gsrap 0.8.1__py3-none-any.whl → 0.8.3__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
@@ -69,13 +72,17 @@ 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("-t", "--taxon", metavar='', type=str, default='-', help="High-level taxon of interest. If provided, it must follow the syntax '{level}:{name}', where {level} is 'kingdom' or 'phylum'.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
     parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     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 +94,11 @@ 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 +169,15 @@ 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
@@ -69,13 +72,17 @@ 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("-t", "--taxon", metavar='', type=str, default='-', help="High-level taxon of interest. If provided, it must follow the syntax '{level}:{name}', where {level} is 'kingdom' or 'phylum'.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
     parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     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 +94,11 @@ 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 +169,15 @@ 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/downloads-checkpoint.py

@@ -243,7 +243,38 @@ def format_expansion(logger, eggnog):
     
 
 
+def check_taxon(logger, taxon, idcollection_dict):
+    
+    
+    # verify presence of needed assets
+    if 'ko_to_taxa' not in idcollection_dict.keys():
+        logger.error(f"Asset 'ko_to_taxa' not found in 'gsrap.maps'. Please update 'gsrap.maps' with 'gsrap getmaps'.")
+        return 1
+    
+    
+    # extract level and name
+    try: level, name = taxon.split(':')
+    except: 
+        logger.error(f"Provided --taxon is not well formatted: '{taxon}'.")
+        return 1
+    
+    
+    # compute available levels and check
+    avail_levels = set(['kingdom', 'phylum'])            
+    if level not in avail_levels:
+        logger.error(f"Provided level is not acceptable: '{level}' (see --taxon). Acceptable levels are {avail_levels}.")
+        return 1
+    
+    
+    # compute available taxa at input level
+    avail_taxa_at_level = set()
+    ko_to_taxa = idcollection_dict['ko_to_taxa']
+    for ko in ko_to_taxa.keys():
+        for taxon_name in ko_to_taxa[ko][level]:
+            avail_taxa_at_level.add(taxon_name)
+    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
 
-
-
-
+    
+    return 0

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
@@ -101,7 +148,7 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
             else: df_T.append(row_dict)
             
     for g in model.genes:
-        row_dict = {'gid': g.id, 'involved_in': '; '.join([r.id for r in g.reactions])}
+        row_dict = {'gid': g.id, 'name': g.name, 'involved_in': '; '.join([r.id for r in g.reactions])}
         
         for db in g.annotation.keys():
             annots = g.annotation[db]
@@ -124,12 +171,13 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
     df_R = df_R[df_R_first_cols + sorted([c for c in df_R.columns if c not in df_R_first_cols])]
     df_T = df_T[df_R_first_cols + sorted([c for c in df_T.columns if c not in df_R_first_cols])]
     df_A = df_A[df_R_first_cols + sorted([c for c in df_A.columns if c not in df_R_first_cols])]
-    df_G_first_cols = ['gid', 'involved_in']
+    df_G_first_cols = ['gid', 'name', 'involved_in']
     df_G = df_G[df_G_first_cols + sorted([c for c in df_G.columns if c not in df_G_first_cols])]
     
     
     
     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/downloads.py

@@ -243,7 +243,38 @@ def format_expansion(logger, eggnog):
     
 
 
+def check_taxon(logger, taxon, idcollection_dict):
+    
+    
+    # verify presence of needed assets
+    if 'ko_to_taxa' not in idcollection_dict.keys():
+        logger.error(f"Asset 'ko_to_taxa' not found in 'gsrap.maps'. Please update 'gsrap.maps' with 'gsrap getmaps'.")
+        return 1
+    
+    
+    # extract level and name
+    try: level, name = taxon.split(':')
+    except: 
+        logger.error(f"Provided --taxon is not well formatted: '{taxon}'.")
+        return 1
+    
+    
+    # compute available levels and check
+    avail_levels = set(['kingdom', 'phylum'])            
+    if level not in avail_levels:
+        logger.error(f"Provided level is not acceptable: '{level}' (see --taxon). Acceptable levels are {avail_levels}.")
+        return 1
+    
+    
+    # compute available taxa at input level
+    avail_taxa_at_level = set()
+    ko_to_taxa = idcollection_dict['ko_to_taxa']
+    for ko in ko_to_taxa.keys():
+        for taxon_name in ko_to_taxa[ko][level]:
+            avail_taxa_at_level.add(taxon_name)
+    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
 
-
-
-
+    
+    return 0

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
@@ -101,7 +148,7 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
             else: df_T.append(row_dict)
             
     for g in model.genes:
-        row_dict = {'gid': g.id, 'involved_in': '; '.join([r.id for r in g.reactions])}
+        row_dict = {'gid': g.id, 'name': g.name, 'involved_in': '; '.join([r.id for r in g.reactions])}
         
         for db in g.annotation.keys():
             annots = g.annotation[db]
@@ -124,12 +171,13 @@ def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None
     df_R = df_R[df_R_first_cols + sorted([c for c in df_R.columns if c not in df_R_first_cols])]
     df_T = df_T[df_R_first_cols + sorted([c for c in df_T.columns if c not in df_R_first_cols])]
     df_A = df_A[df_R_first_cols + sorted([c for c in df_A.columns if c not in df_R_first_cols])]
-    df_G_first_cols = ['gid', 'involved_in']
+    df_G_first_cols = ['gid', 'name', 'involved_in']
     df_G = df_G[df_G_first_cols + sorted([c for c in df_G.columns if c not in df_G_first_cols])]
     
     
     
     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