upgrade the command line interfaces.

anvio/merger.py

@@ -52,7 +52,7 @@ def __init__(self, args, run = run, progress = progress):
         self.progress = progress
         self.run = run 
 
-        self.sample_id = args.sample_id
+        self.sample_id = args.sample_name
         self.merged_sample_ids = []
         self.input_runinfo_dicts = {}
         self.input_runinfo_paths = args.input

anvio/profiler.py

@@ -55,17 +55,17 @@ def __init__(self, args = None):
         if args:
             self.args = args
             self.input_file_path = args.input_file
-            self.contigs_db_path = args.contigs_db_path
-            self.serialized_profile_path = args.profile
-            self.output_directory = args.output_directory
+            self.contigs_db_path = args.contigs_db
+            self.serialized_profile_path = args.serialized_profile
+            self.output_directory = args.output_dir
             self.list_contigs_and_exit = args.list_contigs
             self.min_contig_length = args.min_contig_length
             self.min_mean_coverage = args.min_mean_coverage
             self.min_coverage_for_variability = args.min_coverage_for_variability
             self.contigs_shall_be_clustered = args.cluster_contigs
             self.number_of_threads = 4 
             self.no_trehading = True
-            self.sample_id = args.sample_id
+            self.sample_id = args.sample_name
             self.report_variability_full = args.report_variability_full
             self.overwrite_output_destinations = args.overwrite_output_destinations
 

anvio/summarizer.py

@@ -72,7 +72,7 @@ def __init__(self, args = None, r = run, p = progress):
                 sys.exit()
 
             self.collection_id = args.collection_id
-            self.output_directory = args.output_directory
+            self.output_directory = args.output_dir
             self.debug = args.debug
 
         self.sanity_check()

bin/anvi-cluster-with-concoct

@@ -19,29 +19,21 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 if __name__ == '__main__':
     import argparse
+
     parser = argparse.ArgumentParser(description="A script to call CONCOCT clustering on a merged anvi'o profile")
-    parser.add_argument('-p', '--profile-db', metavar = "PROFILE_DB", required = True,
-                        help = 'Profile database.')
-    parser.add_argument('-c', '--contigs-db', required = True, metavar = 'CONTIGS_DB',
-                        help = 'anvio contigs database.')
-    parser.add_argument('-o', '--output-file', metavar = 'OUTPUT.txt', default = None,
-                        help = 'Store results as a TAB-delimited file')
-    parser.add_argument('--skip-db', default = False, action = 'store_true',
-                        help = 'By default, results are stored in the profile database that is given as a parameter\
-                                Use this flag if you would like to skip that step')
-    parser.add_argument('--source-identifier', default = 'CONCOCT', metavar = 'SOURCE',
-                        help = "The source identifier when results are stored in the profile database. The default id\
-                                is '%(default)s'. If there is another entry for '%(default)s', it will be overwrotten\
-                                with new results. Using this parameter you can avoid that.")
-    parser.add_argument('--debug', action='store_true', help = 'Print out debug info.')
-    args = parser.parse_args()
 
+    parser.add_argument(*anvio.A('profile-db'), **anvio.K('profile-db'))
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
+    parser.add_argument(*anvio.A('output-file'), **anvio.K('output-file'))
+    parser.add_argument(*anvio.A('skip-store-in-db'), **anvio.K('skip-store-in-db'))
+    parser.add_argument(*anvio.A('source-identifier'), **anvio.K('source-identifier', {'default': 'CONCOCT'}))
+    parser.add_argument(*anvio.A('debug'), **anvio.K('debug'))
 
+    args = parser.parse_args()
 
     try:
         source = args.source_identifier.strip()
@@ -63,7 +55,7 @@ if __name__ == '__main__':
 
         if args.output_file:
             c.store_clusters_as_TAB_delimited_text(args.output_file)
-        if not args.skip_db:
+        if not args.skip_store_in_db:
             c.store_clusters_in_db(source = source)
 
     except ConfigError, e:

bin/anvi-compute-completeness

@@ -20,7 +20,6 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
@@ -29,18 +28,11 @@ progress = terminal.Progress()
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='A script to generate completeness info for a given list of _splits_')
-    parser.add_argument('splits_txt', metavar = 'SPLITS_TXT',
-                        help = 'File with split names.')
-    parser.add_argument('contigs_db', metavar = 'CONTIGS_DB',
-                        help = 'Contigs database to read from.')
-    parser.add_argument('-e', '--min-e-value', default=1e-15, type=float, metavar = 'E-VALUE',
-                        help = 'Minimum significance score of an HMM find to be considered as a valid hit.\
-                                Default is %(default)g.')
-    parser.add_argument('--list-sources', action='store_true', default=False,
-                        help = 'Show available single-copy gene search results and exit.')
-    parser.add_argument('--source', default=None,
-                        help = 'Source to focus on. If none declared, all single-copy gene sources\
-                                are going to be listed.')
+    parser.add_argument(*anvio.A('splits-of-interest'), **anvio.K('splits-of-interest'))
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
+    parser.add_argument(*anvio.A('min-e-value'), **anvio.K('min-e-value'))
+    parser.add_argument(*anvio.A('list-completeness-sources'), **anvio.K('list-completeness-sources'))
+    parser.add_argument(*anvio.A('completeness-source'), **anvio.K('completeness-source'))
 
     args = parser.parse_args()
 

bin/anvi-experimental-organization

@@ -21,7 +21,6 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
@@ -76,26 +75,14 @@ if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='why yes we do stuff here.')
     parser.add_argument('config_file', metavar = 'PATH', default = None, type=str,
                         help = 'Config file for clustering of contigs. See documentation for help.')
-    parser.add_argument('-i', '--input-directory', metavar = 'INPUT_DIR', default = None, type=str,
-                        help = 'Input directory where the input files addressed from the configuration\
-                                file can be found (i.e., the profile database, if PROFILE.db::TABLE\
-                                notation is used in the configuration file).')
-    parser.add_argument('-c', '--contigs-db', metavar = 'CONTIGS_DB',
-                        help = 'anvio contigs database.', required = True)
-    parser.add_argument('-p', '--profile-db', default = None, metavar = 'PROFILE_DB',
-                        help = 'anvio contigs database.', required = False)
-    parser.add_argument('-N', '--name', default = None, metavar = 'NAME',
-                        help = "The name to use when storing the resulting clustering in the database.\
-                                This name will appear in the interactive interface and other relevant\
-                                interfaces. Please consider using a short and descriptive single-word\
-                                (if you do not do that you will make anvi'o complain).")
-    parser.add_argument('--skip-store-in-db', default = False, action = 'store_true', 
-                        help = 'By defaut, the resulting tree is stored in the profile database.\
-                                When declared, this flag skips that step.')
-    parser.add_argument('-o', '--output-file', metavar = 'FILE', default = None, type=str,
-                        help = 'To store the newick output.')
-    parser.add_argument('-D', '--dry-run', default = False, action = 'store_true', 
-                        help = 'Do not do anything, just print out the configuration.')
+
+    parser.add_argument(*anvio.A('profile-db'), **anvio.K('profile-db', {'required': False}))
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
+    parser.add_argument(*anvio.A('experimental-org-input-dir'), **anvio.K('experimental-org-input-dir'))
+    parser.add_argument(*anvio.A('clustering-name'), **anvio.K('clustering-name'))
+    parser.add_argument(*anvio.A('skip-store-in-db'), **anvio.K('skip-store-in-db'))
+    parser.add_argument(*anvio.A('output-file'), **anvio.K('output-file'))
+    parser.add_argument(*anvio.A('dry-run'), **anvio.K('dry-run'))
 
     args = parser.parse_args()
 

bin/anvi-export-genes-table

@@ -19,26 +19,24 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
 
 def main(args):
-    contigs_db = dbops.ContigsDatabase(args.db_path)
+    contigs_db = dbops.ContigsDatabase(args.contigs_db)
     genes_contigs_table = contigs_db.db.get_table_as_dict(t.genes_contigs_table_name)
     genes_contigs_table_headers = contigs_db.db.get_table_structure(t.genes_contigs_table_name)
-    utils.store_dict_as_TAB_delimited_file(genes_contigs_table, args.output, genes_contigs_table_headers)
-    run.info('Recovered matrix', os.path.abspath(args.output))
+    utils.store_dict_as_TAB_delimited_file(genes_contigs_table, args.output_file, genes_contigs_table_headers)
+    run.info('Recovered matrix', os.path.abspath(args.output_file))
 
