gsrap 0.10.1__py3-none-any.whl → 0.10.2__py3-none-any.whl

gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -9,21 +9,18 @@ import atexit
 import os
 
 
-
 import cobra
 
 
 from .commons import get_logger
 from .commons import set_usual_formatter
 from .commons import set_header_trailer_formatter
-
 from .getmaps import getmaps_command
 from .parsedb import parsedb_command
 from .mkmodel import mkmodel_command
 from .runsims import runsims_command
 
 
-
 cobra_config = cobra.Configuration()
 solver_name = str(cobra_config.solver.log).split(' ')[1]
 solver_name = solver_name.replace("optlang.", '')
@@ -69,20 +66,21 @@ def main():
     parsedb_parser.add_argument("-o", "--outdir", metavar='', type=str, default='./', help="Main output directory (will be created if not existing).")
     parsedb_parser.add_argument("-i", "--inmaps", metavar='', type=str, default='./gsrap.maps', help="Input file 'gsrap.maps' previously produced using the 'getmaps' subcommand.")
     parsedb_parser.add_argument("-p", "--progress", action='store_true', help="Show progress for each map.")
-    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("--module", action='store_true', help="Show progress for each module of each map (use with --progress).")
+    parsedb_parser.add_argument("-f", "--focus", metavar='', type=str, default='-', help="Focus on a particular map/module obtaining codes of missing reactions (use 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("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. If not provided, the first medium in --media is used. Provide '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).")
+    parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to optional eggnog-mapper annotation table(s). If provided, --progress will be based on such table(s) instead of the entire KEGG.")
+    parsedb_parser.add_argument("-t", "--taxon", metavar='', type=str, default='-', help="Optional high-level taxon of interest accounted during the parsing. If provided, --progress will be based on such taxon instead of the entire KEGG (takes precedence over --eggnog). The syntax '{level}:{name}' must be honored, where {level} is 'kingdom' or 'phylum'.")
+    parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="Optional single KEGG Organism code accounted during parsing. If provided, --progress will be based on such organism instead of the entire KEGG (takes precedence over --taxon and --eggnog).")
+    parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Used to skip rows of M-R-T sheets during parsing. The syntax '{pure_mid}-{rid1}-{rid2}' must be honored. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")
+    parsedb_parser.add_argument("--onlycurator", metavar='', type=str, default='-', help="Build the universe by parsing contents of the specified curator ID only. Contents affected by --goodbefore are parsed anyway.")
+    parsedb_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures in th Excel output.")
+    parsedb_parser.add_argument("-j", "--justparse", action='store_true', help="Parse the database without performing extra activities (saves time).")
     parsedb_parser.add_argument("-d", "--keepdisconn", action='store_true', help="Do not remove disconnected metabolites.")
+    parsedb_parser.add_argument("--escherzip", metavar='', type=str, default='-', help="Optional path to the zipped 'escher' folder downloaded from Google Drive.")
     
     
     

gsrap/__init__.py

@@ -9,21 +9,18 @@ import atexit
 import os
 
 
-
 import cobra
 
 
 from .commons import get_logger
 from .commons import set_usual_formatter
 from .commons import set_header_trailer_formatter
-
 from .getmaps import getmaps_command
 from .parsedb import parsedb_command
 from .mkmodel import mkmodel_command
 from .runsims import runsims_command
 
