gsrap 0.9.0__py3-none-any.whl → 0.10.1__py3-none-any.whl

gsrap/parsedb/.ipynb_checkpoints/manual-checkpoint.py

@@ -14,9 +14,28 @@ def get_deprecated_kos():
 def get_krs_to_exclude():
     return set([
         'R12328', 'R05190',  # general forms of fatty acid biosynthesis
-        'R01347', 'R04121',  # general forms of fatty acid degradation
+        'R01347', 'R01348', 'R04121',  # general forms of fatty acid degradation
+        'R11671',  # multi-step fatty acids reactions
+        'R07860', 'R01317', 'R07064',  # aspecific fatty acid reactions
+        'R11311', 'R11256', 'R11308', 'R08772', 'R08770',  # polymer reactions
+        
+        # inconclusive due to semplification
+        'R12425', 
+        
+        # "incomplete reaction" / "unclear reaction"
+        'R08414', 'R13037', 'R13034', 'R13036', 'R02825', 'R11178', 'R13325', 'R12855', 'R12856', 'R09809', 
+        'R09808', 'R08035', 'R08034', 'R11470', 'R09360', 'R08139', 'R08318', 'R07859', 'R09361', 'R09349', 
+        'R13149', 'R13066', 'R11467', 'R11255', 'R08986', 'R13156', 'R13074', 'R13150', 'R11302', 'R11388', 
+        'R08341', 'R13147', 'R13155', 'R08339', 'R11466', 'R08272', 'R09348', 'R09362', 'R11107', 'R08340', 
+        'R07940', 'R11120', 'R11245', 'R08269', 'R11131', 'R07943', 'R08342', 'R06766', 'R12584', 'R09852',
+        'R08268', 'R11129', 'R06702', 'R08866', 'R12555', 'R08927', 'R08343', 'R13067', 'R13069', 'R13068',
+        'R05670', 'R06694', 'R09851', 'R11465', 'R08928', 'R11389', 'R11464', 'R13087', 'R12586', 'R11304', 
+        'R08984', 'R11254', 'R13165', 'R12884', 'R08865', 'R13151', 'R08132', 'R08929', 'R06701', 'R08345',
+        'R11365', 'R11303', 'R06670', 'R11364', 'R09347', 'R08293', 'R11362', 'R03872', 'R06339', 'R10481', 
+        'R10480', 'R13341', 'R06505', 'R06504', 'R06326', 'R06470', 'R06467', 'R06327', 'R06503', 'R09847',
+        'R13479', 'R13447', 'R13478', 'R07510', 'R04546', 'R06468', 'R05624', 'R10706', 'R13454', 'R13556',
+        'R13455', 'R12691', 
     ])
-    
 
 
 
@@ -29,12 +48,13 @@ def get_rids_with_mancheck_gpr():
     return rids_mancheck_gpr
 
 
+
 def get_rids_with_mancheck_balancing():
     rids_mancheck_bal = [  # same reactions involving ATP can be reversible
         
         # SECTION "reversible both in KEGG and MetaCyc"
         'PGK', 'SUCOAS', 'ADK1', 'GK1', 'NNATr', 'CYTK1', 'ACKr',
-        'DGK1', 'PPAKr', 'ATPSr', 'NDPK10',
+        'DGK1', 'PPAKr', 'ATPSr', 'NDPK10', 'BUTKr',
         
         ### SECTION "reversible in KEGG but not in MetaCyc" ###
         'CYTK2',  # clearly reversible in KEGG but not in MetaCyc (RXN-7913)

gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py

@@ -1,6 +1,7 @@
 import os
 import pickle
 from importlib import resources
+import shutil
 
 
 import cobra
@@ -15,7 +16,6 @@ from ..commons import introduce_universal_biomass
 from ..commons import write_excel_model
 from ..commons import show_contributions
 from ..commons import adjust_biomass_precursors
-from ..commons import count_undrawn_rids
 from ..commons import count_undrawn_rids_focus
 
 from ..commons import format_expansion
@@ -49,13 +49,20 @@ from .cycles import verify_egc_all
 def main(args, logger):
     
