py-drep and ANIcalculator: new packages (#33467)

* py-drep: new package

* fixed file extension

* added darwin conflict

* py-checkm-genome and py-pysam: bumped version and updated deps (#10)

added checkm and pysam deps

* added dep documentation and fixed style

* changed checkm and pysam back to dev version for upstreaming

* added url and perl run dep

* fixed style

2 files changed, 79 insertions, 0 deletions

diff --git a/var/spack/repos/builtin/packages/anicalculator/package.py b/var/spack/repos/builtin/packages/anicalculator/package.py
new file mode 100644
index 0000000000..7d83bb4596
--- /dev/null
+++ b/var/spack/repos/builtin/packages/anicalculator/package.py
@@ -0,0 +1,35 @@
+# Copyright 2013-2022 Lawrence Livermore National Security, LLC and other
+# Spack Project Developers. See the top-level COPYRIGHT file for details.
+#
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+import os
+
+from spack.package import *
+
+
+class Anicalculator(Package):
+    """This tool will calculate the bidirectional average nucleotide identity
+    (gANI) and Alignment Fraction (AF) between two genomes.
+
+    Note: A manual download is required for ANIcalculator.
+    Spack will search your current directory for the download file.
+    Alternatively, add this file to a mirror so that Spack can find it.
+    For instructions on how to set up a mirror, see
+    https://spack.readthedocs.io/en/latest/mirrors.html"""
+
+    homepage = "https://ani.jgi.doe.gov/html/download.php?"
+    url = "file://{0}/ANIcalculator_v1.tgz".format(os.getcwd())
+    manual_download = True
+
+    version("1", sha256="236596a9a204cbcad162fc66be3506b2530b1f48f4f84d9647ccec3ca7483a43")
+
+    depends_on("perl@5:", type="run")
+
+    conflicts("platform=darwin", msg="ANIcalculator requires Linux")
+
+    def install(self, spec, prefix):
+        mkdirp(prefix.bin)
+        install("ANIcalculator", prefix.bin)
+        install("nsimscan", prefix.bin)
+        install_tree("Log", prefix.bin.Log)
diff --git a/var/spack/repos/builtin/packages/py-drep/package.py b/var/spack/repos/builtin/packages/py-drep/package.py
new file mode 100644
index 0000000000..a7ec0b3d00
--- /dev/null
+++ b/var/spack/repos/builtin/packages/py-drep/package.py
@@ -0,0 +1,44 @@
+# Copyright 2013-2022 Lawrence Livermore National Security, LLC and other
+# Spack Project Developers. See the top-level COPYRIGHT file for details.
+#
+# SPDX-License-Identifier: (Apache-2.0 OR MIT)
+
+
+from spack.package import *
+
+
+class PyDrep(PythonPackage):
+    """dRep is a python program for rapidly comparing large numbers of genomes.
+    dRep can also "de-replicate" a genome set by identifying groups of highly
+    similar genomes and choosing the best representative genome for each
+    genome set."""
+
+    homepage = "https://github.com/MrOlm/drep"
+    pypi = "drep/drep-3.4.0.tar.gz"
+
+    version("3.4.0", sha256="a6533eb585122c1ee66ae622b1b97450a3e1e493a3c3c1d55e79a580d5c46d40")
+
+    variant("fastani", default=True, description="Enable fastANI support")
+    variant("py-checkm-genome", default=True, description="Enable CheckM support")
+    variant("anicalculator", default=True, description="Enable gDNA support")
+    variant("prodigal", default=True, description="Used with both checkM and gANI")
+
+    depends_on("py-setuptools", type="build")
+    depends_on("py-numpy", type=("build", "run"))
+    depends_on("py-pandas", type=("build", "run"))
+    depends_on("py-seaborn", type=("build", "run"))
+    depends_on("py-matplotlib", type=("build", "run"))
+    depends_on("py-biopython", type=("build", "run"))
+    depends_on("py-scikit-learn", type=("build", "run"))
+    depends_on("py-tqdm", type=("build", "run"))
+    depends_on("py-pytest", type=("build", "run"))
+    # Non-python dependencies
+    # https://drep.readthedocs.io/en/latest/installation.html#dependencies
+    # essential dependencies
+    depends_on("mash@1.1.1:", type="run")
+    depends_on("mummer@3.23:", type="run")
+    # recommended dependencies
+    depends_on("fastani", type="run", when="+fastani")
+    depends_on("py-checkm-genome@1.0.7:", type="run", when="+py-checkm-genome")
+    depends_on("anicalculator@1:", type="run", when="+anicalculator")
+    depends_on("prodigal@2.6.3:", type="run", when="+prodigal")