README.md

@@ -3,4 +3,4 @@
 # Language: Java, Bash
 # Information about documentation is in /docs/readme.txt.
 
-# Version 38.62
+# Version 38.73

a_sample_mt.sh

@@ -6,6 +6,7 @@ Written by Brian Bushnell
 Last modified July 31, 2019
 
 Description:  Does nothing.  Should be fast.
+This is a template for making wrappers for new tools.
 
 Usage:  a_sample_mt.sh in=<input file> out=<output file>
 

addadapters.sh

@@ -5,6 +5,8 @@ echo "
 Written by Brian Bushnell
 Last modified February 17, 2015
 
+***DEPRECATED***
+
 Description:  Randomly adds adapters to a file, or grades a trimmed file.
 The input is a set of reads, paired or unpaired.
 The output is those same reads with adapter sequence replacing some of the bases in some reads.

addssu.sh

+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified August 22, 2019
+
+Description:  Adds SSU sequence to already-made sketches with TaxIDs.
+
+Usage:           addssu.sh in=a.sketch out=b.sketch ssufile=ssu.fa
+
+Standard parameters:
+in=<file>       Input sketch file.
+out=<file>      Output sketch file.
+ssufile=<file>  A fasta file of SSU sequences.  These should be renamed
+                so that they start with tid|# where # is the taxID.
+
+Java Parameters:
+-Xmx            This will set Java's memory usage, overriding autodetection.
+                -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
+                    The max is typically 85% of physical memory.
+-da             Disable assertions.
+
+For more detailed information, please read /bbmap/docs/guides/BBSketchGuide.txt.
+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/"
+
+z="-Xmx4g"
+z2="-Xms4g"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+	if [[ $set == 1 ]]; then
+		return
+	fi
+	#freeRam 3200m 84
+	#z="-Xmx${RAM}m"
+	#z2="-Xms${RAM}m"
+}
+calcXmx "$@"
+
+sendsketch() {
+	local CMD="java $EA $EOOM $z -cp $CP sketch.AddSSU $@"
+	echo $CMD >&2
+	eval $CMD
+}
+
+sendsketch "$@"

adjusthomopolymers.sh

+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified October 3, 2019
+
+Description:  Shrinks or expands homopolymers.
+
+Usage:  adjusthomopolymers.sh in=<input file> out=<output file> rate=<float>
+
+Input may be fasta or fastq, compressed or uncompressed.
+
+Standard parameters:
+in=<file>       Primary input, or read 1 input.
+in2=<file>      Read 2 input if reads are in two files.
+out=<file>      Primary output, or read 1 output.
+out2=<file>     Read 2 output if reads are in two files.
+overwrite=f     (ow) Set to false to force the program to abort rather than
+                overwrite an existing file.
+ziplevel=2      (zl) Set to 1 (lowest) through 9 (max) to change compression
+                level; lower compression is faster.
+
+Processing parameters:
+rate=0.0        0.1 will expand by 10%; -0.1 will shrink by 10%.
+
+Java Parameters:
+-Xmx            This will set Java's memory usage, overriding autodetection.
+                -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will
+                specify 200 megs. The max is typically 85% of physical memory.
+-eoom           This flag will cause the process to exit if an out-of-memory
+                exception occurs.  Requires Java 8u92+.
+-da             Disable assertions.
+
+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/"
+
+z="-Xmx1g"
+z2="-Xms1g"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+	if [[ $set == 1 ]]; then
+		return
+	fi
+	freeRam 1000m 30
+	z="-Xmx${RAM}m"
+	z2="-Xms${RAM}m"
+}
+calcXmx "$@"
+
+adjusthomopolymers() {
+	local CMD="java $EA $EOOM $z -cp $CP jgi.AdjustHomopolymers $@"
+	echo $CMD >&2
+	eval $CMD
+}
+
+adjusthomopolymers "$@"

analyzeaccession.sh

@@ -3,14 +3,14 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified August 9, 2018
+Last modified September 9, 2019
 
 Description:  Looks at accessions to see how to compress them.
 
 Usage:  analyzeaccession.sh *accession2taxid.gz out=<output file>
 
 Parameters:
-lines=-1        If positive, stop after this many lines.
+perfile=t       Use multiple threads per file and multiple files at a time.
 
