gsrap 0.8.1__py3-none-any.whl → 0.8.2__py3-none-any.whl

gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -5,6 +5,9 @@ import requests
 import importlib.metadata
 from datetime import datetime
 from packaging import version
+import atexit
+import os
+
 
 
 import cobra
@@ -69,6 +72,7 @@ def main():
     parsedb_parser.add_argument("--module", action='store_true', help="Show progress for each module of each map (use only with --progress).")
     parsedb_parser.add_argument("-f", "--focus", metavar='', type=str, default='-', help="Focus on a particular map/module (use only with --progress).")
     parsedb_parser.add_argument("-m", "--media", metavar='', type=str, default='M9,M9an,M9photo', help="Media to use during growth simulations (comma-separated IDs).")
+    parsedb_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. By default, the first medium in --media is used. Use 'none' to avoid initialization.")
     parsedb_parser.add_argument("--precursors", action='store_true', help="Verify biosynthesis of biomass precursors and show blocked ones.")
     parsedb_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
@@ -76,6 +80,8 @@ def main():
     parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Syntax is {pure_mid}-{rid1}-{rid2}. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")
     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).")
+    
     
     
     # add arguments for the 'mkmodel' command
@@ -87,10 +93,11 @@ def main():
     mkmodel_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the eggnog-mapper annotation table(s).")
     mkmodel_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     mkmodel_parser.add_argument("-u", "--universe", metavar='', type=str, default='-', help="Path to the universe model (SBML format).")
-    mkmodel_parser.add_argument("-i", "--force_inclusion", metavar='', type=str, default='-', help="Force the inclusion of the specified reactions (comma-separated IDs).")
-    mkmodel_parser.add_argument("-f", "--gap_fill", metavar='', type=str, default='-', help="Media to use during gap-filling (comma-separated IDs); if not provided, gap-filling will be skipped.")
-    mkmodel_parser.add_argument("-x", "--exclude_orphans", action='store_true', help="Exclude orphan reactions from the gap-filling repository.")
-    #mkmodel_parser.add_argument("-r", "--force_removal", metavar='', type=str, default='-', help="Force the removal of the specified reactions (comma-separated IDs) (it applies after gap-filling, before Biolog(R)-based curation).")
+    mkmodel_parser.add_argument("-i", "--include", metavar='', type=str, default='-', help="Force the inclusion of the specified reactions (comma-separated IDs).")
+    mkmodel_parser.add_argument("-f", "--gapfill", metavar='', type=str, default='-', help="Media to use during gap-filling (comma-separated IDs); if not provided, gap-filling will be skipped.")
+    mkmodel_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the model on the provided medium. By default, the first medium in --gapfill is used. Use 'none' to avoid initialization.")
+    mkmodel_parser.add_argument("-x", "--excludeorp", action='store_true', help="Exclude orphan reactions from the gap-filling repository.")
+    #mkmodel_parser.add_argument("-r", "--remove", metavar='', type=str, default='-', help="Force the removal of the specified reactions (comma-separated IDs) (it applies after gap-filling, before Biolog(R)-based curation).")
     mkmodel_parser.add_argument("-l", "--biolog", metavar='', type=str, default='-', help="Strain ID associated to binary Biolog(R) PM1, PM2A, PM3B and PM4A plates; if not provided, Biolog(R)-based model curation will be skipped (use with --cnps and --gap_fill).")
     mkmodel_parser.add_argument("-s", "--cnps", metavar='', type=str, default='glc__D,nh4,pi,so4', help="Starting C, N, P and S source metabolites (comma-separated IDs).")
     mkmodel_parser.add_argument("--conditional", metavar='', type=float, default=0.5, help="Expected minimum fraction of reactions in a biosynthetic pathway for an actually present conditional biomass precursor.")
@@ -161,6 +168,15 @@ def main():
     
     
     
+    # The following chunk suppresses the warning 
+    # "sys:1: DeprecationWarning: builtin type swigvarlink has no __module__ attribute"
+    # raised at Gsrap shutdown by calling memote.suite.api.test_model() in common/memoteutils.py
+    def _suppress_swigvarlink_warning():
+        sys.stderr = open(os.devnull, 'w')  # tested also with sys.stdout: same effect.
+    atexit.register(_suppress_swigvarlink_warning)
+    
+    
+    
     # run the program:
     set_usual_formatter(logger.handlers[0])
     current_date_time = datetime.now()

gsrap/__init__.py

@@ -5,6 +5,9 @@ import requests
 import importlib.metadata
 from datetime import datetime
 from packaging import version
+import atexit
+import os
+
 
 
 import cobra
@@ -69,6 +72,7 @@ def main():
     parsedb_parser.add_argument("--module", action='store_true', help="Show progress for each module of each map (use only with --progress).")
     parsedb_parser.add_argument("-f", "--focus", metavar='', type=str, default='-', help="Focus on a particular map/module (use only with --progress).")
     parsedb_parser.add_argument("-m", "--media", metavar='', type=str, default='M9,M9an,M9photo', help="Media to use during growth simulations (comma-separated IDs).")
+    parsedb_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. By default, the first medium in --media is used. Use 'none' to avoid initialization.")
     parsedb_parser.add_argument("--precursors", action='store_true', help="Verify biosynthesis of biomass precursors and show blocked ones.")
     parsedb_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
@@ -76,6 +80,8 @@ def main():
     parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Syntax is {pure_mid}-{rid1}-{rid2}. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")
     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).")
+    
     
     
     # add arguments for the 'mkmodel' command
@@ -87,10 +93,11 @@ def main():
     mkmodel_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the eggnog-mapper annotation table(s).")
     mkmodel_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     mkmodel_parser.add_argument("-u", "--universe", metavar='', type=str, default='-', help="Path to the universe model (SBML format).")
-    mkmodel_parser.add_argument("-i", "--force_inclusion", metavar='', type=str, default='-', help="Force the inclusion of the specified reactions (comma-separated IDs).")
-    mkmodel_parser.add_argument("-f", "--gap_fill", metavar='', type=str, default='-', help="Media to use during gap-filling (comma-separated IDs); if not provided, gap-filling will be skipped.")
-    mkmodel_parser.add_argument("-x", "--exclude_orphans", action='store_true', help="Exclude orphan reactions from the gap-filling repository.")
-    #mkmodel_parser.add_argument("-r", "--force_removal", metavar='', type=str, default='-', help="Force the removal of the specified reactions (comma-separated IDs) (it applies after gap-filling, before Biolog(R)-based curation).")
+    mkmodel_parser.add_argument("-i", "--include", metavar='', type=str, default='-', help="Force the inclusion of the specified reactions (comma-separated IDs).")
+    mkmodel_parser.add_argument("-f", "--gapfill", metavar='', type=str, default='-', help="Media to use during gap-filling (comma-separated IDs); if not provided, gap-filling will be skipped.")
+    mkmodel_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the model on the provided medium. By default, the first medium in --gapfill is used. Use 'none' to avoid initialization.")
+    mkmodel_parser.add_argument("-x", "--excludeorp", action='store_true', help="Exclude orphan reactions from the gap-filling repository.")
+    #mkmodel_parser.add_argument("-r", "--remove", metavar='', type=str, default='-', help="Force the removal of the specified reactions (comma-separated IDs) (it applies after gap-filling, before Biolog(R)-based curation).")
     mkmodel_parser.add_argument("-l", "--biolog", metavar='', type=str, default='-', help="Strain ID associated to binary Biolog(R) PM1, PM2A, PM3B and PM4A plates; if not provided, Biolog(R)-based model curation will be skipped (use with --cnps and --gap_fill).")
     mkmodel_parser.add_argument("-s", "--cnps", metavar='', type=str, default='glc__D,nh4,pi,so4', help="Starting C, N, P and S source metabolites (comma-separated IDs).")
     mkmodel_parser.add_argument("--conditional", metavar='', type=float, default=0.5, help="Expected minimum fraction of reactions in a biosynthetic pathway for an actually present conditional biomass precursor.")
@@ -161,6 +168,15 @@ def main():
     
