gsrap 0.8.0__py3-none-any.whl → 0.8.1__py3-none-any.whl

gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -72,7 +72,7 @@ def main():
     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).")
-    parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code.")
+    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.")
@@ -85,7 +85,7 @@ def main():
     mkmodel_parser.add_argument("-c", "--cores", metavar='', type=int, default=0, help="Number of cores to use (if 0, use all available cores).")
     mkmodel_parser.add_argument("-o", "--outdir", metavar='', type=str, default='./', help="Main output directory (will be created if not existing).")
     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.")
+    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.")

gsrap/__init__.py

@@ -72,7 +72,7 @@ def main():
     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).")
-    parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code.")
+    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.")
@@ -85,7 +85,7 @@ def main():
     mkmodel_parser.add_argument("-c", "--cores", metavar='', type=int, default=0, help="Number of cores to use (if 0, use all available cores).")
     mkmodel_parser.add_argument("-o", "--outdir", metavar='', type=str, default='./', help="Main output directory (will be created if not existing).")
     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.")
+    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.")

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

@@ -17,10 +17,9 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
     column = column.to_dict()
 
     
-    # add trace elements:
-    column['fe2'] = 'NL'
-    column['mobd'] = 'NL'
-    column['cobalt2'] = 'NL'
+    # add default elements (acqueous media)
+    column['h2o'] = 'NL'
+    column['h'] = '-0.0001'  # pH=7
 
 
     # reset exchanges

gsrap/commons/medium.py

@@ -17,10 +17,9 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
     column = column.to_dict()
 
     
-    # add trace elements:
-    column['fe2'] = 'NL'
-    column['mobd'] = 'NL'
-    column['cobalt2'] = 'NL'
+    # add default elements (acqueous media)
+    column['h2o'] = 'NL'
+    column['h'] = '-0.0001'  # pH=7
 
 
     # reset exchanges

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

@@ -44,6 +44,9 @@ from ..commons import download_keggorg
 
 from ..runsims.biosynth import biosynthesis_on_media
 
+from ..parsedb.cycles import verify_egc_all
+
+
 
 
 def create_model_incore(params):
@@ -140,6 +143,9 @@ def create_model_incore(params):
 
     
     ###### CHECKS
+    # 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)
     if type(df_S)==int: return 1

gsrap/mkmodel/mkmodel.py

@@ -44,6 +44,9 @@ from ..commons import download_keggorg
 
 from ..runsims.biosynth import biosynthesis_on_media
 
+from ..parsedb.cycles import verify_egc_all
+
+
 
 
 def create_model_incore(params):
@@ -140,6 +143,9 @@ def create_model_incore(params):
 