 if __name__ == '__main__':
     import argparse
     parser = argparse.ArgumentParser(description='Generate a TAB-delimited matrix file from genes tables found in an\
                                                   contigs database')
-    parser.add_argument('db_path', metavar = 'DB_PATH', default = None,
-                        help = 'Path to the contigs database.')
-    parser.add_argument('-o', '--output', default = "CONTIGS.txt",
-                        help = 'Output file path. Default is %(default)s.')
+
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
+    parser.add_argument(*anvio.A('output-file'), **anvio.K('output-file'))
 
     args = parser.parse_args()
 

bin/anvi-export-splits-and-coverages

@@ -30,22 +30,21 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
 
 def main(args):
-    merged_profile_db = db.DB(args.merged_profile_db, anvio.__profile__version__)
+    merged_profile_db = db.DB(args.profile_db, anvio.__profile__version__)
     contigs_db = db.DB(args.contigs_db, anvio.__contigs__version__)
 
     if(merged_profile_db.get_meta_value('merged') != True):
-        raise ConfigError, "'%s' does not seem to be a merged profile database :/" % args.merged_profile_db
+        raise ConfigError, "'%s' does not seem to be a merged profile database :/" % args.profile_db
 
-    if args.output_directory:
-        filesnpaths.gen_output_directory(args.output_directory)
+    if args.output_dir:
+        filesnpaths.gen_output_dir(args.output_dir)
     else:
-        args.output_directory = os.path.dirname(os.path.abspath(args.merged_profile_db))
+        args.output_dir = os.path.dirname(os.path.abspath(args.profile_db))
 
     if not args.output_file_prefix:
         args.output_file_prefix = merged_profile_db.get_meta_value('sample_id')
@@ -58,8 +57,8 @@ def main(args):
     merged_profile_db.disconnect()
     contigs_db.disconnect()
 
-    coverages_file = os.path.join(args.output_directory, args.output_file_prefix + '-COVs.txt')
-    splits_fasta = os.path.join(args.output_directory, args.output_file_prefix + '-SPLITS.fa')
+    coverages_file = os.path.join(args.output_dir, args.output_file_prefix + '-COVs.txt')
+    splits_fasta = os.path.join(args.output_dir, args.output_file_prefix + '-SPLITS.fa')
 
     utils.store_dict_as_TAB_delimited_file(coverages, coverages_file, ['contig'] + samples)
 
@@ -78,14 +77,11 @@ def main(args):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser(description='Export splits and the coverage table from database')
-    parser.add_argument('-p', '---merged-profile-db', metavar = "MERGED PROFILE DB", required = True,
-                        help = 'Profile database.')
-    parser.add_argument('-c', '--contigs-db', required = True, metavar = 'CONTIGS DB',
-                        help = 'anvio contigs database.')
-    parser.add_argument('-o', '--output-directory', default = None, metavar = 'OUTPUT_DIR',
-                        help = 'Output directory for files to be stored')
-    parser.add_argument('-O', '--output-file-prefix', default = None, metavar = 'FILENAME_PREFIX',
-                        help = 'A prefix to name output files.')
+
+    parser.add_argument(*anvio.A('profile-db'), **anvio.K('profile-db'))
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
+    parser.add_argument(*anvio.A('output-dir'), **anvio.K('output-dir'))
+    parser.add_argument(*anvio.A('output-file-prefix'), **anvio.K('output-file-prefix'))
 
     args = parser.parse_args()
 

bin/anvi-gen-contigs-database

@@ -17,7 +17,6 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
@@ -27,34 +26,16 @@ progress = terminal.Progress()
 if __name__ == '__main__':
     import argparse
     parser = argparse.ArgumentParser(description='Generate a new anvio contigs database.')
-    parser.add_argument('-f', '--contigs-fasta', metavar = 'FASTA', required = True,
-                        help = 'The FASTA file that contains reference sequences you mapped your samples against. This\
-                                could be a reference genome, or contigs from your assembler. Contig names in this file\
-                                must match to those in other input files. If there is a problem, anvio will gracefully\
-                                complain about it.')
-    parser.add_argument('-L', '--split-length', metavar = 'INTEGER', default = 20000, type=int,
-                        help = 'Splitting very large contigs into multiple pieces improves\
-                                the efficacy of the visualization step. The default value\
-                                is (%(default)d). If you are not sure, we advise you to not\
-                                go below 10,000. The lower you go, the more complicated the\
-                                tree will be, and will take more time and computational\
-                                resources to finish the analysis. Also this is not a case\
-                                of "the smaller the split size the more sensitive the results". If you do\
-                                not want your contigs to be split, you can either enter a very\
-                                large integer, or "-1".')
-    parser.add_argument('-K', '--kmer-size', metavar = 'INTEGER', default = 4, type=int,
-                        help = 'K-mer size for k-mer frequency calculations. The default k-mer size for composition-based\
-                                analyses is 4, historically. Although tetra-nucleotide frequencies seem to offer the\
-                                the sweet spot of sensitivity, information density, and manageable number of dimensions\
-                                for clustering approaches, you are welcome to experiment (but maybe you should leave\
-                                it as is for your first set of analyses).')
-    parser.add_argument('-o', '--db-path', default = "CONTIGS.db", 
-                        help = 'Output file path for the new contigs database to be generated.')
+
+    parser.add_argument(*anvio.A('contigs-fasta'), **anvio.K('contigs-fasta'))
+    parser.add_argument(*anvio.A('split-length'), **anvio.K('split-length'))
+    parser.add_argument(*anvio.A('kmer-size'), **anvio.K('kmer-size'))
+    parser.add_argument(*anvio.A('output-db-path'), **anvio.K('output-db-path', {'default': 'CONTIGS.db'}))
 