 Java Parameters:
 -Xmx            This will set Java's memory usage, overriding autodetection.

applyvariants.sh

+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified September 4, 2019
+
+Description:  Mutates a reference by applying a set of variants.
+
+Usage:  applyvariants.sh in=<input file> vcf=<vcf file> out=<output file>
+
+Standard parameters:
+in=<file>       Reference fasta.
+vcf=<file>      Variants.
+out=<file>      Output fasta.
+overwrite=f     (ow) Set to false to force the program to abort rather than
+                overwrite an existing file.
+ziplevel=2      (zl) Set to 1 (lowest) through 9 (max) to change compression
+                level; lower compression is faster.
+
+Processing parameters:
+None yet!
+
+Java Parameters:
+-Xmx            This will set Java's memory usage, overriding autodetection.
+                -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will
+                specify 200 megs. The max is typically 85% of physical memory.
+-eoom           This flag will cause the process to exit if an out-of-memory
+                exception occurs.  Requires Java 8u92+.
+-da             Disable assertions.
+
+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/"
+
+z="-Xmx4g"
+z2="-Xms4g"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+	if [[ $set == 1 ]]; then
+		return
+	fi
+	freeRam 4000m 84
+	z="-Xmx${RAM}m"
+	z2="-Xms${RAM}m"
+}
+calcXmx "$@"
+
+applyvariants() {
+	local CMD="java $EA $EOOM $z -cp $CP var2.ApplyVariants $@"
+	echo $CMD >&2
+	eval $CMD
+}
+
+applyvariants "$@"

bbcms.sh

@@ -3,7 +3,7 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified December 19, 2018
+Last modified September 4, 2018
 
 Description:  Error corrects reads and/or filters by depth, storing
 kmer counts in a count-min sketch (a Bloom filter variant).
@@ -50,6 +50,10 @@ k=31            Kmer length, currently 1-31.
 hashes=3        Number of hashes per kmer.  Higher generally reduces 
                 false positives at the expense of speed; rapidly
                 diminishing returns above 4.
+ksmall=         Optional sub-kmer length; setting to slightly lower than k 
+                can improve memory efficiency by reducing the number of hashes
+                needed.  e.g. 'k=31 ksmall=29 hashes=2' has better speed and
+                accuracy than 'k=31 hashes=3' when the filter is very full.
 minprob=0.5     Ignore kmers with probability of being correct below this.
 memmult=1.0     Fraction of free memory to use for Bloom filter.  1.0 should
                 generally work; if the program crashes with an out of memory
@@ -58,7 +62,8 @@ memmult=1.0     Fraction of free memory to use for Bloom filter.  1.0 should
 cells=          Option to set the number of cells manually.  By default this
                 will be autoset to use all available memory.  The only reason
                 to set this is to ensure deterministic output.
-seed=0          This will change the hash function used.
+seed=0          This will change the hash function used.  Useful if running
+                iteratively with a very full table.  -1 uses a random seed.
                 
 Depth filtering parameters:
 mincount=0      If positive, reads with kmer counts below mincount will

bbduk.sh

@@ -3,7 +3,7 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified April 11, 2019
+Last modified November 7, 2019
 
 Description:  Compares reads to the kmers in a reference dataset, optionally 
 allowing an edit distance. Splits the reads into two outputs - those that 
@@ -279,13 +279,19 @@ entropy=-1          Set between 0 and 1 to filter reads with entropy below
 entropywindow=50    Calculate entropy using a sliding window of this length.
 entropyk=5          Calculate entropy using kmers of this length.
 minbasefrequency=0  Discard reads with a minimum base frequency below this.
+entropytrim=f       Values:
+                       f:  (false) Do not entropy-trim.
+                       r:  (right) Trim low entropy on the right end only.
+                       l:  (left) Trim low entropy on the left end only.
+                       rl: (both) Trim low entropy on both ends.
 entropymask=f       Values:
-                       f:  Discard low-entropy sequences.
-                       t:  Mask low-entropy parts of sequences with N.
+                       f:  (filter) Discard low-entropy sequences.
+                       t:  (true) Mask low-entropy parts of sequences with N.
                        lc: Change low-entropy parts of sequences to lowercase.
 entropymark=f       Mark each base with its entropy value.  This is on a scale
                     of 0-41 and is reported as quality scores, so the output
                     should be fastq or fasta+qual.
+NOTE: If set, entropytrim overrides entropymask.
 
