Merge branch 'easybuilders:develop' into 20241128144208_new_pr_jax0435

easybuild/easyconfigs/a/anndata/anndata-0.11.1-foss-2023b.eb

@@ -0,0 +1,45 @@
+easyblock = 'PythonBundle'
+
+name = 'anndata'
+version = '0.11.1'
+
+homepage = 'https://github.com/scverse/anndata'
+description = """anndata is a Python package for handling annotated data matrices in memory and on disk,
+ positioned between pandas and xarray"""
+
+toolchain = {'name': 'foss', 'version': '2023b'}
+
+builddependencies = [
+    ('hatchling', '1.18.0'),
+]
+
+dependencies = [
+    ('Python', '3.11.5'),
+    ('Python-bundle-PyPI', '2023.10'),
+    ('SciPy-bundle', '2023.11'),
+    ('h5py', '3.11.0'),
+]
+
+use_pip = True
+sanity_pip_check = True
+
+exts_list = [
+    ('array_api_compat', '1.9.1', {
+        'checksums': ['17bab828c93c79a5bb8b867145b71fcb889686607c5672b060aef437e0359ea8'],
+    }),
+    ('natsort', '8.4.0', {
+        'checksums': ['45312c4a0e5507593da193dedd04abb1469253b601ecaf63445ad80f0a1ea581'],
+    }),
+    (name, version, {
+        'checksums': ['36bff9a85276fc5f1b9fd01f15aff9aa49408129985f42e0fca4e2c5b7fa909f'],
+    }),
+]
+
+sanity_check_paths = {
+    'files': ['bin/natsort'],
+    'dirs': ['lib/python%(pyshortver)s/site-packages'],
+}
+
+sanity_check_commands = ["natsort --help"]
+
+moduleclass = 'bio'

easybuild/easyconfigs/b/BEDTools/BEDTools-2.31.1-GCC-13.2.0.eb

@@ -0,0 +1,46 @@
+# Author: Maxime Schmitt, University of Luxembourg
+# Author: Adam Huffman, The Francis Crick Institute
+#
+# Based on the work of: Pablo Escobar Lopez
+# Swiss Institute of Bioinformatics (SIB)
+# Biozentrum - University of Basel
+
+easyblock = 'MakeCp'
+
+name = 'BEDTools'
+version = '2.31.1'
+
+homepage = 'https://bedtools.readthedocs.io/'
+description = """BEDTools: a powerful toolset for genome arithmetic.
+The BEDTools utilities allow one to address common genomics tasks such as finding feature overlaps and
+computing coverage.
+The utilities are largely based on four widely-used file formats: BED, GFF/GTF, VCF, and SAM/BAM."""
+
+toolchain = {'name': 'GCC', 'version': '13.2.0'}
+
+source_urls = ['https://github.com/arq5x/bedtools2/archive/refs/tags/']
+sources = ['v%(version)s.tar.gz']
+checksums = ['79a1ba318d309f4e74bfa74258b73ef578dccb1045e270998d7fe9da9f43a50e']
+
+builddependencies = [
+    ('Python', '3.11.5'),
+]
+dependencies = [
+    ('XZ', '5.4.4'),
+    ('zlib', '1.2.13'),
+    ('bzip2', '1.0.8'),
+    ('BamTools', '2.5.2'),
+]
+
+buildopts = 'CXX="$CXX"'
+
+files_to_copy = ['bin', 'docs', 'data', 'genomes', 'scripts', 'test']
+
+sanity_check_paths = {
+    'files': ['bin/%s' % x for x in ['bedtools', 'pairToBed', 'mergeBed', 'bedToBam', 'fastaFromBed']],
+    'dirs': files_to_copy,
+}
+
+sanity_check_commands = ['%(namelower)s --help']
+
+moduleclass = 'bio'

