Mercurial > repos > rliterman > csp2

comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/removehuman2.sh @ 69:33d812a61356

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
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 17GB RAM.
8 It is designed for NERSC and uses hard-coded paths.
9
10 Description: Removes all reads that map to the human genome with at least 88% identity after quality trimming.
11 This is more aggressive than removehuman.sh and uses an unmasked human genome reference.
12 It removes roughly 99.99% of human 2x150bp reads, but may incur false-positive removals.
13 NOTE! This program uses hard-coded paths and will only run on Nersc systems unless you change the path.
14
15 Usage: removehuman.sh in=<input file> outu=<clean output file>
16
17 Input may be fasta or fastq, compressed or uncompressed.
18
19 Parameters:
20 threads=auto (t) Set number of threads to use; default is number of logical processors.
21 overwrite=t (ow) Set to false to force the program to abort rather than overwrite an existing file.
22 interleaved=auto (int) If true, forces fastq input to be paired and interleaved.
23 trim=t Trim read ends to remove bases with quality below minq.
24 Values: t (trim both ends), f (neither end), r (right end only), l (left end only).
25 untrim=t Undo the trimming after mapping.
26 minq=4 Trim quality threshold.
27 ziplevel=2 (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster.
28 outm=<file> File to output the reads that mapped to human.
29 path= Set the path to an indexed human genome.
30
31 ***** All BBMap parameters can be used; run bbmap.sh for more details. *****
32
33 Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
34 "
35 }
36
37 #This block allows symlinked shellscripts to correctly set classpath.
38 pushd . > /dev/null
39 DIR="${BASH_SOURCE[0]}"
40 while [ -h "$DIR" ]; do
41 cd "$(dirname "$DIR")"
42 DIR="$(readlink "$(basename "$DIR")")"
43 done
44 cd "$(dirname "$DIR")"
45 DIR="$(pwd)/"
46 popd > /dev/null
47
48 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
49 CP="$DIR""current/"
50 JNI="-Djava.library.path=""$DIR""jni/"
51 JNI=""
52
53 z="-Xmx16000m"
54 z2="-Xms16000m"
55 set=0
56
57 calcXmx () {
58 source "$DIR""/calcmem.sh"
59 setEnvironment
60 parseXmx "$@"
61 }
62 calcXmx "$@"
63
64 function removehuman() {
65 local CMD="java $EA $EOOM $z $z2 $JNI -cp $CP align2.BBMap minratio=0.75 maxindel=8 bwr=0.22 bw=26 minhits=1 path=/global/cfs/cdirs/bbtools/hg19 build=2 pigz unpigz zl=6 qtrim=r trimq=10 untrim idtag usemodulo printunmappedcount ztd=2 maxsites=1 k=14 tipsearch=0 kfilter=25 bloomfilter $@"
66 echo $CMD >&2
67 eval $CMD
68 }
69
70 removehuman "$@"