 Cardinality estimation:
 cardinality=f       (loglog) Count unique kmers using the LogLog algorithm.

calcmem.sh

 #!/bin/bash
 
 #usage(){
-#	echo "CalcMem v1.12"
+#	echo "CalcMem v1.14"
 #	echo "Written by Brian Bushnell, Doug Jacobsen, Alex Copeland, Bryce Foster"
 #	echo "Calculates available memory in megabytes"
-#	echo "Last modified August 7, 2019"
+#	echo "Last modified October 30, 2019"
 #}
 
 #Also parses other Java flags
@@ -72,6 +72,13 @@ function setEnvironment(){
 	if [[ $SHIFTER_RUNTIME == 1 ]]; then
 		#Ignore NERSC_HOST
 		shifter=1
+	elif [ -v "$EC2_HOME" ]; then
+		#Let's assume this is the AWS taxonomy server...
+		PATH=/test1/binaries/bgzip:$PATH
+		PATH=/test1/binaries/lbzip2/bin:$PATH
+		PATH=/test1/binaries/sambamba:$PATH
+		#PATH=/test1/binaries/java/jdk-11.0.2/bin:$PATH
+		PATH=/test1/binaries/pigz2/pigz-2.4:$PATH
 	elif [ -z "$NERSC_HOST" ]; then
 		#Not NERSC; do nothing
 		:

callgenes.sh

@@ -3,18 +3,19 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified December 19, 2018
+Last modified August 21, 2019
 
 Description:  Finds orfs and calls genes in unspliced prokaryotes.
 This includes bacteria, archaea, viruses, and mitochondria.
 Can also predict 16S, 23S, 5S, and tRNAs.
 
-Usage:  callgenes.sh in=contigs.fa out=calls.gff outa=aminos.faa
+Usage:  callgenes.sh in=contigs.fa out=calls.gff outa=aminos.faa out16S=16S.fa
 
 File parameters:
-in=<file>       A fasta file.
+in=<file>       A fasta file; the only required parameter.
 out=<file>      Output gff file.
 outa=<file>     Amino acid output.
+out16s=<file>   16S output.
 model=<file>    A pgm file or comma-delimited list.
                 If unspecified a default model will be used.
 compareto=      Optional reference gff file to compare with the gene calls.
@@ -47,8 +48,8 @@ popd > /dev/null
 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
 CP="$DIR""current/"
 
-z="-Xmx1g"
-z2="-Xms1g"
+z="-Xmx6g"
+z2="-Xms6g"
 set=0
 
 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
@@ -65,7 +66,8 @@ calcXmx "$@"
 
 function callgenes() {
 	local CMD="java $EA $EOOM $z $z2 -cp $CP prok.CallGenes $@"
-	echo $CMD >&2
+	#Too long to echo sometimes since wildcards can be expanded
+	#echo $CMD >&2
 	eval $CMD
 }
 

clumpify.sh

@@ -3,7 +3,7 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified March 28, 2018
+Last modified October 30, 2019
 
 Description:  Sorts sequences to put similar reads near each other.
 Can be used for increased compression or error correction.

comparesketch.sh

@@ -3,7 +3,7 @@
 usage(){
 echo "
 Written by Brian Bushnell
-Last modified August 5, 2019
+Last modified September 4, 2019
 
 Description:  Compares query sketches to others, and prints their kmer identity.
 The input can be sketches made by sketch.sh, or fasta/fastq files.
@@ -50,8 +50,8 @@ blacklist=<file>    Ignore keys in this sketch file.  Additionally, there are
 whitelist=f         Ignore keys that are not in the index.  Requires index=t.
 
 Sketch-making parameters:
-mode=single         Possible modes, for fasta input:
-                       single: Generate one sketch per file.
+mode=perfile        Possible modes, for sequence input:
+                       single: Generate one sketch.
                        sequence: Generate one sketch per sequence.
                        perfile: Generate one sketch per file.
 sketchonly=f        Don't run comparisons, just write the output sketch file.
@@ -73,6 +73,7 @@ amino=f             Use amino acid mode.  Input should be amino acids.
 translate=f         Call genes and translate to proteins.  Input should be
                     nucleotides.  Designed for prokaryotes.
 sixframes=f         Translate all 6 frames instead of predicting genes.
+ssu=t               Scan for and retain full-length SSU sequence.
 
 Size parameters:
 size=10000          Desired size of sketches (if not using autosize).
@@ -130,6 +131,10 @@ minlevel=           Use this to restrict comparisons to distantly-related
                     using all-to-all comparisons.  minlevel=order would only
                     report hits between organisms related at the order level
                     or higher, not between same species or genus.
+banunclassified=f   Ignore organisms descending from nodes like 
+                    'unclassified Bacteria'
+banvirus=f          Ignore viruses.
+requiressu=f        Ignore records without SSUs.
 
