gsrap 0.8.2__py3-none-any.whl → 0.9.0__py3-none-any.whl

gsrap/getmaps/getmaps.py

@@ -4,6 +4,7 @@ import pickle
 
 
 from .kdown import download_raw_txtfiles
+from .kdown import create_dict_keggorg
 from .kdown import create_dict_ko
 from .kdown import create_dict_c
 from .kdown import create_dict_r
@@ -20,13 +21,19 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     logger.info(f"Respectfully retrieving metabolic information from KEGG. Raw data are being saved into '{outdir}/kdown/'. Be patient, could take a couple of days...")
     os.makedirs(f'{outdir}/kdown/', exist_ok=True)
     
+    
     response = download_raw_txtfiles(logger, outdir, usecache)
     if type(response) == int: return 1
     else: RELEASE_kegg = response
     
+        
     
     logger.info("Parsing downloaded KEGG information...")
-
+    
+    response = create_dict_keggorg(logger, outdir)
+    if type(response) == int: return 1
+    else: dict_keggorg = response
+    
     response = create_dict_ko(logger, outdir)
     if type(response) == int: return 1
     else: dict_ko = response
@@ -49,7 +56,7 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     
     
     # create 'idcollection_dict' and 'summary_dict' dictionaries
-    idcollection_dict = create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md)
+    idcollection_dict = create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md)
     summary_dict = create_summary_dict(dict_c, dict_r, dict_map, dict_md)
     
         
@@ -57,7 +64,6 @@ def do_kdown(logger, outdir, usecache, keeptmp):
 
 
 
-
 def main(args, logger):
     
     
@@ -67,7 +73,7 @@ def main(args, logger):
     os.makedirs(f'{args.outdir}/', exist_ok=True)
     
     
-    # KEGG
+    # KEGG download
     response = do_kdown(logger, args.outdir, args.usecache, args.keeptmp)
     if type(response) == int: return 1
     else: RELEASE_kegg, idcollection_dict, summary_dict = response[0], response[1], response[2]
@@ -76,7 +82,9 @@ def main(args, logger):
     # create 'gsrap.maps':
     with open(f'{args.outdir}/gsrap.maps', 'wb') as wb_handler:
         pickle.dump({
-            'RELEASE_kegg': RELEASE_kegg, 'idcollection_dict': idcollection_dict, 'summary_dict': summary_dict,
+            'RELEASE_kegg': RELEASE_kegg, 
+            'idcollection_dict': idcollection_dict, 
+            'summary_dict': summary_dict, 
         }, wb_handler)
     logger.info(f"'{args.outdir}/gsrap.maps' created!")
     
@@ -87,4 +95,5 @@ def main(args, logger):
         logger.info(f"Temporary raw files deleted!")
     
     
+    
     return 0

gsrap/getmaps/kdown.py

@@ -34,6 +34,7 @@ def download_raw_txtfiles(logger, outdir, usecache):
         'orthology',
         'module', 
         'pathway',
+        'organism',
     ]
     for db in databases:
         time.sleep(0.5)
@@ -45,8 +46,9 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
     # mix the items to download to be respectful/compliant
     items_to_download = []
-
     for db in databases:
+        if db == 'organism': 
+            continue   # here we just need the list
         with open(f"{outdir}/kdown/{db}.txt", 'r') as file:
             res_string = file.read()
             rows = res_string.split('\n')
@@ -54,7 +56,6 @@ def download_raw_txtfiles(logger, outdir, usecache):
                 item_id = row.split('\t', 1)[0]
                 if item_id == '': continue
                 items_to_download.append({'db': db, 'id': item_id})
-
     random.shuffle(items_to_download)
 