     
     
+    # The following chunk suppresses the warning 
+    # "sys:1: DeprecationWarning: builtin type swigvarlink has no __module__ attribute"
+    # raised at Gsrap shutdown by calling memote.suite.api.test_model() in common/memoteutils.py
+    def _suppress_swigvarlink_warning():
+        sys.stderr = open(os.devnull, 'w')  # tested also with sys.stdout: same effect.
+    atexit.register(_suppress_swigvarlink_warning)
+    
+    
+    
     # run the program:
     set_usual_formatter(logger.handlers[0])
     current_date_time = datetime.now()

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

@@ -8,3 +8,4 @@ from .sbmlutils import *
 from .escherutils import *
 from .logutils import *
 from .keggutils import *
+from .memoteutils import *

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

@@ -1,3 +1,6 @@
+import importlib.metadata 
+
+
 import pandas as pnd
 
 
@@ -5,7 +8,51 @@ from .figures import figure_df_C_F1
 
 
 
-def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None):
+
+def get_summary_sheet(model, memote_results_dict):
+    df_gsrap = [
+        # Gsrap
+        {'c1': 'Gsrap version', 'c2': f"v{importlib.metadata.metadata('gsrap')['Version']}", 'c3': '', 'c4': ''},
+        {'c1': 'Model ID', 'c2': f"{model.id}", 'c3': '', 'c4': ''},
+        {'c1': 'Compartments', 'c2': f"{len(model.compartments)}", 'c3': '', 'c4': ''},
+        {'c1': 'Metabolites', 'c2': f"{len(model.metabolites)}", 'c3': '', 'c4': ''},
+        {'c1': '', 'c2': 'Unique', 'c3': f"{len(set([m.id.rsplit('_',1)[0] for m in model.metabolites]))}", 'c4': ''},
+        {'c1': 'Reactions', 'c2': f"{len(model.reactions)}", 'c3': '', 'c4': ''},
+        {'c1': '', 'c2': 'Non-transport', 'c3': f"{len([r for r in model.reactions if ((r.id != 'Biomass' and len(r.metabolites)!=1) and len(set([m.id.rsplit('_',1)[-1] for m in r.metabolites]))==1)])}", 'c4': ''},
+        {'c1': '', 'c2': 'Transport', 'c3': f"{len([r for r in model.reactions if ((r.id != 'Biomass' and len(r.metabolites)!=1) and len(set([m.id.rsplit('_',1)[-1] for m in r.metabolites]))>1)])}", 'c4': ''},
+        {'c1': '', 'c2': 'Artificial', 'c3': f"{len([r for r in model.reactions if ((r.id == 'Biomass' or len(r.metabolites)==1))])}", 'c4': ''},
+        {'c1': 'Genes', 'c2': f"{len(model.genes)}", 'c3': '', 'c4': ''},
+        # empty line
+        {'c1': '', 'c2': '', 'c3': '', 'c4': ''},
+    ]
+    df_gsrap = pnd.DataFrame.from_records(df_gsrap)
+    if memote_results_dict != None:
+        df_memote = [
+            # MEMOTE
+            {'c1': 'MEMOTE version', 'c2': f"v{memote_results_dict['version']}", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE Total Score', 'c2': f"{memote_results_dict['total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE consistency', 'c2': f"{memote_results_dict['consistency']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': '', 'c2': 'stoichiometric consistency', 'c3': f"{memote_results_dict['consistency']['test_stoichiometric_consistency']}%", 'c4': ''},
+            {'c1': '', 'c2': 'mass balance', 'c3': f"{memote_results_dict['consistency']['test_reaction_mass_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'charge balance', 'c3': f"{memote_results_dict['consistency']['test_reaction_charge_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'disconnected metabolites', 'c3': f"{memote_results_dict['consistency']['test_reaction_charge_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'unbounded flux in default conditions', 'c3': f"{memote_results_dict['consistency']['test_find_reactions_unbounded_flux_default_condition']}%", 'c4': ''},
+            {'c1': 'MEMOTE annotation Metabolites', 'c2': f"{memote_results_dict['annotation_M']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation Reactions', 'c2': f"{memote_results_dict['annotation_R']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation Genes', 'c2': f"{memote_results_dict['annotation_G']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation SBO', 'c2': f"{memote_results_dict['annotation_SBO']['sub_total']}%", 'c3': '', 'c4': ''},
+        ]
+        df_memote = pnd.DataFrame.from_records(df_memote)
+    else:
+        df_memote = pnd.DataFrame()
+
+        
+    df = pnd.concat([df_gsrap, df_memote])
+    return df
+
+
+
+def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B, df_P, df_S, df_C=None):
     
     
     # generate figures
@@ -130,6 +177,7 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
     
     
     with pnd.ExcelWriter(filepath, engine='xlsxwriter') as writer:
+        get_summary_sheet(model, memote_results_dict).to_excel(writer, sheet_name='Summary', index=False, header=False)
         df_M.to_excel(writer, sheet_name='Metabolites', index=False)
         df_R.to_excel(writer, sheet_name='Reactions', index=False)
         df_T.to_excel(writer, sheet_name='Transporters', index=False)

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

@@ -1,6 +1,10 @@
 import gempipe
 
 
+from .fluxbal import fba_no_warnings
+
+
+
 
 def apply_medium_given_column(logger, model, medium, column, is_reference=False):
         
@@ -80,4 +84,36 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
             model.reactions.get_by_id(f'EX_{substrate}_e').lower_bound = value -error
             model.reactions.get_by_id(f'EX_{substrate}_e').upper_bound = value +error
 
