Merge pull request #10459 from Darkless012/20200423110746_new_pr_arti…

…c-ncov201920200413 {bio}[foss/2018b] artic-ncov2019 v2020.04.13, rampart v1.2.0rc3, gotree v0.4.0, ... w/ Python 3.6.6
easybuilders · Apr 29, 2020 · 141b445 · 141b445
2 parents 863c376 + e62ddf8
commit 141b445
Show file tree

Hide file tree

Showing 11 changed files with 522 additions and 2 deletions.
diff --git a/easybuild/easyconfigs/a/artic-ncov2019/artic-ncov2019-2020.04.13-foss-2018b-Python-3.6.6.eb b/easybuild/easyconfigs/a/artic-ncov2019/artic-ncov2019-2020.04.13-foss-2018b-Python-3.6.6.eb
@@ -0,0 +1,143 @@
+# Author: Pavel Grochal (INUITS)
+# License: GPLv2
+
+easyblock = 'PythonBundle'
+
+name = 'artic-ncov2019'
+local_commit = '4a7461c3cc9865860d69223ba8360df13a248f13'
+version = '2020.04.13'
+
+versionsuffix = '-Python-%(pyver)s'
+
+homepage = "https://github.com/artic-network/artic-ncov2019"
+description = """Initial implementation of an ARTIC bioinformatics platform 
+for nanopore sequencing of nCoV2019 novel coronavirus."""
+
+toolchain = {'name': 'foss', 'version': '2018b'}
+
+dependencies = [
+    ('Python', '3.6.6'),  # pandas,
+    ('Biopython', '1.72', versionsuffix),
+    ('Pysam', '0.15.1', versionsuffix),
+    ('BWA', '0.7.17'),
+    ('Eigen', '3.3.4', '', True),
+    ('minimap2', '2.13'),
+    ('SAMtools', '1.9'),
+    ('MUSCLE', '3.8.31'),
+    ('ETE', '3.1.1', versionsuffix),
+    ('MAFFT', '7.427', '-with-extensions'),
+    ('IQ-TREE', '1.6.12'),
+    ('snakemake', '5.2.4', versionsuffix),
+    ('Longshot', '0.4.1'),
+    ('medaka', '0.11.4', versionsuffix),
+    ('python-parasail', '1.1.16', versionsuffix),
+    ('PhyML', '3.3.20190321'),
+    ('nodejs', '12.16.1'),
+    ('goalign', '0.3.2', '', True),
+    ('gotree', '0.4.0', '', True),
+    ('rampart', '1.2.0rc3', versionsuffix),
+    ('libdeflate', '1.5'),
+    ('nanopolish', '0.13.1', versionsuffix),
+    ('seqtk', '1.3'),
+    ('BCFtools', '1.9'),
+]
+
+use_pip = True
+sanity_pip_check = True
+
+exts_default_options = {'source_urls': [PYPI_SOURCE]}
+
+exts_list = [
+    ('zipp', '1.0.0', {
+        'checksums': ['d38fbe01bbf7a3593a32bc35a9c4453c32bc42b98c377f9bff7e9f8da157786c'],
+    }),
+    ('pluggy', '0.13.1', {
+        'checksums': ['15b2acde666561e1298d71b523007ed7364de07029219b604cf808bfa1c765b0'],
+    }),
+    ('py', '1.8.1', {
+        'checksums': ['5e27081401262157467ad6e7f851b7aa402c5852dbcb3dae06768434de5752aa'],
+    }),
+    ('wcwidth', '0.1.9', {
+        'checksums': ['ee73862862a156bf77ff92b09034fc4825dd3af9cf81bc5b360668d425f3c5f1'],
+    }),
+    ('attrs', '19.3.0', {
+        'modulename': 'attr',
+        'checksums': ['f7b7ce16570fe9965acd6d30101a28f62fb4a7f9e926b3bbc9b61f8b04247e72'],
+    }),
+    ('importlib-metadata', '1.6.0', {
+        'modulename': 'importlib_metadata',
+        'source_tmpl': 'importlib_metadata-%(version)s.tar.gz',
+        'checksums': ['34513a8a0c4962bc66d35b359558fd8a5e10cd472d37aec5f66858addef32c1e'],
+    }),