 
-
 cobra_config = cobra.Configuration()
 solver_name = str(cobra_config.solver.log).split(' ')[1]
 solver_name = solver_name.replace("optlang.", '')
@@ -69,20 +66,21 @@ def main():
     parsedb_parser.add_argument("-o", "--outdir", metavar='', type=str, default='./', help="Main output directory (will be created if not existing).")
     parsedb_parser.add_argument("-i", "--inmaps", metavar='', type=str, default='./gsrap.maps', help="Input file 'gsrap.maps' previously produced using the 'getmaps' subcommand.")
     parsedb_parser.add_argument("-p", "--progress", action='store_true', help="Show progress for each map.")
-    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("--module", action='store_true', help="Show progress for each module of each map (use with --progress).")
+    parsedb_parser.add_argument("-f", "--focus", metavar='', type=str, default='-', help="Focus on a particular map/module obtaining codes of missing reactions (use 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("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. If not provided, the first medium in --media is used. Provide '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).")
+    parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to optional eggnog-mapper annotation table(s). If provided, --progress will be based on such table(s) instead of the entire KEGG.")
+    parsedb_parser.add_argument("-t", "--taxon", metavar='', type=str, default='-', help="Optional high-level taxon of interest accounted during the parsing. If provided, --progress will be based on such taxon instead of the entire KEGG (takes precedence over --eggnog). The syntax '{level}:{name}' must be honored, where {level} is 'kingdom' or 'phylum'.")
+    parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="Optional single KEGG Organism code accounted during parsing. If provided, --progress will be based on such organism instead of the entire KEGG (takes precedence over --taxon and --eggnog).")
+    parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Used to skip rows of M-R-T sheets during parsing. The syntax '{pure_mid}-{rid1}-{rid2}' must be honored. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")
+    parsedb_parser.add_argument("--onlycurator", metavar='', type=str, default='-', help="Build the universe by parsing contents of the specified curator ID only. Contents affected by --goodbefore are parsed anyway.")
+    parsedb_parser.add_argument("--nofigs", action='store_true', help="Do not generate figures in th Excel output.")
+    parsedb_parser.add_argument("-j", "--justparse", action='store_true', help="Parse the database without performing extra activities (saves time).")
     parsedb_parser.add_argument("-d", "--keepdisconn", action='store_true', help="Do not remove disconnected metabolites.")
+    parsedb_parser.add_argument("--escherzip", metavar='', type=str, default='-', help="Optional path to the zipped 'escher' folder downloaded from Google Drive.")
     
     
     

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

@@ -28,7 +28,7 @@ def get_biomass_dict(logger, universe, dbexp):
     fraction_to_precursors = dict()
     for fraction in ['DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA']:
         fraction_db = dbexp[fraction]
-        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'author', 'units']) 
+        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'curator', 'units']) 
         precursors = [f"{i}_c" for i in fraction_db.index.dropna()]
         for i in precursors: 
             if i not in universal_mids:

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

@@ -26,7 +26,7 @@ def check_exp_biomass_data(logger, dbexp, biomass):
     ftd = dict()  # fraction_to_decimals
     for sheet in ['MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA']:
         fraction_db = dbexp[sheet][biomass].dropna() # they should be str
-        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'author', 'units']) 
+        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'curator', 'units']) 
         ftd[sheet] = {i: Decimal(val) for i, val in fraction_db.items() if Decimal(val) != Decimal('0.0')} # convert to dict
         if sum(ftd[sheet].values()) != Decimal('1.0'):  # check if the sum gives 1 (g/gDW or mol/mol depending on 'sheet')
             logger.error(f"Biomass data provided in sheet '{sheet}' for ID '{biomass}' does not sum up to 1.0. Missing mass is {Decimal('1.0')-sum(ftd[sheet].values())}.")

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

@@ -41,7 +41,7 @@ def get_dbuni(logger):
     
     
     sheet_id = "1dXJBIFjCghrdvQtxEOYlVNWAQU4mK-nqLWyDQeUZqek"
-    #sheet_id = "1dCVOOnpNg7rK3iZmTDz3wybW7YrUNoClnqezT9Q5bpc" # alternative
+    #sheet_id = "15fIBewG1B1jIbg1_9pMnyPJL7LWCLMD8s_vlf3ZUno0"  # alternative
     url = f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=xlsx"
     response = requests.get(url)  # download the requested file
     if response.status_code == 200:
@@ -100,7 +100,7 @@ def get_dbexp(logger):
     
