From 7a2564a7b19badd827f523a45cb83984d0eabc25 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Petr=20Kr=C3=A1l?= Date: Fri, 12 Jan 2024 14:53:06 +0100 Subject: [PATCH] adding easyconfigs: PASA-2.5.3-foss-2022b.eb, pblat-2.5.1-foss-2022b.eb --- .../p/PASA/PASA-2.5.3-foss-2022b.eb | 43 +++++++++++++++++++ .../p/pblat/pblat-2.5.1-foss-2022b.eb | 41 ++++++++++++++++++ 2 files changed, 84 insertions(+) create mode 100644 easybuild/easyconfigs/p/PASA/PASA-2.5.3-foss-2022b.eb create mode 100644 easybuild/easyconfigs/p/pblat/pblat-2.5.1-foss-2022b.eb diff --git a/easybuild/easyconfigs/p/PASA/PASA-2.5.3-foss-2022b.eb b/easybuild/easyconfigs/p/PASA/PASA-2.5.3-foss-2022b.eb new file mode 100644 index 00000000000..3dad7ad19d0 --- /dev/null +++ b/easybuild/easyconfigs/p/PASA/PASA-2.5.3-foss-2022b.eb @@ -0,0 +1,43 @@ +easyblock = 'ConfigureMake' + +name = 'PASA' +version = '2.5.3' + +homepage = 'https://github.com/PASApipeline/PASApipeline' +description = """PASA, acronym for Program to Assemble Spliced Alignments (and pronounced 'pass-uh'), + is a eukaryotic genome annotation tool that exploits spliced alignments of expressed transcript + sequences to automatically model gene structures, and to maintain gene structure annotation consistent + with the most recently available experimental sequence data. PASA also identifies and classifies all + splicing variations supported by the transcript alignments.""" + +toolchain = {'name': 'foss', 'version': '2022b'} + +source_urls = ['https://github.com/PASApipeline/PASApipeline/archive/'] +sources = ['%(namelower)s-v%(version)s.tar.gz'] +checksums = ['9b2f6a301b73fd8c713af0977cf6e97f3d928988d6b79715ebe81e19b51152eb'] + +dependencies = [ + ('SQLite', '3.39.4'), + ('GMAP-GSNAP', '2023-04-20'), + ('pblat', '2.5.1'), + ('minimap2', '2.26'), + ('FASTA', '36.3.8i'), +] + +buildininstalldir = True + +skipsteps = ['configure', 'install'] + +unpack_options = '--strip-components=1' + +local_bins = ['%(namelower)s', 'cdbfasta', 'cdbyank', 'cln2qual', 'mdust', + 'psx', 'seqclean', 'seqclean.psx', 'slclust', 'trimpoly'] + +sanity_check_paths = { + 'files': ['bin/%s' % x for x in local_bins], + 'dirs': [] +} + +sanity_check_commands = ['command -v %(namelower)s'] + +moduleclass = 'bio' diff --git a/easybuild/easyconfigs/p/pblat/pblat-2.5.1-foss-2022b.eb b/easybuild/easyconfigs/p/pblat/pblat-2.5.1-foss-2022b.eb new file mode 100644 index 00000000000..1fee4320100 --- /dev/null +++ b/easybuild/easyconfigs/p/pblat/pblat-2.5.1-foss-2022b.eb @@ -0,0 +1,41 @@ +easyblock = 'MakeCp' + +name = 'pblat' +version = '2.5.1' + +homepage = 'https://github.com/icebert/pblat' +description = """When the query file format is fasta, you can specify many threads to process it. + It can reduce run time linearly, and use almost equal memory as the original blat program. + This is useful when you blat a big query file to a huge reference like human whole genome sequence.""" + +toolchain = {'name': 'foss', 'version': '2022b'} + +github_account = 'icebert' +source_urls = [GITHUB_SOURCE] +sources = ['%(version)s.tar.gz'] +checksums = ['e85a4d752b8e159502d529f0f9e47579851a6b466b6c2f1f4d49f598642bc615'] + +dependencies = [ + ('HTSlib', '1.17'), + ('zlib', '1.2.12'), + ('OpenSSL', '1.1', '', SYSTEM), +] + +# use HTSlib dependency provided through EasyBuild +prebuildopts = "sed -i '5s/.\/htslib/$\{EBROOTHTSLIB\}\/include\/htslib/' Makefile && " +prebuildopts += "sed -i '40s/ htslib\/libhts.a//' Makefile && " +prebuildopts += "sed -i '41s/htslib\/libhts.a/-lhts -lcurl/' Makefile && " +prebuildopts += "sed -i -e '/htslib\/libhts.a:/,+2d' Makefile && " + +files_to_copy = [ + (['%(name)s'], 'bin'), +] + +sanity_check_paths = { + 'files': ['bin/%(name)s'], + 'dirs': [] +} + +sanity_check_commands = ["command -v %(name)s"] + +moduleclass = 'bio'