+    ('more-itertools', '8.2.0', {
+        'modulename': 'more_itertools',
+        'checksums': ['b1ddb932186d8a6ac451e1d95844b382f55e12686d51ca0c68b6f61f2ab7a507'],
+    }),
+    ('packaging', '14.5', {
+        'checksums': ['363f9193daa14085b8dfeeb2bf64227bcf1dc85c02ae2a5c6018b01f77e46491'],
+    }),
+    ('args', '0.1.0', {
+        'checksums': ['a785b8d837625e9b61c39108532d95b85274acd679693b71ebb5156848fcf814'],
+    }),
+    ('pytest', '5.4.1', {
+        'checksums': ['84dde37075b8805f3d1f392cc47e38a0e59518fb46a431cfdaf7cf1ce805f970'],
+    }),
+    ('tqdm', '4.45.0', {
+        'checksums': ['00339634a22c10a7a22476ee946bbde2dbe48d042ded784e4d88e0236eca5d81'],
+    }),
+    ('fieldbioinformatics', '1.1.0-rc2', {
+        'modulename': False,
+        'source_tmpl': '%(version)s.tar.gz',
+        'source_urls': ['https://github.com/artic-network/fieldbioinformatics/archive'],
+        'checksums': ['7083f67b1188e8f9b55f8bd4f7a46853e9c74ae7dde324b1fc8e792a85e58073'],
+    }),
+    # This is not upstream version, but artic tweaked one, which is exactly required.
+    ('Porechop', '0.3.2pre', {
+        'source_tmpl': 'v%(version)s.tar.gz',
+        'source_urls': ['https://github.com/artic-network/Porechop/archive'],
+        'checksums': ['85980d6f37d38a44c66182e7b39bad487211ccfd8cb820c866ceed7ef7a15523'],
+    }),
+    ('binlorry', '1.3.1', {
+        'source_tmpl': 'v%(version)s.tar.gz',
+        'source_urls': ['https://github.com/rambaut/binlorry/archive'],
+        'checksums': ['001b74cad497b7253b821ceaac8c0b829b2787396a896fc2d3940a704a149b48'],
+    }),
+    ('clint', '0.5.1', {
+        'checksums': ['05224c32b1075563d0b16d0015faaf9da43aa214e4a2140e51f08789e7a4c5aa'],
+    }),
+    ('datrie', '0.8.2', {
+        'checksums': ['525b08f638d5cf6115df6ccd818e5a01298cd230b2dac91c8ff2e6499d18765d'],
+    }),
+    ('PyVCF', '0.6.8', {
+        'modulename': 'vcf',
+        'checksums': ['e9d872513d179d229ab61da47a33f42726e9613784d1cb2bac3f8e2642f6f9d9'],
+    }),
+    ('ont-fast5-api', '3.1.1', {
+        'modulename': 'ont_fast5_api',
+        'checksums': ['ce5a955c5e90a393f040fb36fc461382339fc0b9cd63e3969b9763127dc2b0d3'],
+    }),
+]
+
+components = [
+    (name, version, {
+        'easyblock': 'Tarball',
+        'source_urls': ['https://github.com/artic-network/artic-ncov2019/archive/'],
+        'sources': [{
+            'download_filename': '%s.tar.gz' % local_commit,
+            'filename': SOURCE_TAR_GZ,
+        }],
+        'checksums': ['26bc96742e291795d4a7c1154336715d98168d8ce3524ad7adfea0b5562eb34d'],
+    }),
+]
+local_artic_bins = [
+    'artic', 'artic_fasta_header', 'artic_make_depth_mask', 'artic_mask', 'artic_vcf_filter', 'artic_vcf_merge'
+]
+sanity_check_paths = {
+    'files': ['bin/%s' % f for f in local_artic_bins],
+    'dirs': ['lib/python%(pyshortver)s/site-packages'],
+}
+sanity_check_commands = [
+    'artic -v',
+]
+
+moduleclass = 'bio'
