gsrap 0.8.3__py3-none-any.whl → 0.9.0__py3-none-any.whl

gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -82,6 +82,7 @@ def main():
     parsedb_parser.add_argument("--onlyauthor", metavar='', type=str, default='-', help="Build the universe by parsing contents of the specified author ID only. Contents affected by --goodbefore are parsed anyway.")
     parsedb_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
     parsedb_parser.add_argument("-j", "--justparse", action='store_true', help="Just parse the database without performing extra activities (saves time during universe expansion).")
+    parsedb_parser.add_argument("-d", "--keepdisconn", action='store_true', help="Do not remove disconnected metabolites.")
     
     
     

gsrap/__init__.py

@@ -82,6 +82,7 @@ def main():
     parsedb_parser.add_argument("--onlyauthor", metavar='', type=str, default='-', help="Build the universe by parsing contents of the specified author ID only. Contents affected by --goodbefore are parsed anyway.")
     parsedb_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
     parsedb_parser.add_argument("-j", "--justparse", action='store_true', help="Just parse the database without performing extra activities (saves time during universe expansion).")
+    parsedb_parser.add_argument("-d", "--keepdisconn", action='store_true', help="Do not remove disconnected metabolites.")
     
     
     

gsrap/commons/.ipynb_checkpoints/downloads-checkpoint.py

@@ -275,6 +275,67 @@ def check_taxon(logger, taxon, idcollection_dict):
     if name not in avail_taxa_at_level:
         logger.error(f"Provided taxon name is not acceptable: '{name}' (see --taxon). Acceptable taxon names for level '{level}' are {avail_taxa_at_level}.")
         return 1
-
+    
+    
+    """
+    sorted(list(df.query("kingdom == 'Bacteria'")['phylum'].unique()))
+    ['Acidobacteriota',
+     'Actinomycetota',
+     'Alphaproteobacteria',
+     'Aquificota',
+     'Armatimonadota',
+     'Atribacterota',
+     'Bacilli',
+     'Bacteria incertae sedis',
+     'Bacteroidota',
+     'Balneolota',
+     'Bdellovibrionota',
+     'Betaproteobacteria',
+     'Caldisericota',
+     'Calditrichota',
+     'Campylobacterota',
+     'Chlamydiota',
+     'Chlorobiota',
+     'Chloroflexota',
+     'Chrysiogenota',
+     'Cloacimonadota',
+     'Clostridia',
+     'Coprothermobacterota',
+     'Cyanobacteriota',
+     'Deferribacterota',
+     'Deinococcota',
+     'Deltaproteobacteria',
+     'Dictyoglomota',
+     'Elusimicrobiota',
+     'Enterobacteria',
+     'Fibrobacterota',
+     'Fidelibacterota',
+     'Fusobacteriota',
+     'Gemmatimonadota',
+     'Ignavibacteriota',
+     'Kiritimatiellota',
+     'Lentisphaerota',
+     'Melainabacteria',
+     'Mycoplasmatota',
+     'Myxococcota',
+     'Nitrospinota',
+     'Nitrospirota',
+     'Omnitrophota',
+     'Planctomycetota',
+     'Rhodothermota',
+     'Spirochaetota',
+     'Synergistota',
+     'Thermodesulfobacteriota',
+     'Thermodesulfobiota',
+     'Thermomicrobiota',
+     'Thermosulfidibacterota',
+     'Thermotogota',
+     'Verrucomicrobiota',
+     'Vulcanimicrobiota',
+     'other Bacillota',
+     'other Gammaproteobacteria',
+     'other Pseudomonadota',
+     'unclassified Bacteria']
+    """
     
     return 0

gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py

@@ -1,3 +1,9 @@
+import warnings
+import logging
+
+
+import cobra
+
 
 
 def print_json_tree(data, level=0, max_level=2):
@@ -17,7 +23,7 @@ def print_json_tree(data, level=0, max_level=2):
             
             
 