     
-    ###### FORMAT ARGS NOT REQUIRING RESOURCES
+    
+    ###### PRE-PARSING
+    
     # adjust out folder path                      
     while args.outdir.endswith('/'):              
         args.outdir = args.outdir[:-1]
     os.makedirs(f'{args.outdir}/', exist_ok=True)
     
     
+    # prepare empty logs folder
+    shutil.rmtree(f'{args.outdir}/logs', ignore_errors=True)
+    os.makedirs(f'{args.outdir}/logs', exist_ok=True)
+    
+    
     # check compatibility of input parameters
     if args.progress==False and args.module==True: 
         logger.error(f"You cannot ask --module without --progress (see --help).")
@@ -81,8 +88,6 @@ def main(args, logger):
     if args.onlyauthor == '-': args.onlyauthor = None
     
     
-    
-    ###### LOAD LOCAL RESOURCES
     # check and extract the required 'gsrap.maps' file
     if os.path.exists(f'{args.inmaps}') == False:
         logger.error(f"File 'gsrap.maps' not found at {args.inmaps}.")
@@ -105,152 +110,157 @@ def main(args, logger):
         with open(asset_path, 'rb') as handle:
             kegg_reaction_to_others = pickle.load(handle) 
             
-            
-            
-    ###### FORMAT/CHECK FOCUSING ARGS
+                        
     # format the --eggnog param
     args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
     
+    
     # check the --taxon param
     if args.taxon != '-':
         response = check_taxon(logger, args.taxon, idcollection_dict)
         if response == 1: return 1
     
+    
     # get the kegg organism if requested
     if args.keggorg != '-':
         response = download_keggorg(logger, args.keggorg, args.outdir)
         if response == 1: return 1
     
     
-    
-    # DOWNLOAD ONLINE RESOURCES
-    # get dbuni and dbexp:
-    logger.info("Downloading gsrap database...")
-    response = get_databases(logger)
+    # download dbuni, dbexp and lastmap:
+    logger.info("Downloading updated gsrap assets...")
+    response = get_databases(logger, map_id=args.focus)
     if type(response)==int: return 1
     else: dbuni, dbexp, lastmap = response
     
+    
+    
+    ###### PARSING
 
     # show simple statistics of contributions
     response = show_contributions(logger, dbuni, args.goodbefore)
     if response == 1: return 1
-                                    
-        
     
-    ###### RECONSTRUCTION
+    
     # create the model
     universe = cobra.Model('universe')   
-    logger.info("Parsing gsrap database...")
     
-    # introduce M / R / T
-    universe = introduce_metabolites(logger, dbuni, universe, idcollection_dict, kegg_compound_to_others, args.goodbefore[0], args.onlyauthor)
+    
+    # introduce M 
+    universe = introduce_metabolites(logger, dbuni, universe, idcollection_dict, kegg_compound_to_others, args.outdir, args.goodbefore[0], args.onlyauthor)
     if type(universe)==int: return 1
-    universe = introduce_reactions(logger, dbuni, universe, idcollection_dict, kegg_reaction_to_others, args.goodbefore[1], args.onlyauthor)
+
+
+    # introduce R
+    universe = introduce_reactions(logger, dbuni, universe, idcollection_dict, kegg_reaction_to_others, args.outdir, args.goodbefore[1], args.onlyauthor)
     if type(universe)==int: return 1
-    universe = introduce_transporters(logger, dbuni, universe, idcollection_dict, kegg_reaction_to_others, args.goodbefore[2], args.onlyauthor)
+
+
+    # introduce T
+    universe = introduce_transporters(logger, dbuni, universe, idcollection_dict, kegg_reaction_to_others, args.outdir, args.goodbefore[2], args.onlyauthor)
     if type(universe)==int: return 1
 
+
     # introduce sinks / demands (exchanges where included during T)
     universe = introduce_sinks_demands(logger, universe)
     if type(universe)==int: return 1
 
-    # introducce biomass
+
+    # introducce universal biomass
     universe = introduce_universal_biomass(logger, dbexp, universe)
     if type(universe)==int: return 1
 
 
-
-    ###### ANNOTATION
     # translate Gs to symbols and annotate them (EC, COG, GO, ...)
     universe = translate_annotate_genes(logger, universe, idcollection_dict)
     if type(universe)==int: return 1
 
