diff --git a/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6-foss-2022a.eb b/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6-foss-2022a.eb index 1e4df1d96356..f6a9bc03101b 100644 --- a/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6-foss-2022a.eb +++ b/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6-foss-2022a.eb @@ -12,7 +12,11 @@ toolchain = {'name': 'foss', 'version': '2022a'} source_urls = ['https://github.com/Gaius-Augustus/BRAKER/archive/'] sources = ['v%(version)s.tar.gz'] -checksums = ['eef3c4037364472988a010322cbd79b5171158f9c016f4383809adade4866c06'] +patches = ['BRAKER-%(version)s_fix-incorrect-ids.patch'] +checksums = [ + {'v2.1.6.tar.gz': 'eef3c4037364472988a010322cbd79b5171158f9c016f4383809adade4866c06'}, + {'BRAKER-2.1.6_fix-incorrect-ids.patch': '2b219de070d109637a2660a456a1f9ced48c58197385e3b3924ae90c84b41d41'}, +] dependencies = [ ('Perl', '5.34.1'), @@ -25,6 +29,8 @@ dependencies = [ ('Exonerate', '2.4.0'), ('BLAST+', '2.13.0'), ('Biopython', '1.79'), + ('DIAMOND', '2.1.0'), + ('CDBtools', '0.99'), ] fix_perl_shebang_for = ['scripts/*.pl'] diff --git a/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6_fix-incorrect-ids.patch b/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6_fix-incorrect-ids.patch new file mode 100644 index 000000000000..3c9df7a402df --- /dev/null +++ b/easybuild/easyconfigs/b/BRAKER/BRAKER-2.1.6_fix-incorrect-ids.patch @@ -0,0 +1,44 @@ +From f38630c1cad3e11b525f84d517c7949cb4c2d7eb Mon Sep 17 00:00:00 2001 +From: Katharina Hoff +Date: Mon, 19 Apr 2021 16:34:57 +0200 +Subject: [PATCH] fixing part of the issue + https://github.com/Gaius-Augustus/BRAKER/issues/354 where gene and transcript + line have incorrect ids + +--- + scripts/merge_transcript_sets.pl | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +diff --git a/scripts/merge_transcript_sets.pl b/scripts/merge_transcript_sets.pl +index 04f6c3e..5cfd6c0 100755 +--- a/scripts/merge_transcript_sets.pl ++++ b/scripts/merge_transcript_sets.pl +@@ -83,14 +83,15 @@ + my $txid; + if($line =~ m/transcript_id/){ + $line =~ m/transcript_id "([^"]+)";/; ++ + $txid = $1; + push(@{$txid_to_elements{$txid}}, $line); + foreach(@store_for_txid){ +- push(@{$txid_to_elements{$txid}}, $_) ++ push(@{$txid_to_elements{$txid}}, $_); + } + @store_for_txid = (); + }else{ +- $line =~ s/\t([\t]+)$/\tfile_${file_counter}_$1/; ++ $line =~ s/\t([^\t]+)$/\tfile_${file_counter}_$1/; + push(@store_for_txid, $line); + } + # currently, UTR features are ignored +@@ -111,9 +112,8 @@ + # always keep the first occuring transcript structure, only add from other gene sets if it has not been in the set, yet + # this might discard alternative UTR splicing isoforms at present + while (my ($key, $value) = each (%txid_to_struct_local)){ +- #print "key is $key and value is $value\n"; ++ print "key is $key and value is $value\n"; + if(not(defined($uniq_struct_to_txid{$value}))){ +- #print "adding transcript\n"; + $uniq_struct_to_txid{$value} = $key; + } + } diff --git a/easybuild/easyconfigs/c/CDBtools/CDBtools-0.99-GCC-11.3.0.eb b/easybuild/easyconfigs/c/CDBtools/CDBtools-0.99-GCC-11.3.0.eb new file mode 100644 index 000000000000..d2dca1af47d2 --- /dev/null +++ b/easybuild/easyconfigs/c/CDBtools/CDBtools-0.99-GCC-11.3.0.eb @@ -0,0 +1,29 @@ +easyblock = 'MakeCp' + +name = 'CDBtools' +version = '0.99' + +homepage = 'http://compbio.dfci.harvard.edu/tgi' +description = "CDB (Constant DataBase) indexing and retrieval tools for FASTA files" + +toolchain = {'name': 'GCC', 'version': '11.3.0'} + +source_urls = ['ftp://occams.dfci.harvard.edu/pub/bio/tgi/software/cdbfasta'] +sources = [{'download_filename': 'cdbfasta.tar.gz', 'filename': SOURCE_TAR_GZ}] +checksums = ['68767e8b2fb9de5a6d68ee16df73293f65e02f05cf2f747a9dd6b8854766722c'] + +buildopts = 'CC="$CXX" DBGFLAGS="$CXXFLAGS"' + +files_to_copy = [(['cdbfasta', 'cdbyank'], 'bin')] + +sanity_check_paths = { + 'files': ['bin/cdbfasta', 'bin/cdbyank'], + 'dirs': [], +} + +sanity_check_commands = [ + "cdbfasta -v", + "cdbyank -v", +] + +moduleclass = 'bio'