drep 3.6.2__tar.gz → 3.7.1__tar.gz

{drep-3.6.2 → drep-3.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: drep
-Version: 3.6.2
+Version: 3.7.1
 Summary: De-replication of microbial genomes assembled from multiple samples
 Home-page: https://github.com/MrOlm/drep
 Author: Matt Olm
@@ -13,4 +13,12 @@ Requires-Dist: matplotlib
 Requires-Dist: biopython
 Requires-Dist: scikit-learn
 Requires-Dist: tqdm
+Requires-Dist: networkx
+Requires-Dist: setuptools
 Requires-Dist: pytest
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: summary

drep-3.7.1/drep/VERSION

@@ -0,0 +1 @@
+3.7.1

{drep-3.6.2 → drep-3.7.1}/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 2025)
+  Matt Olm. MIT License. Banfield Lab, UC Berkeley. 2017 (last updated 2026)
 
   See https://drep.readthedocs.io/en/latest/index.html for documentation
   Choose one of the operations below for more detailed help. 
@@ -96,8 +96,8 @@ def parse_args(args):
                 or eukaryotes or things where checkM scoring does not work. Will only \
                 choose genomes based on length and N50", action='store_true')
     Iflags.add_argument('--genomeInfo', help='location of .csv file containing quality \
-                    information on the genomes. Must contain: ["genome"(basename of .fasta file \
-                    of that genome), "completeness"(0-100 value for completeness of the genome), \
+                    information on the genomes. Must contain: ["genome"(filename of .fasta file \
+                    of that genome, including extension e.g. genome.fasta), "completeness"(0-100 value for completeness of the genome), \
                     "contamination"(0-100 value of the contamination of the genome)]')
     Iflags.add_argument("--checkM_method", help="Either lineage_wf (more accurate) \
                         or taxonomy_wf (faster)", choices={'taxonomy_wf', 'lineage_wf'}, \

{drep-3.6.2 → drep-3.7.1}/drep/d_analyze.py

@@ -1016,7 +1016,9 @@ def fancy_dendrogram(linkage,names,name2color=False,threshold=False,self_thresh=
         ax = plt.gca()
         xlbls = ax.get_ymajorticklabels()
         for lbl in xlbls:
-            lbl.set_color(name2color[lbl.get_text()])
+            color = name2color[lbl.get_text()]
+            lbl.set_color('black')
+            lbl.set_bbox(dict(facecolor=color, alpha=0.7, edgecolor='none', pad=2))
 
     # Add the threshold
     if threshold:
@@ -1062,7 +1064,7 @@ def gen_color_list(names,name2cluster):
         try:
             cluster2color[cluster] = cm(1.*int(cluster)/NUM_COLORS)
         except:
-            cluster2color[cluster] = cm(1.*int(str(cluster).split('_')[1])/NUM_COLORS)
+            cluster2color[cluster] = cm(1.*float(str(cluster).split('_')[1])/NUM_COLORS)
 
     #2. generate list of colors
     colors = []
@@ -1095,7 +1097,7 @@ def gen_color_dictionary(names, name2cluster):
         try:
             cluster2color[cluster] = cm(1.*int(cluster)/NUM_COLORS)
         except:
-            cluster2color[cluster] = cm(1.*int(str(cluster).split('_')[1])/NUM_COLORS)
+            cluster2color[cluster] = cm(1.*float(str(cluster).split('_')[1])/NUM_COLORS)
 
     #2. name to color
     name2color = {}

{drep-3.6.2 → drep-3.7.1}/drep/d_bonus.py

@@ -118,9 +118,11 @@ def find_program(dep):
     works = False
     if loc != None:
         try:
-            o = subprocess.check_output([loc, '-h'],stderr= subprocess.STDOUT)
-            works = True
-        except:
+            result = subprocess.run([loc, '-h'], capture_output=True)
+            # Some tools (e.g. older fastANI) exit with code 1 on -h even when working
+            if len(result.stdout) > 0 or len(result.stderr) > 0:
+                works = True
+        except Exception:
             pass
 
     return loc, works

{drep-3.6.2 → drep-3.7.1}/drep/d_cluster/compare_utils.py

@@ -41,8 +41,11 @@ class genomeChunk():
 
     def gen_paste_cmd(self, mash_exe):
         all_file = os.path.join(self.chunk_folder, 'chunk_all.msh')
-        cmd = [mash_exe, 'paste', all_file] \
-              + glob.glob(os.path.join(self.chunk_folder, '*'))
+        list_file = os.path.join(self.chunk_folder, 'sketch_list.txt')
+        with open(list_file, 'w') as f:
+            for path in glob.glob(os.path.join(self.chunk_folder, '*.msh')):
+                f.write(path + '\n')
+        cmd = [mash_exe, 'paste', '-l', all_file, list_file]
         self.all_file = all_file
         return cmd
 
