gsrap 0.7.1__py3-none-any.whl → 0.7.2__py3-none-any.whl

gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -72,9 +72,9 @@ 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("-z", "--zeroes", action='store_true', help="Show maps/modules with 0%% coverage, in addition to partials (use only with --progress).")
     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.")
     
     
     # add arguments for the 'mkmodel' command
@@ -94,6 +94,7 @@ def main():
     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.")
     mkmodel_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
     mkmodel_parser.add_argument("-b", "--biomass", metavar='', type=str, default='-', help="Strain ID associated to experimental biomass data.")
+    mkmodel_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
     
     
     # add arguments for the 'runsims' command
@@ -110,6 +111,7 @@ def main():
     runsims_parser.add_argument("--omission", action='store_true', help="Perform single omission experiments to study auxotrophies.")
     runsims_parser.add_argument("--essential", action='store_true', help="Predict essential genes (single-gene knock-out simulations).")
     runsims_parser.add_argument("--factors", action='store_true', help="Predict putative growth factors.")
+    runsims_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
 
     
     # check the inputted subcommand, automatic sys.exit(1) if a bad subprogram was specied. 

gsrap/__init__.py

@@ -72,9 +72,9 @@ 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("-z", "--zeroes", action='store_true', help="Show maps/modules with 0%% coverage, in addition to partials (use only with --progress).")
     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.")
     
     
     # add arguments for the 'mkmodel' command
@@ -94,6 +94,7 @@ def main():
     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.")
     mkmodel_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
     mkmodel_parser.add_argument("-b", "--biomass", metavar='', type=str, default='-', help="Strain ID associated to experimental biomass data.")
+    mkmodel_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
     
     
     # add arguments for the 'runsims' command
@@ -110,6 +111,7 @@ def main():
     runsims_parser.add_argument("--omission", action='store_true', help="Perform single omission experiments to study auxotrophies.")
     runsims_parser.add_argument("--essential", action='store_true', help="Predict essential genes (single-gene knock-out simulations).")
     runsims_parser.add_argument("--factors", action='store_true', help="Predict putative growth factors.")
+    runsims_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures.")
 
     
     # check the inputted subcommand, automatic sys.exit(1) if a bad subprogram was specied. 

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

@@ -1,8 +1,20 @@
 import pandas as pnd
 
 
+from .figures import figure_df_C_F1
 
-def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
+
+
+def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None):
+    
+    
+    # generate figures
+    if nofigs == False:
+              
+        if df_C is not None:
+            df_C_F1 = figure_df_C_F1(df_C)
+        
+        
     
     df_M = []
     df_R = []
@@ -33,6 +45,12 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         df_S.insert(0, 'mid', '')  # new columns as first
         df_S['mid'] = df_S.index
         df_S = df_S.reset_index(drop=True)
+        
+    # format df_C: universal reaction coverage
+    if df_C is not None:
+        df_C.insert(0, 'kr', '')  # new columns as first
+        df_C['kr'] = df_C.index
+        df_C = df_C.reset_index(drop=True)
             
         
     for m in model.metabolites: 
@@ -81,7 +99,7 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
     df_R = pnd.DataFrame.from_records(df_R)
     df_T = pnd.DataFrame.from_records(df_T)
     df_A = pnd.DataFrame.from_records(df_A)
-    with pnd.ExcelWriter(filepath) as writer:
+    with pnd.ExcelWriter(filepath, engine='xlsxwriter') as writer:
         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)
@@ -90,7 +108,12 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         if df_B is not None: df_B.to_excel(writer, sheet_name='Biomass', index=False)
         if df_P is not None and len(df_P)!=0: df_P.to_excel(writer, sheet_name='Biolog®', index=False)
         if df_S is not None and len(df_S.columns)>2: df_S.to_excel(writer, sheet_name='Biosynth', index=False) 
-        
+        if df_C is not None: 
+            df_C.to_excel(writer, sheet_name='Coverage', index=False) 
+            if nofigs == False:
+                worksheet = writer.sheets['Coverage']
+                worksheet.insert_image('A1', 'df_C_F1.png', {'image_data': df_C_F1})
+            
         
     sheets_dict = {
         'model_id': model.id,
@@ -102,6 +125,7 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         'Biomass': df_B,
         'Biolog': df_P,
         'Biosynth': df_S,
+        'Coverage': df_C,
     }
     return sheets_dict
 

