BioArchLinux/Packages
2
0
Fork 0
mirror of https://github.com/BioArchLinux/Packages.git synced 2025-03-10 12:02:42 +00:00
Code Issues Projects Releases Packages Wiki Activity

add cdhit

Browse source
This commit is contained in:
Kuoi 2022-04-18 02:31:19 +01:00
parent 90be2ace5d
commit 40bb265d3d
4 changed files with 487 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

35
BioArchLinux/cdhit/PKGBUILD Normal file
View file

@ -0,0 +1,35 @@
# Maintainer: Christian Krause ("wookietreiber") <kizkizzbangbang@googlemail.com>
pkgname=cdhit
pkgver=4.8.1
#_pkgver="v$pkgver-2019-0228"
pkgrel=1
pkgdesc="clustering DNA/protein sequence database at high identity with tolerance"
arch=('i686' 'x86_64')
url="http://weizhongli-lab.org/cd-hit/"
license=('GPL2')
depends=('perl' 'openmpi')
source=("https://github.com/weizhongli/cdhit/archive/refs/tags/V${pkgver}.tar.gz"
"perl-shebangs.patch::https://patch-diff.githubusercontent.com/raw/weizhongli/cdhit/pull/25.patch")
sha512sums=('28f350c67079f000b4102126a29d2eed110c636fb32a8a53699b60e6f3447348ea3838fe87a4dd952895d62491298394a314254e91036f6a23b1956b1e237a64'
'f9a918ebe2865d84c31fbd5ab4b0b2f58bf3faee879cb304e1fa44969e01db3786f12b3699a712094f9ee261efd306188aff548b1a88f57daae5d02205551236')
prepare() {
cd $srcdir/cdhit-$pkgver
patch -Np1 -i $srcdir/perl-shebangs.patch
}
build() {
cd $srcdir/cdhit-$pkgver
make openmp=yes
}
package() {
cd $srcdir/cdhit-$pkgver
for file in cd-hit cd-hit-est cd-hit-2d cd-hit-est-2d cd-hit-div cd-hit-454 *.pl ; do
install -Dm755 $file $pkgdir/usr/bin/$(basename $file .pl)
done
}

10
BioArchLinux/cdhit/lilac.py Normal file
View file

@ -0,0 +1,10 @@
#!/usr/bin/env python3
from lilaclib import *
def pre_build():
update_pkgver_and_pkgrel(_G.newver.lstrip('v'))
run_cmd(['updpkgsums'])
def post_build():
git_add_files('PKGBUILD')
git_commit()

9
BioArchLinux/cdhit/lilac.yaml Normal file
View file

@ -0,0 +1,9 @@
build_prefix: extra-x86_64
maintainers:
- github: starsareintherose
email: starsareintherose@outlook.com
update_on:
- source: github
github: weizhongli/cdhit
use_max_tag: true
prefix: 'V'

