleted
inserted
replaced
| 67:0e9998148a16 | 69:33d812a61356 |
|---|---|
| 1 #!/bin/bash | |
| 2 | |
| 3 usage(){ | |
| 4 echo " | |
| 5 Written by Brian Bushnell | |
| 6 Last modified December 22, 2021 | |
| 7 This script requires at least 52GB RAM. | |
| 8 It is designed for NERSC and uses hard-coded paths. | |
| 9 | |
| 10 Description: Removes all reads that map to the cat, dog, mouse, or human genome with at least 95% identity after quality trimming. | |
| 11 Removes approximately 98.6% of human 2x150bp reads, with zero false-positives to non-animals. | |
| 12 NOTE! This program uses hard-coded paths and will only run on Nersc systems. | |
| 13 | |
| 14 Usage: removecatdogmousehuman.sh in=<input file> outu=<clean output file> | |
| 15 | |
| 16 Input may be fasta or fastq, compressed or uncompressed. | |
| 17 | |
| 18 Parameters: | |
| 19 threads=auto (t) Set number of threads to use; default is number of logical processors. | |
| 20 overwrite=t (ow) Set to false to force the program to abort rather than overwrite an existing file. | |
| 21 interleaved=auto (int) If true, forces fastq input to be paired and interleaved. | |
| 22 trim=t Trim read ends to remove bases with quality below minq. | |
| 23 Values: t (trim both ends), f (neither end), r (right end only), l (left end only). | |
| 24 untrim=t Undo the trimming after mapping. | |
| 25 minq=4 Trim quality threshold. | |
| 26 ziplevel=2 (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster. | |
| 27 outm=<file> File to output the reads that mapped to human. | |
| 28 | |
| 29 ***** All BBMap parameters can be used; run bbmap.sh for more details. ***** | |
| 30 | |
| 31 Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems. | |
| 32 " | |
| 33 } | |
| 34 | |
| 35 #This block allows symlinked shellscripts to correctly set classpath. | |
| 36 pushd . > /dev/null | |
| 37 DIR="${BASH_SOURCE[0]}" | |
| 38 while [ -h "$DIR" ]; do | |
| 39 cd "$(dirname "$DIR")" | |
| 40 DIR="$(readlink "$(basename "$DIR")")" | |
| 41 done | |
| 42 cd "$(dirname "$DIR")" | |
| 43 DIR="$(pwd)/" | |
| 44 popd > /dev/null | |
| 45 | |
| 46 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/" | |
| 47 CP="$DIR""current/" | |
| 48 JNI="-Djava.library.path=""$DIR""jni/" | |
| 49 JNI="" | |
| 50 | |
| 51 z="-Xmx50g" | |
| 52 z2="-Xms50g" | |
| 53 set=0 | |
| 54 | |
| 55 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then | |
| 56 usage | |
| 57 exit | |
| 58 fi | |
| 59 | |
| 60 calcXmx () { | |
| 61 source "$DIR""/calcmem.sh" | |
| 62 setEnvironment | |
| 63 parseXmx "$@" | |
| 64 if [[ $set == 1 ]]; then | |
| 65 return | |
| 66 fi | |
| 67 } | |
| 68 calcXmx "$@" | |
| 69 | |
| 70 function removecatdogmousehuman() { | |
| 71 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 $@" | |
| 72 echo $CMD >&2 | |
| 73 eval $CMD | |
| 74 } | |
| 75 | |
| 76 removecatdogmousehuman "$@" |