 Output format:
 format=2            2: Default format with, per query, one query header line;
@@ -156,7 +161,7 @@ printgkmers=f       Number of genomic kmers.
 printgsize=t        Estimated number of unique genomic kmers.
 printgseqs=t        Number of sequences (scaffolds/reads).
 printtaxname=t      Name associated with this taxID.
-printname0=t        (pn0) Original seqeuence name.
+printname0=f        (pn0) Original seqeuence name.
 printfname=t        Query filename.
 printtaxa=f         Full taxonomy of each record.
 printcontam=t       Print contamination estimate, and factor contaminant kmers
@@ -166,8 +171,9 @@ printunique=t       Number of matches unique to this reference.
 printunique2=f      Number of matches unique to this reference's taxa.
 printunique3=f      Number of query kmers unique to this reference's taxa,
                     regardless of whether they are in this reference sketch.
-printnohit=t        Number of kmers that don't hit anything.
-printrefhits=t      Average number of ref sketches hit by shared kmers.
+printnohit=f        Number of kmers that don't hit anything.
+printrefhits=f      Average number of ref sketches hit by shared kmers.
+printgc=f           GC content.
 printucontam=f      Contam hits that hit exactly one reference sketch.
 printcontam2=f      Print contamination estimate using only kmer hits
                     to unrelated taxa.

consensus.sh

+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified October 16, 2019
+
+Description:  Generates the consensus sequence of a reference
+using aligned sequences.  This can be used for polishing assemblies,
+making representative ribosomal sub units, correcting PacBio reads, etc.
+
+Usage:  consensus.sh in=mapped.sam ref=ref.fa out=consensus.fa
+
+Recommended settings for assembly polishing via Illumina reads:  mafsub=0.5
+
+
+Standard parameters:
+in=<file>       Reads mapped to the reference; should be sam or bam.
+ref=<file>      Reference; may be fasta or fastq.
+out=<file>      Modified reference; may be fasta or fastq.
+overwrite=f     (ow) Set to false to force the program to abort rather than
+                overwrite an existing file.
+
+Processing parameters:
+mindepth=2      Do not change to alleles present at depth below this.
+mafsub=0.25     Do not incorporate substitutions below this allele fraction.
+mafdel=0.50     Do not incorporate deletions below this allele fraction.
+mafins=0.50     Do not incorporate insertions below this allele fraction.
+mafn=0.40       Do not change Ns (noref) to calls below this allele fraction.
+usemapq=f       Include mapq as a positive factor in edge weight.
+nonly=f         Only change Ns to different bases.
+noindels=f      Don't allow indels.
+ceiling=        If set, alignments will be weighted by their inverse identity.
+                For example, at ceiling=105, a read with 96% identity will get
+                bonus weight of 105-96=9 while a read with 70% identity will
+                get 105-70=35.  This favors low-identity reads.
+name=           Set the output sequence name (for a single output sequence).
+
+Java Parameters:
+-Xmx            This will set Java's memory usage, overriding autodetection.
+                -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will
+                specify 200 megs. The max is typically 85% of physical memory.
+-eoom           This flag will cause the process to exit if an out-of-memory
+                exception occurs.  Requires Java 8u92+.
+-da             Disable assertions.
+
+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/"
+
+z="-Xmx4g"
+z2="-Xms4g"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+	if [[ $set == 1 ]]; then
+		return
+	fi
+	freeRam 4000m 84
+	z="-Xmx${RAM}m"
+	z2="-Xms${RAM}m"
+}
+calcXmx "$@"
+
+consensus() {
+	local CMD="java $EA $EOOM $z -cp $CP consensus.ConsensusMaker $@"
+	echo $CMD >&2
+	eval $CMD
+}
+
+consensus "$@"

current/align2/AbstractMapper.java

@@ -675,10 +675,10 @@ public abstract class AbstractMapper {
 
 			samplerate=parser.samplerate;
 			sampleseed=parser.sampleseed;
-			IDFILTER=parser.idFilter;
+			MIN_IDFILTER=parser.minIdFilter;
 			build=parser.build;
-			if(IDFILTER>0){
-				if(IDFILTER==1f){PERFECTMODE=true;}
+			if(MIN_IDFILTER>0){
+				if(MIN_IDFILTER==1f){PERFECTMODE=true;}
 				MAKE_MATCH_STRING=true;
 			}
 			