-def count_undrawn_rids(logger, universe, lastmap):
+def count_undrawn_rids(logger, universe, lastmap, focus):
     
     
     rids = set([r.id for r in universe.reactions])
@@ -32,6 +38,71 @@ def count_undrawn_rids(logger, universe, lastmap):
     logger.debug(f"Last universal map version detected: '{filename}'.")
     if len(remainings) > 0:
         logger.warning(f"Our universal map is {len(remainings)} reactions behind. Please draw!")
+        if focus == '-':
+            logger.warning(f"Drawing is eased when using '--focus'...")
     else:
         logger.info(f"Our universal map is {len(remainings)} reactions behind. Thank you ♥")
+        
+        
+        
+def count_undrawn_rids_focus(logger, universe, lastmap, focus, outdir):
+    
+    
+    # get modeled reads for this --focus:
+    rids = set()
+    try: gr = universe.groups.get_by_id(focus)
+    except: 
+        logger.warning(f"Group '{focus}' not found!")
+        return 
+    for r in gr.members:
+        rids.add(r.id)
+
+
+    # get rids on Escher: 
+    drawn_rids = set()
+    for key, value in lastmap['json'][1]['reactions'].items():
+        drawn_rids.add(value['bigg_id'])
+
+        
+    # get remaining rids for this map:
+    remainings = rids - drawn_rids
+    remainings_krs = set()
+    for rid in remainings: 
+        r = universe.reactions.get_by_id(rid)
+        krs = r.annotation['kegg.reaction']
+        for kr in krs: 
+            remainings_krs.add(kr)
+    
+    
+    if len(remainings) > 0:
+        if focus != 'transport':
+            logger.warning(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind: {' '.join(list(remainings_krs))}.")
+        else:
+            logger.warning(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind.")  # usually no kegg codes for tranport reactions
+        
+        
+        # subset the universe to ease the drawing: 
+        universe_focus = universe.copy()
+        to_remove = [r for r in universe_focus.reactions if r.id not in rids]
+        
+        
+        # trick to avoid the WARNING "cobra/core/group.py:147: UserWarning: need to pass in a list" 
+        # triggered when trying to remove reactions that are included in groups. 
+        with warnings.catch_warnings():  # temporarily suppress warnings for this block
+            warnings.simplefilter("ignore")  # ignore all warnings
+            cobra_logger = logging.getLogger("cobra.util.solver")
+            old_level = cobra_logger.level
+            cobra_logger.setLevel(logging.ERROR)   
+           
+            universe_focus.remove_reactions(to_remove,remove_orphans=True)
+
+            # restore original behaviour: 
+            cobra_logger.setLevel(old_level)  
+            
+            
+        # save the subset for drawing in Escher!
+        logger.info(f"Writing '{outdir}/{focus}.json' to ease your drawing workflow...")
+        cobra.io.save_json_model(universe_focus, f'{outdir}/{focus}.json')
+    else:
+        logger.info(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind. Thank you ♥")
         

gsrap/commons/downloads.py

@@ -275,6 +275,67 @@ def check_taxon(logger, taxon, idcollection_dict):
     if name not in avail_taxa_at_level:
         logger.error(f"Provided taxon name is not acceptable: '{name}' (see --taxon). Acceptable taxon names for level '{level}' are {avail_taxa_at_level}.")
         return 1
-
+    
+    
+    """
+    sorted(list(df.query("kingdom == 'Bacteria'")['phylum'].unique()))
+    ['Acidobacteriota',
+     'Actinomycetota',
+     'Alphaproteobacteria',
+     'Aquificota',
+     'Armatimonadota',
+     'Atribacterota',
+     'Bacilli',
+     'Bacteria incertae sedis',
+     'Bacteroidota',
+     'Balneolota',
+     'Bdellovibrionota',
+     'Betaproteobacteria',
+     'Caldisericota',
+     'Calditrichota',
+     'Campylobacterota',
+     'Chlamydiota',
+     'Chlorobiota',
+     'Chloroflexota',
+     'Chrysiogenota',
+     'Cloacimonadota',
+     'Clostridia',
+     'Coprothermobacterota',
+     'Cyanobacteriota',
+     'Deferribacterota',
+     'Deinococcota',
+     'Deltaproteobacteria',
+     'Dictyoglomota',
+     'Elusimicrobiota',
+     'Enterobacteria',
+     'Fibrobacterota',
+     'Fidelibacterota',
+     'Fusobacteriota',
+     'Gemmatimonadota',
+     'Ignavibacteriota',
+     'Kiritimatiellota',
+     'Lentisphaerota',
+     'Melainabacteria',
+     'Mycoplasmatota',
+     'Myxococcota',
+     'Nitrospinota',
+     'Nitrospirota',
+     'Omnitrophota',
+     'Planctomycetota',
+     'Rhodothermota',
+     'Spirochaetota',
+     'Synergistota',
+     'Thermodesulfobacteriota',
+     'Thermodesulfobiota',
+     'Thermomicrobiota',
+     'Thermosulfidibacterota',
+     'Thermotogota',
+     'Verrucomicrobiota',
+     'Vulcanimicrobiota',
+     'other Bacillota',
+     'other Gammaproteobacteria',
+     'other Pseudomonadota',
+     'unclassified Bacteria']
+    """
     