+    return 0
+
+
+
+def initialize_model(logger, model, dbexp, initialize, media):
+        
+        
+    if initialize in ['None', 'none']:
+        logger.info(f"Initialization will be skipped.")
+        return 0
+    elif initialize == '-':
+        if media == '-':
+            logger.info(f"No media provided: initialization will be skipped.")
+            return 0
+        else:
+            media = media.split(',')
+            medium = media[0]  # taking the first medium
+    else:
+        medium = initialize
+
+
+    if medium not in dbexp['media'].columns:
+        logger.warning(f"Medium '{medium}' does not exists: initialization will be skipped.")
+        return 0
+
+
+    response = apply_medium_given_column(logger, model, medium, dbexp['media'][medium])
+    if response == 1: return 1
+    res, obj_value, status = fba_no_warnings(model)
+    logger.info(f"Initialized on medium '{medium}': {obj_value} ({status})")
+
+
     return 0

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

@@ -0,0 +1,132 @@
+import os
+import contextlib
+import importlib.metadata 
+
+
+
+import memote
+
+
+
+
+def get_memote_results_dict(logger, model):
+    
+    
+    logger.info(f"Running selected modules of MEMOTE v{importlib.metadata.metadata('memote')['Version']}...")
+
+
+    # launch memote (only relevant modules)        
+    with open(os.devnull, 'w') as devnull:
+        with contextlib.redirect_stdout(devnull), contextlib.redirect_stderr(devnull):
+            try: memote_report = memote.suite.api.test_model(model, exclusive=[
+                'test_annotation', 
+                'test_sbo',
+                'test_stoichiometric_consistency',
+                'test_reaction_mass_balance',
+                'test_reaction_charge_balance',
+                'test_find_disconnected',
+                'test_find_reactions_unbounded_flux_default_condition'], results=True)
+            except ValueError: memote_report = None
+            
+
+    # parse memote's results
+    results_dict = {}
+    results_dict['version'] = importlib.metadata.version("memote")
+    test_results = dict(memote_report[1])['tests']
+    sections = {
+        'consistency': [
+            ('test_stoichiometric_consistency', 3),
+            ('test_reaction_mass_balance', 1),
+            ('test_reaction_charge_balance', 1),
+            ('test_find_disconnected', 1),
+            ('test_find_reactions_unbounded_flux_default_condition', 1)
+        ],
+        'annotation_M': [
+            ('test_metabolite_annotation_presence', 1),
+            ('test_metabolite_annotation_overview', 1),
+            ('test_metabolite_annotation_wrong_ids', 1),
+            ('test_metabolite_id_namespace_consistency', 1),
+        ],
+        'annotation_R': [
+            ('test_reaction_annotation_presence', 1),
+            ('test_reaction_annotation_overview', 1),
+            ('test_reaction_annotation_wrong_ids', 1),
+            ('test_reaction_id_namespace_consistency', 1),
+        ],
+        'annotation_G': [
+            ('test_gene_product_annotation_presence', 1),
+            ('test_gene_product_annotation_overview', 1),
+            ('test_gene_product_annotation_wrong_ids', 1),
+        ],
+        'annotation_SBO': [
+            ('test_metabolite_sbo_presence', 1),
+            ('test_metabolite_specific_sbo_presence', 1),
+            ('test_reaction_sbo_presence', 1),
+            ('test_metabolic_reaction_specific_sbo_presence', 1),
+            ('test_transport_reaction_specific_sbo_presence', 1),
+            ('test_exchange_specific_sbo_presence', 1),
+            ('test_demand_specific_sbo_presence', 1),
+            ('test_sink_specific_sbo_presence', 1),
+            ('test_gene_sbo_presence', 1),
+            ('test_gene_specific_sbo_presence', 1),
+            ('test_biomass_specific_sbo_presence', 1),
+        ],
+    }
+    section_multipliers = {
+        'consistency': 3,
+        'annotation_M': 1,
+        'annotation_R': 1,
+        'annotation_G': 1,
+        'annotation_SBO': 2,
+    }
+    
+    
+    numerator_total = 0
+    denominator_total = 0
+    for section, metrics in sections.items(): 
+        numerator = 0
+        denominator = 0
+        results_dict[section] = {}
+        
+        
+        # iterate metrics of this section: 
+        for metric, metric_multiplier in metrics:
+            metric_raw = test_results[metric]['metric']
+            
+            
+            # no subcategories here: 
+            if type(metric_raw) == float: 
+                metric_percentage = ((1- metric_raw ) *100)
+                numerator = numerator + (metric_percentage * metric_multiplier)
+                denominator = denominator + metric_multiplier
+                results_dict[section][metric] = round(metric_percentage, 1)
+                                
+            
+            # there are subcategories (like in the case of M/R/G/SBO annots)
+            else:   
+                results_dict[section][metric] = {}
+                for key, value in metric_raw.items():
+                    n_subcategories = len(metric_raw)
+                    multiplier_corrected = metric_multiplier / n_subcategories
+                    metric_percentage = ((1- value ) *100)
+                    numerator = numerator + (metric_percentage * multiplier_corrected)
+                    denominator = denominator + multiplier_corrected
+                    results_dict[section][metric][key] = round(metric_percentage, 1)
+                    
+                    
+        # compute the subtotal:
+        sub_total = numerator / denominator
+        results_dict[section]['sub_total'] = int(round(sub_total, 0))
+        
+        
+        # compute the total:
+        denominator_total = denominator_total + section_multipliers[section] *denominator
+        numerator_total = numerator_total + section_multipliers[section] *numerator 
+    total = numerator_total / denominator_total
+    results_dict['total'] = int(round(total, 0))
+
+
+    logger.info(f"Done! MEMOTE Total Score: {results_dict['total']}%.")
+    
+    
+    return results_dict

gsrap/commons/__init__.py

@@ -8,3 +8,4 @@ from .sbmlutils import *
 from .escherutils import *
 from .logutils import *
 from .keggutils import *
+from .memoteutils import *

gsrap/commons/excelhub.py

@@ -1,3 +1,6 @@
+import importlib.metadata 
+
+
 import pandas as pnd
 
 
@@ -5,7 +8,51 @@ from .figures import figure_df_C_F1
 
 
 