@@ -98,6 +101,18 @@ def all_vs_all_MASH(Bdb, data_folder, **kwargs):
         debug: if True, log all of the commands
         wd: if you want to log commands, you also need the wd
     """
+    # Warn if sketch size may be too small for the requested P_ani threshold
+    MASH_s = kwargs.get('MASH_sketch', 1000)
+    P_ani = kwargs.get('P_ani', 0.9)
+    if P_ani < 0.90 and MASH_s <= 1000:
+        logging.warning(
+            f"P_ani is set to {P_ani} but MASH_sketch is only {MASH_s}. "
+            "At low ANI thresholds, a small sketch size can cause Mash to underestimate "
+            "distances and place related genomes into separate primary clusters, which "
+            "means they will never be compared with the secondary algorithm. "
+            "Consider increasing -ms (MASH_sketch) to 10000 or higher."
+        )
+
     # Set up the mash folder structure
     logdir, MASH_folder, sketch_folder, mash_exe = prepare_mash(data_folder, **kwargs)
 

{drep-3.6.2 → drep-3.7.1}/drep/d_cluster/controller.py

@@ -95,6 +95,11 @@ class GenomeClusterController(object):
             Cdb = self.wd.get_db('CdbF')
             logging.info('2. Primary clustering cache loaded')
 
+        elif len(self.Bdb) < 2:
+            logging.warning("Fewer than 2 genomes remain after filtering — skipping MASH clustering")
+            Cdb = drep.d_cluster.external._gen_nomash_cdb(self.Bdb)
+            Mdb = pd.DataFrame({'Blank': []})
+
         else:
             logging.info("Running pair-wise MASH clustering")
             Mdb, Cdb, cluster_ret = drep.d_cluster.compare_utils.all_vs_all_MASH(self.Bdb, self.wd.get_dir('MASH'), **self.kwargs)
@@ -125,7 +130,12 @@ class GenomeClusterController(object):
         # Wipe any old secondary clusters
         self.wd._wipe_secondary_clusters()
 
-        if not self.kwargs.get('SkipSecondary', False):
+        if len(self.Bdb) < 2:
+            logging.warning("Fewer than 2 genomes remain after filtering — skipping secondary clustering")
+            Cdb = drep.d_cluster.utils._gen_nomani_cdb(self.MCdb, data_folder=self.wd.get_dir('data'), **self.kwargs)
+            Ndb = pd.DataFrame({'Blank': []})
+
+        elif not self.kwargs.get('SkipSecondary', False):
             if cached:
                 logging.info('3. Loading cached secondary clustering')
                 Ndb = self.wd.get_db('Ndb')

{drep-3.6.2 → drep-3.7.1}/drep/d_cluster/external.py

@@ -116,6 +116,7 @@ def run_pairwise_fastANI(genome_list, outdir, **kwargs):
         return pd.DataFrame()
 
 def run_pairwise_skani(genome_list, outdir, **kwargs):
+    p = kwargs.get('processors',6)
     code = drep.d_cluster.utils._randomString(stringLength=10)
     extra_cmd = kwargs.get('skani_extra', "")
 
@@ -134,7 +135,7 @@ def run_pairwise_skani(genome_list, outdir, **kwargs):
     exe_loc = drep.get_exe('skani')
     out_base = os.path.join(outdir, 'skani_out_{0}'.format(code))
     #cmd = [exe_loc, '--ql', glist, '--rl', glist, '-o', out_base, '--matrix', '-t', str(p), "--minFraction", str(0)]
-    cmd = [exe_loc, "triangle", "-t", "1", '-o', out_base, '--full-matrix', '-l', glist, '--detailed', '-s', "1", '--min-af', "0"]
+    cmd = [exe_loc, "triangle", "-t", str(p), '-o', out_base, '--full-matrix', '-l', glist, '--detailed', '-s', "1", '--min-af', "0"]
     if extra_cmd != "":
         cmd += extra_cmd.split(' ')
 
