gsrap 0.8.2__tar.gz → 0.8.3__tar.gz

{gsrap-0.8.2 → gsrap-0.8.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: gsrap
-Version: 0.8.2
+Version: 0.8.3
 Summary: 
 License: GNU General Public License v3.0
 Author: Gioele Lazzari

{gsrap-0.8.2 → gsrap-0.8.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "gsrap"
-version = "0.8.2"
+version = "0.8.3"
 description = ""
 authors = ["Gioele Lazzari"]
 license = "GNU General Public License v3.0"

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/.ipynb_checkpoints/__init__-checkpoint.py

@@ -75,6 +75,7 @@ def main():
     parsedb_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. By default, the first medium in --media is used. Use 'none' to avoid initialization.")
     parsedb_parser.add_argument("--precursors", action='store_true', help="Verify biosynthesis of biomass precursors and show blocked ones.")
     parsedb_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
+    parsedb_parser.add_argument("-t", "--taxon", metavar='', type=str, default='-', help="High-level taxon of interest. If provided, it must follow the syntax '{level}:{name}', where {level} is 'kingdom' or 'phylum'.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
     parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Syntax is {pure_mid}-{rid1}-{rid2}. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/__init__.py

@@ -75,6 +75,7 @@ def main():
     parsedb_parser.add_argument("-z", "--initialize", metavar='', type=str, default='-', help="Initialize the universe on the provided medium. By default, the first medium in --media is used. Use 'none' to avoid initialization.")
     parsedb_parser.add_argument("--precursors", action='store_true', help="Verify biosynthesis of biomass precursors and show blocked ones.")
     parsedb_parser.add_argument("--biosynth", action='store_true', help="Check biosynthesis of all metabolites and detect dead-ends.")
+    parsedb_parser.add_argument("-t", "--taxon", metavar='', type=str, default='-', help="High-level taxon of interest. If provided, it must follow the syntax '{level}:{name}', where {level} is 'kingdom' or 'phylum'.")
     parsedb_parser.add_argument("-e", "--eggnog", nargs='+', metavar='', type=str, default='-', help="Path to the optional eggnog-mapper annotation table(s).")
     parsedb_parser.add_argument("-k", "--keggorg", metavar='', type=str, default='-', help="A single KEGG Organism code. If provided, it takes precedence over --eggnog.")
     parsedb_parser.add_argument("--goodbefore", metavar='', type=str, default='-', help="Syntax is {pure_mid}-{rid1}-{rid2}. From top to bottom, build the universe until reaction {rid1}, transport {rid2} and metabolite {pure_mid} are reached.")

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/commons/.ipynb_checkpoints/downloads-checkpoint.py

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

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/commons/.ipynb_checkpoints/excelhub-checkpoint.py

@@ -148,7 +148,7 @@ def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B,
             else: df_T.append(row_dict)
             
     for g in model.genes:
-        row_dict = {'gid': g.id, 'involved_in': '; '.join([r.id for r in g.reactions])}
+        row_dict = {'gid': g.id, 'name': g.name, 'involved_in': '; '.join([r.id for r in g.reactions])}
         
         for db in g.annotation.keys():
             annots = g.annotation[db]
@@ -171,7 +171,7 @@ def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B,
     df_R = df_R[df_R_first_cols + sorted([c for c in df_R.columns if c not in df_R_first_cols])]
     df_T = df_T[df_R_first_cols + sorted([c for c in df_T.columns if c not in df_R_first_cols])]
     df_A = df_A[df_R_first_cols + sorted([c for c in df_A.columns if c not in df_R_first_cols])]
-    df_G_first_cols = ['gid', 'involved_in']
+    df_G_first_cols = ['gid', 'name', 'involved_in']
     df_G = df_G[df_G_first_cols + sorted([c for c in df_G.columns if c not in df_G_first_cols])]
     
     