433
BioArchLinux/cdhit/perl-shebangs.patch Normal file
View file

@ -0,0 +1,433 @@
From eae2a63c25fcb95e6fc1e6e062215ad1e8b24345 Mon Sep 17 00:00:00 2001
From: Christian Krause <kizkizzbangbang@googlemail.com>
Date: Thu, 16 Jul 2015 12:33:10 +0200
Subject: [PATCH] use more portable /usr/bin/env perl for scripts
This is useful, e.g. if your perl is not installed in /usr/bin or you
want to give a specific perl precendence over the one installed in
/usr/bin. Wherever there was `perl -w` there is now `use warnings;`.
---
cd-hit-2d-para.pl | 3 ++-
cd-hit-auxtools/cd-hit-dup-PE-out.pl | 2 +-
cd-hit-div.pl | 2 +-
cd-hit-para.pl | 3 ++-
clstr2tree.pl | 2 +-
clstr2txt.pl | 2 +-
clstr2xml.pl | 2 +-
clstr_cut.pl | 2 +-
clstr_merge.pl | 2 +-
clstr_merge_noorder.pl | 2 +-
clstr_quality_eval.pl | 2 +-
clstr_quality_eval_by_link.pl | 2 +-
clstr_reduce.pl | 2 +-
clstr_renumber.pl | 2 +-
clstr_rep.pl | 2 +-
clstr_reps_faa_rev.pl | 2 +-
clstr_rev.pl | 2 +-
clstr_select.pl | 2 +-
clstr_select_rep.pl | 2 +-
clstr_size_histogram.pl | 2 +-
clstr_size_stat.pl | 2 +-
clstr_sort_by.pl | 2 +-
clstr_sort_prot_by.pl | 2 +-
clstr_sql_tbl.pl | 2 +-
clstr_sql_tbl_sort.pl | 2 +-
make_multi_seq.pl | 2 +-
plot_2d.pl | 2 +-
plot_len1.pl | 2 +-
psi-cd-hit/cd-hit-div.pl | 2 +-
psi-cd-hit/clstr_select_rep.pl | 2 +-
psi-cd-hit/clstr_select_seq.pl | 2 +-
psi-cd-hit/fetch_fasta_by_ids.pl | 2 +-
psi-cd-hit/fetch_fasta_exclude_ids.pl | 2 +-
psi-cd-hit/psi-2d.pl | 2 +-
psi-cd-hit/psi-cd-hit-local.pl | 3 ++-
psi-cd-hit/psi-cd-hit.pl | 4 +++-
36 files changed, 41 insertions(+), 36 deletions(-)
diff --git a/cd-hit-2d-para.pl b/cd-hit-2d-para.pl
index 3cab955..9aa2d8a 100755
--- a/cd-hit-2d-para.pl
+++ b/cd-hit-2d-para.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl -w
+#!/usr/bin/env perl
# =============================================================================
# CD-HIT
# http://cd-hit.org/
@@ -11,6 +11,7 @@
# Email liwz@sdsc.edu
# =============================================================================
+use warnings;
use strict;
no strict "refs";
diff --git a/cd-hit-auxtools/cd-hit-dup-PE-out.pl b/cd-hit-auxtools/cd-hit-dup-PE-out.pl
index bfe5af3..f035229 100755
--- a/cd-hit-auxtools/cd-hit-dup-PE-out.pl
+++ b/cd-hit-auxtools/cd-hit-dup-PE-out.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $script_name = $0;
my $script_dir = $0;
diff --git a/cd-hit-div.pl b/cd-hit-div.pl
index e349394..db8d942 100755
--- a/cd-hit-div.pl
+++ b/cd-hit-div.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#not like cd-hit-div, this script do not sort input
#or throw away seq
diff --git a/cd-hit-para.pl b/cd-hit-para.pl
index 33f1a1b..db62e38 100755
--- a/cd-hit-para.pl
+++ b/cd-hit-para.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl -w
+#!/usr/bin/env perl
# =============================================================================
# CD-HIT
# http://cd-hit.org/
@@ -11,6 +11,7 @@
# Email liwz@sdsc.edu
# =============================================================================
+use warnings;
use strict;
no strict "refs";
diff --git a/clstr2tree.pl b/clstr2tree.pl
index 73fd37a..56d9fe2 100755
--- a/clstr2tree.pl
+++ b/clstr2tree.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
$clstr = shift;
$fr = shift; # for nr80.clstr $fr = 0.8
diff --git a/clstr2txt.pl b/clstr2txt.pl
index 902b083..127537e 100755
--- a/clstr2txt.pl
+++ b/clstr2txt.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $no = 0;
my $clstr_no = "";
diff --git a/clstr2xml.pl b/clstr2xml.pl
index 10d828c..ba8264a 100755
--- a/clstr2xml.pl
+++ b/clstr2xml.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#usage: clstr_xml.pl [-len|-size] level1.clstr [level2.clstr level3.clstr ...]
#purpose: to create xml file from cd-hit or hierarchical cd-hit(h-cd-hit) results
diff --git a/clstr_cut.pl b/clstr_cut.pl
index 498f180..ae0264c 100755
--- a/clstr_cut.pl