diff --git a/easybuild/easyconfigs/i/IQ-TREE/IQ-TREE-1.6.12-foss-2018b.eb b/easybuild/easyconfigs/i/IQ-TREE/IQ-TREE-1.6.12-foss-2018b.eb
@@ -0,0 +1,34 @@
+easyblock = 'CMakeMake'
+
+name = 'IQ-TREE'
+version = '1.6.12'
+
+# HTTPS is not working
+homepage = 'http://www.iqtree.org/'
+description = """Efficient phylogenomic software by maximum likelihood"""
+
+toolchain = {'name': 'foss', 'version': '2018b'}
+# Including 'usempi' will take precedence and override IQTREE_FLAGS and produces only 'iqtree-mpi' binary
+
+github_account = 'Cibiv'
+source_urls = [GITHUB_SOURCE]
+sources = ['v%(version)s.tar.gz']
+checksums = ['9614092de7a157de82c9cc402b19cc8bfa0cb0ffc93b91817875c2b4bb46a284']
+
+builddependencies = [
+    ('CMake', '3.12.1'),
+    ('Eigen', '3.3.7', '', True),
+]
+dependencies = [('zlib', '1.2.11')]
+
+configopts = [
+    '-DIQTREE_FLAGS=omp',
+    '-DIQTREE_FLAGS=mpi',
+]
+
+sanity_check_paths = {
+    'files': ['bin/iqtree', 'bin/iqtree-mpi'],
+    'dirs': [],
+}
+
+moduleclass = 'bio'
diff --git a/easybuild/easyconfigs/l/Longshot/Longshot-0.4.1-GCC-7.3.0-2.30.eb b/easybuild/easyconfigs/l/Longshot/Longshot-0.4.1-GCC-7.3.0-2.30.eb
@@ -0,0 +1,40 @@
+# This easyconfig was created by Simon Branford of the BEAR Software team at the University of Birmingham.
+easyblock = 'Binary'
+
+name = 'Longshot'
+version = '0.4.1'
+
+homepage = 'https://github.com/pjedge/longshot'
+description = """Longshot is a variant calling tool for diploid genomes using long error prone reads such as Pacific
+ Biosciences (PacBio) SMRT and Oxford Nanopore Technologies (ONT). It takes as input an aligned BAM file and outputs
+ a phased VCF file with variants and haplotype information. It can also output haplotype-separated BAM files that can
+ be used for downstream analysis. Currently, it only calls single nucleotide variants (SNVs)."""
+
+toolchain = {'name': 'GCC', 'version': '7.3.0-2.30'}
+
+source_urls = ['https://github.com/pjedge/longshot/archive']
+sources = ['v%(version)s.tar.gz']
+checksums = ['062529eb47fafc2ef4a1a12ea30a565a0df922b310b6fc5705a1605ce4f495f3']
+
+builddependencies = [
+    ('binutils', '2.30'),
+    ('Rust', '1.42.0'),
+    ('Clang', '7.0.1'),
+    ('zlib', '1.2.11'),
+    ('XZ', '5.2.4'),
+]
+
+extract_sources = True
+
+# https://github.com/rust-bio/rust-htslib/issues/112
+install_cmd = "export LIBCLANG_PATH=${EBROOTCLANG}/lib && "
+install_cmd += "cargo install --root %(installdir)s --path ."
+
+sanity_check_paths = {
+    'files': ['bin/%(namelower)s'],
+    'dirs': [],
+}
+
+sanity_check_commands = ["%(namelower)s --help"]
+
+moduleclass = 'bio'
diff --git a/easybuild/easyconfigs/l/libdeflate/libdeflate-1.5-GCCcore-7.3.0.eb b/easybuild/easyconfigs/l/libdeflate/libdeflate-1.5-GCCcore-7.3.0.eb
@@ -0,0 +1,39 @@
+# Author: Pavel Grochal (INUITS)
+# License: GPLv2
+
+easyblock = 'ConfigureMake'
+
+name = 'libdeflate'
+version = '1.5'
+
+homepage = 'https://github.com/ebiggers/libdeflate'
+description = """Generic PCI access library."""
