Starfish110

easyconfigs/c/Circos/Circos-0.69-8-GCCcore-11.3.0.eb

@@ -0,0 +1,43 @@
+# #
+# This is an easyconfig file for EasyBuild, see https://github.com/easybuilders/easybuild
+#
+# Author: Jonas Demeulemeester
+# The Francis Crick Insitute, London, UK
+# #
+# This file is an EasyBuild reciPY as per https://github.com/easybuilders/easybuild
+
+easyblock = 'Tarball'
+
+name = 'Circos'
+version = '0.69-8'
+
+homepage = 'https://www.circos.ca/'
+description = """Circos is a software package for visualizing data and information.
+ It visualizes data in a circular layout - this makes Circos ideal for exploring
+ relationships between objects or positions."""
+
+toolchain = {'name': 'GCCcore', 'version': '11.3.0'}
+
+source_urls = ['https://%(namelower)s.ca/distribution/']
+sources = [SOURCELOWER_TGZ]
+checksums = ['6946ab442bef6b1e97b28486dc44554cf7acf112654d7cf00b960e7dbc27f288']
+
+builddependencies = [
+    ('binutils', '2.38'),
+]
+dependencies = [
+    ('Perl', '5.34.1'),
+    ('GD', '2.75'),
+]
+
+
+sanity_check_paths = {
+    'files': ['bin/%(namelower)s'],
+    'dirs': ['lib/%(name)s'],
+}
+
+sanity_check_commands = [('perl', '-e "use %(name)s"')]
+
+modextrapaths = {'PERL5LIB': 'lib'}
+
+moduleclass = 'bio'

easyconfigs/e/eggnog-mapper/eggnog-mapper-2.1.12-foss-2022a.eb

@@ -0,0 +1,51 @@
+# Eggnog DB installation instructions:
+# 1. 'export EGGNOG_DATA_DIR=/<storage-location>/eggnog-mapper-data'
+# 2. run 'download_eggnog_data.py'
+# 3. Check the expected DB version with 'emapper.py --version'
+
+easyblock = 'PythonPackage'
+
+name = 'eggnog-mapper'
+version = "2.1.12"
+
+homepage = 'https://github.com/eggnogdb/eggnog-mapper'
+description = """EggNOG-mapper is a tool for fast functional annotation of novel
+sequences. It uses precomputed orthologous groups and phylogenies from the
+eggNOG database (http://eggnog5.embl.de) to transfer functional information from
+fine-grained orthologs only. Common uses of eggNOG-mapper include the annotation
+of novel genomes, transcriptomes or even metagenomic gene catalogs."""
+
+toolchain = {'name': 'foss', 'version': '2022a'}
+
+github_account = 'eggnogdb'
+source_urls = [GITHUB_SOURCE]
+sources = ['%(version)s.tar.gz']
+checksums = []
+dependencies = [
+    ('Python', '3.10.4'),
+    ('Biopython', '1.79'),
+    ('HMMER', '3.3.2'),
+    ('DIAMOND', '2.1.0'),
+    ('prodigal', '2.6.3'),
+    ('wget', '1.21.3'),
+    ('MMseqs2', '14-7e284'),
+    ('XlsxWriter', '3.0.8'),
+]
+
+# strip out (too) strict version requirements for dependencies
+preinstallopts = "sed -i 's/==[0-9.]*//g' setup.cfg && "
+
+sanity_check_paths = {
+    'files': ['bin/create_dbs.py', 'bin/download_eggnog_data.py', 'bin/emapper.py'],
+    'dirs': ['lib/python%(pyshortver)s/site-packages'],
+}
+
+sanity_check_commands = [
+    'download_eggnog_data.py --help',
+    'create_dbs.py --help',
+    'emapper.py --version | grep %(version)s',
+]
+
+options = {'modulename': 'eggnogmapper'}
+
+moduleclass = 'bio'