     
     ###### CHECKS
+    # 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)
     if type(df_S)==int: return 1

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

@@ -0,0 +1,128 @@
+import warnings 
+import os
+import logging
+
+
+import cobra
+import gempipe
+
+
+from ..commons import fba_no_warnings
+from ..commons import get_optthr
+
+
+
+def verify_egc(logger, model, mid, outdir): 
+
+    
+    # changes as not permament: 
+    found_egc = False
+    with model: 
+        
+        # close (0; 0) all the exchange reactions: 
+        gempipe.close_boundaries(model)
+        
+                
+        # create a dissipation reaction: 
+        dissip = cobra.Reaction(f'__dissip__{mid}')
+        model.add_reactions([dissip])
+        dissip = model.reactions.get_by_id(f'__dissip__{mid}')
+        
+        
+        # define the dissipation reaction:
+        modeled_mids = [m.id for m in model.metabolites]
+        if   mid == 'atp':
+            dissip_string = 'atp_c + h2o_c --> adp_c + pi_c + h_c'
+        elif mid == 'ctp':
+            dissip_string = 'ctp_c + h2o_c --> cdp_c + pi_c + h_c'
+        elif mid == 'gtp':
+            dissip_string = 'gtp_c + h2o_c --> gdp_c + pi_c + h_c'
+        elif mid == 'utp':
+            dissip_string = 'utp_c + h2o_c --> udp_c + pi_c + h_c'
+        elif mid == 'itp':
+            dissip_string = 'itp_c + h2o_c --> idp_c + pi_c + h_c'
+        elif mid == 'nadh':
+            dissip_string = 'nadh_c --> nad_c + h_c'
+        elif mid == 'nadph':
+            dissip_string = 'nadph_c --> nadp_c + h_c'
+        elif mid == 'fadh2':
+            dissip_string = 'fadh2_c --> fad_c + 2.0 h_c'
+        elif mid == 'accoa':
+            dissip_string = 'accoa_c + h2o_c --> ac_c + coa_c + h_c'
+        elif mid == 'glu__L':
+            dissip_string = 'glu__L_c + h2o_c --> akg_c + nh4_c + 2.0 h_c'
+        elif mid == 'q8h2':
+            dissip_string = 'q8h2_c --> q8_c + 2.0 h_c'
+        dissip.build_reaction_from_string(dissip_string)
+        
+        
+        # set the objective and optimize: 
+        model.objective = f'__dissip__{mid}'
+        res, obj_value, status = fba_no_warnings(model)
+        
+        
+        # apply the threshold:
+        obj_value = res.objective_value
+        status = res.status
+        if status == 'optimal' and obj_value >= get_optthr():
+            found_egc = True
+                
+
+            # get suspect !=0 fluxes 
+            fluxes = res.fluxes
+            # get interesting fluxes (get_optthr() tries to take into account the approximation in glpk and cplex solvers)
+            fluxes_interesting = fluxes[(fluxes > get_optthr()) | (fluxes < -get_optthr())]
+            
+
+            # create a model for escher, remove Rs not beloning to the cycle
+            model_copy = model.copy()
+            all_rids = [r.id for r in model_copy.reactions]
+            to_delete = set(all_rids) - set(fluxes_interesting.index)
+
+
+            # 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)   
+                
+                # triggering code
+                model_copy.remove_reactions(to_delete)  # should work also with IDs
+
+                # restore original behaviour: 
+                cobra_logger.setLevel(old_level) 
+                
+                
+            # save JSON to direct import in Escher:
+            outfile = os.path.join(outdir, f'EGC_{mid}.json')
+            cobra.io.save_json_model(model_copy, outfile)
+
+
+            # log some messages
+            rid_labels = []
+            for rid, flux in fluxes_interesting.to_dict().items():
+                rid_label = "'" + rid + "'" 
+                # mark reversible reactions composing the cycle:
+                r = model.reactions.get_by_id(rid)
+                if r.lower_bound < 0 and r.upper_bound > 0:
+                    rid_label = rid_label + '(<=>)'
+                rid_labels.append(rid_label)
+            logger.warning(f"Found erroneous EGC (N={len(model_copy.reactions)}) for '{mid}' (f={obj_value}): [{', '.join(rid_labels)}]. EGC saved to '{outfile}' to be inspected with Escher-FBA.")
+            
+            
+    return found_egc
+
+
+
+def verify_egc_all(logger, model, outdir='./', mids_to_check=['atp','ctp','gtp','utp','itp','nadh','nadph','fadh2','accoa','glu__L','q8h2']):
+
+    
+    all_results = []
+    for mid in mids_to_check:
+        all_results.append(verify_egc(logger, model, mid, outdir))
+    if any(all_results)==False:
+        logger.info("Found 0 erroneous energy-generating cycles (EGCs).")
+        
+        

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

@@ -287,15 +287,7 @@ def introduce_transporters(logger, db, model, idcollection_dict, kegg_reaction_t
         r = model.reactions.get_by_id(f'EX_{mid_e}')
         r.name = f"Exchange for {model.metabolites.get_by_id(mid_e).name}"
         r.build_reaction_from_string(f'{mid_e} --> ')
-        if mid_e in [
-            # basics:
-            'glc__D_e', 'nh4_e', 'pi_e', 'so4_e', 'h2o_e', 'h_e', 'o2_e', 'co2_e',
-            # metals: 
-            'cu2_e', 'mobd_e', 'fe2_e', 'cobalt2_e',
-        ]:
-            r.bounds = (-1000, 1000)
-        else:
-            r.bounds = (0, 1000)
+        r.bounds = (0, 1000)
             
         # add SBO annotation
         r.annotation['sbo'] = ['SBO:0000627']  # exchange reaction    

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

@@ -19,6 +19,33 @@ def get_rids_with_mancheck_gpr():
     return rids_mancheck_gpr
 