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/commons/downloads.py

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

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/commons/excelhub.py

@@ -148,7 +148,7 @@ def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B,
             else: df_T.append(row_dict)
             
     for g in model.genes:
-        row_dict = {'gid': g.id, 'involved_in': '; '.join([r.id for r in g.reactions])}
+        row_dict = {'gid': g.id, 'name': g.name, 'involved_in': '; '.join([r.id for r in g.reactions])}
         
         for db in g.annotation.keys():
             annots = g.annotation[db]
@@ -171,7 +171,7 @@ def write_excel_model(model, filepath, nofigs, memote_results_dict, df_E, df_B,
     df_R = df_R[df_R_first_cols + sorted([c for c in df_R.columns if c not in df_R_first_cols])]
     df_T = df_T[df_R_first_cols + sorted([c for c in df_T.columns if c not in df_R_first_cols])]
     df_A = df_A[df_R_first_cols + sorted([c for c in df_A.columns if c not in df_R_first_cols])]
-    df_G_first_cols = ['gid', 'involved_in']
+    df_G_first_cols = ['gid', 'name', 'involved_in']
     df_G = df_G[df_G_first_cols + sorted([c for c in df_G.columns if c not in df_G_first_cols])]
     
     

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/getmaps/.ipynb_checkpoints/getmaps-checkpoint.py

@@ -4,6 +4,7 @@ import pickle
 
 
 from .kdown import download_raw_txtfiles
+from .kdown import create_dict_keggorg
 from .kdown import create_dict_ko
 from .kdown import create_dict_c
 from .kdown import create_dict_r
@@ -20,13 +21,19 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     logger.info(f"Respectfully retrieving metabolic information from KEGG. Raw data are being saved into '{outdir}/kdown/'. Be patient, could take a couple of days...")
     os.makedirs(f'{outdir}/kdown/', exist_ok=True)
     
+    
     response = download_raw_txtfiles(logger, outdir, usecache)
     if type(response) == int: return 1
     else: RELEASE_kegg = response
     
+        
     
     logger.info("Parsing downloaded KEGG information...")
-
+    
+    response = create_dict_keggorg(logger, outdir)
+    if type(response) == int: return 1
+    else: dict_keggorg = response
+    
     response = create_dict_ko(logger, outdir)
     if type(response) == int: return 1
     else: dict_ko = response
@@ -49,7 +56,7 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     
     
     # create 'idcollection_dict' and 'summary_dict' dictionaries
-    idcollection_dict = create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md)
+    idcollection_dict = create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md)
     summary_dict = create_summary_dict(dict_c, dict_r, dict_map, dict_md)
     
         
@@ -57,7 +64,6 @@ def do_kdown(logger, outdir, usecache, keeptmp):
 
 
 
-
 def main(args, logger):
     
     
@@ -67,7 +73,7 @@ def main(args, logger):
     os.makedirs(f'{args.outdir}/', exist_ok=True)
     
     
-    # KEGG
+    # KEGG download
     response = do_kdown(logger, args.outdir, args.usecache, args.keeptmp)
     if type(response) == int: return 1
     else: RELEASE_kegg, idcollection_dict, summary_dict = response[0], response[1], response[2]
@@ -76,7 +82,9 @@ def main(args, logger):
     # create 'gsrap.maps':
     with open(f'{args.outdir}/gsrap.maps', 'wb') as wb_handler:
         pickle.dump({
-            'RELEASE_kegg': RELEASE_kegg, 'idcollection_dict': idcollection_dict, 'summary_dict': summary_dict,
+            'RELEASE_kegg': RELEASE_kegg, 
+            'idcollection_dict': idcollection_dict, 
+            'summary_dict': summary_dict, 
         }, wb_handler)
     logger.info(f"'{args.outdir}/gsrap.maps' created!")
     
@@ -87,4 +95,5 @@ def main(args, logger):
         logger.info(f"Temporary raw files deleted!")
     
     
+    
     return 0

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/getmaps/.ipynb_checkpoints/kdown-checkpoint.py

@@ -34,6 +34,7 @@ def download_raw_txtfiles(logger, outdir, usecache):
         'orthology',
         'module', 
         'pathway',
+        'organism',
     ]
     for db in databases:
         time.sleep(0.5)
@@ -45,8 +46,9 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
     # mix the items to download to be respectful/compliant
     items_to_download = []
-
     for db in databases:
+        if db == 'organism': 
+            continue   # here we just need the list
         with open(f"{outdir}/kdown/{db}.txt", 'r') as file:
             res_string = file.read()
             rows = res_string.split('\n')
@@ -54,7 +56,6 @@ def download_raw_txtfiles(logger, outdir, usecache):
                 item_id = row.split('\t', 1)[0]
                 if item_id == '': continue
                 items_to_download.append({'db': db, 'id': item_id})
-
     random.shuffle(items_to_download)
 