+
+toolchain = {'name': 'GCCcore', 'version': '7.3.0'}
+
+# https://github.com/ebiggers/libdeflate
+github_account = 'ebiggers'
+source_urls = [GITHUB_SOURCE]
+sources = ['v%(version)s.tar.gz']
+checksums = ['45b1b2332f443b705c59d06a49be009827291d2c487b076dc8ec2791eff4c711']
+
+builddependencies = [('binutils', '2.30')]
+
+skipsteps = ['configure']
+buildopts = 'PREFIX="%(installdir)s" CFLAGS="$CFLAGS" CPPFLAGS="$CPPFLAGS" LDFLAGS="$LDFLAGS"'
+installopts = 'PREFIX="%(installdir)s" CFLAGS="$CFLAGS" CPPFLAGS="$CPPFLAGS" LDFLAGS="$LDFLAGS"'
+
+sanity_check_paths = {
+    'files': [
+        'bin/%(name)s-gunzip', 'bin/%(name)s-gzip',
+        'lib/%(name)s.a', 'lib/%%(name)s.%s' % SHLIB_EXT,
+        'include/%(name)s.h',
+    ],
+    'dirs': [],
+}
+sanity_check_commands = [
+    '%(name)s-gzip -h',
+    '%(name)s-gunzip -h',
+]
+
+moduleclass = 'system'
diff --git a/easybuild/easyconfigs/m/MAFFT/MAFFT-7.427-foss-2018b-with-extensions.eb b/easybuild/easyconfigs/m/MAFFT/MAFFT-7.427-foss-2018b-with-extensions.eb
@@ -0,0 +1,38 @@
+# This file is an EasyBuild reciPY as per https://github.com/easybuilders/easybuild
+# Author: Pablo Escobar Lopez
+# Swiss Institute of Bioinformatics
+# Biozentrum - University of Basel
+# 7.305 modified by:
+# Adam Huffman
+# The Francis Crick Institute
+
+easyblock = 'ConfigureMake'
+
+name = 'MAFFT'
+version = '7.427'
+versionsuffix = '-with-extensions'
+
+homepage = 'https://mafft.cbrc.jp/alignment/software/source.html'
+description = """MAFFT is a multiple sequence alignment program 
+ for unix-like operating systems.  It offers a range of multiple
+ alignment methods, L-INS-i (accurate; for alignment of <∼200 sequences), 
+ FFT-NS-2 (fast; for alignment of <∼10,000 sequences), etc."""
+
+toolchain = {'name': 'foss', 'version': '2018b'}
+
+source_urls = ['https://mafft.cbrc.jp/alignment/software/']
+sources = ['%(namelower)s-%(version)s%(versionsuffix)s-src.tgz']
+checksums = ['068abcbc20965cbfa4e14c138cbfbcd0d311874ac2fdde384a580ac774f40e26']
+
+skipsteps = ['configure']
+start_dir = 'core'
+installopts = 'PREFIX=%(installdir)s'
+
+modextrapaths = {'MAFFT_BINARIES': 'libexec/mafft'}
+
+sanity_check_paths = {
+    'files': ['bin/mafft'],
+    'dirs': [],
+}
+
+moduleclass = 'bio'
diff --git a/easybuild/easyconfigs/m/MUSCLE/MUSCLE-3.8.31-GCC-7.3.0-2.30.eb b/easybuild/easyconfigs/m/MUSCLE/MUSCLE-3.8.31-GCC-7.3.0-2.30.eb
@@ -0,0 +1,30 @@
+easyblock = 'MakeCp'
+
+name = 'MUSCLE'
+version = "3.8.31"
+
+homepage = 'https://drive5.com/muscle/'
+description = """MUSCLE is one of the best-performing multiple alignment programs
+ according to published benchmark tests, with accuracy and speed that are consistently
+ better than CLUSTALW. MUSCLE can align hundreds of sequences in seconds. Most users
+ learn everything they need to know about MUSCLE in a few minutes-only a handful of
+ command-line options are needed to perform common alignment tasks."""