 
+def get_rids_with_mancheck_balancing():
+    rids_mancheck_bal = [  # same reactions involving ATP can be reversible
+        
+        # SECTION "reversible both in KEGG and MetaCyc"
+        'PGK', 'SUCOAS', 'ADK1', 'GK1', 'NNATr', 'CYTK1', 'ACKr',
+        'DGK1', 'PPAKr', 'ATPSr', 'NDPK10',
+        
+        ### SECTION "reversible in KEGG but not in MetaCyc" ###
+        'CYTK2',  # clearly reversible in KEGG but not in MetaCyc (RXN-7913)
+        'DADK',  # clearly reversible in KEGG but not in MetaCyc (DEOXYADENYLATE-KINASE-RXN)
+        'UMPK',  # clearly reversible in KEGG but not in MetaCyc (RXN-12002)
+        'NDPK1',  # clearly reversible in KEGG but not in MetaCyc (GDPKIN-RXN)
+        'NDPK2',  # clearly reversible in KEGG but not in MetaCyc (UDPKIN-RXN)  
+        'NDPK3',  # clearly reversible in KEGG but not in MetaCyc (CDPKIN-RXN)
+        'NDPK4',  # clearly reversible in KEGG but not in MetaCyc (DTDPKIN-RXN)
+        'NDPK5',  # clearly reversible in KEGG but not in MetaCyc (DGDPKIN-RXN)
+        'NDPK6',  # clearly reversible in KEGG but not in MetaCyc (DUDPKIN-RXN)
+        'NDPK7',  # clearly reversible in KEGG but not in MetaCyc (DCDPKIN-RXN)
+        'NDPK8',  # clearly reversible in KEGG but not in MetaCyc (DADPKIN-RXN)
+        'NDPK9',  # clearly reversible in KEGG but not in MetaCyc (RXN-14120) 
+        
+        ### SECTION "missing reversibility info" ###
+        'LPHERA',  
+    ]
+    return rids_mancheck_bal
+
+
 
 def get_manual_sinks():
     

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

@@ -35,6 +35,8 @@ from ..runsims.biosynth import biosynthesis_on_media
 
 from ..mkmodel.polishing import remove_disconnected
 
+from .cycles import verify_egc_all
+
 
 
 
@@ -173,6 +175,9 @@ def main(args, logger):
     
     
     ###### CHECKS 2
+    # 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

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

@@ -4,6 +4,7 @@ import cobra
 
 from .manual import get_deprecated_kos
 from .manual import get_rids_with_mancheck_gpr
+from .manual import get_rids_with_mancheck_balancing
 
 
 
@@ -138,6 +139,14 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
         return 1    
     
     
+    # check if reversible and using ATP
+    if r.lower_bound < 0 and r.upper_bound > 0:
+        for m in r.metabolites: 
+            if m.id.rsplit('_', 1)[0] == 'atp':
+                if rid not in get_rids_with_mancheck_balancing():
+                    logger.warning(f"Reaction '{rid}' involves ATP and is reversible: are you sure?")
+    
+    
     return 0
 
 