-    # introduce collectionas (groups of Rs as maps/modules)
+
+    # introduce collections (groups of Rs as maps/modules)
     universe = set_up_groups(logger, universe, idcollection_dict)
     if type(universe)==int: return 1
 
 
     
-    # # # # #   PARSING ENDS HERE   # # # # #
+    ###### POST-PARSING
+    
+    # log metrics
     log_metrics(logger, universe)
+    
+    
+    # check absence of unbalancing above the threshold
     log_unbalances(logger, universe)
 
     
-    
-    ###### CHECKS 1
     # check universe completness
     df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.taxon, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
     if type(df_C)==int: return 1
 
 
-
-    ###### POLISHING 1
     # remove disconnected metabolites
     if args.keepdisconn == False:
         universe = remove_disconnected(logger, universe)   # can be commented when using booster.py
 
     
-    
-    ###### CHECKS 2
-    # check erroneous EGCs
-    verify_egc_all(logger, universe, args.outdir)
-    
+    # avoid time-consuming activities
+    if not args.justparse:
     
     
-    if not args.justparse:
+        # check erroneous EGCs
+        verify_egc_all(logger, universe, args.outdir)
+
         
-        ###### CHECKS 3
         # check growth on minmal media
-        df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
+        df_G = grow_on_media(logger, universe, dbexp, args.media, fva=False, universe_in_parsedb=True)
         if type(df_G)==int: return 1
 
+    
         # check blocked biomass precursors
         cond_col_dict = adjust_biomass_precursors(logger, universe, universe, 1.0)
         df_E = precursors_on_media(logger, universe, universe, dbexp, args.media, cond_col_dict, args.precursors)
         if type(df_E)==int: return 1
 
+    
         # check blocked metabolites / dead-ends
         df_S = biosynthesis_on_media(logger, universe, dbexp, args.media, args.biosynth)
         if type(df_S)==int: return 1
 
 
-    
-        ###### POLISHING 2
-        # reset growth environment befor saving the model
+        # reset growth environment befor saving the model (changed during growth sims)
         gempipe.reset_growth_env(universe)
 
+        
         # initialize model
         response = initialize_model(logger, universe, dbexp, args.initialize, args.media)
         if response==1: return 1
 
 
-
-        ###### CHECKS 4
         # compute Memote metrics
         memote_results_dict = get_memote_results_dict(logger, universe)
 
 
-
-    # output the universe (even when --justparse)
+    # write JSON 
     logger.info("Writing universal model...")
     cobra.io.save_json_model(universe, f'{args.outdir}/universe.json')
     logger.info(f"'{args.outdir}/universe.json' created!")
     
     
+    # avoid time-consuming activities
     if not args.justparse:
         
-        # outptu in the remaining formats:
+        
+        # write XML
         cobra.io.write_sbml_model(universe, f'{args.outdir}/universe.xml')   # groups are saved only to SBML 
         logger.info(f"'{args.outdir}/universe.xml' created!")
         force_id_on_sbml(f'{args.outdir}/universe.xml', 'universe')   # force introduction of the 'id=""' field
+        
+        
+        # write XLSX
         sheets_dict = write_excel_model(universe, f'{args.outdir}/universe.parsedb.xlsx', args.nofigs, memote_results_dict, df_E, None, None, df_S, df_C)  
         logger.info(f"'{args.outdir}/universe.parsedb.xlsx' created!")
 
-
     
-    ###### CHECKS 4
-    # check if universal escher map is updated:
-    count_undrawn_rids(logger, universe, lastmap, args.focus)
+    # check if escher map is updated:
     if args.focus != '-':
         count_undrawn_rids_focus(logger, universe, lastmap, args.focus, args.outdir)
     

gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py

@@ -8,9 +8,13 @@ from .manual import get_rids_with_mancheck_balancing
 
 
 
-def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype='R'): 
+def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype, outdir): 
     
-    itemtype = 'Reaction' if addtype=='R' else 'Transporter'
+    
+    # define the itemtype:
+    if addtype=='R':
+        itemtype = 'Reaction' 
+    else: itemtype = 'Transporter'
     
