Merge pull request #196 from rhysnewell/dev

release v0.9.0
rhysnewell · Mar 12, 2024 · 14c7092 · 14c7092
2 parents fafa03e + 7195d25
commit 14c7092
Show file tree

Hide file tree

Showing 27 changed files with 910 additions and 354 deletions.
diff --git a/CITATION.cff b/CITATION.cff
@@ -20,5 +20,6 @@ authors:
     given-names: Ben J.
     orcid: https://orcid.org/0000-0003-0670-7480
 title: "Aviary: Hybrid assembly and genome recovery from metagenomes with Aviary"
-version: 0.8.2
-date-released: 2023-11-05
+version: 0.8.3
+doi: 10.5281/zenodo.10158087
+date-released: 2023-11-20
diff --git a/README.md b/README.md
@@ -1,3 +1,11 @@
+[![install with bioconda](https://img.shields.io/badge/install%20with-bioconda-brightgreen.svg?style=flat)](http://bioconda.github.io/recipes/aviary/README.html)
+![](https://anaconda.org/bioconda/aviary/badges/license.svg)
+![](https://anaconda.org/bioconda/aviary/badges/version.svg)
+![](https://anaconda.org/bioconda/aviary/badges/latest_release_relative_date.svg)
+![](https://anaconda.org/bioconda/aviary/badges/platforms.svg)
+[![DOI](https://zenodo.org/badge/271448699.svg)](https://zenodo.org/doi/10.5281/zenodo.10158086)
+
+
 ![](docs/_include/images/aviary_logo.png)
 
 # Aviary
@@ -57,7 +65,12 @@ conda env create -n aviary -f aviary.yml
 conda activate aviary
 pip install -e .
 ```
+The `aviary` executable can then be run from any directory. Since the code in
+this directory is then used for running, any updates made there will be
+immediately available. We recommend this mode for developing and debugging
+aviary.
 
+## Checking installation
 Whatever option you choose, running `aviary --help` should return the following
 output:
 
@@ -86,22 +99,6 @@ Utility modules:
 
 ```
 
-Upon first running aviary you will be prompted to input the location for where you would like
-your conda environments to be stored, the GTDB release installed on your system, the location of your
-EnrichM database, and the location of your BUSCO database. These locations will be stored as environment
-variables, but for aviary to be able to use those environment variables you will have to either source your .bashrc
-or reactivate your conda environment depending on whether you installed aviary within a conda environment or not:
-
-```
-conda deactivate; conda activate aviary
-
-OR
-
-source ~/.bashrc
-```
-
-These environment variables can be reset using `aviary configure`
-
 ## Databases
 
 Aviary uses programs which require access to locally stored databases. 
@@ -111,7 +108,7 @@ The **required** databases are as follows:
 * [GTDB](https://gtdb.ecogenomic.org/downloads)
 * [EggNog](https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.8#setup)
 * [CheckM2](https://github.com/chklovski/CheckM2)
-
+* [SingleM](https://wwood.github.io/singlem/)
 
 ### Installing databases
 
@@ -121,7 +118,7 @@ ask you to set these environment variables upon first running and if they are no
 the `aviary configure` subcommand to reset the environment variables:
 
 ```commandline
-aviary configure -o logs/ --eggnog-db-path /shared/db/eggnog/ --gtdb-path /shared/db/gtdb/ --checkm2-db-path /shared/db/checkm2db/ --download
+aviary configure -o logs/ --eggnog-db-path /shared/db/eggnog/ --gtdb-path /shared/db/gtdb/ --checkm2-db-path /shared/db/checkm2db/ --singlem-metapackage-path /shared/db/singlem/ --download
 ```
 
 This command will check if the databases exist at those given locations, if they don't then aviary will download and change
@@ -141,6 +138,7 @@ These environment variables can also be configured manually, just set the follow
 ```
 export GTDBTK_DATA_PATH=/path/to/gtdb/gtdb_release207/db/ # https://gtdb.ecogenomic.org/downloads
 export EGGNOG_DATA_DIR=/path/to/eggnog-mapper/2.1.8/ # https://github.com/eggnogdb/eggnog-mapper/wiki/eggNOG-mapper-v2.1.5-to-v2.1.8#setup
+export SINGLEM_METAPACKAGE_PATH=/path/to/singlem_metapackage.smpkg/
 export CHECKM2DB=/path/to/checkm2db/
 export CONDA_ENV_PATH=/path/to/conda/envs/
 ```

diff --git a/aviary/__init__.py b/aviary/__init__.py
@@ -1 +1 @@
-__version__ = "0.8.3"
+__version__ = "0.9.0"
diff --git a/aviary/aviary.py b/aviary/aviary.py
@@ -100,6 +100,17 @@ def str2bool(v):
     else:
         raise argparse.ArgumentTypeError('Boolean value expected.')
 
