1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
|
#!/bin/bash
usage(){
echo "
Written by Brian Bushnell
Last modified June 18, 2018
Description: Filters sequences according to their taxonomy,
as determined by the sequence name. Sequences should
be labeled with a gi number, NCBI taxID, or species name.
Usage: filterbytaxa.sh in=<input file> out=<output file> tree=<tree file> table=<table file> ids=<numbers> level=<name or number>
I/O parameters:
in=<file> Primary input, or read 1 input.
out=<file> Primary output, or read 1 output.
results=<file> Optional; prints a list indicating which taxa were retained.
overwrite=f (ow) Set to false to force the program to abort rather than
overwrite an existing file.
showspeed=t (ss) Set to 'f' to suppress display of processing speed.
ziplevel=2 (zl) Set to 1 (lowest) through 9 (max) to change compression
level; lower compression is faster.
Processing parameters:
level= Taxonomic level, such as phylum. Filtering will operate on
sequences within the same taxonomic level as specified ids.
If not set, only matches to a node or its descendants will
be considered.
reqlevel= Require nodes to have ancestors at these levels. For example,
reqlevel=species,genus would ban nodes that are not defined
at both the species and genus levels.
ids= Comma-delimited list of NCBI numeric IDs. Can also be a
file with one taxID per line. Names (like bacteria) are also
acceptable.
include=f 'f' will discard filtered sequences, 't' will keep them.
besteffort=f Intended for include mode. Iteratively increases level
while the input file has no hits to the tax list.
tree=<file> Specify a TaxTree file like tree.taxtree.gz.
On Genepool, use 'auto'.
gi=<file> Specify a gitable file like gitable.int1d.gz. Only needed
if gi numbers will be used. On Genepool, use 'auto'.
accession= Specify one or more comma-delimited NCBI accession to taxid
files. Only needed if accesions will be used; requires ~45GB
of memory. On Genepool, use 'auto'.
printnodes=t Print the names of nodes added to the filter.
requirepresent=t Crash with an error message if a header cannot be resolved
to a taxid.
String-matching parameters:
regex= Filter names matching this Java regular expression.
contains= Filter names containing this substring (case-insensitive).
* Note *
Tree and table files are in /global/projectb/sandbox/gaag/bbtools/tax
For non-Genepool users, or to make new ones, use taxtree.sh and gitable.sh
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.
"
}
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 [[ $set == 1 ]]; then
return
fi
freeRam 1000m 84
z="-Xmx${RAM}m"
z2="-Xms${RAM}m"
}
calcXmx "$@"
filterbytaxa() {
local CMD="java $EA $EOOM $z -cp $CP tax.FilterByTaxa $@"
echo $CMD >&2
eval $CMD
}
filterbytaxa "$@"
|