     
     # check presence of the GPR
@@ -53,7 +57,8 @@ def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype='R'):
             if ko_id not in ko_for_rid and ko_id != 'spontaneous' and ko_id != 'orphan':
                 if kr_id != 'RXXXXX':
                     if rid not in get_rids_with_mancheck_gpr():
-                        logger.debug(f"Ortholog '{ko_id}' should not be linked to reaction '{rid}' (available for {kr_ids}: {ko_for_rid}).")
+                        with open(f"{outdir}/logs/R.orthlink.txt", 'a') as f:
+                            print(f"Ortholog '{ko_id}' should not be linked to reaction '{rid}' (available for {kr_ids}: {ko_for_rid}).", file=f)
             
     
     # check if some ko_ids are missing from this reaction:
@@ -68,12 +73,79 @@ def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype='R'):
                 
 
 
-def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addtype='R'):
-    
+def check_rstring_arrow(logger, rid, row, addtype='R'):
     
     itemtype = 'Reaction' if addtype=='R' else 'Transporter'
     
     
+    if pnd.isna(row['rstring']): 
+        logger.error(f"{itemtype} '{rid}' has no definition (rstring).")
+        return 1
+    if ' --> ' not in row['rstring'] and ' <=> ' not in row['rstring']:
+        logger.error(f"{itemtype} '{rid}' has invalid arrow: '{row['rstring']}'.")
+        return 1
+        
+        
+    return 0
+
+
+
+def check_author(logger, mrid, row, db, addtype='R'): 
+    
+    
+    # define itemtype:
+    if addtype=='M':
+        itemtype = 'Metabolite'
+    elif  addtype=='R' :
+        itemtype = 'Reaction'
+    else: itemtype = 'Transporter'
+    
+    
+    # check if author was indicated:
+    if pnd.isna(row['curator']): 
+        logger.error(f"{itemtype} '{mrid}' has no curator.")
+        return 1
+    
+    
+    # check if the are valid authors
+    authors = set()
+    for author in row['curator'].split(';'):
+        author = author.strip()
+        authors.add(author)
+        if author not in db['curators']['username'].to_list(): 
+            logger.error(f"{itemtype} '{mrid}' has invalid curator: '{author}'.")
+            return 1
+    
+    
+    return list(authors)
+    
+    
+    
+def get_curator_notes(logger, row):
+    
+    
+    # notes are separated by ';'
+    notes = []
+    if pnd.isna(row['notes']) == False:
+        for i in row['notes'].strip().split(';'):
+            notes.append(i.strip())
+        if notes == ['-']:
+            notes = []
+        
+        
+    return notes
+    
+    
+    
+def add_reaction(logger, model, rid, authors, row, kr_ids, kegg_reaction_to_others, addtype, outdir):
+    
+    
+    # define the itemtype:
+    if addtype=='R':
+        itemtype = 'Reaction' 
+    else: itemtype = 'Transporter'
+    
+    
     # create a frash reaction
     r = cobra.Reaction(rid)
     model.add_reactions([r])
@@ -95,7 +167,8 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
     # handle GPR
     r.gene_reaction_rule = row['gpr_manual'].strip()
     if r.gene_reaction_rule == 'orphan': 
-        r.gene_reaction_rule = ''    # don't want 'orphan' as artificial gene in adition to 'spontaneous'!
+        # don't want 'orphan' as artificial gene in adition to 'spontaneous'!
+        r.gene_reaction_rule = ''    
     r.update_genes_from_gpr()
     
     
@@ -105,22 +178,29 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
             logger.error(f"Metabolite '{m.id}' appears in '{r.id}' but was not previously defined.")
             return 1
         
+        
+    # write curators as annotations
+    r.annotation['curator_codes'] = authors
+        
     