 
@@ -79,6 +80,51 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
 
 
+def create_dict_keggorg(logger, outdir):
+    
+    organisms_raw = open(f'{outdir}/kdown/organism.txt', 'r').read()
+
+    # create a dataframe listing all organisms in KEGG;
+    # columns are [tnumber, name, domain, kingdom, phylum, classification]
+    df = []  # list fo dicts
+    for line in organisms_raw.strip().split("\n"):
+        fields = line.split("\t")
+        if len(fields) == 4:
+            tnumber, keggorg, name, classification = fields
+            levels = classification.split(";")
+            domain = levels[0]
+            kingdom = levels[1]
+            phylum = levels[2]
+            df.append({
+                'tnumber':tnumber, 
+                'keggorg': keggorg, 
+                'name': name, 
+                'domain': domain, 
+                'kingdom': kingdom,
+                'phylum': phylum,
+                'classification': classification
+            })
+        else: 
+            # never verified during tests!
+            logger.warning(f'Strange number of fields found in this line of "organism.txt": """{line}""".')
+    df = pnd.DataFrame.from_records(df)
+    df = df.set_index('keggorg', drop=True, verify_integrity=True)
+    
+    
+    # convert dataframe to dict
+    dict_keggorg = {}
+    for keggorg, row in df.iterrows(): 
+        dict_keggorg[keggorg] = {
+            'kingdom': row['kingdom'],
+            'phylum': row['phylum'],
+            #'name': row['name'],   # not strictly needed. Commented to save disk space.
+        }
+        
+    if logger != None: logger.info(f'Number of unique items (org): {len(dict_keggorg.keys())}.')
+    return dict_keggorg
+
+
+
 def create_dict_ko(logger, outdir):
     
     dict_ko = {}         # main output
@@ -98,6 +144,7 @@ def create_dict_ko(logger, outdir):
                 'ecs': set(),
                 'cogs': set(),
                 'gos': set(),
+                'keggorgs': set(),
             }   
         else:
             logger.error(f"{ko_id} already included!")
@@ -175,7 +222,13 @@ def create_dict_ko(logger, outdir):
                         gos = content[len('GO: '):].strip().split(' ')
                         for go in gos:
                             dict_ko[ko_id]['gos'].add(go)
-                        
+                            
+                            
+                # parse the organism-specific genes
+                if curr_header == 'GENES       ':
+                    keggorg = content.split(': ',1)[0]
+                    dict_ko[ko_id]['keggorgs'].add(keggorg.lower()) # organism.txt has IDs in lowercase
+                    
                         
                 # parse the reactions
                 if curr_header == 'REACTION    ':
@@ -547,7 +600,7 @@ def create_dict_md(logger, outdir):
 
 
 
-def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
+def create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md):
 
     idcollection_dict = {}
     
@@ -620,6 +673,24 @@ def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
         for go in dict_ko[ko_id]['gos']:
             idcollection_dict['ko_to_gos'][ko_id].add(go)
             
+    
+    # creation of 'ko_to_keggorgs' skipped as it takes too much disk space. Replaced with 'ko_to_taxa'. 
+    idcollection_dict['ko_to_taxa'] = {}
+    missing_keggorgs = set()
+    for ko_id in dict_ko.keys():
+        idcollection_dict['ko_to_taxa'][ko_id] = {'kingdom': set(), 'phylum': set()}
+        for keggorg in dict_ko[ko_id]['keggorgs']:
+            try: 
+                kingdom = dict_keggorg[keggorg]['kingdom']
+                phylum = dict_keggorg[keggorg]['phylum']
+            except: 
+                if keggorg not in missing_keggorgs:
+                    missing_keggorgs.add(keggorg)
+                    #print(f"Organism '{keggorg}' appears in 'orthology/' but not in 'organism.txt'.")
+                continue
+            idcollection_dict['ko_to_taxa'][ko_id]['kingdom'].add(kingdom)
+            idcollection_dict['ko_to_taxa'][ko_id]['phylum'].add(phylum)
+
             
     idcollection_dict['map_to_name'] = {}
     for map_id in dict_map.keys():

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

@@ -138,6 +138,15 @@ def set_up_groups(logger, model, idcollection_dict):
         
     # insert custom groups:
     custom_groups = get_custom_groups()
+    #
+    # create a group for transporters on-the-fly
+    custom_groups['transport'] = []
+    for r in model.reactions:
+        if len(r.metabolites) == 1:  # exchanges / sinks/ demands
+            custom_groups['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)
+    #
     for group_id in custom_groups.keys():
         actual_group = cobra.core.Group(
             group_id, 

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

@@ -6,6 +6,9 @@ import os
 import pandas as pnd
 
 
+from .manual import get_krs_to_exclude
+
+
 
 def parse_eggnog(model, eggnog, idcollection_dict):
     
@@ -27,9 +30,8 @@ def parse_eggnog(model, eggnog, idcollection_dict):
             
             
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -49,9 +51,34 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
     
     
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
+        if any([ko in kos_org for ko in kos]):
+            krs_org.add(kr)
+    
+    
+    return krs_org
+
+
+
+def parse_taxon(taxon, idcollection_dict):
+    
+    
+    # formatting of --taxon was already verified at startup.
+    # also the presence of 'ko_to_taxa' in idcollection_dict was veryfied at startup.
+    level, name = taxon.split(':')
+           
+        
+    # PART 1. get KO codes available
+    kos_org = set()
+    for ko in idcollection_dict['ko_to_taxa'].keys():
+        if name in idcollection_dict['ko_to_taxa'][ko][level]:
+            kos_org.add(ko)
+            
+    
+    # PART 2. get reactions in the organism (even the GPR is not complete)
+    krs_org = set()
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -60,7 +87,7 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
 