 
@@ -79,6 +80,51 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
 
 
+def create_dict_keggorg(logger, outdir):
+    
+    organisms_raw = open(f'{outdir}/kdown/organism.txt', 'r').read()
+
+    # create a dataframe listing all organisms in KEGG;
+    # columns are [tnumber, name, domain, kingdom, phylum, classification]
+    df = []  # list fo dicts
+    for line in organisms_raw.strip().split("\n"):
+        fields = line.split("\t")
+        if len(fields) == 4:
+            tnumber, keggorg, name, classification = fields
+            levels = classification.split(";")
+            domain = levels[0]
+            kingdom = levels[1]
+            phylum = levels[2]
+            df.append({
+                'tnumber':tnumber, 
+                'keggorg': keggorg, 
+                'name': name, 
+                'domain': domain, 
+                'kingdom': kingdom,
+                'phylum': phylum,
+                'classification': classification
+            })
+        else: 
+            # never verified during tests!
+            logger.warning(f'Strange number of fields found in this line of "organism.txt": """{line}""".')
+    df = pnd.DataFrame.from_records(df)
+    df = df.set_index('keggorg', drop=True, verify_integrity=True)
+    
+    
+    # convert dataframe to dict
+    dict_keggorg = {}
+    for keggorg, row in df.iterrows(): 
+        dict_keggorg[keggorg] = {
+            'kingdom': row['kingdom'],
+            'phylum': row['phylum'],
+            #'name': row['name'],   # not strictly needed. Commented to save disk space.
+        }
+        
+    if logger != None: logger.info(f'Number of unique items (org): {len(dict_keggorg.keys())}.')
+    return dict_keggorg
+
+
+
 def create_dict_ko(logger, outdir):
     
     dict_ko = {}         # main output
@@ -98,6 +144,7 @@ def create_dict_ko(logger, outdir):
                 'ecs': set(),
                 'cogs': set(),
                 'gos': set(),
+                'keggorgs': set(),
             }   
         else:
             logger.error(f"{ko_id} already included!")
@@ -175,7 +222,13 @@ def create_dict_ko(logger, outdir):
                         gos = content[len('GO: '):].strip().split(' ')
                         for go in gos:
                             dict_ko[ko_id]['gos'].add(go)
-                        
+                            
+                            
+                # parse the organism-specific genes
+                if curr_header == 'GENES       ':
+                    keggorg = content.split(': ',1)[0]
+                    dict_ko[ko_id]['keggorgs'].add(keggorg.lower()) # organism.txt has IDs in lowercase
+                    
                         
                 # parse the reactions
                 if curr_header == 'REACTION    ':
@@ -547,7 +600,7 @@ def create_dict_md(logger, outdir):
 
 
 
-def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
+def create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md):
 
     idcollection_dict = {}
     
@@ -620,6 +673,24 @@ def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
         for go in dict_ko[ko_id]['gos']:
             idcollection_dict['ko_to_gos'][ko_id].add(go)
             
+    
+    # creation of 'ko_to_keggorgs' skipped as it takes too much disk space. Replaced with 'ko_to_taxa'. 
+    idcollection_dict['ko_to_taxa'] = {}
+    missing_keggorgs = set()
+    for ko_id in dict_ko.keys():
+        idcollection_dict['ko_to_taxa'][ko_id] = {'kingdom': set(), 'phylum': set()}
+        for keggorg in dict_ko[ko_id]['keggorgs']:
+            try: 
+                kingdom = dict_keggorg[keggorg]['kingdom']
+                phylum = dict_keggorg[keggorg]['phylum']
+            except: 
+                if keggorg not in missing_keggorgs:
+                    missing_keggorgs.add(keggorg)
+                    #print(f"Organism '{keggorg}' appears in 'orthology/' but not in 'organism.txt'.")
+                continue
+            idcollection_dict['ko_to_taxa'][ko_id]['kingdom'].add(kingdom)
+            idcollection_dict['ko_to_taxa'][ko_id]['phylum'].add(phylum)
+
             
     idcollection_dict['map_to_name'] = {}
     for map_id in dict_map.keys():