     # add annotations to model (same order of Memote)
     ankeys = [
         'rhea', 'kegg.reaction', 'seed.reaction', 'metanetx.reaction', 
         'bigg.reaction', 'reactome', 'ec-code', 'brenda', 'biocyc',         
     ]
+    #
     # initialize sets:
     for ankey in ankeys:
         if ankey == 'kegg.reaction': r.annotation[ankey] = set(kr_ids) - set(['RXXXXX'])
         else: r.annotation[ankey] = set()
+    #
     # populate sets:
     for kr_id in kr_ids:
         if kr_id != 'RXXXXX':
             if kr_id in kegg_reaction_to_others.keys():
                 for ankey in ankeys:
                     r.annotation[ankey].update(kegg_reaction_to_others[kr_id][ankey])
+    #
     # save as list: 
     for ankey in ankeys:
         r.annotation[ankey] = list(r.annotation[ankey])
@@ -133,6 +213,10 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
         r.annotation['sbo'] = ['SBO:0000185']  # transport reaction
         
         
+    # add curator notes
+    r.annotation['curator_notes'] = get_curator_notes(logger, row)
+        
+        
     # check if unbalanced
     if r.check_mass_balance() != {}: 
         logger.error(f"{itemtype} '{r.id}' is unbalanced: {r.check_mass_balance()}.")
@@ -148,50 +232,3 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
     
     
     return 0
-
-
-
-def check_rstring_arrow(logger, rid, row, addtype='R'):
-    
-    itemtype = 'Reaction' if addtype=='R' else 'Transporter'
-    
-    
-    if pnd.isna(row['rstring']): 
-        logger.error(f"{itemtype} '{rid}' has no definition (rstring).")
-        return 1
-    if ' --> ' not in row['rstring'] and ' <=> ' not in row['rstring']:
-        logger.error(f"{itemtype} '{rid}' has invalid arrow: '{row['rstring']}'.")
-        return 1
-        
-        
-    return 0
-
-
-
-def check_author(logger, mrid, row, db, addtype='R'): 
-    
-    
-    if addtype=='M':
-        itemtype = 'Metabolite'
-    elif  addtype=='R' :
-        itemtype = 'Reaction'
-    else: itemtype = 'Transporter'
-    
-    
-    if pnd.isna(row['author']): 
-        logger.error(f"{itemtype} '{mrid}' has no author.")
-        return 1
-    
-    authors = set()
-    for author in row['author'].split(';'):
-        author = author.strip()
-        authors.add(author)
-        if author not in db['authors']['username'].to_list(): 
-            logger.error(f"{itemtype} '{mrid}' has invalid author: '{author}'.")
-            return 1
-    
-    
-    return list(authors)
-    
-    
-    

gsrap/parsedb/annotation.py

@@ -1,23 +1,30 @@
-import cobra
+import threading
 
+import cobra
 
 from .manual import get_deprecated_kos
 from .manual import get_custom_groups
 
+from ..commons.downloads import SimpleLoadingWheel
+
 
 
 def translate_annotate_genes(logger, model, idcollection_dict):
     
-
-       
+    
+    logger.info("Translating and annotating orthologs...")
+    
+      
     ko_to_name = idcollection_dict['ko_to_name']
     ko_to_symbols = idcollection_dict['ko_to_symbols']
     ko_to_ecs = idcollection_dict['ko_to_ecs']
     ko_to_cogs = idcollection_dict['ko_to_cogs']
     ko_to_gos = idcollection_dict['ko_to_gos']
+    ko_to_taxa = idcollection_dict['ko_to_taxa']
     
     
-    # translation dicts: assign to each KO a symbol that is unique in the universe model.
+    # create the translation dicts (ko_to_sym): 
+    # assign to each KO a symbol that is unique in the universe model.
     ko_to_sym = {}
     sym_to_ko = {}
     cnt = 0
@@ -26,20 +33,23 @@ def translate_annotate_genes(logger, model, idcollection_dict):
             continue
         ko = g.id
         cnt += 1
-        
+        #
+        # if the ko is deprecated, it was not included in 'ko_to_symbols'
         if ko in get_deprecated_kos():
-            # if the ko is deprecated, it was not included in 'ko_to_symbols'
             ko_to_sym[ko] = ko
             sym_to_ko[ko] = ko
             continue
-            
-        for symbol in ko_to_symbols[ko]:  # iterate the available symbols for this KO
-            if symbol not in sym_to_ko.keys():   # take the first available (not yet used)
+        #    
+        # iterate the available symbols for this KO
+        for symbol in ko_to_symbols[ko]:  
+            # take the first available (not yet used)
+            if symbol not in sym_to_ko.keys():   
                 ko_to_sym[ko] = symbol
                 sym_to_ko[symbol] = ko
                 break
-        
-        if cnt != len(ko_to_sym):  # no symbol was assigned (symbol was already taken by another KO)
+        #
+        # no symbol was assigned (symbol was already taken by another KO)
+        if cnt != len(ko_to_sym):  
             cnt_dups = 2
             symbol = list(ko_to_symbols[ko])[0] + f'_{cnt_dups}'   # generate a new symbol
             while cnt != len(ko_to_sym):   # until a symbol is assigned
@@ -50,7 +60,6 @@ def translate_annotate_genes(logger, model, idcollection_dict):
                 symbol = list(ko_to_symbols[ko])[0] + f'_{cnt_dups}'   # retry with the next one
                 