easybuild/easyconfigs/c/CellRanger/CellRanger-9.0.0.eb

@@ -0,0 +1,31 @@
+# The STAR binary included in this version has been vectorized with AVX
+# hence it is not recommended for systems that do not support it.
+
+easyblock = 'Tarball'
+
+name = 'CellRanger'
+version = '9.0.0'
+
+homepage = 'https://support.10xgenomics.com/single-cell-gene-expression/software/pipelines/latest/what-is-cell-ranger'
+description = """Cell Ranger is a set of analysis pipelines that process Chromium
+ single-cell RNA-seq output to align reads, generate gene-cell matrices and perform
+ clustering and gene expression analysis."""
+
+toolchain = SYSTEM
+
+download_instructions = """
+Download manually from https://support.10xgenomics.com/single-cell-gene-expression/software/downloads/latest
+"""
+sources = [SOURCELOWER_TAR_GZ]
+checksums = ['d57e574630bc0871299ba0e3e3b9a770b572cd35a819c52bfd58403ccd72035d']
+
+keepsymlinks = True
+
+sanity_check_paths = {
+    'files': ['bin/cellranger'],
+    'dirs': ['bin/rna', 'bin/tenkit'],
+}
+
+sanity_check_commands = ['cellranger testrun --id=tiny']
+
+moduleclass = 'bio'

easybuild/easyconfigs/c/Cluster-Buster/Cluster-Buster-20240927-GCC-12.3.0.eb

@@ -0,0 +1,26 @@
+easyblock = 'MakeCp'
+
+name = 'Cluster-Buster'
+version = '20240927'
+local_commit = '06fee8b'
+
+homepage = 'https://github.com/weng-lab/cluster-buster'
+description = """Cluster-Buster is a program for finding interesting functional regions,
+ such as transcriptional enhancers, in DNA sequences."""
+
+toolchain = {'name': 'GCC', 'version': '12.3.0'}
+
+source_urls = ['https://github.com/weng-lab/cluster-buster/archive/']
+sources = [{'download_filename': '%s.tar.gz' % local_commit, 'filename': SOURCELOWER_TAR_GZ}]
+checksums = ['a77583ae1f38cc08af551932e5f6b35185fde78db330270bb2eb32ecb4d926cc']
+
+files_to_copy = [(['cbust'], 'bin')]
+
+sanity_check_paths = {
+    'files': ['bin/cbust'],
+    'dirs': [],
+}
+
+sanity_check_commands = ['cbust -h']
+
+moduleclass = 'bio'

easybuild/easyconfigs/h/HeFFTe/HeFFTe-2.4.1-foss-2023b.eb

@@ -0,0 +1,33 @@
+easyblock = 'CMakeMake'
+
+name = 'HeFFTe'
+version = '2.4.1'
+
+homepage = 'https://icl.utk.edu/fft'
+description = "Highly Efficient FFT for Exascale (HeFFTe) library"
+
+toolchain = {'name': 'foss', 'version': '2023b'}
+
+source_urls = ['https://github.com/icl-utk-edu/heffte/archive/']
+sources = ['v%(version)s.tar.gz']
+checksums = ['de2cf26df5d61baac7841525db3f393cb007f79612ac7534fd4757f154ba3e6c']
+
+builddependencies = [
+    ('CMake', '3.27.6'),
+]
+
+build_shared_libs = True
+
+configopts = "-DHeffte_ENABLE_FFTW=ON -DFFTW_ROOT=$EBROOTFFTW -DHeffte_ENABLE_CUDA=OFF -DHeffte_ENABLE_MKL=OFF"
+
+# allow oversubscription of MPI ranks to cores, tests are hardcoded to use up to 12 MPI ranks
+pretestopts = "export OMPI_MCA_rmaps_base_oversubscribe=true && "
+
+runtest = 'test'
+
+sanity_check_paths = {
+    'files': ['lib/libheffte.%s' % SHLIB_EXT],
+    'dirs': ['include', 'lib/cmake/Heffte', 'share/heffte/examples'],
+}
+
+moduleclass = 'lib'

