jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified January 26, 2021
jpayne@69: 
jpayne@69: Description:  Given a reference, generates a kmer spectrum including a 
jpayne@69: specified number of substitutions, insertions, and deletions.  The output is 
jpayne@69: useful for analyzing barcodes or other short oligos, and filtering using
jpayne@69: BBDuk or Seal. Input may be fasta or fastq, compressed or raw.
jpayne@69: See also kcompress, kmercountexact, and bbkmerset.
jpayne@69: 
jpayne@69: Usage:  kmutate.sh in=<file> out=<file> k=<kmer length> edist=<edit distance>
jpayne@69: 
jpayne@69: Examples:
jpayne@69: 
jpayne@69:         kmutate.sh in=x.fa out=y.fa k=31 edist=2
jpayne@69: This will generate all 31-mers in x.fa, along with all 31-mer mutants with
jpayne@69: an edit distance of up to 2.  For example, 1 substitution, or 1 substitution
jpayne@69: plus 1 deletion, or any other combination of subsitutions, insertions,
jpayne@69: and deletions that sum to 0, 1, or 2.
jpayne@69: 
jpayne@69:         kmutate.sh in=x.fa out=y.fa k=31 idist=1 ddist=3
jpayne@69: This will generate all 31-mers in x.fa, along with all 31-mer mutants allowing
jpayne@69: up to 1 insertion and 3 deletions, but no substitutions.  For example,
jpayne@69: 1 insertion and 3 deletions is possible (edit distance 4), but 1 deletion and 
jpayne@69: 1 substitution is not directly possible (though some equivalent mutants would
jpayne@69: still be generated because a deletion and subsequent insertion is equivalent 
jpayne@69: to a substitution).
jpayne@69: 
jpayne@69: Note that deletion events have limitations; e.g., they cannot occur on input
jpayne@69: sequences of length k because the resulting sequence is shorter than k.  As
jpayne@69: a result, running the program twice consecutively with edist=1 will not give
jpayne@69: the same results as running once with edist=2 since the intermediate file will
jpayne@69: be only k-length sequences.  However, running consecutively with sdist or
jpayne@69: idist would be equivalent since they do not involve deletions.
jpayne@69: 
jpayne@69: Standard parameters:
jpayne@69: in=<file>       Primary input, or read 1 input.
jpayne@69: in2=<file>      Read 2 input if reads are in two files.
jpayne@69: out=<file>      Primary output, or read 1 output.
jpayne@69: overwrite=t     (ow) Set to false to force the program to abort rather than
jpayne@69:                 overwrite an existing file.
jpayne@69: 
jpayne@69: Processing parameters:
jpayne@69: k=31            Kmer length; 1-31.
jpayne@69: rcomp=t         Consider kmers equivalent to their reverse-complements.
jpayne@69: 
jpayne@69: Edit mode flags (used if edist>0):
jpayne@69: edist=0         Set the maximal edit distance (0-3).
jpayne@69: smax=99         (optional) Don't allow more than this many total substitutions.
jpayne@69: dmax=99         (optional) Don't allow more than this many total deletions.
jpayne@69: imax=99         (optional) Don't allow more than this many total insertions.
jpayne@69: 
jpayne@69: SDI mode flags:
jpayne@69: sdist=0         Maximum substitutions allowed.
jpayne@69: idist=0         Maximum insertions allowed.
jpayne@69: ddist=0         Maximum deletions allowed (0-3).
jpayne@69: emax=99         (optional) Don't allow more than this many total edits.
jpayne@69: 
jpayne@69: *** Note - please use SDI mode flags OR Edit mode flag, not both. ***
jpayne@69: *** Both modes are equivalent, they just have different defaults. ***
jpayne@69: 
jpayne@69: Java Parameters:
jpayne@69: -Xmx            This will set Java's memory usage, overriding autodetection.
jpayne@69:                 -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will
jpayne@69:                 specify 200 megs. The max is typically 85% of physical memory.
jpayne@69: -eoom           This flag will cause the process to exit if an out-of-memory
jpayne@69:                 exception occurs.  Requires Java 8u92+.
jpayne@69: -da             Disable assertions.
jpayne@69: 
jpayne@69: Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
jpayne@69: "
jpayne@69: }
jpayne@69: 
jpayne@69: #This block allows symlinked shellscripts to correctly set classpath.
jpayne@69: pushd . > /dev/null
jpayne@69: DIR="${BASH_SOURCE[0]}"
jpayne@69: while [ -h "$DIR" ]; do
jpayne@69:   cd "$(dirname "$DIR")"
jpayne@69:   DIR="$(readlink "$(basename "$DIR")")"
jpayne@69: done
jpayne@69: cd "$(dirname "$DIR")"
jpayne@69: DIR="$(pwd)/"
jpayne@69: popd > /dev/null
jpayne@69: 
jpayne@69: #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
jpayne@69: CP="$DIR""current/"
jpayne@69: 
jpayne@69: z="-Xmx4g"
jpayne@69: z2="-Xms4g"
jpayne@69: set=0
jpayne@69: 
jpayne@69: if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
jpayne@69: 	usage
jpayne@69: 	exit
jpayne@69: fi
jpayne@69: 
jpayne@69: calcXmx () {
jpayne@69: 	source "$DIR""/calcmem.sh"
jpayne@69: 	setEnvironment
jpayne@69: 	parseXmx "$@"
jpayne@69: 	if [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 4000m 84
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: kmutate() {
jpayne@69: 	local CMD="java $EA $EOOM $z $z2 -cp $CP jgi.KExpand $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: kmutate "$@"