     # check table presence
     sheet_names = exceldb.sheet_names
-    for i in ['media', 'PM1', 'PM2A', 'PM3B', 'PM4A', 'MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA', 'authors']: 
+    for i in ['media', 'PM1', 'PM2A', 'PM3B', 'PM4A', 'MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA', 'curators']: 
         if i not in sheet_names:
             logger.error(f"Sheet '{i}' is missing!")
             return 1
@@ -119,7 +119,7 @@ def get_dbexp(logger):
     dbexp['PROTS'] = exceldb.parse('PROTS')
     dbexp['LIPIDS_PL'] = exceldb.parse('LIPIDS_PL')
     dbexp['LIPIDS_FA'] = exceldb.parse('LIPIDS_FA')
-    dbexp['authors'] = exceldb.parse('authors')
+    dbexp['curators'] = exceldb.parse('curators')
     
     
     # format tables (media):

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

@@ -1,8 +1,15 @@
 import warnings
 import logging
 import threading
+import zipfile
+from pathlib import Path
+import tempfile
+import json
+import os
+import shutil
 
 import cobra
+from escher import Builder
 
 from .downloads import SimpleLoadingWheel
 
@@ -109,4 +116,143 @@ def count_undrawn_rids_focus(logger, universe, lastmap, focus, outdir):
         logger.warning(f"'{outdir}/focus_{focus}.json' created!")
     else:
         logger.info(f"Current '{lastmap['filename']}' is 0 reactions behind. Thank you ♥")
-        
+        
+        
+        
+def parse_zipped_escher(logger, universe, escherzip, outdir): 
+    # used to parse the zipped 'escher' folder downloaded from Google Drive.
+    # 'escherzip' is the path to zipped folder. 
+    
+    
+    logger.info("Processing collection of hand-drawn Escher maps...")
+    
+    
+    # prepare empty logs folder
+    shutil.rmtree(f'{outdir}/escherapps', ignore_errors=True)
+    os.makedirs(f'{outdir}/escherapps', exist_ok=True)
+    
+    
+    drawngid_to_maps = dict()
+    drawnrid_to_maps = dict()
+    drawnpuremid_to_maps = dict()
+    with tempfile.TemporaryDirectory() as tmp_dir:
+        
+        # check path existance: 
+        zip_path = Path(escherzip)  # convert to Path for convenience
+        if not zip_path.exists():
+            logger.error(f"Zipped escher does not exist at provided path '{zip_path}'.")
+            return 1
+        
+        # extract in a auto-deleting temporary directory 
+        with zipfile.ZipFile(zip_path, "r") as z:
+            z.extractall(tmp_dir)
+
+        # extract the inner child dirs:
+        tmp_dir = Path(tmp_dir)
+        child_dirs = [p for p in tmp_dir.iterdir() if p.is_dir()]
+        escher_dir = child_dirs[0]  # the top-level folder in the ZIP
+        inner_child_dirs = [p for p in escher_dir.iterdir() if p.is_dir()]
+        
+        # iterate the inner child dirs:
+        for map_dir in inner_child_dirs:
+            map_id = map_dir.name.rsplit('/',1)[-1]
+            map_files = [f for f in map_dir.iterdir() if f.is_file()]
+            map_files_name = set([f.name.rsplit('/',1)[-1].split('-v',1)[0] for f in map_files])
+            
+            # check presence of maps:
+            if len(map_files_name) == 0:
+                # still no maps in this folder
+                continue
+            
+            # check name consistency:
+            if len(map_files_name) != 1:
+                logger.error(f"Name inconsistency in folder '{map_dir_name}'!")
+                return 1
+            
+            # check consistency with the folder 
+            if list(map_files_name)[0] != map_id:
+                logger.error(f"Versions in '{map_id}' refer to a different map!")
+            
+            # get latest version
+            map_versions = [int(f.name.rsplit('/',1)[-1].split('-v',1)[-1].replace('.json','')) for f in map_files]
+            latest_version = max(map_versions)
+            
+            
+            # read json (last version) to fill the dict
