Mercurial > repos > rliterman > csp2
comparison CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/cutgff.sh @ 69:33d812a61356
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 October 15, 2019 | |
7 | |
8 Description: Cuts out features defined by a gff file, and writes them | |
9 to a new fasta. Features are output in their sense strand. | |
10 | |
11 Usage: cutgff.sh in=<fna file> gff=<gff file> out=<fna file> | |
12 | |
13 in= is optional, and gff filenames will be automaitically assumed based on | |
14 the fasta name if not specified. This allows running on multiple files | |
15 like this: | |
16 | |
17 cutgff.sh types=rRNA out=16S.fa minlen=1440 maxlen=1620 attributes=16S bacteria/*.fna.gz | |
18 | |
19 | |
20 File Parameters: | |
21 in=<file> Input FNA (fasta) file. | |
22 gff=<file> Input GFF file (optional). | |
23 out=<file> Output FNA file. | |
24 | |
25 Other Parameters: | |
26 types=CDS Types of features to cut. | |
27 invert=false Invert selection: rather outputting the features, | |
28 mask them with Ns in the original sequences. | |
29 attributes= A comma-delimited list of strings. If present, one of | |
30 these strings must be in the gff line attributes. | |
31 bannedattributes= A comma-delimited list of banned strings. | |
32 banpartial=t Ignore lines with 'partial=true' in attributes. | |
33 minlen=1 Ignore lines shorter than this. | |
34 maxlen=2147483647 Ignore lines longer than this. | |
35 renamebytaxid=f Rename sequences with their taxID. Input sequences | |
36 must be named appropriately, e.g. in NCBI format. | |
37 taxmode=accession Valid modes are: | |
38 accession: Sequence names must start with an accession. | |
39 gi: Seqence names must start with gi|number | |
40 taxid: Sequence names must start with tid|number | |
41 header: Best effort for various header formats. | |
42 requirepresent=t Crash if a taxID cannot be found for a sequence. | |
43 oneperfile=f Only output one sequence per file. | |
44 align=f Align ribosomal sequences to consensus (if available); | |
45 discard those with low identity, and flip those | |
46 annotated on the wrong strand. | |
47 maxns=-1 If non-negative, ignore features with more than this many | |
48 undefined bases (Ns or IUPAC symbols). | |
49 maxnfraction=-1.0 If non-negative, ignore features with more than this | |
50 fraction of undefined bases (Ns or IUPAC symbols). | |
51 Should be 0.0 to 1.0. | |
52 " | |
53 } | |
54 | |
55 #This block allows symlinked shellscripts to correctly set classpath. | |
56 pushd . > /dev/null | |
57 DIR="${BASH_SOURCE[0]}" | |
58 while [ -h "$DIR" ]; do | |
59 cd "$(dirname "$DIR")" | |
60 DIR="$(readlink "$(basename "$DIR")")" | |
61 done | |
62 cd "$(dirname "$DIR")" | |
63 DIR="$(pwd)/" | |
64 popd > /dev/null | |
65 | |
66 #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/" | |
67 CP="$DIR""current/" | |
68 | |
69 z="-Xmx200m" | |
70 set=0 | |
71 | |
72 if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then | |
73 usage | |
74 exit | |
75 fi | |
76 | |
77 calcXmx () { | |
78 source "$DIR""/calcmem.sh" | |
79 setEnvironment | |
80 parseXmx "$@" | |
81 } | |
82 calcXmx "$@" | |
83 | |
84 gff() { | |
85 local CMD="java $EA $EOOM $z -cp $CP gff.CutGff $@" | |
86 # echo $CMD >&2 | |
87 eval $CMD | |
88 } | |
89 | |
90 gff "$@" |