Updating metric parsing from the CLI

PhiSpyModules/classification.py

@@ -44,8 +44,9 @@ def call_randomforest(**kwargs):
         kwargs['metrics'].append('phmms')
 
     if len(kwargs['metrics']) < len(all_metrics):
-        log_and_message(f"Using the following metric(s): {', '.join(sorted(kwargs['metrics']))}.", c='GREEN', stderr=True, quiet=kwargs['quiet'])
-        skip_metrics = [all_metrics.index(x) for x in set(all_metrics) - set(kwargs['metrics'])]
+        used = b=set(kwargs['metrics']) & set(all_metrics)
+        log_and_message(f"Using the following metric(s): {used}.", c='GREEN', stderr=True, quiet=kwargs['quiet'])
+        skip_metrics = [all_metrics.index(x) for x in set(all_metrics) - used]
         train_data = np.delete(train_data, skip_metrics, 1)
         test_data = np.delete(test_data, skip_metrics, 1)
     else:

PhiSpyModules/helper_functions.py

@@ -92,7 +92,7 @@ def get_args():
     parser.add_argument('--phage_genes', default=1, type=int,
                         help='The minimum number of genes that must be identified as belonging to a phage for the ' +
                              'region to be included. The default is %(default)d or more genes.')
-    parser.add_argument('--metrics', nargs='+', type=str, default=['orf_length_med', 'shannon_slope', 'at_skew', 'gc_skew', 'max_direction'],
+    parser.add_argument('--metrics', nargs='+', type=str, action="extend",
                         help='The set of metrics to consider during classification. If not set, all metrics (orf_length_med, shannon_slope, at_skew, gc_skew, max_direction) will be considered.')
     parser.add_argument('-r', '--randomforest_trees', default=500, type=int,
                         help='Number of trees generated by Random Forest classifier. [Default: %(default)d]')
@@ -148,5 +148,10 @@ def get_args():
     else:
         args.output_dir=""
 
+
+    # check whether any metrics were provided
+    if not args.metrics:
+        args.metrics = ['orf_length_med', 'shannon_slope', 'at_skew', 'gc_skew', 'max_direction']
+
     args.logger = create_logger(args)
     return args

README.md

@@ -175,6 +175,22 @@ cat vog/* > VOGs.hmms
 hmmpress VOGs.hmms
 ```
 
+### Metrics
+
+We use several different metrics to predict regions that are prophages, and there are some optional metrics you can add. The default set of metrics are:
+
+ - `orf_length_med`: median ORF length
+ - `shannon_slope`: the slope of Shannon's diversity of _k_-mers across the window under consideration. You can also expand this with the `--expand_slope` option.
+ - `at_skew`: the normalized AT skew across the window under consideration
+ - `gc_skew`: the normalized GC skew across the window under consideration
+ - `max_direction`: The maximum number of genes in the same direction
+
+You can also add
+
+ - `phmms`: The [phmm](#HMM-Searches) search results
+ - `phage_genes`: The number of genes that must be annotated as phage in the region
+ - `nonprophage_genegaps` : The maximum number of non-phage genes between two phage-like regions that will enable them to be merged
+
 # Help
 
 For the help menu use the `-h` option:

VERSION

@@ -1 +1 @@
-4.1.17
+4.1.18