-def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None):
+
+def get_summary_sheet(model, memote_results_dict):
+    df_gsrap = [
+        # Gsrap
+        {'c1': 'Gsrap version', 'c2': f"v{importlib.metadata.metadata('gsrap')['Version']}", 'c3': '', 'c4': ''},
+        {'c1': 'Model ID', 'c2': f"{model.id}", 'c3': '', 'c4': ''},
+        {'c1': 'Compartments', 'c2': f"{len(model.compartments)}", 'c3': '', 'c4': ''},
+        {'c1': 'Metabolites', 'c2': f"{len(model.metabolites)}", 'c3': '', 'c4': ''},
+        {'c1': '', 'c2': 'Unique', 'c3': f"{len(set([m.id.rsplit('_',1)[0] for m in model.metabolites]))}", 'c4': ''},
+        {'c1': 'Reactions', 'c2': f"{len(model.reactions)}", 'c3': '', 'c4': ''},
+        {'c1': '', 'c2': 'Non-transport', 'c3': f"{len([r for r in model.reactions if ((r.id != 'Biomass' and len(r.metabolites)!=1) and len(set([m.id.rsplit('_',1)[-1] for m in r.metabolites]))==1)])}", 'c4': ''},
+        {'c1': '', 'c2': 'Transport', 'c3': f"{len([r for r in model.reactions if ((r.id != 'Biomass' and len(r.metabolites)!=1) and len(set([m.id.rsplit('_',1)[-1] for m in r.metabolites]))>1)])}", 'c4': ''},
+        {'c1': '', 'c2': 'Artificial', 'c3': f"{len([r for r in model.reactions if ((r.id == 'Biomass' or len(r.metabolites)==1))])}", 'c4': ''},
+        {'c1': 'Genes', 'c2': f"{len(model.genes)}", 'c3': '', 'c4': ''},
+        # empty line
+        {'c1': '', 'c2': '', 'c3': '', 'c4': ''},
+    ]
+    df_gsrap = pnd.DataFrame.from_records(df_gsrap)
+    if memote_results_dict != None:
+        df_memote = [
+            # MEMOTE
+            {'c1': 'MEMOTE version', 'c2': f"v{memote_results_dict['version']}", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE Total Score', 'c2': f"{memote_results_dict['total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE consistency', 'c2': f"{memote_results_dict['consistency']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': '', 'c2': 'stoichiometric consistency', 'c3': f"{memote_results_dict['consistency']['test_stoichiometric_consistency']}%", 'c4': ''},
+            {'c1': '', 'c2': 'mass balance', 'c3': f"{memote_results_dict['consistency']['test_reaction_mass_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'charge balance', 'c3': f"{memote_results_dict['consistency']['test_reaction_charge_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'disconnected metabolites', 'c3': f"{memote_results_dict['consistency']['test_reaction_charge_balance']}%", 'c4': ''},
+            {'c1': '', 'c2': 'unbounded flux in default conditions', 'c3': f"{memote_results_dict['consistency']['test_find_reactions_unbounded_flux_default_condition']}%", 'c4': ''},
+            {'c1': 'MEMOTE annotation Metabolites', 'c2': f"{memote_results_dict['annotation_M']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation Reactions', 'c2': f"{memote_results_dict['annotation_R']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation Genes', 'c2': f"{memote_results_dict['annotation_G']['sub_total']}%", 'c3': '', 'c4': ''},
+            {'c1': 'MEMOTE annotation SBO', 'c2': f"{memote_results_dict['annotation_SBO']['sub_total']}%", 'c3': '', 'c4': ''},
+        ]
+        df_memote = pnd.DataFrame.from_records(df_memote)
+    else:
+        df_memote = pnd.DataFrame()
+
+        
+    df = pnd.concat([df_gsrap, df_memote])
+    return df
+
+
+
+def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B, df_P, df_S, df_C=None):
     
     
     # generate figures
@@ -130,6 +177,7 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
     
     
     with pnd.ExcelWriter(filepath, engine='xlsxwriter') as writer:
+        get_summary_sheet(model, memote_results_dict).to_excel(writer, sheet_name='Summary', index=False, header=False)
         df_M.to_excel(writer, sheet_name='Metabolites', index=False)
         df_R.to_excel(writer, sheet_name='Reactions', index=False)
         df_T.to_excel(writer, sheet_name='Transporters', index=False)

gsrap/commons/medium.py

@@ -1,6 +1,10 @@
 import gempipe
 
 
+from .fluxbal import fba_no_warnings
+
+
+
 
 def apply_medium_given_column(logger, model, medium, column, is_reference=False):
         
@@ -80,4 +84,36 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
             model.reactions.get_by_id(f'EX_{substrate}_e').lower_bound = value -error
             model.reactions.get_by_id(f'EX_{substrate}_e').upper_bound = value +error
 
+    return 0
+
+
+
+def initialize_model(logger, model, dbexp, initialize, media):
+        
+        
+    if initialize in ['None', 'none']:
+        logger.info(f"Initialization will be skipped.")
+        return 0
+    elif initialize == '-':
+        if media == '-':
+            logger.info(f"No media provided: initialization will be skipped.")
+            return 0
+        else:
+            media = media.split(',')
+            medium = media[0]  # taking the first medium
+    else:
+        medium = initialize
+
+
+    if medium not in dbexp['media'].columns:
+        logger.warning(f"Medium '{medium}' does not exists: initialization will be skipped.")
+        return 0
+
+
+    response = apply_medium_given_column(logger, model, medium, dbexp['media'][medium])
+    if response == 1: return 1
+    res, obj_value, status = fba_no_warnings(model)
+    logger.info(f"Initialized on medium '{medium}': {obj_value} ({status})")
+
+
     return 0