easyconfigs/m/MetaEuk/MetaEuk-6-a5d39d9-GCC-11.3.0.eb

@@ -0,0 +1,30 @@
+easyblock = 'CMakeMake'
+
+name = 'MetaEuk'
+version = "6-a5d39d9"
+
+homepage = 'https://metaeuk.soedinglab.org'
+description = """MetaEuk is a modular toolkit designed for large-scale gene discovery and annotation in eukaryotic
+ metagenomic contigs."""
+
+toolchain = {'name': 'GCC', 'version': '11.3.0'}
+
+source_urls = ['https://github.com/soedinglab/%(namelower)s/archive']
+sources = ['%(version)s.tar.gz']
+checksums = ['be19c26f5bdb7dcdd7bc48172105afecf19e5a2e5555edb3ba0c4aa0e4aac126']
+
+builddependencies = [('CMake', '3.23.1')]
+
+dependencies = [
+    ('bzip2', '1.0.8'),
+    ('zlib', '1.2.12'),
+]
+
+sanity_check_paths = {
+    'files': ['bin/metaeuk'],
+    'dirs': [],
+}
+
+sanity_check_commands = ["metaeuk --help"]
+
+moduleclass = 'bio'

easyconfigs/s/sourmash/sourmash-4.6.1-foss-2022a.eb

@@ -0,0 +1,58 @@
+# This easyconfig was created by the BEAR Software team at the University of Birmingham.
+easyblock = 'PythonBundle'
+
+name = 'sourmash'
+version = "4.6.1"
+
+homepage = "https://github.com/sourmash-bio/sourmash"
+description = """Quickly search, compare, and analyze genomic and metagenomic data sets. sourmash is
+ a k-mer analysis multitool, and we aim to provide stable, robust programmatic and command-line APIs
+ for a variety of sequence comparisons."""
+
+toolchain = {'name': 'foss', 'version': '2022a'}
+
+builddependencies = [
+    ('Rust', '1.65.0'),
+]
+
+dependencies = [
+    ('Python', '3.10.4'),
+    ('PyYAML', '6.0'),
+    ('SciPy-bundle', '2022.05'),
+    ('matplotlib', '3.5.2'),
+]
+
+buildininstalldir = True
+exts_list = [
+    ('mmh3', '3.0.0', {
+        'checksums': ['d1ec578c09a07d3518ec9be540b87546397fa3455de73c166fcce51eaa5c41c5'],
+    }),
+    ('deprecation', '2.0.6', {
+        'checksums': ['68071e5ae7cd7e9da6c7dffd750922be4825c7c3a6780d29314076009cc39c35'],
+    }),
+    ('bz2file', '0.98', {
+        'checksums': ['64c1f811e31556ba9931953c8ec7b397488726c63e09a4c67004f43bdd28da88'],
+    }),
+    ('screed', '1.0.5', {
+        'checksums': ['ad1b894aac81a8ad32fd587d37acb3fb4e575f6d828da73713038cc180098178'],
+    }),
+    ('cachetools', '4.0.0', {
+        'checksums': ['9a52dd97a85f257f4e4127f15818e71a0c7899f121b34591fcc1173ea79a0198'],
+    }),
+    ('milksnake', '0.1.6', {
+        'checksums': ['0198f8932b4e136c29c0d0d490ff1bac03f82c3a7b2ee6f666e3683b64314fd9'],
+    }),
+    (name, version, {
+        'preinstallopts': "sed -i 's/, orcid=.*/ },/g' pyproject.toml && ",
+        'checksums': ['c8e6712632a4ff4322946a89c4b81e50f7ac06f878e043aba8fd9e1fa013819c'],
+    }),
+]
+
+sanity_check_paths = {
+    'files': ['bin/%(name)s'],
+    'dirs': ['lib/python%(pyshortver)s/site-packages'],
+}
+
+sanity_check_commands = ["%(name)s --help"]
+
+moduleclass = 'bio'