+++ b/clstr_cut.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#keep only top $no proteins in cluster
diff --git a/clstr_merge.pl b/clstr_merge.pl
index 3fe108e..9186777 100755
--- a/clstr_merge.pl
+++ b/clstr_merge.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
# the order of clusters need to be identical
my ($master_clstr, @clstr) = @ARGV;
diff --git a/clstr_merge_noorder.pl b/clstr_merge_noorder.pl
index f8acdfc..0852aee 100755
--- a/clstr_merge_noorder.pl
+++ b/clstr_merge_noorder.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
# order of clusters don't need to be the same
# but then I have to read everything into memory
diff --git a/clstr_quality_eval.pl b/clstr_quality_eval.pl
index 62f2a3d..060ab01 100755
--- a/clstr_quality_eval.pl
+++ b/clstr_quality_eval.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
## calculate the sensitivity and specificity of clusters
## if the input fasta file has pre-defined classification term
diff --git a/clstr_quality_eval_by_link.pl b/clstr_quality_eval_by_link.pl
index 8fba8df..140c05c 100755
--- a/clstr_quality_eval_by_link.pl
+++ b/clstr_quality_eval_by_link.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
## calculate the sensitivity and specificity of clusters
## if the input fasta file has pre-defined classification term
diff --git a/clstr_reduce.pl b/clstr_reduce.pl
index 990f4ad..3621025 100755
--- a/clstr_reduce.pl
+++ b/clstr_reduce.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
$file90 = shift;
diff --git a/clstr_renumber.pl b/clstr_renumber.pl
index b542304..c66088d 100755
--- a/clstr_renumber.pl
+++ b/clstr_renumber.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
$no = 0;
while($ll=<>){
if ($ll =~ /^>Cluster (\d+)/) {
diff --git a/clstr_rep.pl b/clstr_rep.pl
index 0ebeb88..84b86b3 100755
--- a/clstr_rep.pl
+++ b/clstr_rep.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
$rep = "";
$no = 0;
diff --git a/clstr_reps_faa_rev.pl b/clstr_reps_faa_rev.pl
index 80a4a8a..3574b2b 100755
--- a/clstr_reps_faa_rev.pl
+++ b/clstr_reps_faa_rev.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
# output single fasta file
# for each cluster output at least $cutoff seqs
diff --git a/clstr_rev.pl b/clstr_rev.pl
index d7efdcc..71134e2 100755
--- a/clstr_rev.pl
+++ b/clstr_rev.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
# if nr90 from nr100 and
# nr80 from nr90, so I have nr90.clstr and nr80.clstr
# but, in nr80.clstr, some gi numbers whose from nr100 are there
diff --git a/clstr_select.pl b/clstr_select.pl
index 1b168d9..dc70147 100755
--- a/clstr_select.pl
+++ b/clstr_select.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#my $by = shift;
my $min;
diff --git a/clstr_select_rep.pl b/clstr_select_rep.pl
index 80c7b7e..f7c38f4 100755
--- a/clstr_select_rep.pl
+++ b/clstr_select_rep.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#my $by = shift;
my $min;
diff --git a/clstr_size_histogram.pl b/clstr_size_histogram.pl
index 01ecb63..b726e46 100755
--- a/clstr_size_histogram.pl
+++ b/clstr_size_histogram.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
if(@ARGV==0){
print "Usage:\n\tclstr_size_histogram.pl [-bin N] clstr_file\n";
diff --git a/clstr_size_stat.pl b/clstr_size_stat.pl
index b234b06..ecda7db 100755
--- a/clstr_size_stat.pl
+++ b/clstr_size_stat.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
if(@ARGV==0){
print "Usage:\n\tclstr_size_stat.pl clstr_file\n";
diff --git a/clstr_sort_by.pl b/clstr_sort_by.pl
index 82e9cf8..adb12d8 100755
--- a/clstr_sort_by.pl
+++ b/clstr_sort_by.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $sort_by_what = shift;
$sort_by_what = "no" unless $sort_by_what;
diff --git a/clstr_sort_prot_by.pl b/clstr_sort_prot_by.pl
index 64f19e2..0832b99 100755
--- a/clstr_sort_prot_by.pl
+++ b/clstr_sort_prot_by.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $sort_by = shift;