gsrap/commons/memoteutils.py

@@ -0,0 +1,132 @@
+import os
+import contextlib
+import importlib.metadata 
+
+
+
+import memote
+
+
+
+
+def get_memote_results_dict(logger, model):
+    
+    
+    logger.info(f"Running selected modules of MEMOTE v{importlib.metadata.metadata('memote')['Version']}...")
+
+
+    # launch memote (only relevant modules)        
+    with open(os.devnull, 'w') as devnull:
+        with contextlib.redirect_stdout(devnull), contextlib.redirect_stderr(devnull):
+            try: memote_report = memote.suite.api.test_model(model, exclusive=[
+                'test_annotation', 
+                'test_sbo',
+                'test_stoichiometric_consistency',
+                'test_reaction_mass_balance',
+                'test_reaction_charge_balance',
+                'test_find_disconnected',
+                'test_find_reactions_unbounded_flux_default_condition'], results=True)
+            except ValueError: memote_report = None
+            
+
+    # parse memote's results
+    results_dict = {}
+    results_dict['version'] = importlib.metadata.version("memote")
+    test_results = dict(memote_report[1])['tests']
+    sections = {
+        'consistency': [
+            ('test_stoichiometric_consistency', 3),
+            ('test_reaction_mass_balance', 1),
+            ('test_reaction_charge_balance', 1),
+            ('test_find_disconnected', 1),
+            ('test_find_reactions_unbounded_flux_default_condition', 1)
+        ],
+        'annotation_M': [
+            ('test_metabolite_annotation_presence', 1),
+            ('test_metabolite_annotation_overview', 1),
+            ('test_metabolite_annotation_wrong_ids', 1),
+            ('test_metabolite_id_namespace_consistency', 1),
+        ],
+        'annotation_R': [
+            ('test_reaction_annotation_presence', 1),
+            ('test_reaction_annotation_overview', 1),
+            ('test_reaction_annotation_wrong_ids', 1),
+            ('test_reaction_id_namespace_consistency', 1),
+        ],
+        'annotation_G': [
+            ('test_gene_product_annotation_presence', 1),
+            ('test_gene_product_annotation_overview', 1),
+            ('test_gene_product_annotation_wrong_ids', 1),
+        ],
+        'annotation_SBO': [
+            ('test_metabolite_sbo_presence', 1),
+            ('test_metabolite_specific_sbo_presence', 1),
+            ('test_reaction_sbo_presence', 1),
+            ('test_metabolic_reaction_specific_sbo_presence', 1),
+            ('test_transport_reaction_specific_sbo_presence', 1),
+            ('test_exchange_specific_sbo_presence', 1),
+            ('test_demand_specific_sbo_presence', 1),
+            ('test_sink_specific_sbo_presence', 1),
+            ('test_gene_sbo_presence', 1),
+            ('test_gene_specific_sbo_presence', 1),
+            ('test_biomass_specific_sbo_presence', 1),
+        ],
+    }
+    section_multipliers = {
+        'consistency': 3,
+        'annotation_M': 1,
+        'annotation_R': 1,
+        'annotation_G': 1,
+        'annotation_SBO': 2,
+    }
+    
+    
+    numerator_total = 0
+    denominator_total = 0
+    for section, metrics in sections.items(): 
+        numerator = 0
+        denominator = 0
+        results_dict[section] = {}
+        
+        
+        # iterate metrics of this section: 
+        for metric, metric_multiplier in metrics:
+            metric_raw = test_results[metric]['metric']
+            
+            
+            # no subcategories here: 
+            if type(metric_raw) == float: 
+                metric_percentage = ((1- metric_raw ) *100)
+                numerator = numerator + (metric_percentage * metric_multiplier)
+                denominator = denominator + metric_multiplier
+                results_dict[section][metric] = round(metric_percentage, 1)
+                                
+            
+            # there are subcategories (like in the case of M/R/G/SBO annots)
+            else:   
+                results_dict[section][metric] = {}
+                for key, value in metric_raw.items():
+                    n_subcategories = len(metric_raw)
+                    multiplier_corrected = metric_multiplier / n_subcategories
+                    metric_percentage = ((1- value ) *100)
+                    numerator = numerator + (metric_percentage * multiplier_corrected)
+                    denominator = denominator + multiplier_corrected
+                    results_dict[section][metric][key] = round(metric_percentage, 1)
+                    
+                    
+        # compute the subtotal:
+        sub_total = numerator / denominator
+        results_dict[section]['sub_total'] = int(round(sub_total, 0))
+        
+        
+        # compute the total:
+        denominator_total = denominator_total + section_multipliers[section] *denominator
+        numerator_total = numerator_total + section_multipliers[section] *numerator 
+    total = numerator_total / denominator_total
+    results_dict['total'] = int(round(total, 0))
+
+
+    logger.info(f"Done! MEMOTE Total Score: {results_dict['total']}%.")
+    
+    
+    return results_dict

gsrap/mkmodel/.ipynb_checkpoints/mkmodel-checkpoint.py

@@ -41,8 +41,12 @@ from ..commons import log_unbalances
 from ..commons import format_expansion
 from ..commons import comparative_table
 from ..commons import download_keggorg
+from ..commons import initialize_model
+from ..commons import get_memote_results_dict
+
 
 from ..runsims.biosynth import biosynthesis_on_media
+from ..runsims.simplegrowth import grow_on_media
 
 from ..parsedb.cycles import verify_egc_all
 
@@ -103,7 +107,7 @@ def create_model_incore(params):
 
     ###### GAPFILLING
     # force inclusion of reactions:  
-    include_forced(logger, model, universe, args.force_inclusion)
+    include_forced(logger, model, universe, args.include)
 
     # remove missing conditional precursors + get the 'cond_col_dict' dict.
     # 'cond_col_dict' is str-to-str: {'pheme_c': 'M00868: 1/8; M00121: 2/12;', 'hemeO_c': 'gr_HemeO: 0/1'}
@@ -114,15 +118,15 @@ def create_model_incore(params):
     if response == 1: return 1
 
     # gap-fill based on media:
-    df_B = gapfill_on_media(logger, model, universe, dbexp, args.gap_fill, cond_col_dict, args.exclude_orphans)
+    df_B = gapfill_on_media(logger, model, universe, dbexp, args.gapfill, cond_col_dict, args.excludeorp)
     if type(df_B)==int: return 1
 
     # force removal of reactions
-    setattr(args, 'force_removal', '-')  # experimental feature, not public. It's main purpose was to test gap-filling in biolog_on_media().
-    remove_forced(logger, model, universe, args.force_removal)
+    setattr(args, 'remove', '-')  # experimental feature, not public. It's main purpose was to test gap-filling in biolog_on_media().
+    remove_forced(logger, model, universe, args.remove)
 
     # perform Biolog(R) curation based on media
-    df_P = biolog_on_media(logger, model, universe, dbexp, args.gap_fill, args.biolog, args.exclude_orphans, args.cnps)
+    df_P = biolog_on_media(logger, model, universe, dbexp, args.gapfill, args.biolog, args.excludeorp, args.cnps)
     if type(df_P)==int: return 1
 
 
@@ -142,12 +146,12 @@ def create_model_incore(params):
 
 
     
-    ###### CHECKS
+    ###### CHECKS 1
     # check erroneous EGCs
     verify_egc_all(logger, model, args.outdir)
     
     # check blocked metabolites / dead-ends
-    df_S = biosynthesis_on_media(logger, model, dbexp, args.gap_fill, args.biosynth)
+    df_S = biosynthesis_on_media(logger, model, dbexp, args.gapfill, args.biosynth)
     if type(df_S)==int: return 1
 
 
@@ -155,6 +159,16 @@ def create_model_incore(params):
     ###### POLISHING 3
     # reset growth environment befor saving the model
     gempipe.reset_growth_env(model)
+    
+    # initialize model
+    response = initialize_model(logger, model, dbexp, args.initialize, args.gapfill)
+    if response==1: return 1
+
+
+
+    ###### CHECKS 2
+    # compute Memote metrics
+    memote_results_dict = get_memote_results_dict(logger, model)
 
 
     
@@ -165,7 +179,7 @@ def create_model_incore(params):
     cobra.io.write_sbml_model(model, f'{args.outdir}/{model.id}.xml')        # SBML   # groups are saved only to SBML
     logger.info(f"'{args.outdir}/{model.id}.xml' created!")
     force_id_on_sbml(f'{args.outdir}/{model.id}.xml', model.id)   # force introduction of the 'id=""' field
-    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, None, df_B, df_P, df_S)  
+    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, memote_results_dict, None, df_B, df_P, df_S)  
     logger.info(f"'{args.outdir}/{model.id}.mkmodel.xlsx' created!")
         