+def add_workflow_arg(parser, default, help=None):
+    if help is None:
+        help = 'Main workflow to run. This is the snakemake target rule to run.'
+    parser.add_argument(
+        '-w', '--workflow',
+        help=help,
+        dest='workflow',
+        nargs="+",
+        default=default,
+    )
+
 def main():
     if len(sys.argv) == 1 or sys.argv[1] == '-h' or sys.argv[1] == '--help':
         phelp()
@@ -138,21 +149,14 @@ def main():
 
     base_group.add_argument(
         '-t', '--max-threads', '--max_threads',
-        help='Maximum number of threads given to any particular process',
+        help='Maximum number of threads given to any particular process. If max_threads > n_cores then n_cores will be bumped up to max_threads. Useful if you want more fine grain control over the number of threads used by each process.',
         dest='max_threads',
         default=8,
     )
 
-    base_group.add_argument(
-        '-p', '--pplacer-threads', '--pplacer_threads',
-        help=argparse.SUPPRESS,
-        dest='pplacer_threads',
-        default=8,
-    )
-
     base_group.add_argument(
         '-n', '--n-cores', '--n_cores',
-        help='Maximum number of cores available for use. Must be >= to max_threads',
+        help='Maximum number of cores available for use. Setting to multiples of max_threads will allow for multiple processes to be run in parallel.',
         dest='n_cores',
         default=16,
     )
@@ -266,11 +270,11 @@ def main():
 
     base_group.add_argument(
         '--download', '--download',
-        help='Downloads the required GTDB, EggNOG, & CheckM2 databases if required',
-        type=str2bool,
-        nargs='?',
-        const=True,
+        help='Downloads the requested GTDB, EggNOG, SingleM, & CheckM2 databases',
         dest='download',
+        default=[],
+        nargs="*",
+        choices=["gtdb", "eggnog", "singlem", "checkm2"]
     )
 
     base_group.add_argument(
@@ -594,23 +598,65 @@ def main():
         default=3
     )
 
+    binning_group.add_argument(
+        '--extra-binners', '--extra_binners', '--extra-binner', '--extra_binner',
+        help='Optional list of extra binning algorithms to run. Can be any combination of: \n'
+             'maxbin, maxbin2, concoct \n'
+             'These binners are skipped by default as they can have long runtimes \n'
+             'N.B. specifying "maxbin" and "maxbin2" are equivalent \n',
+        dest='extra_binners',
+        nargs='*',
+        choices=["maxbin", "maxbin2", "concoct"]
+    )
+
     binning_group.add_argument(
         '--skip-binners', '--skip_binners', '--skip_binner', '--skip-binner',
         help='Optional list of binning algorithms to skip. Can be any combination of: \n'
-             'rosella, semibin, metabat1, metabat2, metabat, vamb, concoct, maxbin2, maxbin \n'
-             'Capitals will be auto-corrected. N.B. specifying "metabat" will skip both \n'
-             'MetaBAT1 and MetaBAT2.',
+             'rosella, semibin, metabat1, metabat2, metabat, vamb \n'
+             'N.B. specifying "metabat" will skip both MetaBAT1 and MetaBAT2. \n',
         dest='skip_binners',
-        nargs='*'
-        # default=["maxbin2"]
+        nargs='*',
+        choices=["rosella", "semibin", "metabat1", "metabat2", "metabat", "vamb"]
+    )
+
+    binning_group.add_argument(
+        '--binning-only', '--binning_only',
+        help='Only run up to the binning stage. Do not run SingleM, GTDB-tk, or CoverM',
+        type=str2bool,
+        nargs='?',
+        const=True,
+        dest='binning_only',
+        default=False,
     )
 
     binning_group.add_argument(
         '--skip-abundances', '--skip_abundances',
         help='Skip CoverM post-binning abundance calculations.',
         dest='skip_abundances',
+        type=str2bool,
+        nargs='?',
+        const=True,
+        default=False,
+    )
+
+    binning_group.add_argument(
+        '--skip-taxonomy', '--skip_taxonomy',
+        help='Skip GTDB-tk post-binning taxonomy assignment.',
+        dest='skip_taxonomy',
+        type=str2bool,
+        nargs='?',
+        const=True,
+        default=False,
+    )
+
+    binning_group.add_argument(
+        '--skip-singlem', '--skip_singlem',
+        help='Skip SingleM post-binning recovery assessment.',
+        dest='skip_singlem',
+        type=str2bool,
+        nargs='?',
+        const=True,
         default=False,
-        action="store_true",
     )
 