     args = parser.parse_args()
 
     try:
-        a = dbops.ContigsDatabase(args.db_path, run, progress, quiet=False)
+        a = dbops.ContigsDatabase(args.output_db_path, run, progress, quiet=False)
         a.create(args.contigs_fasta, args.split_length, args.kmer_size)
     except ConfigError, e:
         print e

bin/anvi-gen-network

@@ -22,7 +22,6 @@ __license__ = "GPL 3.0"
 __version__ = anvio.__version__
 __maintainer__ = "A. Murat Eren"
 __email__ = "a.murat.eren@gmail.com"
-__status__ = "Development"
 
 
 run = terminal.Run()
@@ -219,10 +218,9 @@ if __name__ == '__main__':
     import argparse
 
     parser = argparse.ArgumentParser(description='Generate a network description file')
-    parser.add_argument('runinfo', metavar = 'RUNINFO',
-                        help = 'anvio RUNINFO file')
-    parser.add_argument('contigs_db', metavar = 'CONTIGS',
-                        help = 'Contigs database that has been used for the run described in RUNINFO file')
+
+    parser.add_argument(*anvio.A('runinfo'), **anvio.K('runinfo'))
+    parser.add_argument(*anvio.A('contigs-db'), **anvio.K('contigs-db'))
 
     args = parser.parse_args()
 

bin/anvi-gen-samples-info-database

@@ -26,25 +26,15 @@ progress = terminal.Progress()
 if __name__ == '__main__':
     import argparse
     parser = argparse.ArgumentParser(description="Create a new anvi'o samples information database.")
-    parser.add_argument('-D', '--samples-information', metavar = "FILE", default = None,
-                  help = "A TAB-delimited file with information about samples in your dataset (which also correspond)\
-                          to 'view layers'. Each row in this file must correspond to a sample name. Each column must\
-                          contain a unique attribute. Please refer to the documentation to learn more about the \
-                          structure and purpose of this file.")
-    parser.add_argument('-R', '--samples-order', metavar = "FILE", default = None,
-                  help = "A TAB-delimited file with three columns: 'attribute', 'basic', 'newick'. For each attribute,\
-                          the order of samples must be defined either in the 'basic' form or via a 'newick'-formatted\
-                          tree structurei that describes the organization of each sample. Anvi'o will look for a\
-                          comma-separated list of sample names for the 'basic' form. Please refer to the online docs\
-                          for more info. Also you shouldn't hesitate to try to find the right file format until you get\
-                          it working. There are stringent checks on this file, and you will not break anything while trying!.")
-    parser.add_argument('-o', '--db-path', default = "SAMPLES.db", 
-                  help = 'Output file path for the new contigs database to be generated.')
+
+    parser.add_argument(*anvio.A('samples-information'), **anvio.K('samples-information'))
+    parser.add_argument(*anvio.A('samples-order'), **anvio.K('samples-order'))
+    parser.add_argument(*anvio.A('output-db-path'), **anvio.K('output-db-path', {'default': 'SAMPLES.db'}))
 
     args = parser.parse_args()
 
     try:
-        s = dbops.SamplesInformationDatabase(args.db_path, run, progress, quiet=False)
+        s = dbops.SamplesInformationDatabase(args.output_db_path, run, progress, quiet=False)
         s.create(args.samples_information, args.samples_order)
     except ConfigError, e:
         print e