     return 0

gsrap/commons/escherutils.py

@@ -1,3 +1,9 @@
+import warnings
+import logging
+
+
+import cobra
+
 
 
 def print_json_tree(data, level=0, max_level=2):
@@ -17,7 +23,7 @@ def print_json_tree(data, level=0, max_level=2):
             
             
 
-def count_undrawn_rids(logger, universe, lastmap):
+def count_undrawn_rids(logger, universe, lastmap, focus):
     
     
     rids = set([r.id for r in universe.reactions])
@@ -32,6 +38,71 @@ def count_undrawn_rids(logger, universe, lastmap):
     logger.debug(f"Last universal map version detected: '{filename}'.")
     if len(remainings) > 0:
         logger.warning(f"Our universal map is {len(remainings)} reactions behind. Please draw!")
+        if focus == '-':
+            logger.warning(f"Drawing is eased when using '--focus'...")
     else:
         logger.info(f"Our universal map is {len(remainings)} reactions behind. Thank you ♥")
+        
+        
+        
+def count_undrawn_rids_focus(logger, universe, lastmap, focus, outdir):
+    
+    
+    # get modeled reads for this --focus:
+    rids = set()
+    try: gr = universe.groups.get_by_id(focus)
+    except: 
+        logger.warning(f"Group '{focus}' not found!")
+        return 
+    for r in gr.members:
+        rids.add(r.id)
+
+
+    # get rids on Escher: 
+    drawn_rids = set()
+    for key, value in lastmap['json'][1]['reactions'].items():
+        drawn_rids.add(value['bigg_id'])
+
+        
+    # get remaining rids for this map:
+    remainings = rids - drawn_rids
+    remainings_krs = set()
+    for rid in remainings: 
+        r = universe.reactions.get_by_id(rid)
+        krs = r.annotation['kegg.reaction']
+        for kr in krs: 
+            remainings_krs.add(kr)
+    
+    
+    if len(remainings) > 0:
+        if focus != 'transport':
+            logger.warning(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind: {' '.join(list(remainings_krs))}.")
+        else:
+            logger.warning(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind.")  # usually no kegg codes for tranport reactions
+        
+        
+        # subset the universe to ease the drawing: 
+        universe_focus = universe.copy()
+        to_remove = [r for r in universe_focus.reactions if r.id not in rids]
+        
+        
+        # trick to avoid the WARNING "cobra/core/group.py:147: UserWarning: need to pass in a list" 
+        # triggered when trying to remove reactions that are included in groups. 
+        with warnings.catch_warnings():  # temporarily suppress warnings for this block
+            warnings.simplefilter("ignore")  # ignore all warnings
+            cobra_logger = logging.getLogger("cobra.util.solver")
+            old_level = cobra_logger.level
+            cobra_logger.setLevel(logging.ERROR)   
+           
+            universe_focus.remove_reactions(to_remove,remove_orphans=True)
+
+            # restore original behaviour: 
+            cobra_logger.setLevel(old_level)  
+            
+            
+        # save the subset for drawing in Escher!
+        logger.info(f"Writing '{outdir}/{focus}.json' to ease your drawing workflow...")
+        cobra.io.save_json_model(universe_focus, f'{outdir}/{focus}.json')
+    else:
+        logger.info(f"Focusing on '{focus}', our universal map is {len(remainings)} reactions behind. Thank you ♥")
         

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):
     
@@ -112,7 +115,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
         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).")
     
@@ -141,8 +144,12 @@ 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:
-        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
@@ -175,7 +182,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
             
         # 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)
@@ -287,7 +294,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
 
             # 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)
@@ -336,7 +343,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
         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

@@ -16,6 +16,8 @@ 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
@@ -184,7 +186,8 @@ def main(args, logger):
 
     ###### 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
 
     
     
@@ -193,9 +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)
@@ -228,10 +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
@@ -242,7 +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):
     
@@ -112,7 +115,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
         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).")
     