+            latest_filepath = str(map_dir / f"{map_id}-v{latest_version}.json")
+            with open(latest_filepath, 'r') as file:
+                json_data = json.load(file)
+        
+                # get elements on Escher:
+                map_drawngids = set()
+                map_drawnrids = set()
+                map_drawnpuremids = set()
+                for key, value in json_data[1]['reactions'].items():
+                    map_drawnrids.add(value['bigg_id'])
+                    for i in value['genes']:
+                        map_drawngids.add(i['bigg_id'])
+                    #for i in value['metabolites']:
+                    #    puremeid = i['bigg_id'].rsplit('_',1)[0]
+                    #    map_drawnpuremids.add(puremeid)
+                for key, value in json_data[1]['nodes'].items():
+                    if value['node_type'] == 'metabolite':
+                        puremeid = value['bigg_id'].rsplit('_',1)[0]
+                        map_drawnpuremids.add(puremeid)
+                    
+                # populat dicts
+                for drawngid in map_drawngids:
+                    if drawngid not in drawngid_to_maps.keys():
+                        drawngid_to_maps[drawngid] = set()
+                    drawngid_to_maps[drawngid].add(map_id)
+                for drawnrid in map_drawnrids:
+                    if drawnrid not in drawnrid_to_maps.keys():
+                        drawnrid_to_maps[drawnrid] = set()
+                    drawnrid_to_maps[drawnrid].add(map_id)
+                for drawnpuremid in map_drawnpuremids:
+                    if drawnpuremid not in drawnpuremid_to_maps.keys():
+                        drawnpuremid_to_maps[drawnpuremid] = set()
+                    drawnpuremid_to_maps[drawnpuremid].add(map_id)
+                    
+                    
+            # read json (last version) to create the escher app
+            builder = Builder(
+                map_json = latest_filepath,   
+                model_json = None, 
+            )
+            builder.never_ask_before_quit = True
+            builder.scroll_behavior = 'zoom'
+
+            builder.menu = 'all'
+            builder.enable_editing = False
+
+            builder.enable_keys = False  # switch not working
+            builder.enable_search = True  # switch not working
+            builder.full_screen_button = True  # switch not working
+
+            builder.highlight_missing = True 
+            builder.show_gene_reaction_rules = True
+            builder.enable_tooltips = 'label'
+    
+            builder.save_html(f"{outdir}/escherapps/{map_id}.html")
+            
+        
+    # apply annotation to universe
+    for g in universe.genes: 
+        if g.id in drawngid_to_maps.keys():
+            g.annotation['drawn_in_maps'] = list(drawngid_to_maps[g.id])
+        else:
+            g.annotation['drawn_in_maps'] = []
+    for r in universe.reactions: 
+        if r.id in drawnrid_to_maps.keys():
+            r.annotation['drawn_in_maps'] = list(drawnrid_to_maps[r.id])
+        else:
+            r.annotation['drawn_in_maps'] = []
+    for m in universe.metabolites: 
+        puremid = m.id.rsplit('_',1)[0]
+        if puremid in drawnpuremid_to_maps.keys():
+            m.annotation['drawn_in_maps'] = list(drawnpuremid_to_maps[puremid])
+        else:
+            m.annotation['drawn_in_maps'] = []
+            
+    
+    return universe

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

@@ -12,7 +12,7 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
     # retrieve metadata
     description = column.iloc[0]
     doi = column.iloc[1]
-    author = column.iloc[2]
+    curator = column.iloc[2]
     units = column.iloc[3]
 
     

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

@@ -58,8 +58,8 @@ def show_contributions(logger, db, goodbefore):
         return 0
     
