drep 3.5.0__tar.gz → 3.6.2__tar.gz

{drep-3.5.0 → drep-3.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: drep
-Version: 3.5.0
+Version: 3.6.2
 Summary: De-replication of microbial genomes assembled from multiple samples
 Home-page: https://github.com/MrOlm/drep
 Author: Matt Olm

{drep-3.5.0 → drep-3.6.2}/README.md

@@ -9,7 +9,7 @@ Manual, installation instructions, and API are at available at
 [ReadTheDocs](https://drep.readthedocs.io/en/latest/)
 
 Publication is available at
-[ISMEJ](http://www.nature.com/ismej/journal/vaop/ncurrent/full/ismej2017126a.html)
+[ISMEJ](https://doi.org/10.1038/ismej.2017.126)
 
 Open source pre-print publication is available at
 [bioRxiv](https://doi.org/10.1101/108142)

drep-3.6.2/drep/VERSION

@@ -0,0 +1 @@
+3.6.2

{drep-3.5.0 → drep-3.6.2}/drep/argumentParser.py

@@ -44,7 +44,7 @@ def printHelp():
     print('                ...::: dRep v' + VERSION + ' :::...''')
     print('''\
 
-  Matt Olm. MIT License. Banfield Lab, UC Berkeley. 2017 (last updated 2024)
+  Matt Olm. MIT License. Banfield Lab, UC Berkeley. 2017 (last updated 2025)
 
   See https://drep.readthedocs.io/en/latest/index.html for documentation
   Choose one of the operations below for more detailed help. 
@@ -149,6 +149,8 @@ def parse_args(args):
     Compflags.add_argument("--clusterAlg", help="Algorithm used to cluster genomes (passed\
                         to scipy.cluster.hierarchy.linkage", default='average',
                            choices={'single', 'complete', 'average', 'weighted', 'centroid', 'median', 'ward'})
+    Compflags.add_argument("--low_ram_primary_clustering", help="Use a memory-efficient algorithm for primary clustering. This only affects primary clustering and not secondary clustering.", 
+                          action='store_true', default=False)
 
     GRflags = cluster_parent.add_argument_group('GREEDY CLUSTERING OPTIONS\n'
                                                 'These decrease RAM use and runtime at the expense of a minor loss in '

{drep-3.5.0 → drep-3.6.2}/drep/d_cluster/cluster_utils.py

@@ -6,6 +6,7 @@ import numpy as np
 import pandas as pd
 import scipy.cluster
 from scipy.spatial import distance as ssd
+import networkx as nx
 
 import drep.d_cluster.utils
 
@@ -87,7 +88,33 @@ def iteratre_clusters(Bdb, Cdb, id='primary_cluster'):
         yield d, cluster
 
 
-def cluster_hierarchical(db, linkage_method= 'single', linkage_cutoff= 0.10):
+def cluster_threshold_graph_optimized(db, linkage_cutoff=0.10, linkage_method='single'):
+    # Filter distances below threshold first
+    filtered_edges = db[db['dist'] <= linkage_cutoff]
+    
+    # Create graph directly from filtered edges
+    G = nx.Graph()
+    G.add_edges_from(filtered_edges[['genome1', 'genome2']].values)
+    
+    # Log that we're using the optimized method
+    logging.debug("Using low-RAM optimized clustering method with {0} edges".format(len(filtered_edges)))
+    
+    # Find connected components
+    clusters = {}
+    for cluster_id, component in enumerate(nx.connected_components(G)):
+        for genome in component:
+            clusters[genome] = cluster_id + 1
+            
+    # Add isolated nodes (if needed)
+    all_genomes = set(db['genome1']).union(set(db['genome2']))
+    for genome in all_genomes:
+        if genome not in clusters:
+            clusters[genome] = len(clusters)
+            
+    # Return clusters and a special value indicating we used the optimized method
+    return clusters, "optimized_method_used"
+
+def cluster_hierarchical(db, linkage_method= 'single', linkage_cutoff= 0.10, low_ram=False):
     '''
     Perform hierarchical clustering on a symmetrical distiance matrix
 
@@ -95,6 +122,7 @@ def cluster_hierarchical(db, linkage_method= 'single', linkage_cutoff= 0.10):
         db: result of db.pivot usually
         linkage_method: passed to scipy.cluster.hierarchy.fcluster
         linkage_cutoff: distance to draw the clustering line (default = .1)
+        low_ram: whether to use the memory-efficient algorithm
 