         

gsrap/mkmodel/mkmodel.py

@@ -41,8 +41,12 @@ from ..commons import log_unbalances
 from ..commons import format_expansion
 from ..commons import comparative_table
 from ..commons import download_keggorg
+from ..commons import initialize_model
+from ..commons import get_memote_results_dict
+
 
 from ..runsims.biosynth import biosynthesis_on_media
+from ..runsims.simplegrowth import grow_on_media
 
 from ..parsedb.cycles import verify_egc_all
 
@@ -103,7 +107,7 @@ def create_model_incore(params):
 
     ###### GAPFILLING
     # force inclusion of reactions:  
-    include_forced(logger, model, universe, args.force_inclusion)
+    include_forced(logger, model, universe, args.include)
 
     # remove missing conditional precursors + get the 'cond_col_dict' dict.
     # 'cond_col_dict' is str-to-str: {'pheme_c': 'M00868: 1/8; M00121: 2/12;', 'hemeO_c': 'gr_HemeO: 0/1'}
@@ -114,15 +118,15 @@ def create_model_incore(params):
     if response == 1: return 1
 
     # gap-fill based on media:
-    df_B = gapfill_on_media(logger, model, universe, dbexp, args.gap_fill, cond_col_dict, args.exclude_orphans)
+    df_B = gapfill_on_media(logger, model, universe, dbexp, args.gapfill, cond_col_dict, args.excludeorp)
     if type(df_B)==int: return 1
 
     # force removal of reactions
-    setattr(args, 'force_removal', '-')  # experimental feature, not public. It's main purpose was to test gap-filling in biolog_on_media().
-    remove_forced(logger, model, universe, args.force_removal)
+    setattr(args, 'remove', '-')  # experimental feature, not public. It's main purpose was to test gap-filling in biolog_on_media().
+    remove_forced(logger, model, universe, args.remove)
 
     # perform Biolog(R) curation based on media
-    df_P = biolog_on_media(logger, model, universe, dbexp, args.gap_fill, args.biolog, args.exclude_orphans, args.cnps)
+    df_P = biolog_on_media(logger, model, universe, dbexp, args.gapfill, args.biolog, args.excludeorp, args.cnps)
     if type(df_P)==int: return 1
 
 
@@ -142,12 +146,12 @@ def create_model_incore(params):
 
 
     
-    ###### CHECKS
+    ###### CHECKS 1
     # check erroneous EGCs
     verify_egc_all(logger, model, args.outdir)
     
     # check blocked metabolites / dead-ends
-    df_S = biosynthesis_on_media(logger, model, dbexp, args.gap_fill, args.biosynth)
+    df_S = biosynthesis_on_media(logger, model, dbexp, args.gapfill, args.biosynth)
     if type(df_S)==int: return 1
 
 
@@ -155,6 +159,16 @@ def create_model_incore(params):
     ###### POLISHING 3
     # reset growth environment befor saving the model
     gempipe.reset_growth_env(model)
+    
+    # initialize model
+    response = initialize_model(logger, model, dbexp, args.initialize, args.gapfill)
+    if response==1: return 1
+
+
+
+    ###### CHECKS 2
+    # compute Memote metrics
+    memote_results_dict = get_memote_results_dict(logger, model)
 
 
     
@@ -165,7 +179,7 @@ def create_model_incore(params):
     cobra.io.write_sbml_model(model, f'{args.outdir}/{model.id}.xml')        # SBML   # groups are saved only to SBML
     logger.info(f"'{args.outdir}/{model.id}.xml' created!")
     force_id_on_sbml(f'{args.outdir}/{model.id}.xml', model.id)   # force introduction of the 'id=""' field
-    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, None, df_B, df_P, df_S)  
+    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, memote_results_dict, None, df_B, df_P, df_S)  
     logger.info(f"'{args.outdir}/{model.id}.mkmodel.xlsx' created!")
         
         

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

@@ -18,6 +18,9 @@ from ..commons import adjust_biomass_precursors
 from ..commons import count_undrawn_rids
 from ..commons import format_expansion
 from ..commons import download_keggorg
+from ..commons import initialize_model
+from ..commons import get_memote_results_dict
+
 
 from .introduce import introduce_metabolites
 from .introduce import introduce_reactions
@@ -178,41 +181,56 @@ def main(args, logger):
     # check erroneous EGCs
     verify_egc_all(logger, universe, args.outdir)
     
-    # check growth on minmal media
-    df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
-    if type(df_G)==int: return 1
     
-    # check blocked biomass precursors
-    cond_col_dict = adjust_biomass_precursors(logger, universe, universe, 1.0)
-    df_E = precursors_on_media(logger, universe, universe, dbexp, args.media, cond_col_dict, args.precursors)
-    if type(df_E)==int: return 1
+    if not args.justparse:
+        
+        
+        ###### CHECKS 3
+        # check growth on minmal media
+        df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
+        if type(df_G)==int: return 1
 
-    # check blocked metabolites / dead-ends
-    df_S = biosynthesis_on_media(logger, universe, dbexp, args.media, args.biosynth)
-    if type(df_S)==int: return 1
+        # check blocked biomass precursors
+        cond_col_dict = adjust_biomass_precursors(logger, universe, universe, 1.0)
+        df_E = precursors_on_media(logger, universe, universe, dbexp, args.media, cond_col_dict, args.precursors)
+        if type(df_E)==int: return 1
+
+        # check blocked metabolites / dead-ends
+        df_S = biosynthesis_on_media(logger, universe, dbexp, args.media, args.biosynth)
+        if type(df_S)==int: return 1
 
 
     
-    ###### POLISHING 2
-    # reset growth environment befor saving the model
-    gempipe.reset_growth_env(universe)
-    
+        ###### POLISHING 2
+        # reset growth environment befor saving the model
+        gempipe.reset_growth_env(universe)
+
+        # initialize model
+        response = initialize_model(logger, universe, dbexp, args.initialize, args.media)
+        if response==1: return 1
+
+
+
+        ###### CHECKS 4
+        # compute Memote metrics
+        memote_results_dict = get_memote_results_dict(logger, universe)
+
 
 
-    # output the universe
-    logger.info("Writing universal model...")
-    cobra.io.save_json_model(universe, f'{args.outdir}/universe.json')
-    logger.info(f"'{args.outdir}/universe.json' created!")
-    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
-    sheets_dict = write_excel_model(universe, f'{args.outdir}/universe.parsedb.xlsx', args.nofigs, df_E, None, None, df_S, df_C)  
-    logger.info(f"'{args.outdir}/universe.parsedb.xlsx' created!")
+        # 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!")
+        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
+        sheets_dict = write_excel_model(universe, f'{args.outdir}/universe.parsedb.xlsx', args.nofigs, memote_results_dict, df_E, None, None, df_S, df_C)  
+        logger.info(f"'{args.outdir}/universe.parsedb.xlsx' created!")
 