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

@@ -0,0 +1,105 @@
+from io import BytesIO
+
+import numpy as np
+import pandas as pnd
+
+from scipy.spatial.distance import pdist
+from scipy.cluster.hierarchy import linkage, cut_tree, dendrogram, leaves_list
+
+import matplotlib.pyplot as plt
+from matplotlib.patches import Patch
+
+
+
+def figure_df_C_F1(df_coverage):
+
+    bin_matrix = df_coverage[[i for i in df_coverage.columns if i not in ['map_ids', 'modeled']]]
+    strains = bin_matrix.columns
+    bin_matrix = bin_matrix.T  # features in column
+
+    # pdist() / linkage() will loose the accession information. So here we save a dict: 
+    index_to_strain = {i: strain for i, strain in enumerate(bin_matrix.index)}
+
+    # Calculate the linkage matrix using Ward clustering and Jaccard dissimilarity
+    distances = pdist(bin_matrix, 'jaccard')
+    linkage_matrix = linkage(distances, method='ward')
+
+
+    # PART 0: create the frame
+    fig, axs = plt.subplots(
+        nrows=2, ncols=2, 
+        figsize=(15, 10), 
+        gridspec_kw={  # suplots width proportions. 
+            'width_ratios': [0.5, 1.0],
+            'height_ratios': [0.015, 0.985]
+        }
+    ) 
+
+    # PART 1: dendrogram
+    dn = dendrogram(
+        linkage_matrix, ax=axs[1,0],
+        orientation='left',
+        color_threshold=0, above_threshold_color='black',
+    )
+
+
+    ### PART 2: heatmap
+    ord_leaves = leaves_list(linkage_matrix)
+    ord_leaves = np.flip(ord_leaves)  # because leaves are returned in the inverse sense.
+    ord_leaves = [index_to_strain[i] for i in ord_leaves]  # convert index as number to index as accession
+    bin_matrix = bin_matrix.loc[ord_leaves, :]  # reordered dataframe.
+    axs[1,1].matshow(
+        bin_matrix,  
+        cmap='viridis',
+        aspect='auto', # non-squared pixels to fit the axis
+    )
+
+
+    ### PART 3: coverage bar
+    axs[0,1].matshow(
+        df_coverage[['modeled']].T,  
+        cmap='cool_r',
+        aspect='auto', # non-squared pixels to fit the axis
+    )
+
+
+    ### PART 4: legends
+    legend_feat = [
+        Patch(facecolor=plt.colormaps.get_cmap('viridis')(0.0), edgecolor='black', label='Absent'),
+        Patch(facecolor=plt.colormaps.get_cmap('viridis')(1.0), edgecolor='black', label='Probably present'),
+    ]
+    legend_cov = [
+        Patch(facecolor=plt.colormaps.get_cmap('cool_r')(0.0), edgecolor='black', label='Not modeled'),
+        Patch(facecolor=plt.colormaps.get_cmap('cool_r')(1.0), edgecolor='black', label='Modeled'),
+    ]
+    l1 = axs[1,0].legend(handles=legend_cov, title='Universe coverage', loc='upper left')
+    l2 = axs[1,0].legend(handles=legend_feat, title='KEGG reaction in strain', loc='lower left')
+    axs[1,0].add_artist(l1)  # keep both legends visible
+
+
+    ### PART 5: aesthetics
+    plt.subplots_adjust(wspace=0, hspace=0)  # adjust the space between subplots: 
+    axs[0,0].axis('off')  # remove frame and axis
+    axs[1,0].axis('off')  # remove frame and axis
+
+    axs[0,1].yaxis.set_visible(False)  # remove ticks, tick labels, axis label
+
+    axs[1,1].xaxis.set_ticks([])       # remove ticks
+    axs[1,1].set_xticklabels([])       # remove tick labels
+    axs[1,1].xaxis.set_label_position("bottom")
+    axs[1,1].set_xlabel("KEGG reactions")
+
+    axs[1,1].yaxis.set_ticks([])       # remove ticks
+    axs[1,1].set_yticklabels([])       # remove tick labels
+    axs[1,1].yaxis.set_label_position("right")
+    axs[1,1].set_ylabel(f"{len(strains)} strains", rotation=270, labelpad=13)  # labelpad is in points (1 point = 1/72 inch)
+
+
+    ### PART 6: save fig
+    buf = BytesIO()
+    fig.savefig(buf, dpi=300, bbox_inches='tight')  # labelpad is in inches (1 point = 1/72 inch)
+    plt.close(fig)
+    buf.seek(0)  # rewind the buffer to the beginning
+    
+    
+    return buf

gsrap/commons/excelhub.py

@@ -1,8 +1,20 @@
 import pandas as pnd
 
 
+from .figures import figure_df_C_F1
 
-def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
+
+
+def write_excel_model(model, filepath, nofigs, df_E, df_B, df_P, df_S, df_C=None):
+    
+    
+    # generate figures
+    if nofigs == False:
+              
+        if df_C is not None:
+            df_C_F1 = figure_df_C_F1(df_C)
+        
+        
     
     df_M = []
     df_R = []
@@ -33,6 +45,12 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         df_S.insert(0, 'mid', '')  # new columns as first
         df_S['mid'] = df_S.index
         df_S = df_S.reset_index(drop=True)
+        
+    # format df_C: universal reaction coverage
+    if df_C is not None:
+        df_C.insert(0, 'kr', '')  # new columns as first
+        df_C['kr'] = df_C.index
+        df_C = df_C.reset_index(drop=True)
             
         
     for m in model.metabolites: 
@@ -81,7 +99,7 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
     df_R = pnd.DataFrame.from_records(df_R)
     df_T = pnd.DataFrame.from_records(df_T)
     df_A = pnd.DataFrame.from_records(df_A)
-    with pnd.ExcelWriter(filepath) as writer:
+    with pnd.ExcelWriter(filepath, engine='xlsxwriter') as writer:
         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)
@@ -90,7 +108,12 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         if df_B is not None: df_B.to_excel(writer, sheet_name='Biomass', index=False)
         if df_P is not None and len(df_P)!=0: df_P.to_excel(writer, sheet_name='Biolog®', index=False)
         if df_S is not None and len(df_S.columns)>2: df_S.to_excel(writer, sheet_name='Biosynth', index=False) 
-        
+        if df_C is not None: 
+            df_C.to_excel(writer, sheet_name='Coverage', index=False) 
+            if nofigs == False:
+                worksheet = writer.sheets['Coverage']
+                worksheet.insert_image('A1', 'df_C_F1.png', {'image_data': df_C_F1})
+            
         
     sheets_dict = {
         'model_id': model.id,
@@ -102,6 +125,7 @@ def write_excel_model(model, filepath, df_E, df_B, df_P, df_S):
         'Biomass': df_B,
         'Biolog': df_P,
         'Biosynth': df_S,
+        'Coverage': df_C,
     }
     return sheets_dict
 

