Fixstart expose mincluster opt

circlator/start_fixer.py

@@ -14,6 +14,7 @@ def __init__(self,
         input_assembly_fa,
         outprefix,
         min_percent_identity=70,
+        promer_mincluster=None,
         genes_fa=None,
         ignore=None,
         verbose=False,
@@ -33,6 +34,7 @@ def __init__(self,
         pyfastaq.tasks.file_to_dict(input_assembly_fa, self.input_assembly)
 
         self.min_percent_identity = min_percent_identity
+        self.promer_mincluster = promer_mincluster
         self.outprefix = os.path.abspath(outprefix)
         self.verbose = verbose
 
@@ -108,7 +110,7 @@ def _write_fasta_plus_circularized_ends(cls, contigs, outfile, end_length, ignor
 
 
     @classmethod
-    def _find_circular_using_promer(cls, outprefix, ref_genes_fa, contigs_dict, min_percent_id, end_length, log_fh, ignore=None):
+    def _find_circular_using_promer(cls, outprefix, ref_genes_fa, contigs_dict, min_percent_id, end_length, log_fh, ignore=None, promer_mincluster=None):
         if ignore is None:
             ignore = set()
         promer_out = outprefix + '.promer'
@@ -126,6 +128,7 @@ def _find_circular_using_promer(cls, outprefix, ref_genes_fa, contigs_dict, min_
             promer=True,
             verbose=False,
             maxmatch=True,
+            mincluster=promer_mincluster,
         )
         prunner.run()
 
@@ -303,7 +306,8 @@ def run(self):
             self.min_percent_identity,
             end_extend,
             log_fh,
-            ignore=self.ignore
+            ignore=self.ignore,
+            promer_mincluster=self.promer_mincluster,
         )
 
         if self.verbose:

circlator/tasks/all.py

@@ -59,6 +59,7 @@ def run():
 
     fixstart_group = parser.add_argument_group('fixstart options')
     fixstart_group.add_argument('--genes_fa', help='FASTA file of genes to search for to use as start point. If this option is not used, a built-in set of dnaA genes is used', metavar='FILENAME')
+    fixstart_group.add_argument('--fixstart_mincluster', type=int, help='The -c|mincluster option of promer. If this option is used, it overrides promer\'s default value', metavar='INT')
     fixstart_group.add_argument('--fixstart_min_id', type=float, help='Minimum percent identity of promer match between contigs and gene(s) to use as start point [%(default)s]', default=70, metavar='FLOAT')
 
     options = parser.parse_args()
@@ -249,6 +250,7 @@ def run():
         clean_fasta,
         fixstart_prefix,
         min_percent_identity=options.fixstart_min_id,
+        promer_mincluster=options.fixstart_mincluster,
         genes_fa=options.genes_fa,
         ignore=not_fix_start_file,
         verbose=options.verbose

circlator/tasks/fixstart.py

@@ -7,6 +7,7 @@ def run():
         usage = 'circlator fixstart [options] <assembly.fasta> <outprefix>')
     parser.add_argument('--genes_fa', help='FASTA file of genes to search for to use as start point. If this option is not used, a built-in set of dnaA genes is used', metavar='FILENAME')
     parser.add_argument('--ignore', help='Absolute path to file of IDs of contigs to not change', metavar='FILENAME')
+    parser.add_argument('--mincluster', type=int, help='The -c|mincluster option of promer. If this option is used, it overrides promer\'s default value', metavar='INT')
     parser.add_argument('--min_id', type=float, help='Minimum percent identity of promer match between contigs and gene(s) to use as start point [%(default)s]', default=70, metavar='FLOAT')
     parser.add_argument('--verbose', action='store_true', help='Be verbose')
     parser.add_argument('assembly_fa', help='Name of input FASTA file', metavar='assembly.fasta')
@@ -17,6 +18,7 @@ def run():
         options.assembly_fa,
         options.outprefix,
         min_percent_identity=options.min_id,
+        promer_mincluster=options.mincluster,
         genes_fa=options.genes_fa,
         ignore=options.ignore,
         verbose=options.verbose,

setup.py

@@ -7,7 +7,7 @@
 
 setup(
     name='circlator',
-    version='1.3.1',
+    version='1.4.0',
     description='circlator: a tool to circularise genome assemblies',
     packages = find_packages(),
     package_data={'circlator': ['data/*']},
@@ -21,7 +21,7 @@
         'openpyxl',
         'pyfastaq >= 3.12.1',
         'pysam >= 0.8.1',
-        'pymummer>=0.7.1',
+        'pymummer>=0.9.0',
     ],
     license='GPLv3',
     classifiers=[