@@ -141,8 +144,12 @@ 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:
-        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
@@ -175,7 +182,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
             
         # 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)
@@ -287,7 +294,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
 
             # 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)
@@ -336,7 +343,7 @@ def check_completeness(logger, model, progress, module, focus, taxon, eggnog, ke
         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',

gsrap/parsedb/parsedb.py

@@ -16,6 +16,8 @@ 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
@@ -184,7 +186,8 @@ def main(args, logger):
 
     ###### 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
 
     
     
@@ -193,9 +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)
@@ -228,10 +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
@@ -242,7 +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/repeating.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-0.8.3.dist-info → gsrap-0.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: gsrap
-Version: 0.8.3
+Version: 0.9.0
 Summary: 
 License: GNU General Public License v3.0
 Author: Gioele Lazzari

{gsrap-0.8.3.dist-info → gsrap-0.9.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
-gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=Epw4X8B1O9kWnfC9v-X4jvDXE4X-G0XlRfkMdtNvMq0,15459
-gsrap/__init__.py,sha256=Epw4X8B1O9kWnfC9v-X4jvDXE4X-G0XlRfkMdtNvMq0,15459
+gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=8or3yeJRjjuaKUSWD5w3-I27LWKUF5hz9ECtzdQ_PKU,15583
+gsrap/__init__.py,sha256=8or3yeJRjjuaKUSWD5w3-I27LWKUF5hz9ECtzdQ_PKU,15583
 gsrap/assets/.ipynb_checkpoints/PM1-checkpoint.csv,sha256=0qjaMVG_t9aFxbHbxON6ecmEUnWPwN9nhmxc61QFeCU,8761
 gsrap/assets/.ipynb_checkpoints/PM2A-checkpoint.csv,sha256=rjYTdwe8lpRS552BYiUP3J71juG2ywVdR5Sux6fjZTY,8816
 gsrap/assets/.ipynb_checkpoints/PM3B-checkpoint.csv,sha256=42IGX_2O5bRYSiHoMuVKT-T-bzVj0cSRZBvGOrbnQMA,8130
@@ -9,13 +9,13 @@ gsrap/assets/PM2A.csv,sha256=rjYTdwe8lpRS552BYiUP3J71juG2ywVdR5Sux6fjZTY,8816
 gsrap/assets/PM3B.csv,sha256=42IGX_2O5bRYSiHoMuVKT-T-bzVj0cSRZBvGOrbnQMA,8130
 gsrap/assets/PM4A.csv,sha256=f_5__0Ap_T0KYje5h9veW29I2qB4yU0h7Hr7WpaHjSc,9081
 gsrap/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-gsrap/assets/kegg_compound_to_others.pickle,sha256=pz1897cfQ7PLsYZiBVcoMQPzvRzT-nHUdgphBe0g5ZQ,8233860
-gsrap/assets/kegg_reaction_to_others.pickle,sha256=AGW8CGN5hKeXZoYn3JRF4Xu832WyNrTlMcLw7luttlc,1703146
+gsrap/assets/kegg_compound_to_others.pickle,sha256=ddo1bdFSQOSmXJBuvsWWKSsFDWT_XOfV6ZG1BBj4-ew,8498114
+gsrap/assets/kegg_reaction_to_others.pickle,sha256=x53Ch8GjNWXHeqCF5wCPdANmi0ZxmhusYGNfDlk2ZpQ,1582568
 gsrap/commons/.ipynb_checkpoints/__init__-checkpoint.py,sha256=9lrb0sBFSWEgV_e5FYzSgjTbam8b959rW_8VuxQHt1M,268
 gsrap/commons/.ipynb_checkpoints/biomass-checkpoint.py,sha256=4u7WBaUgo42tBoXDU1D0VUjICatb44e0jfswZrBeHYs,17987
