github.com/matsengrp/olmsted/issues/13

SConstruct

@@ -502,9 +502,10 @@ def add_cluster_analysis(w):
         where N is the ranking of vlads untrimmed deduplication, and M is the multiplicity of said deduplication."""
         # This option controls which sequences get joined on in the merge for the partis_seqmeta file, which has
         # orig/new names, joined on sequence from the other file
-        sources = {'--partis-seqmeta': c['partis_seqmeta'],
+	sources = {'--partis-seqmeta': c['partis_seqmeta'],
                    '--cluster-mapping': c['cluster_mapping'] if c['reconstruction']['prune_strategy'] == 'min_adcl' else None,
-                   }
+                   '--pruned-ids': c['pruned_ids'] if c['reconstruction']['prune_strategy'] == 'seed_lineage' else None, 
+		  }
         sources = {k: v for k, v in sources.items() if v}
         base_call = 'aggregate_minadcl_cluster_multiplicities.py '
         for i, (k, v) in enumerate(sources.items()):

bin/aggregate_minadcl_cluster_multiplicities.py

@@ -5,7 +5,9 @@
 import collections
 #import itertools
 
-
+def filter_by_ids(results, ids):
+    filtered_results = [result for result in results if result['unique_id'] in ids]
+    return filtered_results
 
 def aggregate_clusters(merge_results, cluster_mapping):
     merge_results = {row['sequence']: row for row in merge_results}
@@ -69,11 +71,18 @@ def seqmeta_reader(filename):
                       'duplicates': d['duplicates'].split(':')})
             for d in data]
 
+def pruned_ids_reader(filename):
+    data = set()
+    with open(filename) as f:
+        for line in f:
+	    data.add(line.rstrip())
+    return data 
 
 def get_args():
     parser = argparse.ArgumentParser()
     parser.add_argument('--cluster-mapping', type=cluster_reader)
     parser.add_argument('--partis-seqmeta', type=seqmeta_reader)
+    parser.add_argument('--pruned-ids', type=pruned_ids_reader)
     parser.add_argument('output', type=argparse.FileType('w'))
     args = parser.parse_args()
     return args
@@ -91,6 +100,8 @@ def main():
     results = args.partis_seqmeta
     if args.cluster_mapping:
         results = aggregate_clusters(results, args.cluster_mapping)
+    if args.pruned_ids:
+	results = filter_by_ids(results, args.pruned_ids)
     out_writer.writerows(format_results(results))
     args.output.close()
 

site_scons/software_versions.py

@@ -25,9 +25,9 @@ def tripl_version():
     'muscle': 'muscle -version',
     'seqmagick': 'seqmagick --version',
     'FastTree': None,
-    'prank': 'prank -v',
+#    'prank': 'prank -v',
     'tripl': tripl_version,
-    #'nestly': lambda: nestly.__version__,
+#    'nestly': lambda: nestly.__version__,
     'ete3': lambda: ete3.__version__,
     'biopython': lambda: Bio.__version__,
     'scons': 'scons -v',