     
-    # create a counter for each author
-    cnt = {author: 0 for author in db['curators']['username']}
+    # create a counter for each curator
+    cnt = {curator: 0 for curator in db['curators']['username']}
     cnt_tot = 0
     
     
@@ -67,9 +67,9 @@ def show_contributions(logger, db, goodbefore):
         if type(row['curator']) != str: 
             logger.error(f"Missing curator in tab 'R', rid '{row['rid']}'.")
             return 1
-        for author in row['curator'].split(';'):
-            author = author.rstrip().strip()
-            cnt[author] += 1
+        for curator in row['curator'].split(';'):
+            curator = curator.rstrip().strip()
+            cnt[curator] += 1
             cnt_tot += 1
             
             
@@ -77,18 +77,18 @@ def show_contributions(logger, db, goodbefore):
         if type(row['curator']) != str: 
             logger.error(f"Missing curator in tab 'T', rid '{row['rid']}'.")
             return 1
-        for author in row['curator'].split(';'):
-            author = author.rstrip().strip()
-            cnt[author] += 1
+        for curator in row['curator'].split(';'):
+            curator = curator.rstrip().strip()
+            cnt[curator] += 1
             cnt_tot += 1
         
         
     # compute percentages:
-    pct = {author: cnt[author]/cnt_tot*100 for author in cnt.keys()}
+    pct = {curator: cnt[curator]/cnt_tot*100 for curator in cnt.keys()}
     # sort in descending order: 
     pct = dict(sorted(pct.items(), key=lambda item: item[1], reverse=True))
     # convert to string:
-    pct = {author: f'{round(pct[author],2)}%' for author in pct.keys()}
+    pct = {curator: f'{round(pct[curator],2)}%' for curator in pct.keys()}
     logger.debug(f"Contributions: {pct}.")
     
     

gsrap/commons/biomass.py

@@ -28,7 +28,7 @@ def get_biomass_dict(logger, universe, dbexp):
     fraction_to_precursors = dict()
     for fraction in ['DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA']:
         fraction_db = dbexp[fraction]
-        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'author', 'units']) 
+        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'curator', 'units']) 
         precursors = [f"{i}_c" for i in fraction_db.index.dropna()]
         for i in precursors: 
             if i not in universal_mids:

gsrap/commons/coeffs.py

@@ -26,7 +26,7 @@ def check_exp_biomass_data(logger, dbexp, biomass):
     ftd = dict()  # fraction_to_decimals
     for sheet in ['MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA']:
         fraction_db = dbexp[sheet][biomass].dropna() # they should be str
-        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'author', 'units']) 
+        fraction_db = fraction_db.iloc[4:] # ignore ['description', 'doi', 'curator', 'units']) 
         ftd[sheet] = {i: Decimal(val) for i, val in fraction_db.items() if Decimal(val) != Decimal('0.0')} # convert to dict
         if sum(ftd[sheet].values()) != Decimal('1.0'):  # check if the sum gives 1 (g/gDW or mol/mol depending on 'sheet')
             logger.error(f"Biomass data provided in sheet '{sheet}' for ID '{biomass}' does not sum up to 1.0. Missing mass is {Decimal('1.0')-sum(ftd[sheet].values())}.")

gsrap/commons/downloads.py

@@ -41,7 +41,7 @@ def get_dbuni(logger):
     
     
     sheet_id = "1dXJBIFjCghrdvQtxEOYlVNWAQU4mK-nqLWyDQeUZqek"
-    #sheet_id = "1dCVOOnpNg7rK3iZmTDz3wybW7YrUNoClnqezT9Q5bpc" # alternative
+    #sheet_id = "15fIBewG1B1jIbg1_9pMnyPJL7LWCLMD8s_vlf3ZUno0"  # alternative
     url = f"https://docs.google.com/spreadsheets/d/{sheet_id}/export?format=xlsx"
     response = requests.get(url)  # download the requested file
     if response.status_code == 200:
@@ -100,7 +100,7 @@ def get_dbexp(logger):
     
