gsrap 0.8.3__tar.gz → 0.9.0__tar.gz

{gsrap-0.8.3 → gsrap-0.9.0}/PKG-INFO

@@ -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 → gsrap-0.9.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gsrap"
-version = "0.8.3"
+version = "0.9.0"
 description = ""
 authors = ["Gioele Lazzari"]
 license = "GNU General Public License v3.0"

{gsrap-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.9.0/src/gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py

@@ -0,0 +1,108 @@
+import warnings
+import logging
+
+
+import cobra
+
+
+
+def print_json_tree(data, level=0, max_level=2):
+    # explore contents of a json object
+    
+    if level > max_level:
+        return
+    indent = '  ' * level
+    if isinstance(data, dict):
+        for key, value in data.items():
+            print(f"{indent}{key}")
+            print_tree(value, level + 1, max_level)
+    elif isinstance(data, list):
+        for i, item in enumerate(data):
+            print(f"{indent}[{i}]")
+            print_tree(item, level + 1, max_level)
+            
+            
+
+def count_undrawn_rids(logger, universe, lastmap, focus):
+    
+    
+    rids = set([r.id for r in universe.reactions])
+    
+    drawn_rids = set()
+    for key, value in lastmap['json'][1]['reactions'].items():
+        drawn_rids.add(value['bigg_id'])
+        
+        
+    remainings = rids - drawn_rids
+    filename = lastmap['filename']
+    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-0.8.3 → gsrap-0.9.0}/src/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-0.9.0/src/gsrap/commons/escherutils.py

@@ -0,0 +1,108 @@
+import warnings
+import logging
+
+
+import cobra
+
+
+
+def print_json_tree(data, level=0, max_level=2):
+    # explore contents of a json object
+    
+    if level > max_level:
+        return
+    indent = '  ' * level
+    if isinstance(data, dict):
+        for key, value in data.items():
+            print(f"{indent}{key}")
+            print_tree(value, level + 1, max_level)
+    elif isinstance(data, list):
+        for i, item in enumerate(data):
+            print(f"{indent}[{i}]")
+            print_tree(item, level + 1, max_level)
+            
+            
+
+def count_undrawn_rids(logger, universe, lastmap, focus):
+    
+    
+    rids = set([r.id for r in universe.reactions])
+    
+    drawn_rids = set()
+    for key, value in lastmap['json'][1]['reactions'].items():
+        drawn_rids.add(value['bigg_id'])
+        
+        
+    remainings = rids - drawn_rids
+    filename = lastmap['filename']
+    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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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-0.8.3 → gsrap-0.9.0}/src/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/src/gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py

@@ -1,37 +0,0 @@
-
-
-def print_json_tree(data, level=0, max_level=2):
-    # explore contents of a json object
-    
-    if level > max_level:
-        return
-    indent = '  ' * level
-    if isinstance(data, dict):
-        for key, value in data.items():
-            print(f"{indent}{key}")
-            print_tree(value, level + 1, max_level)
-    elif isinstance(data, list):
-        for i, item in enumerate(data):
-            print(f"{indent}[{i}]")
-            print_tree(item, level + 1, max_level)
-            
-            
-
-def count_undrawn_rids(logger, universe, lastmap):
-    
-    
-    rids = set([r.id for r in universe.reactions])
-    
-    drawn_rids = set()
-    for key, value in lastmap['json'][1]['reactions'].items():
-        drawn_rids.add(value['bigg_id'])
-        
-        
-    remainings = rids - drawn_rids
-    filename = lastmap['filename']
-    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!")
-    else:
-        logger.info(f"Our universal map is {len(remainings)} reactions behind. Thank you ♥")
-        

gsrap-0.8.3/src/gsrap/commons/escherutils.py

@@ -1,37 +0,0 @@
-
-
-def print_json_tree(data, level=0, max_level=2):
-    # explore contents of a json object
-    
-    if level > max_level:
-        return
-    indent = '  ' * level
-    if isinstance(data, dict):
-        for key, value in data.items():
-            print(f"{indent}{key}")
-            print_tree(value, level + 1, max_level)
-    elif isinstance(data, list):
-        for i, item in enumerate(data):
-            print(f"{indent}[{i}]")
-            print_tree(item, level + 1, max_level)
-            
-            
-
-def count_undrawn_rids(logger, universe, lastmap):
-    
-    
-    rids = set([r.id for r in universe.reactions])
-    
-    drawn_rids = set()
-    for key, value in lastmap['json'][1]['reactions'].items():
-        drawn_rids.add(value['bigg_id'])
-        
-        
-    remainings = rids - drawn_rids
-    filename = lastmap['filename']
-    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!")
-    else:
-        logger.info(f"Our universal map is {len(remainings)} reactions behind. Thank you ♥")
-