     ####################################################################
@@ -839,13 +885,7 @@ def main():
 
 
 
-    assemble_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['complete_assembly_with_qc'],
-    )
+    add_workflow_arg(assemble_options, ['complete_assembly_with_qc'])
 
     ##########################  ~ RECOVER ~   ###########################
 
@@ -869,13 +909,7 @@ def main():
         required=False,
     )
 
-    recover_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['recover_mags'],
-    )
+    add_workflow_arg(recover_options, ['recover_mags'])
 
     recover_options.add_argument(
         '--perform-strain-analysis', '--perform_strain_analysis',
@@ -909,13 +943,7 @@ def main():
         required=False,
     )
 
-    annotate_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['annotate'],
-    )
+    add_workflow_arg(annotate_options, ['annotate'])
 
     ##########################  ~ diversity ~   ###########################
 
@@ -940,13 +968,7 @@ def main():
         required=False,
     )
 
-    diversity_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['lorikeet'],
-    )
+    add_workflow_arg(diversity_options, ['lorikeet'])
 
     diversity_options.add_argument(
         '--perform-strain-analysis', '--perform_strain_analysis',
@@ -982,13 +1004,7 @@ def main():
         required=True,
     )
 
-    cluster_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['complete_cluster'],
-    )
+    add_workflow_arg(cluster_options, ['complete_cluster'])
 
     ##########################  ~ VIRAL ~   ###########################
 
@@ -1004,13 +1020,7 @@ def main():
  
                                           ''')
 
-    viral_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['create_webpage_genotype'],
-    )
+    add_workflow_arg(viral_options, ['create_webpage_genotype'])
 
     ##########################   ~ COMPLETE ~  ###########################
 
@@ -1035,13 +1045,7 @@ def main():
         required=False,
     )
 
-    complete_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run',
-        dest='workflow',
-        nargs="+",
-        default=['get_bam_indices', 'recover_mags', 'annotate', 'lorikeet'],
-    )
+    add_workflow_arg(complete_options, ['get_bam_indices', 'recover_mags', 'annotate', 'lorikeet'])
 
     ##########################  ~ ISOLATE ~  ###########################
 
@@ -1057,13 +1061,7 @@ def main():
                                  
                                              ''')
 
-    isolate_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflows to run',
-        dest='workflow',
-        nargs="+",
-        default=['circlator'],
-    )
+    add_workflow_arg(isolate_options, ['circlator'])
 
     ##########################   ~ BATCH ~  ###########################
 
@@ -1138,12 +1136,10 @@ def main():
         default='95'
     )
 
-    batch_options.add_argument(
-        '-w', '--workflow',
-        help='Main workflow to run for each sample',
-        dest='workflow',
-        nargs="+",
-        default=['get_bam_indices', 'recover_mags', 'annotate', 'lorikeet'],
+    add_workflow_arg(
+        batch_options,
+        ['get_bam_indices', 'recover_mags', 'annotate', 'lorikeet'],
+        help='Main workflow (snakemake target rule) to run for each sample'
     )
 
     ##########################   ~ configure ~  ###########################
@@ -1195,13 +1191,7 @@ def main():
         required=False,
     )
 
-    configure_options.add_argument(
-        '-w', '--workflow',
-        help=argparse.SUPPRESS,
-        dest='workflow',
-        nargs="+",
-        default=['download_databases'],
-    )
+    add_workflow_arg(configure_options, ['download_databases'], help=argparse.SUPPRESS)
 
     ###########################################################################
     # ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #
@@ -1261,6 +1251,9 @@ def main():
 
     # else:
     args = manage_env_vars(args)
+    if int(args.max_threads) > int(args.n_cores):
+        args.n_cores = args.max_threads
+
     prefix = args.output
     if not os.path.exists(prefix):
         os.makedirs(prefix)
@@ -1307,6 +1300,8 @@ def manage_env_vars(args):
             args.eggnog_db_path = Config.get_software_db_path('EGGNOG_DATA_DIR', '--eggnog-db-path')
         if args.checkm2_db_path is None:
             args.checkm2_db_path = Config.get_software_db_path('CHECKM2DB', '--checkm2-db-path')
+        if args.singlem_metapackage_path is None:
+            args.singlem_db_path = Config.get_software_db_path('SINGLEM_METAPACKAGE_PATH', '--singlem-metapackage-path')
     except AttributeError:
         pass