gsrap/commons/figures.py

@@ -0,0 +1,105 @@
+from io import BytesIO
+
+import numpy as np
+import pandas as pnd
+
+from scipy.spatial.distance import pdist
+from scipy.cluster.hierarchy import linkage, cut_tree, dendrogram, leaves_list
+
+import matplotlib.pyplot as plt
+from matplotlib.patches import Patch
+
+
+
+def figure_df_C_F1(df_coverage):
+
+    bin_matrix = df_coverage[[i for i in df_coverage.columns if i not in ['map_ids', 'modeled']]]
+    strains = bin_matrix.columns
+    bin_matrix = bin_matrix.T  # features in column
+
+    # pdist() / linkage() will loose the accession information. So here we save a dict: 
+    index_to_strain = {i: strain for i, strain in enumerate(bin_matrix.index)}
+
+    # Calculate the linkage matrix using Ward clustering and Jaccard dissimilarity
+    distances = pdist(bin_matrix, 'jaccard')
+    linkage_matrix = linkage(distances, method='ward')
+
+
+    # PART 0: create the frame
+    fig, axs = plt.subplots(
+        nrows=2, ncols=2, 
+        figsize=(15, 10), 
+        gridspec_kw={  # suplots width proportions. 
+            'width_ratios': [0.5, 1.0],
+            'height_ratios': [0.015, 0.985]
+        }
+    ) 
+
+    # PART 1: dendrogram
+    dn = dendrogram(
+        linkage_matrix, ax=axs[1,0],
+        orientation='left',
+        color_threshold=0, above_threshold_color='black',
+    )
+
+
+    ### PART 2: heatmap
+    ord_leaves = leaves_list(linkage_matrix)
+    ord_leaves = np.flip(ord_leaves)  # because leaves are returned in the inverse sense.
+    ord_leaves = [index_to_strain[i] for i in ord_leaves]  # convert index as number to index as accession
+    bin_matrix = bin_matrix.loc[ord_leaves, :]  # reordered dataframe.
+    axs[1,1].matshow(
+        bin_matrix,  
+        cmap='viridis',
+        aspect='auto', # non-squared pixels to fit the axis
+    )
+
+
+    ### PART 3: coverage bar
+    axs[0,1].matshow(
+        df_coverage[['modeled']].T,  
+        cmap='cool_r',
+        aspect='auto', # non-squared pixels to fit the axis
+    )
+
+
+    ### PART 4: legends
+    legend_feat = [
+        Patch(facecolor=plt.colormaps.get_cmap('viridis')(0.0), edgecolor='black', label='Absent'),
+        Patch(facecolor=plt.colormaps.get_cmap('viridis')(1.0), edgecolor='black', label='Probably present'),
+    ]
+    legend_cov = [
+        Patch(facecolor=plt.colormaps.get_cmap('cool_r')(0.0), edgecolor='black', label='Not modeled'),
+        Patch(facecolor=plt.colormaps.get_cmap('cool_r')(1.0), edgecolor='black', label='Modeled'),
+    ]
+    l1 = axs[1,0].legend(handles=legend_cov, title='Universe coverage', loc='upper left')
+    l2 = axs[1,0].legend(handles=legend_feat, title='KEGG reaction in strain', loc='lower left')
+    axs[1,0].add_artist(l1)  # keep both legends visible
+
+
+    ### PART 5: aesthetics
+    plt.subplots_adjust(wspace=0, hspace=0)  # adjust the space between subplots: 
+    axs[0,0].axis('off')  # remove frame and axis
+    axs[1,0].axis('off')  # remove frame and axis
+
+    axs[0,1].yaxis.set_visible(False)  # remove ticks, tick labels, axis label
+
+    axs[1,1].xaxis.set_ticks([])       # remove ticks
+    axs[1,1].set_xticklabels([])       # remove tick labels
+    axs[1,1].xaxis.set_label_position("bottom")
+    axs[1,1].set_xlabel("KEGG reactions")
+
+    axs[1,1].yaxis.set_ticks([])       # remove ticks
+    axs[1,1].set_yticklabels([])       # remove tick labels
+    axs[1,1].yaxis.set_label_position("right")
+    axs[1,1].set_ylabel(f"{len(strains)} strains", rotation=270, labelpad=13)  # labelpad is in points (1 point = 1/72 inch)
+
+
+    ### PART 6: save fig
+    buf = BytesIO()
+    fig.savefig(buf, dpi=300, bbox_inches='tight')  # labelpad is in inches (1 point = 1/72 inch)
+    plt.close(fig)
+    buf.seek(0)  # rewind the buffer to the beginning
+    
+    
+    return buf

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

@@ -141,7 +141,7 @@ 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', None, df_B, df_P, df_S)  
+    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, None, df_B, df_P, df_S)  
     logger.info(f"'{args.outdir}/{model.id}.mkmodel.xlsx' created!")
         
         

gsrap/mkmodel/mkmodel.py

@@ -141,7 +141,7 @@ 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', None, df_B, df_P, df_S)  
+    sheets_dict = write_excel_model(model, f'{args.outdir}/{model.id}.mkmodel.xlsx', args.nofigs, None, df_B, df_P, df_S)  
     logger.info(f"'{args.outdir}/{model.id}.mkmodel.xlsx' created!")
         
         

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

@@ -1,3 +1,6 @@
+from pathlib import Path
+
+
 import pandas as pnd
 
 
@@ -33,7 +36,7 @@ def parse_eggnog(model, eggnog, idcollection_dict):
     
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, idcollection_dict, summary_dict): 
+def check_completeness(logger, model, progress, module, focus, eggnog, idcollection_dict, summary_dict): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -55,10 +58,22 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
         if 'kegg.reaction' in r.annotation.keys():
             for kr_id in r.annotation['kegg.reaction']:
                 kr_ids_modeled.add(kr_id)
-    kr_uni_missing = len(kr_uni - kr_ids_modeled.intersection(kr_uni))
+    kr_uni_missing = kr_uni - kr_ids_modeled
     kr_uni_coverage = len(kr_ids_modeled.intersection(kr_uni)) / len(kr_uni) * 100
-    logger.info(f"Coverage for '{kr_uni_label}': {round(kr_uni_coverage, 0)}% ({kr_uni_missing} missing).")
+    logger.info(f"Coverage for '{kr_uni_label}': {round(kr_uni_coverage, 0)}% ({len(kr_uni_missing)} missing).")
+    
     
+    # define the map?????, containing krs not included in maps
+    krs_in_maps = set()
+    for i in summary_dict: krs_in_maps = krs_in_maps.union(i['kr_ids']) 
+    krs_not_in_maps = idcollection_dict['kr'] - krs_in_maps
+    summary_dict.append({
+        'map_id': 'map?????',
+        'map_name': 'Not included in maps',
+        'kr_ids': krs_not_in_maps,
+        'cnt_r': len(krs_not_in_maps),
+        'mds': []
+    })    
     
     
     # get all the map / md codes:
@@ -112,52 +127,77 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
             missing_logger = (map_id, missing)
 
         
+        # put the map in the right bucket:
         if missing == set() and map_krs != set():
             maps_finished.add(map_id)
-            
         elif map_krs == set():
             maps_noreac.add(map_id)
-            
         elif missing == map_krs:
             maps_missing.add(map_id)
-            
-            if zeroes:
-                list_coverage.append({
-                    'map_id': map_id,
-                    'map_name_short': map_name_short, 
-                    'perc_completeness': 0,
-                    'perc_completeness_str': ' 0',
-                    'present': present,
-                    'missing': missing,
-                    'md_ids': [j['md_id'] for j in i['mds']],
-                })
-            
         elif len(missing) < len(map_krs):
             maps_partial.add(map_id)
             