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
+def check_completeness(logger, model, progress, module, focus, taxon, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -69,6 +96,9 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
     if keggorg != '-':  # keggorg has precedence
         kr_uni = parse_keggorg(keggorg, outdir, idcollection_dict)
         kr_uni_label = f"organism code '{keggorg}'"
+    elif taxon != '-':
+        kr_uni = parse_taxon(taxon, idcollection_dict)
+        kr_uni_label = f"taxon '{taxon}'"
     elif eggnog != '-':
         for eggfile in eggnog:
             eggset = parse_eggnog(model, eggfile, idcollection_dict)
@@ -85,7 +115,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
         if 'kegg.reaction' in r.annotation.keys():
             for kr_id in r.annotation['kegg.reaction']:
                 kr_ids_modeled.add(kr_id)
-    kr_uni_missing = kr_uni - kr_ids_modeled
+    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).")
     
@@ -114,8 +144,12 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
             
     # check if 'focus' exist
     if focus != '-' and focus not in map_ids and focus not in md_ids:
-        logger.error(f"The ID provided with --focus does not exist: {focus}.")
-        return 1
+        if focus == 'transport':
+            df_coverage = None
+            return df_coverage  # just the jeneration of 'transport.json' for Escher drawing is needed here
+        else:
+            logger.error(f"The ID provided with --focus does not exist: {focus}.")
+            return 1
     if focus.startswith('map'):
         logger.debug(f"With --focus {focus}, --module will switch to False.")
         module = False
@@ -148,7 +182,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
             
         # check if this map was (at least partially) covered:
         map_krs = set([kr for kr in i['kr_ids'] if kr in kr_uni])
-        missing = map_krs - kr_ids_modeled
+        missing = (map_krs - kr_ids_modeled) - get_krs_to_exclude()
         present = kr_ids_modeled.intersection(map_krs)
         if focus == map_id: 
             missing_logger = (map_id, missing)
@@ -260,7 +294,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
 
             # check if this module was (at least partially) covered:
             md_krs = set([kr for kr in z['kr_ids_md'] if kr in kr_uni])
-            missing = md_krs - kr_ids_modeled
+            missing = (md_krs - kr_ids_modeled) - get_krs_to_exclude()
             present = kr_ids_modeled.intersection(md_krs)
             if focus == md_id: 
                 missing_logger = (md_id, missing)
@@ -309,7 +343,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
         if module and focus=='-':
             logger.info(f"{spacer}Modules of {right_item['map_id']}: completed {len(mds_completed)} - partial {len(mds_partial)} - missing {len(mds_missing)} - noreac {len(mds_noreac)}")
     if focus != '-':
-        logger.info(f"Missing reactions focusing on {missing_logger[0]}: {' '.join(list(missing_logger[1]))}.")
+        logger.info(f"Missing reactions focusing on '{missing_logger[0]}': {' '.join(list(missing_logger[1]))}.")
     if progress:
         logger.info(f"Maps: finished {len(maps_finished)} - partial {len(maps_partial)} - missing {len(maps_missing)} - noreac {len(maps_noreac)}")
             

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

@@ -5,11 +5,21 @@ def get_deprecated_kos():
     deprecated_kos = [
         'K11189',  # should be K02784
         'K07011',  # linked to lp_1215(cps3A) and lp_1216(cps3B) during 2018 and not replaced
+        #'K24301',   # to be introduced in GPRs
     ]
     return 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
+    ])
+    
+
+
+
 def get_rids_with_mancheck_gpr():
     rids_mancheck_gpr = [  # reactions with manually checked GPRs
         'SUCD1', 'ALKP', 'PFK_3', 'TCMPTS', 'PPA', 'APSR',

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

@@ -16,7 +16,10 @@ 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
+from ..commons import check_taxon
 from ..commons import download_keggorg
 from ..commons import initialize_model
 from ..commons import get_memote_results_dict
@@ -46,6 +49,7 @@ from .cycles import verify_egc_all
 def main(args, logger):
     