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/getmaps/getmaps.py

@@ -4,6 +4,7 @@ import pickle
 
 
 from .kdown import download_raw_txtfiles
+from .kdown import create_dict_keggorg
 from .kdown import create_dict_ko
 from .kdown import create_dict_c
 from .kdown import create_dict_r
@@ -20,13 +21,19 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     logger.info(f"Respectfully retrieving metabolic information from KEGG. Raw data are being saved into '{outdir}/kdown/'. Be patient, could take a couple of days...")
     os.makedirs(f'{outdir}/kdown/', exist_ok=True)
     
+    
     response = download_raw_txtfiles(logger, outdir, usecache)
     if type(response) == int: return 1
     else: RELEASE_kegg = response
     
+        
     
     logger.info("Parsing downloaded KEGG information...")
-
+    
+    response = create_dict_keggorg(logger, outdir)
+    if type(response) == int: return 1
+    else: dict_keggorg = response
+    
     response = create_dict_ko(logger, outdir)
     if type(response) == int: return 1
     else: dict_ko = response
@@ -49,7 +56,7 @@ def do_kdown(logger, outdir, usecache, keeptmp):
     
     
     # create 'idcollection_dict' and 'summary_dict' dictionaries
-    idcollection_dict = create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md)
+    idcollection_dict = create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md)
     summary_dict = create_summary_dict(dict_c, dict_r, dict_map, dict_md)
     
         
@@ -57,7 +64,6 @@ def do_kdown(logger, outdir, usecache, keeptmp):
 
 
 
-
 def main(args, logger):
     
     
@@ -67,7 +73,7 @@ def main(args, logger):
     os.makedirs(f'{args.outdir}/', exist_ok=True)
     
     
-    # KEGG
+    # KEGG download
     response = do_kdown(logger, args.outdir, args.usecache, args.keeptmp)
     if type(response) == int: return 1
     else: RELEASE_kegg, idcollection_dict, summary_dict = response[0], response[1], response[2]
@@ -76,7 +82,9 @@ def main(args, logger):
     # create 'gsrap.maps':
     with open(f'{args.outdir}/gsrap.maps', 'wb') as wb_handler:
         pickle.dump({
-            'RELEASE_kegg': RELEASE_kegg, 'idcollection_dict': idcollection_dict, 'summary_dict': summary_dict,
+            'RELEASE_kegg': RELEASE_kegg, 
+            'idcollection_dict': idcollection_dict, 
+            'summary_dict': summary_dict, 
         }, wb_handler)
     logger.info(f"'{args.outdir}/gsrap.maps' created!")
     
@@ -87,4 +95,5 @@ def main(args, logger):
         logger.info(f"Temporary raw files deleted!")
     
     
+    
     return 0

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/getmaps/kdown.py

@@ -34,6 +34,7 @@ def download_raw_txtfiles(logger, outdir, usecache):
         'orthology',
         'module', 
         'pathway',
+        'organism',
     ]
     for db in databases:
         time.sleep(0.5)
@@ -45,8 +46,9 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
     # mix the items to download to be respectful/compliant
     items_to_download = []
-
     for db in databases:
+        if db == 'organism': 
+            continue   # here we just need the list
         with open(f"{outdir}/kdown/{db}.txt", 'r') as file:
             res_string = file.read()
             rows = res_string.split('\n')
@@ -54,7 +56,6 @@ def download_raw_txtfiles(logger, outdir, usecache):
                 item_id = row.split('\t', 1)[0]
                 if item_id == '': continue
                 items_to_download.append({'db': db, 'id': item_id})
-
     random.shuffle(items_to_download)
 
 
@@ -79,6 +80,51 @@ def download_raw_txtfiles(logger, outdir, usecache):
 
 
 