     # check table presence
     sheet_names = exceldb.sheet_names
-    for i in ['media', 'PM1', 'PM2A', 'PM3B', 'PM4A', 'MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA', 'authors']: 
+    for i in ['media', 'PM1', 'PM2A', 'PM3B', 'PM4A', 'MWF', 'DNA', 'RNA', 'PROTS', 'LIPIDS_PL', 'LIPIDS_FA', 'curators']: 
         if i not in sheet_names:
             logger.error(f"Sheet '{i}' is missing!")
             return 1
@@ -119,7 +119,7 @@ def get_dbexp(logger):
     dbexp['PROTS'] = exceldb.parse('PROTS')
     dbexp['LIPIDS_PL'] = exceldb.parse('LIPIDS_PL')
     dbexp['LIPIDS_FA'] = exceldb.parse('LIPIDS_FA')
-    dbexp['authors'] = exceldb.parse('authors')
+    dbexp['curators'] = exceldb.parse('curators')
     
     
     # format tables (media):

gsrap/commons/escherutils.py

@@ -1,8 +1,15 @@
 import warnings
 import logging
 import threading
+import zipfile
+from pathlib import Path
+import tempfile
+import json
+import os
+import shutil
 
 import cobra
+from escher import Builder
 
 from .downloads import SimpleLoadingWheel
 
@@ -109,4 +116,143 @@ def count_undrawn_rids_focus(logger, universe, lastmap, focus, outdir):
         logger.warning(f"'{outdir}/focus_{focus}.json' created!")
     else:
         logger.info(f"Current '{lastmap['filename']}' is 0 reactions behind. Thank you ♥")
-        
+        
+        
+        
+def parse_zipped_escher(logger, universe, escherzip, outdir): 
+    # used to parse the zipped 'escher' folder downloaded from Google Drive.
+    # 'escherzip' is the path to zipped folder. 
+    
+    
+    logger.info("Processing collection of hand-drawn Escher maps...")
+    
+    
+    # prepare empty logs folder
+    shutil.rmtree(f'{outdir}/escherapps', ignore_errors=True)
+    os.makedirs(f'{outdir}/escherapps', exist_ok=True)
+    
+    
+    drawngid_to_maps = dict()
+    drawnrid_to_maps = dict()
+    drawnpuremid_to_maps = dict()
+    with tempfile.TemporaryDirectory() as tmp_dir:
+        
+        # check path existance: 
+        zip_path = Path(escherzip)  # convert to Path for convenience
+        if not zip_path.exists():
+            logger.error(f"Zipped escher does not exist at provided path '{zip_path}'.")
+            return 1
+        
+        # extract in a auto-deleting temporary directory 
+        with zipfile.ZipFile(zip_path, "r") as z:
+            z.extractall(tmp_dir)
+
+        # extract the inner child dirs:
+        tmp_dir = Path(tmp_dir)
+        child_dirs = [p for p in tmp_dir.iterdir() if p.is_dir()]
+        escher_dir = child_dirs[0]  # the top-level folder in the ZIP
+        inner_child_dirs = [p for p in escher_dir.iterdir() if p.is_dir()]
+        
+        # iterate the inner child dirs:
+        for map_dir in inner_child_dirs:
+            map_id = map_dir.name.rsplit('/',1)[-1]
+            map_files = [f for f in map_dir.iterdir() if f.is_file()]
+            map_files_name = set([f.name.rsplit('/',1)[-1].split('-v',1)[0] for f in map_files])
+            
+            # check presence of maps:
+            if len(map_files_name) == 0:
+                # still no maps in this folder
+                continue
+            
+            # check name consistency:
+            if len(map_files_name) != 1:
+                logger.error(f"Name inconsistency in folder '{map_dir_name}'!")
+                return 1
+            
+            # check consistency with the folder 
+            if list(map_files_name)[0] != map_id:
+                logger.error(f"Versions in '{map_id}' refer to a different map!")
+            
+            # get latest version
+            map_versions = [int(f.name.rsplit('/',1)[-1].split('-v',1)[-1].replace('.json','')) for f in map_files]
+            latest_version = max(map_versions)
+            
+            