-            # get '%' of completeness:
-            perc_completeness = len(present)/len(map_krs)*100
-            perc_completeness_str = str(round(perc_completeness))   # version to be printed
-            if len(perc_completeness_str)==1: 
-                perc_completeness_str = ' ' + perc_completeness_str
-                
-            list_coverage.append({
-                'map_id': map_id,
-                'map_name_short': map_name_short, 
-                'perc_completeness': perc_completeness,
-                'perc_completeness_str': perc_completeness_str,
-                'present': present,
-                'missing': missing,
-                'md_ids': [j['md_id'] for j in i['mds']],
-            })
             
+        # get '%' of completeness:
+        if len(map_krs) != 0: perc_completeness = len(present)/len(map_krs)*100
+        else: perc_completeness = 100   # for maps_noreac
+        perc_completeness_str = str(round(perc_completeness))   # version to be printed
+        if len(perc_completeness_str)==1: 
+            perc_completeness_str = ' ' + perc_completeness_str
+
+            
+        # append map to list:
+        list_coverage.append({
+            'map_id': map_id,
+            'map_name_short': map_name_short, 
+            'perc_completeness': perc_completeness,
+            'perc_completeness_str': perc_completeness_str,
+            'present': present,
+            'missing': missing,
+            'md_ids': [j['md_id'] for j in i['mds']],
+        })
+        
+        
+    
+    # create coverage dataframe
+    if eggnog != '-' and len(eggnog) >= 2:  
+        df_coverage = {}
+        for i in list_coverage:
+            for kr in i['present'].union(i['missing']):
+                if kr not in df_coverage.keys(): 
+                    df_coverage[kr] = {'map_ids': set()}
+                df_coverage[kr]['map_ids'].add(i['map_id'])
+        df_coverage = pnd.DataFrame.from_records(df_coverage).T
+        df_coverage['modeled'] = False
+        for kr, row in df_coverage.iterrows():
+            if kr in kr_ids_modeled:
+                df_coverage.loc[kr, 'modeled'] = True
+        # build strain columns all at once
+        df_strains = []  # list of small DataFrames
+        for eggfile in eggnog:
+            strain = Path(eggfile).stem
+            eggset = parse_eggnog(model, eggfile, idcollection_dict)
+            col = df_coverage.index.to_series().isin(eggset).astype(int)
+            df_strains.append(col.rename(strain))
+        df_strains = pnd.concat(df_strains, axis=1)
+        # sort rows: upper rows are present in more strains
+        df_strains = df_strains.loc[df_strains.sum(axis=1).sort_values(ascending=False).index]
+        df_coverage = df_coverage.loc[df_strains.index]
+        df_coverage = pnd.concat([df_coverage, df_strains], axis=1)
+        # split in 2: modeled above, non-modeled below:
+        df_coverage = pnd.concat([df_coverage[df_coverage['modeled']==True], df_coverage[df_coverage['modeled']==False]])
+    else:  # not interesting in a super-long table without strains in column
+        df_coverage = None
+    
+           
             
-    # order list by '%' of completness and print:
+    # order list by '%' of completness and print if needed:
     list_coverage = sorted(list_coverage, key=lambda x: x['perc_completeness'], reverse=True)
     for i in list_coverage:
         if progress:
             if focus=='-' or focus in i['md_ids'] or focus==i['map_id']:
-                logger.info(f"{i['map_id']}: {i['map_name_short']} {i['perc_completeness_str']}% completed, {len(i['present'])} added, {len(i['missing'])} missing.")
+                if i['map_id'] in maps_missing or i['map_id'] in maps_partial:
+                    logger.info(f"{i['map_id']}: {i['map_name_short']} {i['perc_completeness_str']}% completed, {len(i['present'])} added, {len(i['missing'])} missing.")
         
         
         # get the correspondent pathway element of the 'summary_dict'
@@ -199,50 +239,43 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
                 missing_logger = (md_id, missing)
             
             
+            # put the map in the right bucket:
             if missing == set() and md_krs != set():
                 mds_completed.add(md_id)
-
             elif md_krs == set():
                 mds_noreac.add(md_id)
-
             elif missing == md_krs:
                 mds_missing.add(md_id)
-                
-                if zeroes:
-                    list_coverage_md.append({
-                        'md_id': md_id,
-                        'md_name_short': md_name_short, 
-                        'perc_completeness': 0,
-                        'perc_completeness_str': ' 0',
-                        'present': present,
-                        'missing': missing,
-                    })
-                
             elif len(missing) < len(md_krs):
                 mds_partial.add(md_id)
 
-                # get '%' of completeness:
-                perc_completeness = len(present)/len(md_krs)*100
-                perc_completeness_str = str(round(perc_completeness))   # version to be printed
-                if len(perc_completeness_str)==1: 
-                    perc_completeness_str = ' ' + perc_completeness_str
+                
+            # get '%' of completeness:
+            if len(md_krs) != 0: perc_completeness = len(present)/len(md_krs)*100
+            else: perc_completeness = 100   # for mds_noreac
+            perc_completeness_str = str(round(perc_completeness))   # version to be printed
+            if len(perc_completeness_str)==1: 
+                perc_completeness_str = ' ' + perc_completeness_str
 
-                list_coverage_md.append({
-                    'md_id': md_id,
-                    'md_name_short': md_name_short, 
-                    'perc_completeness': perc_completeness,
-                    'perc_completeness_str': perc_completeness_str,
-                    'present': present,
-                    'missing': missing,
-                })
+                
+            # append md to list:
+            list_coverage_md.append({
+                'md_id': md_id,
+                'md_name_short': md_name_short, 
+                'perc_completeness': perc_completeness,
+                'perc_completeness_str': perc_completeness_str,
+                'present': present,
+                'missing': missing,
+            })
                
             
-        # order list by '%' of completness and print:
+        # order list by '%' of completness and print if needed:
         list_coverage_md = sorted(list_coverage_md, key=lambda x: x['perc_completeness'], reverse=True)
         for z in list_coverage_md:
             if module:
                 if focus=='-' or focus==z['md_id']:
-                    logger.info(f"{spacer}{z['md_id']}: {z['md_name_short']} {z['perc_completeness_str']}% completed, {len(z['present'])} added, {len(z['missing'])} missing.")
+                    if z['md_id'] in mds_missing or z['md_id'] in mds_partial:
+                        logger.info(f"{spacer}{z['md_id']}: {z['md_name_short']} {z['perc_completeness_str']}% completed, {len(z['present'])} added, {len(z['missing'])} missing.")
         