+def create_dict_keggorg(logger, outdir):
+    
+    organisms_raw = open(f'{outdir}/kdown/organism.txt', 'r').read()
+
+    # create a dataframe listing all organisms in KEGG;
+    # columns are [tnumber, name, domain, kingdom, phylum, classification]
+    df = []  # list fo dicts
+    for line in organisms_raw.strip().split("\n"):
+        fields = line.split("\t")
+        if len(fields) == 4:
+            tnumber, keggorg, name, classification = fields
+            levels = classification.split(";")
+            domain = levels[0]
+            kingdom = levels[1]
+            phylum = levels[2]
+            df.append({
+                'tnumber':tnumber, 
+                'keggorg': keggorg, 
+                'name': name, 
+                'domain': domain, 
+                'kingdom': kingdom,
+                'phylum': phylum,
+                'classification': classification
+            })
+        else: 
+            # never verified during tests!
+            logger.warning(f'Strange number of fields found in this line of "organism.txt": """{line}""".')
+    df = pnd.DataFrame.from_records(df)
+    df = df.set_index('keggorg', drop=True, verify_integrity=True)
+    
+    
+    # convert dataframe to dict
+    dict_keggorg = {}
+    for keggorg, row in df.iterrows(): 
+        dict_keggorg[keggorg] = {
+            'kingdom': row['kingdom'],
+            'phylum': row['phylum'],
+            #'name': row['name'],   # not strictly needed. Commented to save disk space.
+        }
+        
+    if logger != None: logger.info(f'Number of unique items (org): {len(dict_keggorg.keys())}.')
+    return dict_keggorg
+
+
+
 def create_dict_ko(logger, outdir):
     
     dict_ko = {}         # main output
@@ -98,6 +144,7 @@ def create_dict_ko(logger, outdir):
                 'ecs': set(),
                 'cogs': set(),
                 'gos': set(),
+                'keggorgs': set(),
             }   
         else:
             logger.error(f"{ko_id} already included!")
@@ -175,7 +222,13 @@ def create_dict_ko(logger, outdir):
                         gos = content[len('GO: '):].strip().split(' ')
                         for go in gos:
                             dict_ko[ko_id]['gos'].add(go)
-                        
+                            
+                            
+                # parse the organism-specific genes
+                if curr_header == 'GENES       ':
+                    keggorg = content.split(': ',1)[0]
+                    dict_ko[ko_id]['keggorgs'].add(keggorg.lower()) # organism.txt has IDs in lowercase
+                    
                         
                 # parse the reactions
                 if curr_header == 'REACTION    ':
@@ -547,7 +600,7 @@ def create_dict_md(logger, outdir):
 
 
 
-def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
+def create_idcollection_dict(dict_keggorg, dict_ko, dict_c, dict_r, dict_map, dict_md):
 
     idcollection_dict = {}
     
@@ -620,6 +673,24 @@ def create_idcollection_dict(dict_ko, dict_c, dict_r, dict_map, dict_md):
         for go in dict_ko[ko_id]['gos']:
             idcollection_dict['ko_to_gos'][ko_id].add(go)
             
+    
+    # creation of 'ko_to_keggorgs' skipped as it takes too much disk space. Replaced with 'ko_to_taxa'. 
+    idcollection_dict['ko_to_taxa'] = {}
+    missing_keggorgs = set()
+    for ko_id in dict_ko.keys():
+        idcollection_dict['ko_to_taxa'][ko_id] = {'kingdom': set(), 'phylum': set()}
+        for keggorg in dict_ko[ko_id]['keggorgs']:
+            try: 
+                kingdom = dict_keggorg[keggorg]['kingdom']
+                phylum = dict_keggorg[keggorg]['phylum']
+            except: 
+                if keggorg not in missing_keggorgs:
+                    missing_keggorgs.add(keggorg)
+                    #print(f"Organism '{keggorg}' appears in 'orthology/' but not in 'organism.txt'.")
+                continue
+            idcollection_dict['ko_to_taxa'][ko_id]['kingdom'].add(kingdom)
+            idcollection_dict['ko_to_taxa'][ko_id]['phylum'].add(phylum)
+
             
     idcollection_dict['map_to_name'] = {}
     for map_id in dict_map.keys():

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/parsedb/.ipynb_checkpoints/completeness-checkpoint.py

@@ -27,9 +27,8 @@ def parse_eggnog(model, eggnog, idcollection_dict):
             
             
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -49,9 +48,34 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
     
     
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
+        if any([ko in kos_org for ko in kos]):
+            krs_org.add(kr)
+    
+    
+    return krs_org
+
+
+
+def parse_taxon(taxon, idcollection_dict):
+    
+    
+    # formatting of --taxon was already verified at startup.
+    # also the presence of 'ko_to_taxa' in idcollection_dict was veryfied at startup.
+    level, name = taxon.split(':')
+           
+        
+    # PART 1. get KO codes available
+    kos_org = set()
+    for ko in idcollection_dict['ko_to_taxa'].keys():
+        if name in idcollection_dict['ko_to_taxa'][ko][level]:
+            kos_org.add(ko)
+            
+    
+    # PART 2. get reactions in the organism (even the GPR is not complete)
+    krs_org = set()
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -60,7 +84,7 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
 
