Mercurial > repos > rliterman > csp2

comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/representative.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 September 4, 2019
7
8 Description: Makes a representative set of taxa from all-to-all identity
9 comparison. Input should be in 3+ column TSV format (first 3 are required):
10 (query, ref, ANI, qsize, rsize, qbases, rbases)
11 ...as produced by CompareSketch with format=3 and usetaxidname.
12 Additional columns are allowed and will be ignored.
13
14 Usage: representative.sh in=<input file> out=<output file>
15
16 Parameters:
17 overwrite=f (ow) Set to false to force the program to abort rather than
18 overwrite an existing file.
19 threshold=0 Ignore edges under threshold value. This also affects the
20 choice of centroids; a high threshold gives more weight to
21 higher-value edges.
22 minratio=0 Ignores edges with a ratio below this value.
23 invertratio=f Invert the ratio when greater than 1.
24 printheader=t Print a header line in the output.
25 printsize=t Print the size of retained nodes.
26 printclusters=t Print the nodes subsumed by each retained node.
27 minsize=0 Ignore nodes under this size (in unique kmers).
28 maxsize=0 If positive, ignore nodes over this size (unique kmers).
29 minbases=0 Ignore nodes under this size (in total bases).
30 maxbases=0 If positive, ignore nodes over this size (total bases).
31
32 Taxonomy parameters:
33 level= Taxonomic level, such as phylum. Filtering will operate on
34 sequences within the same taxonomic level as specified ids.
35 If not set, only matches to a node or its descendants will
36 be considered.
37 ids= Comma-delimited list of NCBI numeric IDs. Can also be a
38 file with one taxID per line.
39 names= Alternately, a list of names (such as 'Homo sapiens').
40 Note that spaces need special handling.
41 include=f 'f' will discard filtered sequences, 't' will keep them.
42 tree=<file> Specify a TaxTree file like tree.taxtree.gz.
43 On Genepool, use 'auto'.
44
45 Java Parameters:
46 -Xmx This will set Java's memory usage, overriding autodetection.
47 -Xmx20g will
48 specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
49 The max is typically around 85% of physical memory.
50 -eoom This flag will cause the process to exit if an out-of-memory
51 exception occurs. Requires Java 8u92+.
52 -da Disable assertions.
53
54 Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
55 "
56 }
57
58 #This block allows symlinked shellscripts to correctly set classpath.
59 pushd . > /dev/null
60 DIR="${BASH_SOURCE[0]}"
61 while [ -h "$DIR" ]; do
62 cd "$(dirname "$DIR")"
63 DIR="$(readlink "$(basename "$DIR")")"
64 done
65 cd "$(dirname "$DIR")"
66 DIR="$(pwd)/"
67 popd > /dev/null
68
69 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
70 CP="$DIR""current/"
71
72 z="-Xmx4g"
73 z2="-Xms4g"
74 set=0
75
76 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
77 usage
78 exit
79 fi
80
81 calcXmx () {
82 source "$DIR""/calcmem.sh"
83 setEnvironment
84 parseXmx "$@"
85 if [[ $set == 1 ]]; then
86 return
87 fi
88 freeRam 4000m 84
89 z="-Xmx${RAM}m"
90 z2="-Xms${RAM}m"
91 }
92 calcXmx "$@"
93
94 a_sample_mt() {
95 local CMD="java $EA $EOOM $z -cp $CP jgi.RepresentativeSet $@"
96 echo $CMD >&2
97 eval $CMD
98 }
99
100 a_sample_mt "$@"