         
         # print summary:
@@ -254,6 +287,6 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
         logger.info(f"Maps: finished {len(maps_finished)} - partial {len(maps_partial)} - missing {len(maps_missing)} - noreac {len(maps_noreac)}")
             
         
-    return 0     
+    return df_coverage     
 
 

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

@@ -153,9 +153,8 @@ def main(args, logger):
     
     ###### CHECKS 1
     # check universe completness
-    setattr(args, 'zeroes', True)  # old parameter, forced to True from v0.6.1
-    response = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, args.zeroes, idcollection_dict, summary_dict)
-    if response==1: return 1
+    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, idcollection_dict, summary_dict)
+    if type(df_C)==int: return 1
 
 
 
@@ -194,7 +193,7 @@ def main(args, logger):
     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', df_E, None, None, df_S)  
+    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!")
 
 

gsrap/parsedb/completeness.py

@@ -1,3 +1,6 @@
+from pathlib import Path
+
+
 import pandas as pnd
 
 
@@ -33,7 +36,7 @@ def parse_eggnog(model, eggnog, idcollection_dict):
     
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, idcollection_dict, summary_dict): 
+def check_completeness(logger, model, progress, module, focus, eggnog, idcollection_dict, summary_dict): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -55,10 +58,22 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
         if 'kegg.reaction' in r.annotation.keys():
             for kr_id in r.annotation['kegg.reaction']:
                 kr_ids_modeled.add(kr_id)
-    kr_uni_missing = len(kr_uni - kr_ids_modeled.intersection(kr_uni))
+    kr_uni_missing = kr_uni - kr_ids_modeled
     kr_uni_coverage = len(kr_ids_modeled.intersection(kr_uni)) / len(kr_uni) * 100
-    logger.info(f"Coverage for '{kr_uni_label}': {round(kr_uni_coverage, 0)}% ({kr_uni_missing} missing).")
+    logger.info(f"Coverage for '{kr_uni_label}': {round(kr_uni_coverage, 0)}% ({len(kr_uni_missing)} missing).")
+    
     
+    # define the map?????, containing krs not included in maps
+    krs_in_maps = set()
+    for i in summary_dict: krs_in_maps = krs_in_maps.union(i['kr_ids']) 
+    krs_not_in_maps = idcollection_dict['kr'] - krs_in_maps
+    summary_dict.append({
+        'map_id': 'map?????',
+        'map_name': 'Not included in maps',
+        'kr_ids': krs_not_in_maps,
+        'cnt_r': len(krs_not_in_maps),
+        'mds': []
+    })    
     
     
     # get all the map / md codes:
@@ -112,52 +127,77 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
             missing_logger = (map_id, missing)
 
         
+        # put the map in the right bucket:
         if missing == set() and map_krs != set():
             maps_finished.add(map_id)
-            
         elif map_krs == set():
             maps_noreac.add(map_id)
-            
         elif missing == map_krs:
             maps_missing.add(map_id)
-            
-            if zeroes:
-                list_coverage.append({
-                    'map_id': map_id,
-                    'map_name_short': map_name_short, 
-                    'perc_completeness': 0,
-                    'perc_completeness_str': ' 0',
-                    'present': present,
-                    'missing': missing,
-                    'md_ids': [j['md_id'] for j in i['mds']],
-                })
-            
         elif len(missing) < len(map_krs):
             maps_partial.add(map_id)
             
-            # get '%' of completeness:
-            perc_completeness = len(present)/len(map_krs)*100
-            perc_completeness_str = str(round(perc_completeness))   # version to be printed
-            if len(perc_completeness_str)==1: 
-                perc_completeness_str = ' ' + perc_completeness_str
-                
-            list_coverage.append({
-                'map_id': map_id,
-                'map_name_short': map_name_short, 
-                'perc_completeness': perc_completeness,
-                'perc_completeness_str': perc_completeness_str,
-                'present': present,
-                'missing': missing,
-                'md_ids': [j['md_id'] for j in i['mds']],
-            })
             
+        # get '%' of completeness:
+        if len(map_krs) != 0: perc_completeness = len(present)/len(map_krs)*100
+        else: perc_completeness = 100   # for maps_noreac
+        perc_completeness_str = str(round(perc_completeness))   # version to be printed
+        if len(perc_completeness_str)==1: 
+            perc_completeness_str = ' ' + perc_completeness_str
+
+            
+        # append map to list:
+        list_coverage.append({
+            'map_id': map_id,
+            'map_name_short': map_name_short, 
+            'perc_completeness': perc_completeness,
+            'perc_completeness_str': perc_completeness_str,
+            'present': present,
+            'missing': missing,
+            'md_ids': [j['md_id'] for j in i['mds']],
+        })
+        
+        
+    
+    # create coverage dataframe
+    if eggnog != '-' and len(eggnog) >= 2:  
+        df_coverage = {}
+        for i in list_coverage:
+            for kr in i['present'].union(i['missing']):
+                if kr not in df_coverage.keys(): 
+                    df_coverage[kr] = {'map_ids': set()}
+                df_coverage[kr]['map_ids'].add(i['map_id'])
+        df_coverage = pnd.DataFrame.from_records(df_coverage).T
+        df_coverage['modeled'] = False
+        for kr, row in df_coverage.iterrows():
+            if kr in kr_ids_modeled:
+                df_coverage.loc[kr, 'modeled'] = True
+        # build strain columns all at once
+        df_strains = []  # list of small DataFrames
+        for eggfile in eggnog:
+            strain = Path(eggfile).stem
+            eggset = parse_eggnog(model, eggfile, idcollection_dict)
+            col = df_coverage.index.to_series().isin(eggset).astype(int)
+            df_strains.append(col.rename(strain))
+        df_strains = pnd.concat(df_strains, axis=1)
+        # sort rows: upper rows are present in more strains
+        df_strains = df_strains.loc[df_strains.sum(axis=1).sort_values(ascending=False).index]
+        df_coverage = df_coverage.loc[df_strains.index]
+        df_coverage = pnd.concat([df_coverage, df_strains], axis=1)
+        # split in 2: modeled above, non-modeled below:
+        df_coverage = pnd.concat([df_coverage[df_coverage['modeled']==True], df_coverage[df_coverage['modeled']==False]])
+    else:  # not interesting in a super-long table without strains in column
+        df_coverage = None
+    
+           
             
-    # order list by '%' of completness and print:
+    # order list by '%' of completness and print if needed:
     list_coverage = sorted(list_coverage, key=lambda x: x['perc_completeness'], reverse=True)
     for i in list_coverage:
         if progress:
             if focus=='-' or focus in i['md_ids'] or focus==i['map_id']:
-                logger.info(f"{i['map_id']}: {i['map_name_short']} {i['perc_completeness_str']}% completed, {len(i['present'])} added, {len(i['missing'])} missing.")
+                if i['map_id'] in maps_missing or i['map_id'] in maps_partial:
+                    logger.info(f"{i['map_id']}: {i['map_name_short']} {i['perc_completeness_str']}% completed, {len(i['present'])} added, {len(i['missing'])} missing.")
         