easybuild/easyconfigs/m/MATES/MATES-0.1.5-20241121-foss-2023b.eb

@@ -0,0 +1,53 @@
+easyblock = 'PythonBundle'
+
+name = 'MATES'
+version = '0.1.5-20241121'
+local_commit = '3846ad5'
+
+homepage = 'https://github.com/mcgilldinglab/MATES'
+description = "A Deep Learning-Based Model for Quantifying Transposable Elements in Single-Cell Sequencing Data."
+
+toolchain = {'name': 'foss', 'version': '2023b'}
+
+dependencies = [
+    ('Python', '3.11.5'),
+    ('Python-bundle-PyPI', '2023.10'),
+    ('SciPy-bundle', '2023.11'),
+    ('matplotlib', '3.8.2'),
+    ('anndata', '0.11.1'),
+    ('pybedtools', '0.10.0'),
+    ('PyTorch', '2.1.2'),
+    ('Pysam', '0.22.0'),
+    ('tqdm', '4.66.2'),
+    ('SAMtools', '1.19.2'),
+]
+
+use_pip = True
+sanity_pip_check = True
+
+exts_list = [
+    ('sorted_nearest', '0.0.39', {
+        'checksums': ['16a51d5db87ae226b47ace43c176bb672477a1b7ba8052ea9291a6356c9c69b1'],
+    }),
+    ('ncls', '0.0.68', {
+        'checksums': ['81aaa5abb123bb21797ed2f8ef921e20222db14a3ecbc61ccf447532f2b7ba93'],
+    }),
+    ('pyranges', '0.0.129', {
+        'checksums': ['bee83b4fad0062be9586668c6b0fc4270d5e761951975e018202993680071fb3'],
+    }),
+    (name, version, {
+        'modulename': 'MATES',
+        # unpin exact versions of dependencies
+        'preinstallopts': """sed -i 's/==.*//g' requirements.txt && sed -i 's/==.*/\",/g' setup.py && """,
+        'source_urls': ['https://github.com/mcgilldinglab/MATES/archive'],
+        'sources': [{'download_filename': '%s.tar.gz' % local_commit, 'filename': SOURCE_TAR_GZ}],
+        'checksums': ['40fbb87dd72ca4c9e5347f2e984f9c0a0caa817d4eee692476be71e733e76f61'],
+    }),
+]
+
+sanity_check_commands = [
+    "python -c 'from MATES import bam_processor, data_processor, MATES_model'",
+    "python -c 'from MATES import TE_quantifier, TE_quantifier_LongRead, TE_quantifier_Intronic'",
+]
+
+moduleclass = 'bio'

easybuild/easyconfigs/m/makedepend/makedepend-1.0.9-GCCcore-13.3.0.eb

@@ -0,0 +1,26 @@
+easyblock = 'ConfigureMake'
+
+name = 'makedepend'
+version = '1.0.9'
+
+homepage = 'https://linux.die.net/man/1/makedepend'
+description = "The makedepend package contains a C-preprocessor like utility to determine build-time dependencies."
+
+toolchain = {'name': 'GCCcore', 'version': '13.3.0'}
+
+source_urls = [XORG_UTIL_SOURCE]
+sources = [SOURCE_TAR_GZ]
+checksums = ['bc94ffda6cd4671603a69c39dbe8f96b317707b9185b2aaa3b54b5d134b41884']
+
+builddependencies = [
+    ('binutils', '2.42'),
+    ('xproto', '7.0.31'),
+    ('xorg-macros', '1.20.1'),
+]
+
+sanity_check_paths = {
+    'files': ['bin/makedepend'],
+    'dirs': [],
+}
+
+moduleclass = 'devel'