@@ -2832,7 +2832,7 @@ public abstract class AbstractMapper {
 	/** Only allow sites with at least this many contiguous matches */
 	static int KFILTER=-1;
 	/** Only allow sites with identity of at least this */
-	static float IDFILTER=0f;
+	static float MIN_IDFILTER=0f;
 	
 	/** Rename reads to indicate their mapped insert size */
 	static boolean RenameByInsert=false;

current/align2/BBMap.java

@@ -432,7 +432,7 @@ public final class BBMap extends AbstractMapper {
 				t.stop("Loaded Bloom Filter: ");
 			}else{
 				if(bloomSerial){System.out.println("Could not read "+serialPath+", generating filter from reference.");}
-				bloomFilter=new BloomFilter(true, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
+				bloomFilter=new BloomFilter(true, bloomFilterK, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
 				t.stop("Made Bloom Filter: ");
 				if(bloomSerial && !RefToIndex.NODISK && !RefToIndex.FORCE_READ_ONLY){
 //					 && serialFile.canWrite()
@@ -491,7 +491,7 @@ public final class BBMap extends AbstractMapper {
 						SLOW_ALIGN_PADDING, SLOW_RESCUE_PADDING, OUTPUT_MAPPED_ONLY, DONT_OUTPUT_BLACKLISTED_READS, MAX_SITESCORES_TO_PRINT, PRINT_SECONDARY_ALIGNMENTS,
 						REQUIRE_CORRECT_STRANDS_PAIRS, SAME_STRAND_PAIRS, KILL_BAD_PAIRS, rcompMate,
 						PERFECTMODE, SEMIPERFECTMODE, FORBID_SELF_MAPPING, TIP_SEARCH_DIST,
-						ambiguousRandom, ambiguousAll, KFILTER, IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
+						ambiguousRandom, ambiguousAll, KFILTER, MIN_IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
 						LOCAL_ALIGN, RESCUE, STRICT_MAX_INDEL, MSA_TYPE, bloomFilter);
 			} catch (Throwable e) {
 				e.printStackTrace();

current/align2/BBMap5.java

@@ -414,7 +414,7 @@ public final class BBMap5 extends AbstractMapper  {
 				t.stop("Loaded Bloom Filter: ");
 			}else{
 				if(bloomSerial){System.out.println("Could not read "+serialPath+", generating filter from reference.");}
-				bloomFilter=new BloomFilter(true, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
+				bloomFilter=new BloomFilter(true, bloomFilterK, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
 				t.stop("Made Bloom Filter: ");
 				if(bloomSerial && !RefToIndex.NODISK && !RefToIndex.FORCE_READ_ONLY){
 //					 && serialFile.canWrite()
@@ -471,7 +471,7 @@ public final class BBMap5 extends AbstractMapper  {
 						SLOW_ALIGN_PADDING, SLOW_RESCUE_PADDING, OUTPUT_MAPPED_ONLY, DONT_OUTPUT_BLACKLISTED_READS, MAX_SITESCORES_TO_PRINT, PRINT_SECONDARY_ALIGNMENTS,
 						REQUIRE_CORRECT_STRANDS_PAIRS, SAME_STRAND_PAIRS, KILL_BAD_PAIRS, rcompMate,
 						PERFECTMODE, SEMIPERFECTMODE, FORBID_SELF_MAPPING, TIP_SEARCH_DIST,
-						ambiguousRandom, ambiguousAll, KFILTER, IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
+						ambiguousRandom, ambiguousAll, KFILTER, MIN_IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
 						LOCAL_ALIGN, RESCUE, STRICT_MAX_INDEL, MSA_TYPE, bloomFilter);
 			} catch (Exception e) {
 				e.printStackTrace();