 
     
-    ###### CHECKS 3
-    # check if universal escher map os updated:
+    ###### CHECKS 4
+    # check if universal escher map is updated:
     count_undrawn_rids(logger, universe, lastmap)
     
     

gsrap/parsedb/parsedb.py

@@ -18,6 +18,9 @@ from ..commons import adjust_biomass_precursors
 from ..commons import count_undrawn_rids
 from ..commons import format_expansion
 from ..commons import download_keggorg
+from ..commons import initialize_model
+from ..commons import get_memote_results_dict
+
 
 from .introduce import introduce_metabolites
 from .introduce import introduce_reactions
@@ -178,41 +181,56 @@ def main(args, logger):
     # check erroneous EGCs
     verify_egc_all(logger, universe, args.outdir)
     
-    # check growth on minmal media
-    df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
-    if type(df_G)==int: return 1
     
-    # check blocked biomass precursors
-    cond_col_dict = adjust_biomass_precursors(logger, universe, universe, 1.0)
-    df_E = precursors_on_media(logger, universe, universe, dbexp, args.media, cond_col_dict, args.precursors)
-    if type(df_E)==int: return 1
+    if not args.justparse:
+        
+        
+        ###### CHECKS 3
+        # check growth on minmal media
+        df_G = grow_on_media(logger, universe, dbexp, args.media, '-', True)
+        if type(df_G)==int: return 1
 
-    # check blocked metabolites / dead-ends
-    df_S = biosynthesis_on_media(logger, universe, dbexp, args.media, args.biosynth)
-    if type(df_S)==int: return 1
+        # check blocked biomass precursors
+        cond_col_dict = adjust_biomass_precursors(logger, universe, universe, 1.0)
+        df_E = precursors_on_media(logger, universe, universe, dbexp, args.media, cond_col_dict, args.precursors)
+        if type(df_E)==int: return 1
+
+        # check blocked metabolites / dead-ends
+        df_S = biosynthesis_on_media(logger, universe, dbexp, args.media, args.biosynth)
+        if type(df_S)==int: return 1
 
 
     
-    ###### POLISHING 2
-    # reset growth environment befor saving the model
-    gempipe.reset_growth_env(universe)
-    
+        ###### POLISHING 2
+        # reset growth environment befor saving the model
+        gempipe.reset_growth_env(universe)
+
+        # initialize model
+        response = initialize_model(logger, universe, dbexp, args.initialize, args.media)
+        if response==1: return 1
+
+
+
+        ###### CHECKS 4
+        # compute Memote metrics
+        memote_results_dict = get_memote_results_dict(logger, universe)
+
 
 
-    # output the universe
-    logger.info("Writing universal model...")
-    cobra.io.save_json_model(universe, f'{args.outdir}/universe.json')
-    logger.info(f"'{args.outdir}/universe.json' created!")
-    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
-    sheets_dict = write_excel_model(universe, f'{args.outdir}/universe.parsedb.xlsx', args.nofigs, df_E, None, None, df_S, df_C)  
-    logger.info(f"'{args.outdir}/universe.parsedb.xlsx' created!")
+        # 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!")
+        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
+        sheets_dict = write_excel_model(universe, f'{args.outdir}/universe.parsedb.xlsx', args.nofigs, memote_results_dict, df_E, None, None, df_S, df_C)  
+        logger.info(f"'{args.outdir}/universe.parsedb.xlsx' created!")
 
 
     
-    ###### CHECKS 3
-    # check if universal escher map os updated:
+    ###### CHECKS 4
+    # check if universal escher map is updated:
     count_undrawn_rids(logger, universe, lastmap)
     
     

{gsrap-0.8.1.dist-info → gsrap-0.8.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: gsrap
-Version: 0.8.1
+Version: 0.8.2
 Summary: 
 License: GNU General Public License v3.0
 Author: Gioele Lazzari