     
+    ###### FORMAT ARGS NOT REQUIRING RESOURCES
     # adjust out folder path                      
     while args.outdir.endswith('/'):              
         args.outdir = args.outdir[:-1]
@@ -77,17 +81,8 @@ def main(args, logger):
     if args.onlyauthor == '-': args.onlyauthor = None
     
     
-    # format the --eggnog param
-    args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
-    
-    # get the kegg organism if requested
-    if args.keggorg != '-':
-        response = download_keggorg(logger, args.keggorg, args.outdir)
-        if response == 1: return 1
-    
-    
-    
     
+    ###### 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}.")
@@ -108,9 +103,27 @@ def main(args, logger):
             kegg_compound_to_others = pickle.load(handle)
     with resources.path("gsrap.assets", f"kegg_reaction_to_others.pickle") as asset_path: 
         with open(asset_path, 'rb') as handle:
-            kegg_reaction_to_others = pickle.load(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)
@@ -166,14 +179,15 @@ def main(args, logger):
     
     ###### CHECKS 1
     # check universe completness
-    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
+    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
-    universe = remove_disconnected(logger, universe)
+    if args.keepdisconn == False:
+        universe = remove_disconnected(logger, universe)   # can be commented when using booster.py
 
     
     
@@ -182,9 +196,9 @@ def main(args, logger):
     verify_egc_all(logger, universe, args.outdir)
     
     
+    
     if not args.justparse:
         
-        
         ###### CHECKS 3
         # check growth on minmal media
         df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
@@ -217,10 +231,15 @@ def main(args, logger):
 
 
 
-        # output the universe
-        logger.info("Writing universal model...")
-        cobra.io.save_json_model(universe, f'{args.outdir}/universe.json')
-        logger.info(f"'{args.outdir}/universe.json' created!")
+    # output the universe (even when --justparse)
+    logger.info("Writing universal model...")
+    cobra.io.save_json_model(universe, f'{args.outdir}/universe.json')
+    logger.info(f"'{args.outdir}/universe.json' created!")
+    
+    
+    if not args.justparse:
+        
+        # outptu in the remaining formats:
         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
@@ -231,7 +250,9 @@ def main(args, logger):
     
     ###### CHECKS 4
     # check if universal escher map is updated:
-    count_undrawn_rids(logger, universe, lastmap)
+    count_undrawn_rids(logger, universe, lastmap, args.focus)
+    if args.focus != '-':
+        count_undrawn_rids_focus(logger, universe, lastmap, args.focus, args.outdir)
     
     
     return 0

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

@@ -45,7 +45,7 @@ def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype='R'):
             pass
         elif ko_id not in idcollection_dict['ko'] and ko_id != 'spontaneous' and ko_id != 'orphan':
             logger.error(f"{itemtype} '{rid}' has an invalid KEGG Ortholog: '{ko_id}'.")
-            return 1
+            return 1   # can be commented when migrating to new kegg release
         
         
         # check if these ko_ids are really assigned to this reaction:
@@ -61,7 +61,7 @@ def check_gpr(logger, rid, row, kr_ids, idcollection_dict, addtype='R'):
         missing_ko_ids = ko_for_rid - (set(ko_ids_parsed) - set(['spontaneous', 'orphan']))
         if len(missing_ko_ids) > 0:
             logger.error(f"Orthologs {missing_ko_ids} are missing from reaction '{rid}' ({kr_ids}).")
-            return 1
+            return 1   # can be commented when migrating to new kegg release
             
             
     return 0

gsrap/parsedb/annotation.py

@@ -138,6 +138,15 @@ def set_up_groups(logger, model, idcollection_dict):
         
     # insert custom groups:
     custom_groups = get_custom_groups()
+    #
+    # create a group for transporters on-the-fly
+    custom_groups['transport'] = []
+    for r in model.reactions:
+        if len(r.metabolites) == 1:  # exchanges / sinks/ demands
+            custom_groups['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)
+    #
     for group_id in custom_groups.keys():
         actual_group = cobra.core.Group(
             group_id, 

gsrap/parsedb/completeness.py

@@ -6,6 +6,9 @@ import os
 import pandas as pnd
 
 
+from .manual import get_krs_to_exclude
+
+
 
 def parse_eggnog(model, eggnog, idcollection_dict):
     
@@ -27,9 +30,8 @@ def parse_eggnog(model, eggnog, idcollection_dict):
             
             
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -49,9 +51,34 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
     
