update

gethog3/_config.py

@@ -4,24 +4,24 @@
 oma_database_address = "/work/FAC/FBM/DBC/cdessim2/default/smajidi1/omafast/archive/OmaServer.h5"
 
 # bird
-working_folder_root = "/work/FAC/FBM/DBC/cdessim2/default/smajidi1/fastget/bird_hog/"  # bird_hog
-species_tree_address = working_folder_root + "birds370_iqtree_treefile_95bootstrap_internal_name_6let_16Nov_.nwk"
-working_id = "hog3_nov25/"
-protein_format_qfo_dataset = False
+# working_folder_root = "/work/FAC/FBM/DBC/cdessim2/default/smajidi1/fastget/bird_hog/"  # bird_hog
+# species_tree_address = working_folder_root + "birds370_iqtree_treefile_95bootstrap_internal_name_6let_16Nov_.nwk"
+# working_id = "hog3_nov25f/"
+# protein_format_qfo_dataset = False
 
 # qfo
-# working_folder_root = "/work/FAC/FBM/DBC/cdessim2/default/smajidi1/fastget/qfo3/"  # bird_hog
-# species_tree_address = working_folder_root + "lineage_tree_qfo_.nwk" #phyloxml"
-# working_id = "hog3_nov25/"
-# protein_format_qfo_dataset = True
+working_folder_root = "/work/FAC/FBM/DBC/cdessim2/default/smajidi1/fastget/qfo3/"  # bird_hog
+species_tree_address = working_folder_root + "lineage_tree_qfo_.nwk" #phyloxml"
+working_id = "hog3_nov25_prof/"
+protein_format_qfo_dataset = True
 
 
 
 working_folder = working_folder_root + working_id
 
 ## output writing files
-gene_trees_write = True  # this also goes for writing msas
-keep_subhog_each_pickle = True #False
+gene_trees_write = False  # this also goes for writing msas
+keep_subhog_each_pickle = False #False
 
 
 # filtering omamer
@@ -35,7 +35,7 @@
 dask_n_core = 1
 dask_machine = "slurm"  # "local"  "slurm"
 dask_memory_slurm = "40GB"
-dask_time_slurm = "11:00:00"
+dask_time_slurm = "00:10:00"
 dask_n_jobs = 2
 
 ## hogclass configs

gethog3/_utils.py

@@ -103,6 +103,7 @@ def prepare_species_tree(rhog_i, species_tree, rhogid_num):
 
     output: species_tree (pruned), species_names_rhog, prot_names_rhog
     """
+    assert len(rhog_i) > 0, 'input hog_i is empty, probably previous step find_rhog has issue, rhogs/HOG_B0'+str(rhogid_num)+'is empty?'
     species_names_rhog = []
     prot_names_rhog = []
     for rec in rhog_i:
@@ -119,6 +120,7 @@ def prepare_species_tree(rhog_i, species_tree, rhogid_num):
         # gene_id = prot_id[2]
         species_names_rhog.append(species_name)
         prot_names_rhog.append(prot_name)
+    assert len(species_names_rhog) > 0, "species names list is empty in rhog, probably issue in formating with || in previous step find rhog"
 
     species_names_uniqe = set(species_names_rhog)
     first_common_ancestor_name = species_tree.get_common_ancestor(species_names_uniqe).name

gethog3/main.py

@@ -113,7 +113,7 @@
 
         logger_hog.info("number of remained is " + str(len(rhogid_num_list)))
 
-        # rhogid_num_list = rhogid_num_list[:2]
+        rhogid_num_list = rhogid_num_list[:2]
         # print(rhogid_num_list[:4])
         logger_hog.info("working on a list with number of " + str(len(rhogid_num_list)))
         if not rhogid_num_list:
@@ -167,6 +167,7 @@
                 hogs_rhogs_xml_all.extend(hogs_rhog_xml_batch)
 
             logger_hog.info("Dask out gathered")
+            client_dask.p(filename=_config.working_folder+"dask-profile.html")rofile
             client_dask.close()
             client_dask.shutdown()
             logger_hog.info("Client dask closed and shut down.")