         
         # get the correspondent pathway element of the 'summary_dict'
@@ -199,50 +239,43 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
                 missing_logger = (md_id, missing)
             
             
+            # put the map in the right bucket:
             if missing == set() and md_krs != set():
                 mds_completed.add(md_id)
-
             elif md_krs == set():
                 mds_noreac.add(md_id)
-
             elif missing == md_krs:
                 mds_missing.add(md_id)
-                
-                if zeroes:
-                    list_coverage_md.append({
-                        'md_id': md_id,
-                        'md_name_short': md_name_short, 
-                        'perc_completeness': 0,
-                        'perc_completeness_str': ' 0',
-                        'present': present,
-                        'missing': missing,
-                    })
-                
             elif len(missing) < len(md_krs):
                 mds_partial.add(md_id)
 
-                # get '%' of completeness:
-                perc_completeness = len(present)/len(md_krs)*100
-                perc_completeness_str = str(round(perc_completeness))   # version to be printed
-                if len(perc_completeness_str)==1: 
-                    perc_completeness_str = ' ' + perc_completeness_str
+                
+            # get '%' of completeness:
+            if len(md_krs) != 0: perc_completeness = len(present)/len(md_krs)*100
+            else: perc_completeness = 100   # for mds_noreac
+            perc_completeness_str = str(round(perc_completeness))   # version to be printed
+            if len(perc_completeness_str)==1: 
+                perc_completeness_str = ' ' + perc_completeness_str
 
-                list_coverage_md.append({
-                    'md_id': md_id,
-                    'md_name_short': md_name_short, 
-                    'perc_completeness': perc_completeness,
-                    'perc_completeness_str': perc_completeness_str,
-                    'present': present,
-                    'missing': missing,
-                })
+                
+            # append md to list:
+            list_coverage_md.append({
+                'md_id': md_id,
+                'md_name_short': md_name_short, 
+                'perc_completeness': perc_completeness,
+                'perc_completeness_str': perc_completeness_str,
+                'present': present,
+                'missing': missing,
+            })
                
             
-        # order list by '%' of completness and print:
+        # order list by '%' of completness and print if needed:
         list_coverage_md = sorted(list_coverage_md, key=lambda x: x['perc_completeness'], reverse=True)
         for z in list_coverage_md:
             if module:
                 if focus=='-' or focus==z['md_id']:
-                    logger.info(f"{spacer}{z['md_id']}: {z['md_name_short']} {z['perc_completeness_str']}% completed, {len(z['present'])} added, {len(z['missing'])} missing.")
+                    if z['md_id'] in mds_missing or z['md_id'] in mds_partial:
+                        logger.info(f"{spacer}{z['md_id']}: {z['md_name_short']} {z['perc_completeness_str']}% completed, {len(z['present'])} added, {len(z['missing'])} missing.")
         
         
         # print summary:
@@ -254,6 +287,6 @@ def check_completeness(logger, model, progress, module, focus, eggnog, zeroes, i
         logger.info(f"Maps: finished {len(maps_finished)} - partial {len(maps_partial)} - missing {len(maps_missing)} - noreac {len(maps_noreac)}")
             
         
-    return 0     
+    return df_coverage     
 
 

gsrap/parsedb/parsedb.py

@@ -153,9 +153,8 @@ def main(args, logger):
     
     ###### CHECKS 1
     # check universe completness
-    setattr(args, 'zeroes', True)  # old parameter, forced to True from v0.6.1
-    response = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, args.zeroes, idcollection_dict, summary_dict)
-    if response==1: return 1
+    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, idcollection_dict, summary_dict)
+    if type(df_C)==int: return 1
 
 
 
@@ -194,7 +193,7 @@ def main(args, logger):
     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', df_E, None, None, df_S)  
+    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!")
 
 

gsrap/runsims/.ipynb_checkpoints/simplegrowth-checkpoint.py

@@ -57,9 +57,9 @@ def grow_on_media(logger, model, dbexp, media, fva, universe_in_parsedb=False):
         df_G.loc[obj_id, f'{medium}'] = res_fba
         if universe_in_parsedb:
             if res_fba == 'infeasible' or res_fba == 0.0:
-                logger.warning(f"Growth on '{medium}': {res_fba}.")
+                logger.warning(f"Growth on medium '{medium}': {res_fba}.")
             else:
-                logger.info(f"Growth on '{medium}': {res_fba}.")
+                logger.info(f"Growth on medium '{medium}': {res_fba}.")
         
         
         # perform FVA if requested:

gsrap/runsims/simplegrowth.py

@@ -57,9 +57,9 @@ def grow_on_media(logger, model, dbexp, media, fva, universe_in_parsedb=False):
         df_G.loc[obj_id, f'{medium}'] = res_fba
         if universe_in_parsedb:
             if res_fba == 'infeasible' or res_fba == 0.0:
-                logger.warning(f"Growth on '{medium}': {res_fba}.")
+                logger.warning(f"Growth on medium '{medium}': {res_fba}.")
             else:
-                logger.info(f"Growth on '{medium}': {res_fba}.")
+                logger.info(f"Growth on medium '{medium}': {res_fba}.")
         
         
         # perform FVA if requested:

{gsrap-0.7.1.dist-info → gsrap-0.7.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: gsrap
-Version: 0.7.1
+Version: 0.7.2
 Summary: 
 License: GNU General Public License v3.0
 Author: Gioele Lazzari
@@ -17,9 +17,11 @@ Requires-Dist: cobra (>=0.29)
 Requires-Dist: colorlog (>=6.9.0)
 Requires-Dist: gdown (>=5.2.0)
 Requires-Dist: gempipe (>=1.38.1)
+Requires-Dist: matplotlib (>=3.9.0)
 Requires-Dist: memote (>=0.17.0)
 Requires-Dist: openpyxl (>=3.1.0)
 Requires-Dist: pandas (>=2.0.0)
+Requires-Dist: xlsxwriter (>=3.1.0)
 Description-Content-Type: text/markdown
 
 Source code for `gsrap`.