     Returns:
         list: [Cdb, linkage]
@@ -102,21 +130,32 @@ def cluster_hierarchical(db, linkage_method= 'single', linkage_cutoff= 0.10):
     # Save names
     names = list(db.columns)
 
-    # Generate linkage dataframe
-    arr =  np.asarray(db)
-    try:
-        arr = ssd.squareform(arr)
-    except:
-        logging.error("The database passed in is not symmetrical!")
-        logging.error(arr)
-        logging.error(names)
-        sys.exit()
-    linkage = scipy.cluster.hierarchy.linkage(arr, method= linkage_method)
-
-    # Form clusters
-    fclust = scipy.cluster.hierarchy.fcluster(linkage,linkage_cutoff, \
-                    criterion='distance')
-    # Make Cdb
-    Cdb = drep.d_cluster.utils._gen_cdb_from_fclust(fclust,names)
-
-    return Cdb, linkage
+    if low_ram:
+        # Convert to long format for optimized clustering
+        db_long = db.stack().reset_index()
+        db_long.columns = ['genome1', 'genome2', 'dist']
+        clusters, _ = cluster_threshold_graph_optimized(db_long, linkage_cutoff, linkage_method)
+        
+        # Convert clusters to Cdb format
+        Cdb = pd.DataFrame({'genome': list(clusters.keys()), 
+                          'cluster': list(clusters.values())})
+        return Cdb, _
+    else:
+        # Generate linkage dataframe
+        arr =  np.asarray(db)
+        try:
+            arr = ssd.squareform(arr)
+        except:
+            logging.error("The database passed in is not symmetrical!")
+            logging.error(arr)
+            logging.error(names)
+            sys.exit()
+        linkage = scipy.cluster.hierarchy.linkage(arr, method= linkage_method)
+
+        # Form clusters
+        fclust = scipy.cluster.hierarchy.fcluster(linkage,linkage_cutoff, \
+                        criterion='distance')
+        # Make Cdb
+        Cdb = drep.d_cluster.utils._gen_cdb_from_fclust(fclust,names)
+
+        return Cdb, linkage

{drep-3.5.0 → drep-3.6.2}/drep/d_cluster/compare_utils.py

@@ -264,6 +264,7 @@ def cluster_mash_database(db, **kwargs):
     Keyword arguments:
         clusterAlg: how to cluster database (default = single)
         P_ani: threshold to cluster at (default = 0.9)
+        low_ram_primary_clustering: whether to use memory-efficient algorithm
 
     Returns:
         list: [Cdb, [linkage, linkage_db, arguments]]
@@ -273,12 +274,13 @@ def cluster_mash_database(db, **kwargs):
     # Load key words
     P_Lmethod = kwargs.get('clusterAlg','single')
     P_Lcutoff = 1 - kwargs.get('P_ani',.9)
+    low_ram = kwargs.get('low_ram_primary_clustering', False)
 
     # Do the actual clustering
     db['dist'] = 1 - db['similarity']
     linkage_db = db.pivot(index="genome1", columns="genome2", values="dist")
     Cdb, linkage = drep.d_cluster.cluster_utils.cluster_hierarchical(linkage_db, linkage_method= P_Lmethod, \
-                                                                     linkage_cutoff= P_Lcutoff)
+                                                                     linkage_cutoff= P_Lcutoff, low_ram=low_ram)
     Cdb = Cdb.rename(columns={'cluster':'primary_cluster'})
     Cdb['primary_cluster'] = Cdb['primary_cluster'].astype(int)
 

{drep-3.5.0 → drep-3.6.2}/drep/d_cluster/utils.py

@@ -354,7 +354,7 @@ def gen_goANI_cmd(file, g1, g2, exe):
         return []
 
     else:
-        cmd = [exe,'--om','TABX', g1, g2, file]
+        cmd = [exe,'--om','TABX', '--rpq', '1', g1, g2, file]
     return cmd
 
 def process_deltafiles(deltafiles, org_lengths, logger=None, **kwargs):

{drep-3.5.0 → drep-3.6.2}/drep.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: drep
-Version: 3.5.0
+Version: 3.6.2
 Summary: De-replication of microbial genomes assembled from multiple samples
 Home-page: https://github.com/MrOlm/drep
 Author: Matt Olm

{drep-3.5.0 → drep-3.6.2}/drep.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 README.md
+pyproject.toml
 setup.py
 bin/dRep
 drep/VERSION

drep-3.6.2/pyproject.toml

@@ -0,0 +1,3 @@
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-v"

drep-3.5.0/drep/VERSION

@@ -1 +0,0 @@
-3.5.0