gsrap/parsedb/cycles.py

@@ -0,0 +1,128 @@
+import warnings 
+import os
+import logging
+
+
+import cobra
+import gempipe
+
+
+from ..commons import fba_no_warnings
+from ..commons import get_optthr
+
+
+
+def verify_egc(logger, model, mid, outdir): 
+
+    
+    # changes as not permament: 
+    found_egc = False
+    with model: 
+        
+        # close (0; 0) all the exchange reactions: 
+        gempipe.close_boundaries(model)
+        
+                
+        # create a dissipation reaction: 
+        dissip = cobra.Reaction(f'__dissip__{mid}')
+        model.add_reactions([dissip])
+        dissip = model.reactions.get_by_id(f'__dissip__{mid}')
+        
+        
+        # define the dissipation reaction:
+        modeled_mids = [m.id for m in model.metabolites]
+        if   mid == 'atp':
+            dissip_string = 'atp_c + h2o_c --> adp_c + pi_c + h_c'
+        elif mid == 'ctp':
+            dissip_string = 'ctp_c + h2o_c --> cdp_c + pi_c + h_c'
+        elif mid == 'gtp':
+            dissip_string = 'gtp_c + h2o_c --> gdp_c + pi_c + h_c'
+        elif mid == 'utp':
+            dissip_string = 'utp_c + h2o_c --> udp_c + pi_c + h_c'
+        elif mid == 'itp':
+            dissip_string = 'itp_c + h2o_c --> idp_c + pi_c + h_c'
+        elif mid == 'nadh':
+            dissip_string = 'nadh_c --> nad_c + h_c'
+        elif mid == 'nadph':
+            dissip_string = 'nadph_c --> nadp_c + h_c'
+        elif mid == 'fadh2':
+            dissip_string = 'fadh2_c --> fad_c + 2.0 h_c'
+        elif mid == 'accoa':
+            dissip_string = 'accoa_c + h2o_c --> ac_c + coa_c + h_c'
+        elif mid == 'glu__L':
+            dissip_string = 'glu__L_c + h2o_c --> akg_c + nh4_c + 2.0 h_c'
+        elif mid == 'q8h2':
+            dissip_string = 'q8h2_c --> q8_c + 2.0 h_c'
+        dissip.build_reaction_from_string(dissip_string)
+        
+        
+        # set the objective and optimize: 
+        model.objective = f'__dissip__{mid}'
+        res, obj_value, status = fba_no_warnings(model)
+        
+        
+        # apply the threshold:
+        obj_value = res.objective_value
+        status = res.status
+        if status == 'optimal' and obj_value >= get_optthr():
+            found_egc = True
+                
+
+            # get suspect !=0 fluxes 
+            fluxes = res.fluxes
+            # get interesting fluxes (get_optthr() tries to take into account the approximation in glpk and cplex solvers)
+            fluxes_interesting = fluxes[(fluxes > get_optthr()) | (fluxes < -get_optthr())]
+            
+
+            # create a model for escher, remove Rs not beloning to the cycle
+            model_copy = model.copy()
+            all_rids = [r.id for r in model_copy.reactions]
+            to_delete = set(all_rids) - set(fluxes_interesting.index)
+
+
+            # 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)   
+                
+                # triggering code
+                model_copy.remove_reactions(to_delete)  # should work also with IDs
+
+                # restore original behaviour: 
+                cobra_logger.setLevel(old_level) 
+                
+                
+            # save JSON to direct import in Escher:
+            outfile = os.path.join(outdir, f'EGC_{mid}.json')
+            cobra.io.save_json_model(model_copy, outfile)
+
+
+            # log some messages
+            rid_labels = []
+            for rid, flux in fluxes_interesting.to_dict().items():
+                rid_label = "'" + rid + "'" 
+                # mark reversible reactions composing the cycle:
+                r = model.reactions.get_by_id(rid)
+                if r.lower_bound < 0 and r.upper_bound > 0:
+                    rid_label = rid_label + '(<=>)'
+                rid_labels.append(rid_label)
+            logger.warning(f"Found erroneous EGC (N={len(model_copy.reactions)}) for '{mid}' (f={obj_value}): [{', '.join(rid_labels)}]. EGC saved to '{outfile}' to be inspected with Escher-FBA.")
+            
+            
+    return found_egc
+
+
+
+def verify_egc_all(logger, model, outdir='./', mids_to_check=['atp','ctp','gtp','utp','itp','nadh','nadph','fadh2','accoa','glu__L','q8h2']):
+
+    
+    all_results = []
+    for mid in mids_to_check:
+        all_results.append(verify_egc(logger, model, mid, outdir))
+    if any(all_results)==False:
+        logger.info("Found 0 erroneous energy-generating cycles (EGCs).")
+        
+        

gsrap/parsedb/introduce.py

@@ -287,15 +287,7 @@ def introduce_transporters(logger, db, model, idcollection_dict, kegg_reaction_t
         r = model.reactions.get_by_id(f'EX_{mid_e}')
         r.name = f"Exchange for {model.metabolites.get_by_id(mid_e).name}"
         r.build_reaction_from_string(f'{mid_e} --> ')
-        if mid_e in [
-            # basics:
-            'glc__D_e', 'nh4_e', 'pi_e', 'so4_e', 'h2o_e', 'h_e', 'o2_e', 'co2_e',
-            # metals: 
-            'cu2_e', 'mobd_e', 'fe2_e', 'cobalt2_e',
-        ]:
-            r.bounds = (-1000, 1000)
-        else:
-            r.bounds = (0, 1000)
+        r.bounds = (0, 1000)
             
         # add SBO annotation
         r.annotation['sbo'] = ['SBO:0000627']  # exchange reaction    

gsrap/parsedb/manual.py

@@ -19,6 +19,33 @@ def get_rids_with_mancheck_gpr():
     return rids_mancheck_gpr
 