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
+def check_completeness(logger, model, progress, module, focus, taxon, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -69,6 +93,9 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
     if keggorg != '-':  # keggorg has precedence
         kr_uni = parse_keggorg(keggorg, outdir, idcollection_dict)
         kr_uni_label = f"organism code '{keggorg}'"
+    elif taxon != '-':
+        kr_uni = parse_taxon(taxon, idcollection_dict)
+        kr_uni_label = f"taxon '{taxon}'"
     elif eggnog != '-':
         for eggfile in eggnog:
             eggset = parse_eggnog(model, eggfile, idcollection_dict)

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/parsedb/.ipynb_checkpoints/parsedb-checkpoint.py

@@ -17,6 +17,7 @@ from ..commons import show_contributions
 from ..commons import adjust_biomass_precursors
 from ..commons import count_undrawn_rids
 from ..commons import format_expansion
+from ..commons import check_taxon
 from ..commons import download_keggorg
 from ..commons import initialize_model
 from ..commons import get_memote_results_dict
@@ -46,6 +47,7 @@ from .cycles import verify_egc_all
 def main(args, logger):
     
     
+    ###### FORMAT ARGS NOT REQUIRING RESOURCES
     # adjust out folder path                      
     while args.outdir.endswith('/'):              
         args.outdir = args.outdir[:-1]
@@ -77,17 +79,8 @@ def main(args, logger):
     if args.onlyauthor == '-': args.onlyauthor = None
     
     
-    # format the --eggnog param
-    args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
-    
-    # get the kegg organism if requested
-    if args.keggorg != '-':
-        response = download_keggorg(logger, args.keggorg, args.outdir)
-        if response == 1: return 1
-    
-    
-    
     
+    ###### LOAD LOCAL RESOURCES
     # check and extract the required 'gsrap.maps' file
     if os.path.exists(f'{args.inmaps}') == False:
         logger.error(f"File 'gsrap.maps' not found at {args.inmaps}.")
@@ -108,9 +101,27 @@ def main(args, logger):
             kegg_compound_to_others = pickle.load(handle)
     with resources.path("gsrap.assets", f"kegg_reaction_to_others.pickle") as asset_path: 
         with open(asset_path, 'rb') as handle:
-            kegg_reaction_to_others = pickle.load(handle)   
+            kegg_reaction_to_others = pickle.load(handle) 
+            
+            
+            
+    ###### FORMAT/CHECK FOCUSING ARGS
+    # format the --eggnog param
+    args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
+    
+    # check the --taxon param
+    if args.taxon != '-':
+        response = check_taxon(logger, args.taxon, idcollection_dict)
+        if response == 1: return 1
+    
+    # get the kegg organism if requested
+    if args.keggorg != '-':
+        response = download_keggorg(logger, args.keggorg, args.outdir)
+        if response == 1: return 1
+    
     
     
+    # DOWNLOAD ONLINE RESOURCES
     # get dbuni and dbexp:
     logger.info("Downloading gsrap database...")
     response = get_databases(logger)
@@ -166,7 +177,7 @@ def main(args, logger):
     
     ###### CHECKS 1
     # check universe completness
-    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
+    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.taxon, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
     if type(df_C)==int: return 1
 
 

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/parsedb/completeness.py

@@ -27,9 +27,8 @@ def parse_eggnog(model, eggnog, idcollection_dict):
             
             
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -49,9 +48,34 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
     
     
     # PART 2. get reactions in the organism (even the GPR is not complete)
-    kr_to_kos = idcollection_dict['kr_to_kos']
     krs_org = set()
-    for kr, kos in kr_to_kos.items(): 
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
+        if any([ko in kos_org for ko in kos]):
+            krs_org.add(kr)
+    
+    
+    return krs_org
+
+
+
+def parse_taxon(taxon, idcollection_dict):
+    
+    
+    # formatting of --taxon was already verified at startup.
+    # also the presence of 'ko_to_taxa' in idcollection_dict was veryfied at startup.
+    level, name = taxon.split(':')
+           
+        
+    # PART 1. get KO codes available
+    kos_org = set()
+    for ko in idcollection_dict['ko_to_taxa'].keys():
+        if name in idcollection_dict['ko_to_taxa'][ko][level]:
+            kos_org.add(ko)
+            
+    
+    # PART 2. get reactions in the organism (even the GPR is not complete)
+    krs_org = set()
+    for kr, kos in idcollection_dict['kr_to_kos'].items(): 
         if any([ko in kos_org for ko in kos]):
             krs_org.add(kr)
     
