Mercurial > repos > rliterman > csp2

comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/kmercoverage.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 May 23, 2014
7
8 *** DEPRECATED: This should still work but is no longer maintained. ***
9
10 Description: Annotates reads with their kmer depth.
11
12 Usage: kmercoverage in=<input> out=<read output> hist=<histogram output>
13
14 Input parameters:
15 in2=null Second input file for paired reads
16 extra=null Additional files to use for input (generating hash table) but not for output
17 fastareadlen=2^31 Break up FASTA reads longer than this. Can be useful when processing scaffolded genomes
18 tablereads=-1 Use at most this many reads when building the hashtable (-1 means all)
19 kmersample=1 Process every nth kmer, and skip the rest
20 readsample=1 Process every nth read, and skip the rest
21
22 Output parameters:
23 hist=null Specify a file to output the depth histogram
24 histlen=10000 Max depth displayed on histogram
25 reads=-1 Only process this number of reads, then quit (-1 means all)
26 sampleoutput=t Use sampling on output as well as input (not used if sample rates are 1)
27 printcoverage=f Only print coverage information instead of reads
28 useheader=f Append coverage info to the read's header
29 minmedian=0 Don't output reads with median coverage below this
30 minaverage=0 Don't output reads with average coverage below this
31 zerobin=f Set to true if you want kmers with a count of 0 to go in the 0 bin instead of the 1 bin in histograms.
32 Default is false, to prevent confusion about how there can be 0-count kmers.
33 The reason is that based on the 'minq' and 'minprob' settings, some kmers may be excluded from the bloom filter.
34
35 Hashing parameters:
36 k=31 Kmer length (values under 32 are most efficient, but arbitrarily high values are supported)
37 cbits=8 Bits per cell in bloom filter; must be 2, 4, 8, 16, or 32. Maximum kmer depth recorded is 2^cbits.
38 Large values decrease accuracy for a fixed amount of memory.
39 hashes=4 Number of times a kmer is hashed. Higher is slower.
40 Higher is MORE accurate if there is enough memory, and LESS accurate if there is not enough memory.
41 prefilter=f True is slower, but generally more accurate; filters out low-depth kmers from the main hashtable.
42 prehashes=2 Number of hashes for prefilter.
43 passes=1 More passes can sometimes increase accuracy by iteratively removing low-depth kmers
44 minq=7 Ignore kmers containing bases with quality below this
45 minprob=0.5 Ignore kmers with overall probability of correctness below this
46 threads=X Spawn exactly X hashing threads (default is number of logical processors). Total active threads may exceed X by up to 4.
47
48 Java Parameters:
49 -Xmx This will set Java's memory usage, overriding autodetection.
50 -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
51 The max is typically 85% of physical memory.
52 -eoom This flag will cause the process to exit if an
53 out-of-memory exception occurs. Requires Java 8u92+.
54 -da Disable assertions.
55
56 Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
57 "
58 }
59
60 #This block allows symlinked shellscripts to correctly set classpath.
61 pushd . > /dev/null
62 DIR="${BASH_SOURCE[0]}"
63 while [ -h "$DIR" ]; do
64 cd "$(dirname "$DIR")"
65 DIR="$(readlink "$(basename "$DIR")")"
66 done
67 cd "$(dirname "$DIR")"
68 DIR="$(pwd)/"
69 popd > /dev/null
70
71 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
72 CP="$DIR""current/"
73
74 z="-Xmx1g"
75 z2="-Xms1g"
76 set=0
77
78 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
79 usage
80 exit
81 fi
82
83 calcXmx () {
84 source "$DIR""/calcmem.sh"
85 setEnvironment
86 parseXmx "$@"
87 if [[ $set == 1 ]]; then
88 return
89 fi
90 freeRam 3200m 84
91 z="-Xmx${RAM}m"
92 z2="-Xms${RAM}m"
93 }
94 calcXmx "$@"
95
96 kmercoverage() {
97 local CMD="java $EA $EOOM $z -cp $CP jgi.KmerCoverage prefilter=true bits=16 interleaved=false $@"
98 echo $CMD >&2
99 eval $CMD
100 }
101
102 kmercoverage "$@"