{gsrap-0.7.1.dist-info → gsrap-0.7.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
-gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=93coHbPQfWL7XSudRvKh5RGgqJbyOvECVmMaHPfShOU,13693
-gsrap/__init__.py,sha256=93coHbPQfWL7XSudRvKh5RGgqJbyOvECVmMaHPfShOU,13693
+gsrap/.ipynb_checkpoints/__init__-checkpoint.py,sha256=nTCojQmYOSv1tRDBEZu7p2Ne_jB9xTUEIylln19tHkk,13818
+gsrap/__init__.py,sha256=nTCojQmYOSv1tRDBEZu7p2Ne_jB9xTUEIylln19tHkk,13818
 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
@@ -16,7 +16,8 @@ gsrap/commons/.ipynb_checkpoints/biomass-checkpoint.py,sha256=4u7WBaUgo42tBoXDU1
 gsrap/commons/.ipynb_checkpoints/coeffs-checkpoint.py,sha256=qI3_GuqHkeA2KbK9pYdkqJaFwYemAVZJGLRR4QtHt6w,19182
 gsrap/commons/.ipynb_checkpoints/downloads-checkpoint.py,sha256=JFrOYXrzLFhclwMtLmq8xo0QZVyjEn7QfzaTRad7y6I,8460
 gsrap/commons/.ipynb_checkpoints/escherutils-checkpoint.py,sha256=lftRIKAbP4eztaZM83V3LKWZK4DtKDuCiC9A46paVoM,1148
-gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py,sha256=XO7ZZFqORB1nnH1Nj07VSGr18em1rt_AH6oAqwqhp4o,5867
+gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py,sha256=wQKAyWZxfy9w_uhR_DzBZz0v7vdiVM-PGDA3k1TOraI,6622
+gsrap/commons/.ipynb_checkpoints/figures-checkpoint.py,sha256=qIjyMMFrm7AkUkdYY4ZZ8SjprUfoC3brW34oHRQvNQk,3689
 gsrap/commons/.ipynb_checkpoints/fluxbal-checkpoint.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
 gsrap/commons/.ipynb_checkpoints/logutils-checkpoint.py,sha256=VsnrkIsUftS3MOOwAd0n0peQ7a2X5ZEx930eCtzmW7g,1317
 gsrap/commons/.ipynb_checkpoints/medium-checkpoint.py,sha256=VYKN8X1PNERP6uQDbznZXfgflLEvnw4j1T8AIAdrE7s,2902
@@ -27,7 +28,8 @@ gsrap/commons/biomass.py,sha256=4u7WBaUgo42tBoXDU1D0VUjICatb44e0jfswZrBeHYs,1798
 gsrap/commons/coeffs.py,sha256=qI3_GuqHkeA2KbK9pYdkqJaFwYemAVZJGLRR4QtHt6w,19182
 gsrap/commons/downloads.py,sha256=JFrOYXrzLFhclwMtLmq8xo0QZVyjEn7QfzaTRad7y6I,8460
 gsrap/commons/escherutils.py,sha256=lftRIKAbP4eztaZM83V3LKWZK4DtKDuCiC9A46paVoM,1148
-gsrap/commons/excelhub.py,sha256=XO7ZZFqORB1nnH1Nj07VSGr18em1rt_AH6oAqwqhp4o,5867
+gsrap/commons/excelhub.py,sha256=wQKAyWZxfy9w_uhR_DzBZz0v7vdiVM-PGDA3k1TOraI,6622
+gsrap/commons/figures.py,sha256=qIjyMMFrm7AkUkdYY4ZZ8SjprUfoC3brW34oHRQvNQk,3689
 gsrap/commons/fluxbal.py,sha256=jgC3-vI9Tbjvqohh2mJwFra4rl_pbUzHWrSa_QAxVO4,1262
 gsrap/commons/logutils.py,sha256=VsnrkIsUftS3MOOwAd0n0peQ7a2X5ZEx930eCtzmW7g,1317
 gsrap/commons/medium.py,sha256=VYKN8X1PNERP6uQDbznZXfgflLEvnw4j1T8AIAdrE7s,2902
@@ -43,29 +45,29 @@ 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=bXKBU8sUhRWKU-MYqiHgZFEwqvpAtoJa6_1h6D94REM,8537
+gsrap/mkmodel/.ipynb_checkpoints/mkmodel-checkpoint.py,sha256=5dW5eAKW9iAFlPITM-0ZjL2FmFp3OTSvLI-xbJ-zGgs,8550
 gsrap/mkmodel/.ipynb_checkpoints/polishing-checkpoint.py,sha256=R1UdFPxN8N27Iu0jsYW2N_1BkWEbBHaMYW6NkCYZK_k,3256
 gsrap/mkmodel/.ipynb_checkpoints/pruner-checkpoint.py,sha256=BVOK1iFXpTgZswDgAv-TgHxKB6W3iucIAo1XWrAbu4A,7009
 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=bXKBU8sUhRWKU-MYqiHgZFEwqvpAtoJa6_1h6D94REM,8537
+gsrap/mkmodel/mkmodel.py,sha256=5dW5eAKW9iAFlPITM-0ZjL2FmFp3OTSvLI-xbJ-zGgs,8550
 gsrap/mkmodel/polishing.py,sha256=R1UdFPxN8N27Iu0jsYW2N_1BkWEbBHaMYW6NkCYZK_k,3256
 gsrap/mkmodel/pruner.py,sha256=BVOK1iFXpTgZswDgAv-TgHxKB6W3iucIAo1XWrAbu4A,7009
 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=5P_OxGfKXSJDDV0qIcd6xQvAJymsMQKvhsUvMl79dkk,9478
+gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py,sha256=mLK2YawP9FjR3yogHhGxF2b2ti9DKmLu9uhibsq0jy4,11064
 gsrap/parsedb/.ipynb_checkpoints/introduce-checkpoint.py,sha256=PuIdXvkF7gmihOEMECXVZ1V4VBOld8p3lZZ2rqXjPH8,16871