@@ -60,7 +84,7 @@ def parse_keggorg(keggorg, outdir, idcollection_dict):
 
     
     
-def check_completeness(logger, model, progress, module, focus, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
+def check_completeness(logger, model, progress, module, focus, taxon, eggnog, keggorg, idcollection_dict, summary_dict, outdir): 
     # check KEGG annotations in the universe model to get '%' of completeness per pathway/module.
     
             
@@ -69,6 +93,9 @@ def check_completeness(logger, model, progress, module, focus, eggnog, keggorg,
     if keggorg != '-':  # keggorg has precedence
         kr_uni = parse_keggorg(keggorg, outdir, idcollection_dict)
         kr_uni_label = f"organism code '{keggorg}'"
+    elif taxon != '-':
+        kr_uni = parse_taxon(taxon, idcollection_dict)
+        kr_uni_label = f"taxon '{taxon}'"
     elif eggnog != '-':
         for eggfile in eggnog:
             eggset = parse_eggnog(model, eggfile, idcollection_dict)

{gsrap-0.8.2 → gsrap-0.8.3}/src/gsrap/parsedb/parsedb.py

@@ -17,6 +17,7 @@ from ..commons import show_contributions
 from ..commons import adjust_biomass_precursors
 from ..commons import count_undrawn_rids
 from ..commons import format_expansion
+from ..commons import check_taxon
 from ..commons import download_keggorg
 from ..commons import initialize_model
 from ..commons import get_memote_results_dict
@@ -46,6 +47,7 @@ from .cycles import verify_egc_all
 def main(args, logger):
     
     
+    ###### FORMAT ARGS NOT REQUIRING RESOURCES
     # adjust out folder path                      
     while args.outdir.endswith('/'):              
         args.outdir = args.outdir[:-1]
@@ -77,17 +79,8 @@ def main(args, logger):
     if args.onlyauthor == '-': args.onlyauthor = None
     
     
-    # format the --eggnog param
-    args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
-    
-    # get the kegg organism if requested
-    if args.keggorg != '-':
-        response = download_keggorg(logger, args.keggorg, args.outdir)
-        if response == 1: return 1
-    
-    
-    
     
+    ###### LOAD LOCAL RESOURCES
     # check and extract the required 'gsrap.maps' file
     if os.path.exists(f'{args.inmaps}') == False:
         logger.error(f"File 'gsrap.maps' not found at {args.inmaps}.")
@@ -108,9 +101,27 @@ def main(args, logger):
             kegg_compound_to_others = pickle.load(handle)
     with resources.path("gsrap.assets", f"kegg_reaction_to_others.pickle") as asset_path: 
         with open(asset_path, 'rb') as handle:
-            kegg_reaction_to_others = pickle.load(handle)   
+            kegg_reaction_to_others = pickle.load(handle) 
+            
+            
+            
+    ###### FORMAT/CHECK FOCUSING ARGS
+    # format the --eggnog param
+    args.eggnog = format_expansion(logger, args.eggnog)  # now 'args.eggnog' could still be '-'
+    
+    # check the --taxon param
+    if args.taxon != '-':
+        response = check_taxon(logger, args.taxon, idcollection_dict)
+        if response == 1: return 1
+    
+    # get the kegg organism if requested
+    if args.keggorg != '-':
+        response = download_keggorg(logger, args.keggorg, args.outdir)
+        if response == 1: return 1
+    
     
     
+    # DOWNLOAD ONLINE RESOURCES
     # get dbuni and dbexp:
     logger.info("Downloading gsrap database...")
     response = get_databases(logger)
@@ -166,7 +177,7 @@ def main(args, logger):
     
     ###### CHECKS 1
     # check universe completness
-    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
+    df_C = check_completeness(logger, universe, args.progress, args.module, args.focus, args.taxon, args.eggnog, args.keggorg, idcollection_dict, summary_dict, args.outdir)
     if type(df_C)==int: return 1