{gsrap-0.8.1.dist-info → gsrap-0.8.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=lOurIE_Gn0jYS3ks3UmX11uuMrMScHADH9ivFoLpg5k,14160
-gsrap/__init__.py,sha256=lOurIE_Gn0jYS3ks3UmX11uuMrMScHADH9ivFoLpg5k,14160
+gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=o4xMVuraz_Qnf6ZOtxcYjNl-a7-zlRuZsP-GEw8lP4I,15240
+gsrap/__init__.py,sha256=o4xMVuraz_Qnf6ZOtxcYjNl-a7-zlRuZsP-GEw8lP4I,15240
 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
@@ -11,30 +11,32 @@ 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/commons/.ipynb_checkpoints/__init__-checkpoint.py,sha256=QuHINLSWNb0XKagHRWXzU5UVxw3ECTncvR7llRKblso,241
+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=e-7ffMD4R07MWEgXyGcwjhScbWnG7A3L100YWbpNMk0,8461
 gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py,sha256=_y0TgM0-Im0RT8W8z5rr4vlnGK55iRFds6DlDsjGD-8,1151
-gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py,sha256=zFTR6H7I3XeAt9_ORL0dfrwMRvshU3JPRmGif7fSY7w,7971
+gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py,sha256=1KemKQ5oWziFlrT3__70-AKjXwdsqwEzVswEOSbNBDs,11433
 gsrap/commons/.ipynb_checkpoints/figures-checkpoint.py,sha256=IRHSQXrCi4SQoISEfNB0rDhvUzbjcgsPi9zUSefsRto,4316
 gsrap/commons/.ipynb_checkpoints/fluxbal-checkpoint.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
 gsrap/commons/.ipynb_checkpoints/keggutils-checkpoint.py,sha256=M2nhHRiNH_xObHSxOIdt7ix59MrPdl9q3HNICC8X36M,4514
 gsrap/commons/.ipynb_checkpoints/logutils-checkpoint.py,sha256=VsnrkIsUftS3MOOwAd0n0peQ7a2X5ZEx930eCtzmW7g,1317
-gsrap/commons/.ipynb_checkpoints/medium-checkpoint.py,sha256=wcWiuZ-mqryoYBrsIHkIen6fBssR_1FGVoXUTApylNc,2901
+gsrap/commons/.ipynb_checkpoints/medium-checkpoint.py,sha256=AMj95IvyWpbqKAYW5QdG_pyFXHDllUZ-b8dAsPR7tvU,3859
+gsrap/commons/.ipynb_checkpoints/memoteutils-checkpoint.py,sha256=rulJFSVX4I-XGi4uHXloL0eGIkC5zhpuJYWJn9zCDbY,4981
 gsrap/commons/.ipynb_checkpoints/metrics-checkpoint.py,sha256=gvqF2c0e31m5qQWQ11JF4-eMqxtuONy_7lUiC7uaXX4,3291
 gsrap/commons/.ipynb_checkpoints/sbmlutils-checkpoint.py,sha256=gkY02qbGXrbYStn2F8J0KM0fmqati2Nbvi128EF7coI,365
-gsrap/commons/__init__.py,sha256=QuHINLSWNb0XKagHRWXzU5UVxw3ECTncvR7llRKblso,241
+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=e-7ffMD4R07MWEgXyGcwjhScbWnG7A3L100YWbpNMk0,8461
 gsrap/commons/escherutils.py,sha256=_y0TgM0-Im0RT8W8z5rr4vlnGK55iRFds6DlDsjGD-8,1151
-gsrap/commons/excelhub.py,sha256=zFTR6H7I3XeAt9_ORL0dfrwMRvshU3JPRmGif7fSY7w,7971
+gsrap/commons/excelhub.py,sha256=1KemKQ5oWziFlrT3__70-AKjXwdsqwEzVswEOSbNBDs,11433
 gsrap/commons/figures.py,sha256=IRHSQXrCi4SQoISEfNB0rDhvUzbjcgsPi9zUSefsRto,4316
 gsrap/commons/fluxbal.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
 gsrap/commons/keggutils.py,sha256=M2nhHRiNH_xObHSxOIdt7ix59MrPdl9q3HNICC8X36M,4514
 gsrap/commons/logutils.py,sha256=VsnrkIsUftS3MOOwAd0n0peQ7a2X5ZEx930eCtzmW7g,1317
-gsrap/commons/medium.py,sha256=wcWiuZ-mqryoYBrsIHkIen6fBssR_1FGVoXUTApylNc,2901
+gsrap/commons/medium.py,sha256=AMj95IvyWpbqKAYW5QdG_pyFXHDllUZ-b8dAsPR7tvU,3859
+gsrap/commons/memoteutils.py,sha256=rulJFSVX4I-XGi4uHXloL0eGIkC5zhpuJYWJn9zCDbY,4981
 gsrap/commons/metrics.py,sha256=gvqF2c0e31m5qQWQ11JF4-eMqxtuONy_7lUiC7uaXX4,3291
 gsrap/commons/sbmlutils.py,sha256=gkY02qbGXrbYStn2F8J0KM0fmqati2Nbvi128EF7coI,365
 gsrap/getmaps/.ipynb_checkpoints/__init__-checkpoint.py,sha256=L4gLwk1vgnPlQuIP-FPnvy9uXnmGVQ4Rvjv3uyciDfk,92
@@ -47,14 +49,14 @@ gsrap/mkmodel/.ipynb_checkpoints/__init__-checkpoint.py,sha256=PNze-26HMOwfdJ92K
 gsrap/mkmodel/.ipynb_checkpoints/biologcuration-checkpoint.py,sha256=Nn7z-js-mzzeO23kVM2L7sJ5PNle7AkCUeBcEAYjlFU,15378
 gsrap/mkmodel/.ipynb_checkpoints/gapfill-checkpoint.py,sha256=BPZw4sszlBhAYfHnV0pA7EpG0b2ePwS6kUfFt0Ww-ss,5159
 gsrap/mkmodel/.ipynb_checkpoints/gapfillutils-checkpoint.py,sha256=S6nFUZ1Bbdf13nVJhGK2S5C_V3hd5zwTg2o5nzejngg,3123
-gsrap/mkmodel/.ipynb_checkpoints/mkmodel-checkpoint.py,sha256=3o4_B3ALcq6GYLAZ7zteNOcLTfE3KVJO6s9L4uMmw8E,10448
+gsrap/mkmodel/.ipynb_checkpoints/mkmodel-checkpoint.py,sha256=zm-JA2sXwqTLalCc0L5POw2iRI56QK0UJMUgorHQrLw,10830
 gsrap/mkmodel/.ipynb_checkpoints/polishing-checkpoint.py,sha256=R1UdFPxN8N27Iu0jsYW2N_1BkWEbBHaMYW6NkCYZK_k,3256
 gsrap/mkmodel/.ipynb_checkpoints/pruner-checkpoint.py,sha256=FAZid-0H6j66wR2dVKRAaMaDREVt1edflmZXbX7blXg,9836
 gsrap/mkmodel/__init__.py,sha256=PNze-26HMOwfdJ92KiXpr--VV1ftVfo3CAxBZgeokp8,92
 gsrap/mkmodel/biologcuration.py,sha256=Nn7z-js-mzzeO23kVM2L7sJ5PNle7AkCUeBcEAYjlFU,15378
 gsrap/mkmodel/gapfill.py,sha256=BPZw4sszlBhAYfHnV0pA7EpG0b2ePwS6kUfFt0Ww-ss,5159
 gsrap/mkmodel/gapfillutils.py,sha256=S6nFUZ1Bbdf13nVJhGK2S5C_V3hd5zwTg2o5nzejngg,3123
-gsrap/mkmodel/mkmodel.py,sha256=3o4_B3ALcq6GYLAZ7zteNOcLTfE3KVJO6s9L4uMmw8E,10448
+gsrap/mkmodel/mkmodel.py,sha256=zm-JA2sXwqTLalCc0L5POw2iRI56QK0UJMUgorHQrLw,10830
 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
@@ -63,7 +65,7 @@ gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py,sha256=yhFiEslK1qmMC
 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=M44zFmaYu50LYDjFH3IdiezjPbzuDIzZ9ukzwU4ZBBM,7583
+gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=fTZlQvjV_wyRIxWJbW5TCVvydn0-CsYknsx9FYspdu8,8127
 gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py,sha256=WwPOzlZgsZWmJ-rvhFg21iOJ6gajgKFc2vCIHh6weBg,6103
 gsrap/parsedb/__init__.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
 gsrap/parsedb/annotation.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
@@ -71,7 +73,7 @@ gsrap/parsedb/completeness.py,sha256=yhFiEslK1qmMCk_GWZ7UZtX02FUqLU39UafG5886WsY
 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=M44zFmaYu50LYDjFH3IdiezjPbzuDIzZ9ukzwU4ZBBM,7583
+gsrap/parsedb/parsedb.py,sha256=fTZlQvjV_wyRIxWJbW5TCVvydn0-CsYknsx9FYspdu8,8127
 gsrap/parsedb/repeating.py,sha256=WwPOzlZgsZWmJ-rvhFg21iOJ6gajgKFc2vCIHh6weBg,6103
 gsrap/runsims/.ipynb_checkpoints/__init__-checkpoint.py,sha256=6E6E1gWgH0V7ls4Omx4mxxC85gMJ_27YqhjugJzlZtY,97
 gsrap/runsims/.ipynb_checkpoints/biosynth-checkpoint.py,sha256=fUlHUo4CfB4rGX9Dth87B1p5E5sz7i6spR7ZoqDDGaI,2836
@@ -91,8 +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-0.8.1.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gsrap-0.8.1.dist-info/METADATA,sha256=TvK87lEyotFJA3LRgzVFROv7mHMya-p0xPv5EUQNUJE,898
-gsrap-0.8.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-gsrap-0.8.1.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
-gsrap-0.8.1.dist-info/RECORD,,
+gsrap-0.8.2.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gsrap-0.8.2.dist-info/METADATA,sha256=CEZpXejZ1b_KWKhxPbSXKGdW01ZU_nkKFqzfafDXXGE,898
+gsrap-0.8.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+gsrap-0.8.2.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
+gsrap-0.8.2.dist-info/RECORD,,