 
+def get_rids_with_mancheck_balancing():
+    rids_mancheck_bal = [  # same reactions involving ATP can be reversible
+        
+        # SECTION "reversible both in KEGG and MetaCyc"
+        'PGK', 'SUCOAS', 'ADK1', 'GK1', 'NNATr', 'CYTK1', 'ACKr',
+        'DGK1', 'PPAKr', 'ATPSr', 'NDPK10',
+        
+        ### SECTION "reversible in KEGG but not in MetaCyc" ###
+        'CYTK2',  # clearly reversible in KEGG but not in MetaCyc (RXN-7913)
+        'DADK',  # clearly reversible in KEGG but not in MetaCyc (DEOXYADENYLATE-KINASE-RXN)
+        'UMPK',  # clearly reversible in KEGG but not in MetaCyc (RXN-12002)
+        'NDPK1',  # clearly reversible in KEGG but not in MetaCyc (GDPKIN-RXN)
+        'NDPK2',  # clearly reversible in KEGG but not in MetaCyc (UDPKIN-RXN)  
+        'NDPK3',  # clearly reversible in KEGG but not in MetaCyc (CDPKIN-RXN)
+        'NDPK4',  # clearly reversible in KEGG but not in MetaCyc (DTDPKIN-RXN)
+        'NDPK5',  # clearly reversible in KEGG but not in MetaCyc (DGDPKIN-RXN)
+        'NDPK6',  # clearly reversible in KEGG but not in MetaCyc (DUDPKIN-RXN)
+        'NDPK7',  # clearly reversible in KEGG but not in MetaCyc (DCDPKIN-RXN)
+        'NDPK8',  # clearly reversible in KEGG but not in MetaCyc (DADPKIN-RXN)
+        'NDPK9',  # clearly reversible in KEGG but not in MetaCyc (RXN-14120) 
+        
+        ### SECTION "missing reversibility info" ###
+        'LPHERA',  
+    ]
+    return rids_mancheck_bal
+
+
 
 def get_manual_sinks():
     

gsrap/parsedb/parsedb.py

@@ -35,6 +35,8 @@ from ..runsims.biosynth import biosynthesis_on_media
 
 from ..mkmodel.polishing import remove_disconnected
 
+from .cycles import verify_egc_all
+
 
 
 
@@ -173,6 +175,9 @@ def main(args, logger):
     
     
     ###### CHECKS 2
+    # 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

gsrap/parsedb/repeating.py

@@ -4,6 +4,7 @@ import cobra
 
 from .manual import get_deprecated_kos
 from .manual import get_rids_with_mancheck_gpr
+from .manual import get_rids_with_mancheck_balancing
 
 
 
@@ -138,6 +139,14 @@ def add_reaction(logger, model, rid, row, kr_ids, kegg_reaction_to_others, addty
         return 1    
     
     
+    # check if reversible and using ATP
+    if r.lower_bound < 0 and r.upper_bound > 0:
+        for m in r.metabolites: 
+            if m.id.rsplit('_', 1)[0] == 'atp':
+                if rid not in get_rids_with_mancheck_balancing():
+                    logger.warning(f"Reaction '{rid}' involves ATP and is reversible: are you sure?")
+    
+    
     return 0
 
 

{gsrap-0.8.0.dist-info → gsrap-0.8.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: gsrap
-Version: 0.8.0
+Version: 0.8.1
 Summary: 
 License: GNU General Public License v3.0
 Author: Gioele Lazzari