 gsrap/parsedb/.ipynb_checkpoints/manual-checkpoint.py,sha256=F16wU8vLyM6V4F611ABuMJtwSAskL5KEgCJ7EQm_F9Y,2177
-gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=F0vYUvlFkBvg1Jis1nNJ9cS4f3tSF61hbM4zg7D3OJs,7242
+gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py,sha256=tTWohNPIrw47a08ECFTyHuT4W5KlkznllIEBCpg7Kv0,7169
 gsrap/parsedb/.ipynb_checkpoints/repeating-checkpoint.py,sha256=9PgsSw-H84eN_dFUwK5FLgbqvydsdic4-VjCrZqkfnY,5703
 gsrap/parsedb/__init__.py,sha256=1k2K1gz4lIdXAwHEdJ0OhdkPu83woGv0Z4TpT1kGrTk,97
 gsrap/parsedb/annotation.py,sha256=Y02_zXJj_tS1GyBdfuLBy9YJjMgx3mjX6tqr1KhQ-9Q,4810
-gsrap/parsedb/completeness.py,sha256=5P_OxGfKXSJDDV0qIcd6xQvAJymsMQKvhsUvMl79dkk,9478
+gsrap/parsedb/completeness.py,sha256=mLK2YawP9FjR3yogHhGxF2b2ti9DKmLu9uhibsq0jy4,11064
 gsrap/parsedb/introduce.py,sha256=PuIdXvkF7gmihOEMECXVZ1V4VBOld8p3lZZ2rqXjPH8,16871
 gsrap/parsedb/manual.py,sha256=F16wU8vLyM6V4F611ABuMJtwSAskL5KEgCJ7EQm_F9Y,2177
-gsrap/parsedb/parsedb.py,sha256=F0vYUvlFkBvg1Jis1nNJ9cS4f3tSF61hbM4zg7D3OJs,7242
+gsrap/parsedb/parsedb.py,sha256=tTWohNPIrw47a08ECFTyHuT4W5KlkznllIEBCpg7Kv0,7169
 gsrap/parsedb/repeating.py,sha256=9PgsSw-H84eN_dFUwK5FLgbqvydsdic4-VjCrZqkfnY,5703
 gsrap/runsims/.ipynb_checkpoints/__init__-checkpoint.py,sha256=6E6E1gWgH0V7ls4Omx4mxxC85gMJ_27YqhjugJzlZtY,97
 gsrap/runsims/.ipynb_checkpoints/biosynth-checkpoint.py,sha256=fUlHUo4CfB4rGX9Dth87B1p5E5sz7i6spR7ZoqDDGaI,2836
@@ -74,7 +76,7 @@ gsrap/runsims/.ipynb_checkpoints/essentialgenes-checkpoint.py,sha256=MzHiuaU1gwi
 gsrap/runsims/.ipynb_checkpoints/growthfactors-checkpoint.py,sha256=r_W4idtOSJBDh7HURRsU8s1TqfOZ3TfeVw2HHDxmnGU,2265
 gsrap/runsims/.ipynb_checkpoints/precursors-checkpoint.py,sha256=1RNt_Rxs0L1lolDmYh4_CiZgiwHfU5B_AcomJO6vJ28,2219
 gsrap/runsims/.ipynb_checkpoints/runsims-checkpoint.py,sha256=2FC5Gs8oSYyZTjHF3A7aXB_O6myVfcn3bCxQfLJlZTk,2842
-gsrap/runsims/.ipynb_checkpoints/simplegrowth-checkpoint.py,sha256=whNezVUgdTFO5H8_Q6_jo5rM-zyzj17bzGDcrxfTotc,2339
+gsrap/runsims/.ipynb_checkpoints/simplegrowth-checkpoint.py,sha256=tCQHTMUqum1YwlBKRTNaQoag2co_yQlCaKmISOARAlE,2353
 gsrap/runsims/.ipynb_checkpoints/singleomission-checkpoint.py,sha256=jMuKAi0pINP8Jlrm-yI-tX7D110VzttR3YfTSnDRe4I,2847
 gsrap/runsims/__init__.py,sha256=6E6E1gWgH0V7ls4Omx4mxxC85gMJ_27YqhjugJzlZtY,97
 gsrap/runsims/biosynth.py,sha256=fUlHUo4CfB4rGX9Dth87B1p5E5sz7i6spR7ZoqDDGaI,2836
@@ -83,10 +85,10 @@ gsrap/runsims/essentialgenes.py,sha256=MzHiuaU1gwiPdjZAgG7tkdYzkTTvoNCLp5tkezZhz
 gsrap/runsims/growthfactors.py,sha256=r_W4idtOSJBDh7HURRsU8s1TqfOZ3TfeVw2HHDxmnGU,2265
 gsrap/runsims/precursors.py,sha256=1RNt_Rxs0L1lolDmYh4_CiZgiwHfU5B_AcomJO6vJ28,2219
 gsrap/runsims/runsims.py,sha256=2FC5Gs8oSYyZTjHF3A7aXB_O6myVfcn3bCxQfLJlZTk,2842
-gsrap/runsims/simplegrowth.py,sha256=whNezVUgdTFO5H8_Q6_jo5rM-zyzj17bzGDcrxfTotc,2339
+gsrap/runsims/simplegrowth.py,sha256=tCQHTMUqum1YwlBKRTNaQoag2co_yQlCaKmISOARAlE,2353
 gsrap/runsims/singleomission.py,sha256=jMuKAi0pINP8Jlrm-yI-tX7D110VzttR3YfTSnDRe4I,2847
-gsrap-0.7.1.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
-gsrap-0.7.1.dist-info/METADATA,sha256=ps1z-ZR33q-YL1KeATh-RUNNuB4VU47Mz4OAl2b1F24,826
-gsrap-0.7.1.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-gsrap-0.7.1.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
-gsrap-0.7.1.dist-info/RECORD,,
+gsrap-0.7.2.dist-info/LICENSE.txt,sha256=OXLcl0T2SZ8Pmy2_dmlvKuetivmyPd5m1q-Gyd-zaYY,35149
+gsrap-0.7.2.dist-info/METADATA,sha256=bZQ9_fiR3Fo5_mUcnWD4GgMRYtFDjO0LG74yxtjSkBs,898
+gsrap-0.7.2.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+gsrap-0.7.2.dist-info/entry_points.txt,sha256=S9MY0DjfnbKGlZbp5bV7W6dNFy3APoEV84u9x6MV1eI,36
+gsrap-0.7.2.dist-info/RECORD,,