     
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
+        if any([ko in kos_org for ko in kos]):
+            krs_org.add(kr)
+    
+    
+    return krs_org
+
+
+
+def parse_taxon(taxon, idcollection_dict):
+    
+    
+    # formatting of --taxon was already verified at startup.
+    # also the presence of 'ko_to_taxa' in idcollection_dict was veryfied at startup.
+    level, name = taxon.split(':')
+           
+        
+    # PART 1. get KO codes available
+    kos_org = set()
+    for ko in idcollection_dict['ko_to_taxa'].keys():
+        if name in idcollection_dict['ko_to_taxa'][ko][level]:
+            kos_org.add(ko)
+            
+    
+    # PART 2. get reactions in the organism (even the GPR is not complete)
+    krs_org = set()
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -60,7 +87,7 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
 
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
+def check_completeness(logger, model, progress, module, focus, taxon, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -69,6 +96,9 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
     if keggorg != '-':  # keggorg has precedence
         kr_uni = parse_keggorg(keggorg, outdir, idcollection_dict)
         kr_uni_label = f"organism code '{keggorg}'"
+    elif taxon != '-':
+        kr_uni = parse_taxon(taxon, idcollection_dict)
+        kr_uni_label = f"taxon '{taxon}'"
     elif eggnog != '-':
         for eggfile in eggnog:
             eggset = parse_eggnog(model, eggfile, idcollection_dict)
@@ -85,7 +115,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
         if 'kegg.reaction' in r.annotation.keys():
             for kr_id in r.annotation['kegg.reaction']:
                 kr_ids_modeled.add(kr_id)
-    kr_uni_missing = kr_uni - kr_ids_modeled
+    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).")
     
@@ -114,8 +144,12 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
             
     # check if 'focus' exist
     if focus != '-' and focus not in map_ids and focus not in md_ids:
-        logger.error(f"The ID provided with --focus does not exist: {focus}.")
-        return 1
+        if focus == 'transport':
+            df_coverage = None
+            return df_coverage  # just the jeneration of 'transport.json' for Escher drawing is needed here
+        else:
+            logger.error(f"The ID provided with --focus does not exist: {focus}.")
+            return 1
     if focus.startswith('map'):
         logger.debug(f"With --focus {focus}, --module will switch to False.")
         module = False
@@ -148,7 +182,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
             
         # check if this map was (at least partially) covered:
         map_krs = set([kr for kr in i['kr_ids'] if kr in kr_uni])
-        missing = map_krs - kr_ids_modeled
+        missing = (map_krs - kr_ids_modeled) - get_krs_to_exclude()
         present = kr_ids_modeled.intersection(map_krs)
         if focus == map_id: 
             missing_logger = (map_id, missing)
@@ -260,7 +294,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
 
             # check if this module was (at least partially) covered:
             md_krs = set([kr for kr in z['kr_ids_md'] if kr in kr_uni])
-            missing = md_krs - kr_ids_modeled
+            missing = (md_krs - kr_ids_modeled) - get_krs_to_exclude()
             present = kr_ids_modeled.intersection(md_krs)
             if focus == md_id: 
                 missing_logger = (md_id, missing)
@@ -309,7 +343,7 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
         if module and focus=='-':
             logger.info(f"{spacer}Modules of {right_item['map_id']}: completed {len(mds_completed)} - partial {len(mds_partial)} - missing {len(mds_missing)} - noreac {len(mds_noreac)}")
     if focus != '-':
-        logger.info(f"Missing reactions focusing on {missing_logger[0]}: {' '.join(list(missing_logger[1]))}.")
+        logger.info(f"Missing reactions focusing on '{missing_logger[0]}': {' '.join(list(missing_logger[1]))}.")
     if progress:
         logger.info(f"Maps: finished {len(maps_finished)} - partial {len(maps_partial)} - missing {len(maps_missing)} - noreac {len(maps_noreac)}")
             

gsrap/parsedb/manual.py

@@ -5,11 +5,21 @@ def get_deprecated_kos():
     deprecated_kos = [
         'K11189',  # should be K02784
         'K07011',  # linked to lp_1215(cps3A) and lp_1216(cps3B) during 2018 and not replaced
+        #'K24301',   # to be introduced in GPRs
     ]
     return deprecated_kos
 
 
 
+def get_krs_to_exclude():
+    return set([
+        'R12328', 'R05190',  # general forms of fatty acid biosynthesis
+        'R01347', 'R01348', 'R04121',  # general forms of fatty acid degradation
+    ])
+    
+
+
+
 def get_rids_with_mancheck_gpr():
     rids_mancheck_gpr = [  # reactions with manually checked GPRs
         'SUCD1', 'ALKP', 'PFK_3', 'TCMPTS', 'PPA', 'APSR',