current/align2/BBMapAcc.java

@@ -414,7 +414,7 @@ public final class BBMapAcc extends AbstractMapper  {
 				t.stop("Loaded Bloom Filter: ");
 			}else{
 				if(bloomSerial){System.out.println("Could not read "+serialPath+", generating filter from reference.");}
-				bloomFilter=new BloomFilter(true, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
+				bloomFilter=new BloomFilter(true, bloomFilterK, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
 				t.stop("Made Bloom Filter: ");
 				if(bloomSerial && !RefToIndex.NODISK && !RefToIndex.FORCE_READ_ONLY){
 //					 && serialFile.canWrite()
@@ -471,7 +471,7 @@ public final class BBMapAcc extends AbstractMapper  {
 						SLOW_ALIGN_PADDING, SLOW_RESCUE_PADDING, OUTPUT_MAPPED_ONLY, DONT_OUTPUT_BLACKLISTED_READS, MAX_SITESCORES_TO_PRINT, PRINT_SECONDARY_ALIGNMENTS,
 						REQUIRE_CORRECT_STRANDS_PAIRS, SAME_STRAND_PAIRS, KILL_BAD_PAIRS, rcompMate,
 						PERFECTMODE, SEMIPERFECTMODE, FORBID_SELF_MAPPING, TIP_SEARCH_DIST,
-						ambiguousRandom, ambiguousAll, KFILTER, IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
+						ambiguousRandom, ambiguousAll, KFILTER, MIN_IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
 						LOCAL_ALIGN, RESCUE, STRICT_MAX_INDEL, MSA_TYPE, bloomFilter);
 			} catch (Exception e) {
 				e.printStackTrace();

current/align2/BBMapPacBio.java

@@ -414,7 +414,7 @@ public final class BBMapPacBio extends AbstractMapper  {
 				t.stop("Loaded Bloom Filter: ");
 			}else{
 				if(bloomSerial){System.out.println("Could not read "+serialPath+", generating filter from reference.");}
-				bloomFilter=new BloomFilter(true, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
+				bloomFilter=new BloomFilter(true, bloomFilterK, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
 				t.stop("Made Bloom Filter: ");
 				if(bloomSerial && !RefToIndex.NODISK && !RefToIndex.FORCE_READ_ONLY){
 //					 && serialFile.canWrite()
@@ -460,7 +460,7 @@ public final class BBMapPacBio extends AbstractMapper  {
 						SLOW_ALIGN_PADDING, SLOW_RESCUE_PADDING, OUTPUT_MAPPED_ONLY, DONT_OUTPUT_BLACKLISTED_READS, MAX_SITESCORES_TO_PRINT, PRINT_SECONDARY_ALIGNMENTS,
 						REQUIRE_CORRECT_STRANDS_PAIRS, SAME_STRAND_PAIRS, KILL_BAD_PAIRS, rcompMate,
 						PERFECTMODE, SEMIPERFECTMODE, FORBID_SELF_MAPPING, TIP_SEARCH_DIST,
-						ambiguousRandom, ambiguousAll, KFILTER, IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
+						ambiguousRandom, ambiguousAll, KFILTER, MIN_IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
 						LOCAL_ALIGN, RESCUE, STRICT_MAX_INDEL, MSA_TYPE, bloomFilter);
 			} catch (Exception e) {
 				e.printStackTrace();

current/align2/BBMapPacBioSkimmer.java

@@ -413,7 +413,7 @@ public final class BBMapPacBioSkimmer extends AbstractMapper  {
 				t.stop("Loaded Bloom Filter: ");
 			}else{
 				if(bloomSerial){System.out.println("Could not read "+serialPath+", generating filter from reference.");}
-				bloomFilter=new BloomFilter(true, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
+				bloomFilter=new BloomFilter(true, bloomFilterK, bloomFilterK, 1, bloomFilterHashes, bloomFilterMinHits, true);
 				t.stop("Made Bloom Filter: ");
 				if(bloomSerial && !RefToIndex.NODISK && !RefToIndex.FORCE_READ_ONLY){
 //					 && serialFile.canWrite()
@@ -459,7 +459,7 @@ public final class BBMapPacBioSkimmer extends AbstractMapper  {
 						SLOW_ALIGN_PADDING, SLOW_RESCUE_PADDING, OUTPUT_MAPPED_ONLY, DONT_OUTPUT_BLACKLISTED_READS, MAX_SITESCORES_TO_PRINT, PRINT_SECONDARY_ALIGNMENTS,
 						REQUIRE_CORRECT_STRANDS_PAIRS, SAME_STRAND_PAIRS, KILL_BAD_PAIRS, rcompMate,
 						PERFECTMODE, SEMIPERFECTMODE, FORBID_SELF_MAPPING, TIP_SEARCH_DIST,
-						ambiguousRandom, ambiguousAll, KFILTER, IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
+						ambiguousRandom, ambiguousAll, KFILTER, MIN_IDFILTER, qtrimLeft, qtrimRight, untrim, TRIM_QUALITY, minTrimLength,
 						LOCAL_ALIGN, RESCUE, STRICT_MAX_INDEL, MSA_TYPE, bloomFilter);
 			} catch (Exception e) {
 				e.printStackTrace();