 gsrap/commons/.ipynb_checkpoints/coeffs-checkpoint.py,sha256=qI3_GuqHkeA2KbK9pYdkqJaFwYemAVZJGLRR4QtHt6w,19182
-gsrap/commons/.ipynb_checkpoints/downloads-checkpoint.py,sha256=VnIFC6Y8QZ4oPyi04J_rtC2imzk5yOe0i5SpTP3MA6M,9713
-gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py,sha256=_y0TgM0-Im0RT8W8z5rr4vlnGK55iRFds6DlDsjGD-8,1151
+gsrap/commons/.ipynb_checkpoints/downloads-checkpoint.py,sha256=JrVk-UbQzelefGvOz5k4j8Ofib58u_KD_zlUzTcuv6g,11170
+gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py,sha256=VQ1FXyby6Cbfw3UNHzRoePH8M8owJ8E2rzB-11vBweA,3732
 gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py,sha256=_LtaWripY_D99f14Yk-3v9VIov2cUGzJ53AXgmNFpUk,11457
 gsrap/commons/.ipynb_checkpoints/figures-checkpoint.py,sha256=IRHSQXrCi4SQoISEfNB0rDhvUzbjcgsPi9zUSefsRto,4316
 gsrap/commons/.ipynb_checkpoints/fluxbal-checkpoint.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
@@ -28,8 +28,8 @@ gsrap/commons/.ipynb_checkpoints/sbmlutils-checkpoint.py,sha256=gkY02qbGXrbYStn2
 gsrap/commons/__init__.py,sha256=9lrb0sBFSWEgV_e5FYzSgjTbam8b959rW_8VuxQHt1M,268
 gsrap/commons/biomass.py,sha256=4u7WBaUgo42tBoXDU1D0VUjICatb44e0jfswZrBeHYs,17987
 gsrap/commons/coeffs.py,sha256=qI3_GuqHkeA2KbK9pYdkqJaFwYemAVZJGLRR4QtHt6w,19182
-gsrap/commons/downloads.py,sha256=VnIFC6Y8QZ4oPyi04J_rtC2imzk5yOe0i5SpTP3MA6M,9713
-gsrap/commons/escherutils.py,sha256=_y0TgM0-Im0RT8W8z5rr4vlnGK55iRFds6DlDsjGD-8,1151
+gsrap/commons/downloads.py,sha256=JrVk-UbQzelefGvOz5k4j8Ofib58u_KD_zlUzTcuv6g,11170
+gsrap/commons/escherutils.py,sha256=VQ1FXyby6Cbfw3UNHzRoePH8M8owJ8E2rzB-11vBweA,3732
 gsrap/commons/excelhub.py,sha256=_LtaWripY_D99f14Yk-3v9VIov2cUGzJ53AXgmNFpUk,11457
 gsrap/commons/figures.py,sha256=IRHSQXrCi4SQoISEfNB0rDhvUzbjcgsPi9zUSefsRto,4316
 gsrap/commons/fluxbal.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
@@ -60,21 +60,21 @@ gsrap/mkmodel/mkmodel.py,sha256=zm-JA2sXwqTLalCc0L5POw2iRI56QK0UJMUgorHQrLw,1083
 gsrap/mkmodel/polishing.py,sha256=R1UdFPxN8N27Iu0jsYW2N_1BkWEbBHaMYW6NkCYZK_k,3256
 gsrap/mkmodel/pruner.py,sha256=FAZid-0H6j66wR2dVKRAaMaDREVt1edflmZXbX7blXg,9836
 gsrap/parsedb/.ipynb_checkpoints/__init__-checkpoint.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
-gsrap/parsedb/.ipynb_checkpoints/annotation-checkpoint.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
-gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py,sha256=Op7VwmmwHmt1nhcl_0ISAejtLz-F9IkmnTrcJvO0BGc,12829
+gsrap/parsedb/.ipynb_checkpoints/annotation-checkpoint.py,sha256=r0sYkSqA6b8mZOGD1tgk7I__ZFkH8r4aqxVA6EUspEY,5205
+gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py,sha256=IziYv6xShUnKVxnHUwJ_I2TfiKplSXoiHQoUakI1xFI,13141
 gsrap/parsedb/.ipynb_checkpoints/cycles-checkpoint.py,sha256=HJ58LcHQseQ1eploysfXd5Y8Rip8n62qhje4pmL22VM,4761
 gsrap/parsedb/.ipynb_checkpoints/introduce-checkpoint.py,sha256=UuwGWGB2saG9VDMoboumeRBWhHOO68bs5_1r2RSkyVo,17145
-gsrap/parsedb/.ipynb_checkpoints/manual-checkpoint.py,sha256=qMKYshVftSGCRAjHC87E6n9-6kAiffFFCgHOUbqlyC0,3625
-gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=8mQgUTMOLpoeHK_X28s5jaW8adltKZ40nn_0uxmIXz8,8515
-gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py,sha256=WwPOzlZgsZWmJ-rvhFg21iOJ6gajgKFc2vCIHh6weBg,6103
+gsrap/parsedb/.ipynb_checkpoints/manual-checkpoint.py,sha256=sDux5CFNC8v2YJ3oDMV0vXsQrvSG6gov1f4hftc4nyo,3874
+gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=HbjkcWRI916_pvKVwTruNUbRWrHRlT__200wocLSOMY,8860
+gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py,sha256=ph1gC-84SyBnBuM7s0A9jTJBJmBlRzq0lk4FYG70228,6215
 gsrap/parsedb/__init__.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
-gsrap/parsedb/annotation.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
-gsrap/parsedb/completeness.py,sha256=Op7VwmmwHmt1nhcl_0ISAejtLz-F9IkmnTrcJvO0BGc,12829
+gsrap/parsedb/annotation.py,sha256=r0sYkSqA6b8mZOGD1tgk7I__ZFkH8r4aqxVA6EUspEY,5205
+gsrap/parsedb/completeness.py,sha256=IziYv6xShUnKVxnHUwJ_I2TfiKplSXoiHQoUakI1xFI,13141
 gsrap/parsedb/cycles.py,sha256=HJ58LcHQseQ1eploysfXd5Y8Rip8n62qhje4pmL22VM,4761
 gsrap/parsedb/introduce.py,sha256=UuwGWGB2saG9VDMoboumeRBWhHOO68bs5_1r2RSkyVo,17145
-gsrap/parsedb/manual.py,sha256=qMKYshVftSGCRAjHC87E6n9-6kAiffFFCgHOUbqlyC0,3625
-gsrap/parsedb/parsedb.py,sha256=8mQgUTMOLpoeHK_X28s5jaW8adltKZ40nn_0uxmIXz8,8515
-gsrap/parsedb/repeating.py,sha256=WwPOzlZgsZWmJ-rvhFg21iOJ6gajgKFc2vCIHh6weBg,6103
+gsrap/parsedb/manual.py,sha256=8UCvfMK7HSXd_-JlnIWgMmBnsFGojTGE63iOJE5J_6E,3884
+gsrap/parsedb/parsedb.py,sha256=HbjkcWRI916_pvKVwTruNUbRWrHRlT__200wocLSOMY,8860
+gsrap/parsedb/repeating.py,sha256=ph1gC-84SyBnBuM7s0A9jTJBJmBlRzq0lk4FYG70228,6215
 gsrap/runsims/.ipynb_checkpoints/__init__-checkpoint.py,sha256=6E6E1gWgH0V7ls4Omx4mxxC85gMJ_27YqhjugJzlZtY,97
 gsrap/runsims/.ipynb_checkpoints/biosynth-checkpoint.py,sha256=fUlHUo4CfB4rGX9Dth87B1p5E5sz7i6spR7ZoqDDGaI,2836
 gsrap/runsims/.ipynb_checkpoints/cnps-checkpoint.py,sha256=A0U8QPqW_uyrtHs99F286aEDEC6eukHXeMWrmnd0efA,5636
@@ -93,8 +93,8 @@ gsrap/runsims/precursors.py,sha256=1RNt_Rxs0L1lolDmYh4_CiZgiwHfU5B_AcomJO6vJ28,2
 gsrap/runsims/runsims.py,sha256=2FC5Gs8oSYyZTjHF3A7aXB_O6myVfcn3bCxQfLJlZTk,2842
 gsrap/runsims/simplegrowth.py,sha256=tCQHTMUqum1YwlBKRTNaQoag2co_yQlCaKmISOARAlE,2353
 gsrap/runsims/singleomission.py,sha256=jMuKAi0pINP8Jlrm-yI-tX7D110VzttR3YfTSnDRe4I,2847
-gsrap-0.8.3.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gsrap-0.8.3.dist-info/METADATA,sha256=JADff6H-Y_SWY5PtR9qzEhmabesB6A5dLa-V0GTKqgc,898
-gsrap-0.8.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-gsrap-0.8.3.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
-gsrap-0.8.3.dist-info/RECORD,,
+gsrap-0.9.0.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gsrap-0.9.0.dist-info/METADATA,sha256=Zd_nRZYHhrKBle7mzTBWnQQ1KdMWlHPuKqH9-YU5IHA,898
+gsrap-0.9.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+gsrap-0.9.0.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
+gsrap-0.9.0.dist-info/RECORD,,