easyconfigs/s/starfish/starfish-1.1.0-foss-2022a.eb

@@ -0,0 +1,73 @@
+# This easyconfig was created by the BEAR Software team at the University of Birmingham.
+easyblock = 'ConfigureMake'
+
+name = 'starfish'
+version = '1.1.0'
+
+homepage = "https://github.com/egluckthaler/starfish"
+description = """starfish is a modular toolkit for giant mobile element annotation. Built primarily for
+ annotating Starship elements in fungal genomes, it can be easily adapted to find any large mobile element (≥6kb)
+ that shares the same basic architecture as a fungal Starship or a bacterial integrative and conjugative element:
+ a "captain" gene with zero or more "cargo" genes downstream of its 3' end. It is particularly well suited
+ for annotating low-copy number elements in a content independent manner.
+"""
+citing = """Gluck-Thaler, E., & Vogan, A. A. (2024).
+ Systematic identification of cargo-carrying genetic elements reveals
+ new dimensions of eukaryotic diversity. Nucleic Acids Research, 2024-06
+"""
+github_account = 'egluckthaler'
+
+toolchain = {'name': 'foss', 'version': '2022a'}
+
+dependencies = [
+    ('Perl', '5.34.1'),
+    ('Boost.MPI', '1.79.0'),
+    ('Cantera', '2.5.1'),
+    ('Circos', '0.69-8'),
+    ('sourmash', '4.6.1'),
+    ('eggnog-mapper', '2.1.12'),
+    ('BEDTools', '2.30.0'),
+    ('SAMtools', '1.16.1'),  # differ from pinned 1.6, but mostly bug-fixes and reliability
+    ('MCL', '14.137'),
+    ('HMMER', '3.3.2'),
+    ('BLAST+', '2.13.0'),  # no major API change compared to pinned 1.12
+    ('minimap2', '2.24'),
+    ('MetaEuk', '6-a5d39d9'),  # excplicit indication of commit, otherwise the exact same version 6
+    ('MAFFT', '7.505', '-with-extensions'),
+    ('MMseqs2', '14-7e284'),
+    ('MUMmer', '4.0.0rc1'),
+]
+source_urls = ['https://github.com/%(github_account)s/%(name)s/archive']
+sources = ['v%(version)s.tar.gz']
+patches = ['%(name)s-%(version)s_updated-version-in-starfish-exe.patch',
+           ('%(name)s-%(version)s_added-utility-script-for-concatenating-annotate-outp.patch', 1),
+           '%(name)s-%(version)s_bug-fix.patch']
+checksums = [
+    {'v1.1.0.tar.gz': '6f734403488d3cc1c2baae45aafdad204d682175556af2721234eab24f9bd49d'},
+    {'starfish-1.1.0_updated-version-in-starfish-exe.patch':
+     'c659b63f9f9cf8ecf8a121ce0ddc33750e3c78464452c367bf9ec145502fca65'},
+    {'starfish-1.1.0_added-utility-script-for-concatenating-annotate-outp.patch':
+     '16a59d1da223a23c03fe0349894d6f230a0be9900e82b7160119aed141810afa'},
+    {'starfish-1.1.0_bug-fix.patch': '49ff8f0c7e390888a332b7bf77eb2af6a96c08cb5bb9040b51253f97533e092a'},
+]
+
+skipsteps = ['configure', 'install']
+
+local_pattern = r's|.*\(boost/.*\.hpp\).*|#include <\1>|'
+local_opts = r' CC=g++ LFLAGS=\"-std=c++11 -I$EBROOTBOOST/include\" '
+
+prebuildopts = "sed -i '5d' build.sh && chmod +x {build.sh,bin/*} && "
+prebuildopts += "sed -i '%s' CNEFinder/qgrams.cc && " % local_pattern
+prebuildopts += 'sed -i "s|Makefile|Makefile %s|" build.sh && ' % local_opts
+prebuildopts += 'PREFIX=%(installdir)s SRC_DIR=%(start_dir)s '
+build_cmd = './build.sh'
+buildopts = [' && chmod +x %(installdir)s/{aux/*,bin/cnef,bin/starfish}']
+
+test_cmd = 'PATH="%(installdir)s/bin:$PATH" bash'
+runtest = 'test.sh'
+sanity_check_paths = {
+    'files': ['bin/cnef'],
+    'dirs': ['aux', 'main', 'lib', 'bin', 'db']
+}
+
+moduleclass = 'bio'

easyconfigs/s/starfish/starfish-1.1.0_updated-version-in-starfish-exe.patch

@@ -0,0 +1,13 @@
+diff --git a/bin/starfish b/bin/starfish
+index 86b3db1..053ed3e 100755
+--- a/bin/starfish
++++ b/bin/starfish
+@@ -66,7 +66,7 @@ $starfishDIR\/db contains fastas and hmms of genes of interest, including YRs
+ }
+
+ # Change software version here
+-my $VERSION = "1.0.1";
++my $VERSION = "1.1.0";
+
+ main: {
+