easybuild/easyconfigs/n/NECI/NECI-20230620-foss-2023a.eb

@@ -0,0 +1,52 @@
+easyblock = 'CMakeMakeCp'
+name = 'NECI'
+version = '20230620'
+_commit = '558e88c5ae6c30d0505a9badbc69111be0866ba1'
+
+homepage = 'https://github.com/ghb24/NECI_STABLE'
+description = """Standalone NECI codebase designed for FCIQMC and other stochastic quantum
+chemistry methods."""
+
+toolchain = {'name': 'foss', 'version': '2023a'}
+toolchainopts = {'usempi': True}
+
+sources = [{
+    'git_config': {
+        'url': 'https://github.com/ghb24',
+        'repo_name': 'NECI_STABLE',
+        'recursive': True,
+        'commit': _commit,
+    },
+    'filename': SOURCE_TAR_GZ,
+}]
+patches = ['NECI-20230620_segfault.patch']
+checksums = [
+    None,
+    'f0b5f62e115a1e07d6b90bc66ee9957a5f5d686bef65beba9c2be4bd8f29f0e4',
+]
+
+builddependencies = [
+    ('CMake', '3.26.3'),
+    ('Python', '3.11.3'),
+    ('SciPy-bundle', '2023.07'),
+]
+
+dependencies = [
+    ('HDF5', '1.14.0'),
+]
+
+# enable support for HDF5
+configopts = "-DENABLE_HDF5=ON"
+
+test_cmd = 'ctest'
+runtest = '-j'
+
+files_to_copy = ['bin', 'lib', (['modules'], 'include')]
+
+_binaries = ['dneci', 'kdneci', 'kmneci', 'kneci', 'mneci', 'neci']
+sanity_check_paths = {
+    'files': ['bin/%s' % x for x in _binaries] + ['lib/lib%s.a' % x for x in _binaries],
+    'dirs': ['include'],
+}
+
+moduleclass = 'chem'

easybuild/easyconfigs/n/NECI/NECI-20230620_segfault.patch

@@ -0,0 +1,21 @@
+Fixes SEGFAULT error in tests.
+See https://github.com/ghb24/NECI_STABLE/issues/18
+Author: Petr Král (INUITS)
+--- unit_tests/back_spawn_excit_gen/test_back_spawn_excit_gen.F90.orig	2023-06-20 10:15:17.000000000 +0200
++++ unit_tests/back_spawn_excit_gen/test_back_spawn_excit_gen.F90	2024-11-21 14:58:46.602604509 +0100
+@@ -64,6 +64,7 @@
+         nmaxy = 2
+         nmaxz = 2
+         allocate(KPointToBasisFn(-nmaxx:nmaxx, -nmaxy:nmaxy, -nmaxz:nmaxz, 2))
++        KPointToBasisFn = -1
+         tOrbECutoff = .false.
+
+         allocate(projedet(nel,1)); projedet(:,1) = [1,2]
+@@ -403,6 +404,7 @@
+         tOrbECutoff = .false.
+         niftot = 1
+         allocate(KPointToBasisFn(-nmaxx:nmaxx, -nmaxy:nmaxy, -nmaxz:nmaxz, 2))
++        KPointToBasisFn = -1
+
+         t_back_spawn_flex = .true.
+         occ_virt_level = 0

easybuild/easyconfigs/n/Nextflow/Nextflow-24.10.2.eb

@@ -0,0 +1,36 @@
+easyblock = 'Binary'
+
+name = 'Nextflow'
+version = '24.10.2'
+
+homepage = 'https://www.nextflow.io/'
+description = """Nextflow is a reactive workflow framework and a programming DSL
+ that eases writing computational pipelines with complex data"""
+
+toolchain = SYSTEM
+
+source_urls = ['https://github.com/nextflow-io/nextflow/releases/download/v%(version)s/']
+sources = ['nextflow-%(version)s-dist']
+checksums = ['972bb4f4bcd30bb474c29c247ccf79289bbcd444f799f0307f61123e6b0f7475']
+
+dependencies = [('Java', '21')]
+
+install_cmds = [
+    "mkdir -p %(installdir)s/bin",
+    "cp %(builddir)s/nextflow-%(version)s-dist %(installdir)s/bin",
+    "cd %(installdir)s/bin && ln -s nextflow-%(version)s-dist nextflow",
+    "cd %(installdir)s/bin && chmod +x %(installdir)s/bin/nextflow-%(version)s-dist",
+]
+
+sanity_check_paths = {
+    'files': ['bin/nextflow-%(version)s-dist', 'bin/nextflow'],
+    'dirs': []
+}
+
+sanity_check_commands = [
+    "nextflow -v",
+    "nextflow help",
+    "nextflow info",
+]
+
+moduleclass = 'tools'