+            # read json (last version) to fill the dict
+            latest_filepath = str(map_dir / f"{map_id}-v{latest_version}.json")
+            with open(latest_filepath, 'r') as file:
+                json_data = json.load(file)
+        
+                # get elements on Escher:
+                map_drawngids = set()
+                map_drawnrids = set()
+                map_drawnpuremids = set()
+                for key, value in json_data[1]['reactions'].items():
+                    map_drawnrids.add(value['bigg_id'])
+                    for i in value['genes']:
+                        map_drawngids.add(i['bigg_id'])
+                    #for i in value['metabolites']:
+                    #    puremeid = i['bigg_id'].rsplit('_',1)[0]
+                    #    map_drawnpuremids.add(puremeid)
+                for key, value in json_data[1]['nodes'].items():
+                    if value['node_type'] == 'metabolite':
+                        puremeid = value['bigg_id'].rsplit('_',1)[0]
+                        map_drawnpuremids.add(puremeid)
+                    
+                # populat dicts
+                for drawngid in map_drawngids:
+                    if drawngid not in drawngid_to_maps.keys():
+                        drawngid_to_maps[drawngid] = set()
+                    drawngid_to_maps[drawngid].add(map_id)
+                for drawnrid in map_drawnrids:
+                    if drawnrid not in drawnrid_to_maps.keys():
+                        drawnrid_to_maps[drawnrid] = set()
+                    drawnrid_to_maps[drawnrid].add(map_id)
+                for drawnpuremid in map_drawnpuremids:
+                    if drawnpuremid not in drawnpuremid_to_maps.keys():
+                        drawnpuremid_to_maps[drawnpuremid] = set()
+                    drawnpuremid_to_maps[drawnpuremid].add(map_id)
+                    
+                    
+            # read json (last version) to create the escher app
+            builder = Builder(
+                map_json = latest_filepath,   
+                model_json = None, 
+            )
+            builder.never_ask_before_quit = True
+            builder.scroll_behavior = 'zoom'
+
+            builder.menu = 'all'
+            builder.enable_editing = False
+
+            builder.enable_keys = False  # switch not working
+            builder.enable_search = True  # switch not working
+            builder.full_screen_button = True  # switch not working
+
+            builder.highlight_missing = True 
+            builder.show_gene_reaction_rules = True
+            builder.enable_tooltips = 'label'
+    
+            builder.save_html(f"{outdir}/escherapps/{map_id}.html")
+            
+        
+    # apply annotation to universe
+    for g in universe.genes: 
+        if g.id in drawngid_to_maps.keys():
+            g.annotation['drawn_in_maps'] = list(drawngid_to_maps[g.id])
+        else:
+            g.annotation['drawn_in_maps'] = []
+    for r in universe.reactions: 
+        if r.id in drawnrid_to_maps.keys():
+            r.annotation['drawn_in_maps'] = list(drawnrid_to_maps[r.id])
+        else:
+            r.annotation['drawn_in_maps'] = []
+    for m in universe.metabolites: 
+        puremid = m.id.rsplit('_',1)[0]
+        if puremid in drawnpuremid_to_maps.keys():
+            m.annotation['drawn_in_maps'] = list(drawnpuremid_to_maps[puremid])
+        else:
+            m.annotation['drawn_in_maps'] = []
+            
+    
+    return universe

gsrap/commons/medium.py

@@ -12,7 +12,7 @@ def apply_medium_given_column(logger, model, medium, column, is_reference=False)
     # retrieve metadata
     description = column.iloc[0]
     doi = column.iloc[1]
-    author = column.iloc[2]
+    curator = column.iloc[2]
     units = column.iloc[3]