Merge pull request #495 from Ecogenomics/staging

Staging
Ecogenomics · Mar 23, 2023 · 21bd14d · 21bd14d
2 parents 4a922a7 + a2d71f4
commit 21bd14d
Show file tree

Hide file tree

Showing 4 changed files with 27 additions and 16 deletions.
diff --git a/gtdbtk/__init__.py b/gtdbtk/__init__.py
@@ -29,4 +29,4 @@
 __status__ = 'Production'
 __title__ = 'GTDB-Tk'
 __url__ = 'https://github.com/Ecogenomics/GTDBTk'
-__version__ = '2.2.5'
+__version__ = '2.2.6'
diff --git a/gtdbtk/classify.py b/gtdbtk/classify.py
@@ -605,13 +605,15 @@ def run(self,
                             for disappearing_genome in disappearing_genomes:
                                 disappearing_genomes_file.add_genome(disappearing_genome, tree_iter)
 
-                        class_level_classification, classified_user_genomes,warning_counter = self._parse_tree(mrca_lowtree, genomes, msa_dict,
-                                                                      percent_multihit_dict,genes, tln_table_summary_file.genomes,
-                                                                      bac_ar_diff, submsa_file_path, red_dict_file.data,
-                                                                      summary_file, pplacer_taxonomy_dict,warning_counter,
-                                                                      high_classification, debug_file, debugopt,
-                                                                      tree_mapping_file, tree_iter,
-                                                                      tree_mapping_dict_reverse)
+                        class_level_classification, classified_user_genomes,warning_counter = self._parse_tree(mrca_lowtree, genomes,
+                                                                                                               msa_dict,percent_multihit_dict,
+                                                                                                               genes, tln_table_summary_file.genomes,
+                                                                                                               bac_ar_diff, submsa_file_path,
+                                                                                                               red_dict_file.data,summary_file,
+                                                                                                               pplacer_taxonomy_dict,warning_counter,
+                                                                                                               high_classification, debug_file,
+                                                                                                               debugopt,tree_mapping_file,
+                                                                                                               tree_iter,tree_mapping_dict_reverse)
 
                         if debugopt:
                             with open(out_dir + '/' + prefix + '_class_level_classification.txt', 'a') as olf:
@@ -658,11 +660,15 @@ def run(self,
                                                                        tree_to_process)
 
                     disappearing_genomes = [seq_id for seq_id in genomes_to_process if seq_id not in pplacer_taxonomy_dict]
-                    class_level_classification, classified_user_genomes,warning_counter = self._parse_tree(tree_to_process, genomes, msa_dict, percent_multihit_dict,
-                                     tln_table_summary_file.genomes,
-                                     bac_ar_diff, user_msa_file, red_dict_file.data, summary_file,
-                                     pplacer_taxonomy_dict,warning_counter, None,
-                                     debug_file,skip_ani_screen, debugopt, None, None, None)
+                    class_level_classification, classified_user_genomes,warning_counter = self._parse_tree(tree_to_process, genomes,
+                                                                                                           msa_dict, percent_multihit_dict,
+                                                                                                           genes,tln_table_summary_file.genomes,
+                                                                                                           bac_ar_diff, user_msa_file,
+                                                                                                           red_dict_file.data, summary_file,
+                                                                                                           pplacer_taxonomy_dict,warning_counter,
+                                                                                                           None,debug_file,
+                                                                                                           debugopt,None,
+                                                                                                           None, None)
                     # add filtered genomes to the summary file
                     warning_counter = self.add_filtered_genomes_to_summary(align_dir,warning_counter, summary_file, marker_set_id, prefix)
 

diff --git a/gtdbtk/config/config.py b/gtdbtk/config/config.py
@@ -15,7 +15,7 @@
     print('_' * 80 + '\n')
     print("The 'GTDBTK_DATA_PATH' environment variable is not defined.".center(80) + '\n')
     print('Please set this variable to your reference data package.'.center(80))
-    print('https://github.com/Ecogenomics/GTDBTk#installation'.center(80))
+    print('https://ecogenomics.github.io/GTDBTk/installing/index.html'.center(80))
     print('=' * 80)
     sys.exit(1)
 

diff --git a/gtdbtk/external/mash.py b/gtdbtk/external/mash.py
@@ -79,13 +79,18 @@ def run(self, qry, ref, mash_d, mash_k, mash_v, mash_s, mash_max_dist, mash_db)
                                   self.cpus, max_d=mash_d, mash_v=mash_v)
         results = mash_dists.read(mash_max_dist)
 
+        # mash_db can be moved from filesystem to filesystem, so we need to update the path in the mash_db to
+        # reflect the new location.
+        current_ref = {os.path.basename(v): v for v in ref.values()}
+
         # Convert the results back to the accession
         path_to_qry = {v: k for (k, v) in qry.items()}
         path_to_ref = {v: k for (k, v) in ref.items()}
         out = defaultdict(dict)
         for qry_path, ref_hits in results.items():
             for ref_path, hit in ref_hits.items():
-                out[path_to_qry[qry_path]][path_to_ref[ref_path]] = hit
+                current_ref_path = current_ref[ref_path]
+                out[path_to_qry[qry_path]][path_to_ref[current_ref_path]] = hit
         return out
 
 
@@ -149,7 +154,7 @@ def read(self,max_mash_dist=100) -> Dict[str, Dict[str, Tuple[float, float, int,
             dist, p_val = float(dist), float(p_val)
             if dist <= max_mash_dist:
                 shared_num, shared_den = int(shared_n), int(shared_d)
-                out[qry_id][ref_id] = (dist, p_val, shared_num, shared_den)
+                out[qry_id][os.path.basename(ref_id)] = (dist, p_val, shared_num, shared_den)
         return out