+
+toolchain = {'name': 'GCC', 'version': '7.3.0-2.30'}
+
+source_urls = ['http://www.drive5.com/muscle/downloads%(version)s/']
+sources = ['%(namelower)s%(version)s_src.tar.gz']
+patches = ['%(name)s-%(version)s_fix-mk-hardcoding.patch']
+checksums = [
+    '43c5966a82133bd7da5921e8142f2f592c2b5f53d802f0527a2801783af809ad',  # muscle3.8.31_src.tar.gz
+    'e108d1cc2d394236f839facc1304ff96c0e11f7fdd6d2444761808ec860cd58a',  # MUSCLE-3.8.31_fix-mk-hardcoding.patch
+]
+
+files_to_copy = [(["muscle"], 'bin')]
+
+sanity_check_paths = {
+    'files': ["bin/%(namelower)s"],
+    'dirs': [],
+}
+
+moduleclass = 'bio'
diff --git a/easybuild/easyconfigs/n/nanopolish/nanopolish-0.13.1-foss-2018b-Python-3.6.6.eb b/easybuild/easyconfigs/n/nanopolish/nanopolish-0.13.1-foss-2018b-Python-3.6.6.eb
@@ -0,0 +1,53 @@
+easyblock = 'MakeCp'
+
+name = 'nanopolish'
+version = '0.13.1'
+versionsuffix = '-Python-%(pyver)s'
+
+homepage = 'https://github.com/jts/nanopolish'
+description = "Software package for signal-level analysis of Oxford Nanopore sequencing data."
+
+toolchain = {'name': 'foss', 'version': '2018b'}
+
+source_urls = [
+    'https://github.com/jts/nanopolish/archive/',
+    'https://github.com/mateidavid/fast5/archive/',
+]
+sources = [
+    {'download_filename': 'v%(version)s.tar.gz', 'filename': SOURCE_TAR_GZ},
+    {'download_filename': 'v0.6.5.tar.gz', 'filename': 'fast5-v0.6.5.tar.gz'},
+]
+checksums = [
+    '0cf0a6aea3d3b0dd81fa8877618b12bb45e2a39b2ec2fbfc6bc0df77084a7fac',  # nanopolish-0.13.1.tar.gz
+    'f8b1ce2c07adb56b4f13337ef008e124255f86cdb7e74e4233afa8dca878ee1a',  # fast5-v0.6.5.tar.gz
+]
+
+builddependencies = [('Eigen', '3.3.7', '', True)]
+
+dependencies = [
+    ('zlib', '1.2.11'),
+    ('HDF5', '1.10.2'),
+    ('HTSlib', '1.9'),
+    ('Python', '3.6.6'),
+    ('Biopython', '1.72', versionsuffix),
+    ('Pysam', '0.15.1', versionsuffix),
+    ('minimap2', '2.13'),
+]
+
+prebuildopts = "rmdir fast5 && ln -s %(builddir)s/fast5-*/ fast5 && "
+buildopts = "HDF5=noinstall EIGEN=noinstall HTS=noinstall MINIMAP2=noinstall"
+
+runtest = 'test ' + buildopts
+
+files_to_copy = [(['nanopolish'], 'bin'), 'scripts']
+
+postinstallcmds = ["chmod a+rx %(installdir)s/scripts/*"]
+
+sanity_check_paths = {
+    'files': ['bin/nanopolish'],
+    'dirs': ['scripts'],
+}
+
+modextrapaths = {'PATH': 'scripts'}
+
+moduleclass = 'bio'