$sort_by = "len" unless ($sort_by);
diff --git a/clstr_sql_tbl.pl b/clstr_sql_tbl.pl
index f2dba07..68bfd7d 100755
--- a/clstr_sql_tbl.pl
+++ b/clstr_sql_tbl.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
if(@ARGV==0){
print "Usage:\n\tclstr_sql_tbl.pl clstr_file tbl_file\n";
diff --git a/clstr_sql_tbl_sort.pl b/clstr_sql_tbl_sort.pl
index 67d60a8..3dfe9c4 100755
--- a/clstr_sql_tbl_sort.pl
+++ b/clstr_sql_tbl_sort.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
if(@ARGV==0){
print "Usage:\n\tclstr_sql_tbl_sort.pl table_file level\n";
diff --git a/make_multi_seq.pl b/make_multi_seq.pl
index 7b05636..3678654 100755
--- a/make_multi_seq.pl
+++ b/make_multi_seq.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#note you have to use "-d 0" in the cd-hit run
#note you better to use "-g 1" in the cd-hit run
diff --git a/plot_2d.pl b/plot_2d.pl
index 418a5cf..91342ca 100755
--- a/plot_2d.pl
+++ b/plot_2d.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
use Image::Magick;
diff --git a/plot_len1.pl b/plot_len1.pl
index efcdfe0..e8be6e3 100755
--- a/plot_len1.pl
+++ b/plot_len1.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
$file90 = shift;
$segs = shift;
diff --git a/psi-cd-hit/cd-hit-div.pl b/psi-cd-hit/cd-hit-div.pl
index e349394..db8d942 100755
--- a/psi-cd-hit/cd-hit-div.pl
+++ b/psi-cd-hit/cd-hit-div.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
#not like cd-hit-div, this script do not sort input
#or throw away seq
diff --git a/psi-cd-hit/clstr_select_rep.pl b/psi-cd-hit/clstr_select_rep.pl
index b465586..63db0ce 100755
--- a/psi-cd-hit/clstr_select_rep.pl
+++ b/psi-cd-hit/clstr_select_rep.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $by = shift;
my $min;
diff --git a/psi-cd-hit/clstr_select_seq.pl b/psi-cd-hit/clstr_select_seq.pl
index fd7bb8b..598b0e9 100755
--- a/psi-cd-hit/clstr_select_seq.pl
+++ b/psi-cd-hit/clstr_select_seq.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $by = shift;
my $min;
diff --git a/psi-cd-hit/fetch_fasta_by_ids.pl b/psi-cd-hit/fetch_fasta_by_ids.pl
index bfdbb26..9c17504 100755
--- a/psi-cd-hit/fetch_fasta_by_ids.pl
+++ b/psi-cd-hit/fetch_fasta_by_ids.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my ($gi_file, $seq_file) = @ARGV;
diff --git a/psi-cd-hit/fetch_fasta_exclude_ids.pl b/psi-cd-hit/fetch_fasta_exclude_ids.pl
index 90e237e..13d061a 100755
--- a/psi-cd-hit/fetch_fasta_exclude_ids.pl
+++ b/psi-cd-hit/fetch_fasta_exclude_ids.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my ($gi_file, $seq_file) = @ARGV;
diff --git a/psi-cd-hit/psi-2d.pl b/psi-cd-hit/psi-2d.pl
index ab3f655..f3884a3 100755
--- a/psi-cd-hit/psi-2d.pl
+++ b/psi-cd-hit/psi-2d.pl
@@ -1,4 +1,4 @@
-#!/usr/bin/perl
+#!/usr/bin/env perl
my $script_name = $0;
diff --git a/psi-cd-hit/psi-cd-hit-local.pl b/psi-cd-hit/psi-cd-hit-local.pl
index a77c7f7..e7866c3 100755
--- a/psi-cd-hit/psi-cd-hit-local.pl
+++ b/psi-cd-hit/psi-cd-hit-local.pl
@@ -1,7 +1,8 @@
-#!/usr/bin/perl -w
+#!/usr/bin/env perl
################################################################################
######### PSI-cd-hit written by Weizhong Li at http://cd-hit.org
################################################################################
+use warnings;
our $pid = $$;
our $db_in = ""; ###################
our $db_out = ""; # input / output
diff --git a/psi-cd-hit/psi-cd-hit.pl b/psi-cd-hit/psi-cd-hit.pl
index af99e52..35aaeda 100755
--- a/psi-cd-hit/psi-cd-hit.pl
+++ b/psi-cd-hit/psi-cd-hit.pl
@@ -1,8 +1,10 @@
-#!/usr/bin/perl -w
+#!/usr/bin/env perl
################################################################################
######### PSI-cd-hit written by Weizhong Li at http://cd-hit.org
################################################################################
+use warnings;
+
our $script_name = $0;
our $script_dir = $0;
$script_dir =~ s/[^\/]+$//;