@@ -219,7 +220,7 @@ def fastani_one_vs_many(one, many, genome_rep_file, outdir, **kwargs):
     return fdb
 
 def load_fastani(file):
-    fdb = pd.read_csv(file, names=['reference', 'querry', 'ANI', 'j1', 'j2'], delim_whitespace=True)
+    fdb = pd.read_csv(file, names=['reference', 'querry', 'ANI', 'j1', 'j2'], sep=r'\s+')
     for c in ['reference', 'querry']:
         fdb[c] = [drep.d_cluster.utils._get_genome_name_from_fasta(x) for x in fdb[c]]
     fdb = fdb.rename(columns={'ANI':'ani'})

{drep-3.6.2 → drep-3.7.1}/drep/d_evaluate.py

@@ -253,6 +253,27 @@ def evaluate_winners(wd, **kwrags):
             Table['N50'].append(d['N50 (scaffolds)'].tolist()[0])
             Table['completeness_metric'].append(comp_str(d['Completeness'].tolist()[0]))
             Table['contamination_metric'].append(con_str(d['Contamination'].tolist()[0]))
+        elif wd.hasDb('genomeInfo'):
+            Gdb = wd.get_db('genomeInfo')
+            d = Gdb[Gdb['genome'] == row['genome']]
+            if len(d) > 0:
+                comp = d['completeness'].tolist()[0]
+                con = d['contamination'].tolist()[0]
+                Table['completeness'].append(comp)
+                Table['contamination'].append(con)
+                Table['strain_heterogeneity'].append(d['strain_heterogeneity'].tolist()[0] if 'strain_heterogeneity' in d.columns else "NA")
+                Table['size'].append(d['length'].tolist()[0] if 'length' in d.columns else "NA")
+                Table['N50'].append(d['N50'].tolist()[0] if 'N50' in d.columns else "NA")
+                Table['completeness_metric'].append(comp_str(comp))
+                Table['contamination_metric'].append(con_str(con))
+            else:
+                Table['completeness'].append("NA")
+                Table['contamination'].append("NA")
+                Table['strain_heterogeneity'].append("NA")
+                Table['size'].append("NA")
+                Table['N50'].append("NA")
+                Table['completeness_metric'].append("NA")
+                Table['contamination_metric'].append("NA")
         else:
             Table['completeness'].append("NA")
             Table['contamination'].append("NA")

{drep-3.6.2 → drep-3.7.1}/drep/d_filter.py

@@ -571,7 +571,7 @@ def run_checkM(genome_folder_whole, checkm_outf_whole, **kwargs):
         else:
              cmd = [check_exe,checkm_method,genome_folder,checkm_outf,'-f',\
                 checkm_outf + '/results.tsv','--tab_table','-t',str(t),'--pplacer_threads',\
-                str(t),'-g','-x','faa']
+                str(min(64, int(t))),'-g','-x','faa']
 
         logging.debug("Running CheckM with command: {0}".format(' '.join(cmd)))
 

{drep-3.6.2 → drep-3.7.1}/drep.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: drep
-Version: 3.6.2
+Version: 3.7.1
 Summary: De-replication of microbial genomes assembled from multiple samples
 Home-page: https://github.com/MrOlm/drep
 Author: Matt Olm
@@ -13,4 +13,12 @@ Requires-Dist: matplotlib
 Requires-Dist: biopython
 Requires-Dist: scikit-learn
 Requires-Dist: tqdm
+Requires-Dist: networkx
+Requires-Dist: setuptools
 Requires-Dist: pytest
+Dynamic: author
+Dynamic: author-email
+Dynamic: home-page
+Dynamic: license
+Dynamic: requires-dist
+Dynamic: summary

{drep-3.6.2 → drep-3.7.1}/drep.egg-info/requires.txt

@@ -5,4 +5,6 @@ matplotlib
 biopython
 scikit-learn
 tqdm
+networkx
+setuptools
 pytest

{drep-3.6.2 → drep-3.7.1}/setup.py

@@ -24,6 +24,8 @@ setup(name='drep',
           'biopython',
           'scikit-learn',
           'tqdm',
+          'networkx',
+          'setuptools',
           'pytest'
       ],
       zip_safe=False)

drep-3.6.2/drep/VERSION

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