{gsrap-0.8.0.dist-info → gsrap-0.8.1.dist-info}/RECORD

@@ -1,5 +1,5 @@
-gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=JlR5ICkhkJwQrMHJOFOZg1R-0aYQAZu9h51SlC67Mtw,14064
-gsrap/__init__.py,sha256=JlR5ICkhkJwQrMHJOFOZg1R-0aYQAZu9h51SlC67Mtw,14064
+gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=lOurIE_Gn0jYS3ks3UmX11uuMrMScHADH9ivFoLpg5k,14160
+gsrap/__init__.py,sha256=lOurIE_Gn0jYS3ks3UmX11uuMrMScHADH9ivFoLpg5k,14160
 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
@@ -21,7 +21,7 @@ gsrap/commons/.ipynb_checkpoints/figures-checkpoint.py,sha256=IRHSQXrCi4SQoISEfN
 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=VYKN8X1PNERP6uQDbznZXfgflLEvnw4j1T8AIAdrE7s,2902
+gsrap/commons/.ipynb_checkpoints/medium-checkpoint.py,sha256=wcWiuZ-mqryoYBrsIHkIen6fBssR_1FGVoXUTApylNc,2901
 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
@@ -34,7 +34,7 @@ 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=VYKN8X1PNERP6uQDbznZXfgflLEvnw4j1T8AIAdrE7s,2902
+gsrap/commons/medium.py,sha256=wcWiuZ-mqryoYBrsIHkIen6fBssR_1FGVoXUTApylNc,2901
 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
@@ -47,30 +47,32 @@ 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=0ekGXmNULzVbkl6QW_Z8xDrHlevgtVDWEURJJR2uQRM,10323
+gsrap/mkmodel/.ipynb_checkpoints/mkmodel-checkpoint.py,sha256=3o4_B3ALcq6GYLAZ7zteNOcLTfE3KVJO6s9L4uMmw8E,10448
 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=0ekGXmNULzVbkl6QW_Z8xDrHlevgtVDWEURJJR2uQRM,10323
+gsrap/mkmodel/mkmodel.py,sha256=3o4_B3ALcq6GYLAZ7zteNOcLTfE3KVJO6s9L4uMmw8E,10448
 gsrap/mkmodel/polishing.py,sha256=R1UdFPxN8N27Iu0jsYW2N_1BkWEbBHaMYW6NkCYZK_k,3256
 gsrap/mkmodel/pruner.py,sha256=FAZid-0H6j66wR2dVKRAaMaDREVt1edflmZXbX7blXg,9836
 gsrap/parsedb/.ipynb_checkpoints/__init__-checkpoint.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
 gsrap/parsedb/.ipynb_checkpoints/annotation-checkpoint.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
 gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py,sha256=yhFiEslK1qmMCk_GWZ7UZtX02FUqLU39UafG5886WsY,12016
-gsrap/parsedb/.ipynb_checkpoints/introduce-checkpoint.py,sha256=TpW-Hp_rq6AGUQ-IVFwU8Vhij6poKWz8EF-NhdsAOsI,17414
-gsrap/parsedb/.ipynb_checkpoints/manual-checkpoint.py,sha256=F16wU8vLyM6V4F611ABuMJtwSAskL5KEgCJ7EQm_F9Y,2177
-gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=OPc8PrTVD2szrmvZISlyhP1Q51AlaoQ_EghAJs4jfFU,7465
-gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py,sha256=9PgsSw-H84eN_dFUwK5FLgbqvydsdic4-VjCrZqkfnY,5703
+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/repeating-checkpoint.py,sha256=WwPOzlZgsZWmJ-rvhFg21iOJ6gajgKFc2vCIHh6weBg,6103
 gsrap/parsedb/__init__.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
 gsrap/parsedb/annotation.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
 gsrap/parsedb/completeness.py,sha256=yhFiEslK1qmMCk_GWZ7UZtX02FUqLU39UafG5886WsY,12016
-gsrap/parsedb/introduce.py,sha256=TpW-Hp_rq6AGUQ-IVFwU8Vhij6poKWz8EF-NhdsAOsI,17414
-gsrap/parsedb/manual.py,sha256=F16wU8vLyM6V4F611ABuMJtwSAskL5KEgCJ7EQm_F9Y,2177
-gsrap/parsedb/parsedb.py,sha256=OPc8PrTVD2szrmvZISlyhP1Q51AlaoQ_EghAJs4jfFU,7465
-gsrap/parsedb/repeating.py,sha256=9PgsSw-H84eN_dFUwK5FLgbqvydsdic4-VjCrZqkfnY,5703
+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/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
 gsrap/runsims/.ipynb_checkpoints/cnps-checkpoint.py,sha256=A0U8QPqW_uyrtHs99F286aEDEC6eukHXeMWrmnd0efA,5636
@@ -89,8 +91,8 @@ 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-0.8.0.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gsrap-0.8.0.dist-info/METADATA,sha256=T5COI9B29df6TdmUbZvFrQsficCTN3SVzJGHJ5yw4Us,898
-gsrap-0.8.0.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-gsrap-0.8.0.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
-gsrap-0.8.0.dist-info/RECORD,,
+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,,