 
-                
     
     # insert annotations
     for g in model.genes:
@@ -67,16 +76,30 @@ def translate_annotate_genes(logger, model, idcollection_dict):
             g.annotation['cog'] = list(ko_to_cogs[ko])
             g.annotation['go'] = list(ko_to_gos[ko])
             
+            # add taxa information
+            g.annotation['kingdom'] = list(ko_to_taxa[ko]['kingdom'])
+            g.annotation['phylum'] = list(ko_to_taxa[ko]['phylum'])
+                
+            
         # add SBO annotation
         g.annotation['sbo'] = ['SBO:0000243']  # demand reaction 
         
     
         
-    # finally apply translations of IDs
+    # handle orphan and spontaneous
     translation_dict = ko_to_sym
     translation_dict['orphan'] = 'orphan'
     translation_dict['spontaneous'] = 'spontaneous'
-    cobra.manipulation.rename_genes(model, translation_dict)
+    
+    
+    # finally apply translations of IDs in a dedicated Thread
+    t1 = threading.Thread(target = cobra.manipulation.rename_genes, args=(
+        model, translation_dict))
+    t1.start()
+    slw = SimpleLoadingWheel(msg="Please wait... ")
+    while t1.is_alive():
+        slw.proceed()
+    slw.clear()
     
     
     return model
@@ -85,6 +108,8 @@ def translate_annotate_genes(logger, model, idcollection_dict):
 
 def set_up_groups(logger, model, idcollection_dict):
     
+    
+    logger.debug("Introducing groups...")
 
        
     kr_to_maps = idcollection_dict['kr_to_maps']
@@ -140,12 +165,12 @@ def set_up_groups(logger, model, idcollection_dict):
     custom_groups = get_custom_groups()
     #
     # create a group for transporters on-the-fly
-    custom_groups['transport'] = []
+    custom_groups['gr_transport'] = []
     for r in model.reactions:
-        if len(r.metabolites) == 1:  # exchanges / sinks/ demands
-            custom_groups['transport'].append(r.id)
+        if len(r.metabolites) == 1 and list(r.metabolites)[0].id.rsplit('_',1)[-1] != 'c':  # just exchanges (esclude sinks/demands)
+            custom_groups['gr_transport'].append(r.id)
         if len(set([m.id.rsplit('_', 1)[-1] for m in r.metabolites])) > 1:  # transport reactions
-            custom_groups['transport'].append(r.id)
+            custom_groups['gr_transport'].append(r.id)
     #
     for group_id in custom_groups.keys():
         actual_group = cobra.core.Group(

gsrap/parsedb/completeness.py

@@ -118,6 +118,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
     kr_uni_missing = (kr_uni - kr_ids_modeled) - get_krs_to_exclude()
     kr_uni_coverage = len(kr_ids_modeled.intersection(kr_uni)) / len(kr_uni) * 100
     logger.info(f"Coverage for {kr_uni_label}: {round(kr_uni_coverage, 0)}% ({len(kr_uni_missing)} missing).")
+    #logger.warning(f"Copy these: {kr_uni_missing}")
     
     
     # define the map?????, containing krs not included in maps
@@ -144,7 +145,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
             
     # check if 'focus' exist
     if focus != '-' and focus not in map_ids and focus not in md_ids:
-        if focus == 'transport':
+        if focus == 'gr_transport':
             df_coverage = None
             return df_coverage  # just the jeneration of 'transport.json' for Escher drawing is needed here
         else: