#!/usr/bin/env python
import os, sys
temp=list();
header=1;
sys.path.append('../../Libs/Python')
from BiochemPy import Reactions, Compounds, InChIs
compounds_helper = Compounds()
compounds_dict = compounds_helper.loadCompounds()
cpds_aliases_dict = compounds_helper.loadMSAliases()
cpds_names_dict = compounds_helper.loadNames()
# We actually don't want obsolete reactions and compounds in our database
# So we're striving to remove any 'new' ones that are obsolete
# Any information attached to them should be associated with their linked counterpart
# We need to retain older compounds that are now obsolete as these may be present in prior published models
# The number used here is the last compound entered before we re-integrated updates from KEGG and MetaCyc
# In the fall of 2018, so after this point, we'll take out obsolete compounds
last_cpd_str='cpd31000'
last_cpd_int=int(last_cpd_str[3:])
delete_cpds=list()
for cpd in compounds_dict:
cpd_int = int(cpd[3:])
if(cpd_int > last_cpd_int and compounds_dict[cpd]['is_obsolete']):
delete_cpds.append(cpd)
for cpd in delete_cpds:
#!/usr/bin/env python
import os, sys
from csv import DictReader
temp = list()
header = 1
sys.path.append('../../Libs/Python')
from BiochemPy import Reactions, Compounds, InChIs
CompoundsHelper = Compounds()
Compounds_Dict = CompoundsHelper.loadCompounds()
Aliases_Dict = CompoundsHelper.loadMSAliases()
Names_Dict = CompoundsHelper.loadNames()
Source_Classes = dict()
reader = DictReader(
open('../../../Biochemistry/Aliases/Source_Classifiers.txt'),
dialect='excel-tab')
for line in reader:
if (line['Source Type'] not in Source_Classes):
Source_Classes[line['Source Type']] = dict()
Source_Classes[line['Source Type']][line['Source ID']] = 1
for cpd in sorted(Compounds_Dict.keys()):
if (cpd not in Aliases_Dict):
continue
Cpd_Aliases = dict()
Alias_Count = 0
for source_type in 'Primary Database', 'Secondary Database', 'Published Model':
for source in sorted(Aliases_Dict[cpd].keys()):
'formula': array[1],
'charge': array[2]
}
#Load Curated Structures
Ignored_Structures = dict()
with open(Structures_Root + "Ignored_ModelSEED_Structures.txt") as ignore_file:
for line in ignore_file.readlines():
array = line.split('\t')
Ignored_Structures[array[0]] = 1
ignore_file.close()
#Load Structures and Aliases
Structures_Dict = CompoundsHelper.loadStructures(
["SMILE", "InChIKey", "InChI"], ["KEGG", "MetaCyc"])
MS_Aliases_Dict = CompoundsHelper.loadMSAliases(["KEGG", "MetaCyc"])
master_structs_file = open(Structures_Root + "All_ModelSEED_Structures.txt",
'w')
unique_structs_file = open(Structures_Root + "Unique_ModelSEED_Structures.txt",
'w')
unique_structs_file.write("ID\tType\tAliases\tFormula\tCharge\tStructure\n")
structure_conflicts_file = open("Structure_Conflicts.txt", 'w')
formula_conflicts_file = open("Formula_Conflicts.txt", 'w')
for msid in sorted(MS_Aliases_Dict.keys()):
#Build collection of all structures for the ModelSEED ID
Structs = dict()
Formulas = dict()
for source in 'KEGG', 'MetaCyc':
if (source not in MS_Aliases_Dict[msid].keys()):
if (compounds_dict[disambiguating_cpd]['is_obsolete'] == 1):
print("Warning: compound " + disambiguating_cpd +
" is obsolete, consider using the non-obsolete version")
Disambiguation_Object['from'] = {
'id': disambiguating_cpd,
'structures': {},
'aliases': {},
'names': {},
'formula': compounds_dict[disambiguating_cpd]['formula'],
'charge': compounds_dict[disambiguating_cpd]['charge'],
'mass': compounds_dict[disambiguating_cpd]['mass']
}
Aliases_Dict = compounds_helper.loadMSAliases()
Names_Dict = compounds_helper.loadNames()
Structures_Dict = compounds_helper.loadStructures(["InChI", "SMILE"],
["KEGG", "MetaCyc"])
#For reverse lookup
reverse_aliases_dict = dict()
for cpd in Aliases_Dict:
for source in Aliases_Dict[cpd]:
for alias in Aliases_Dict[cpd][source]:
if (alias not in reverse_aliases_dict):
reverse_aliases_dict[alias] = dict()
if (source not in reverse_aliases_dict[alias]):
reverse_aliases_dict[alias][source] = dict()
reverse_aliases_dict[alias][source][cpd] = 1
compounds_dict = compounds_helper.loadCompounds()
names_dict = compounds_helper.loadNames()
searchnames_dict = dict()
all_names_dict = dict()
new_name_count = dict()
for msid in sorted(names_dict):
for name in names_dict[msid]:
all_names_dict[name] = 1
searchname = compounds_helper.searchname(name)
#Avoid redundancy where possible
if (searchname not in searchnames_dict):
searchnames_dict[searchname] = msid
original_alias_dict = compounds_helper.loadMSAliases()
source_alias_dict = dict()
all_aliases = dict()
new_alias_count = dict()
for msid in original_alias_dict:
for source in original_alias_dict[msid]:
if (source not in source_alias_dict):
source_alias_dict[source] = dict()
for alias in original_alias_dict[msid][source]:
if (alias not in all_aliases):
all_aliases[alias] = dict()
all_aliases[alias][msid] = 1
if (alias not in source_alias_dict[source]):
source_alias_dict[source][alias] = list()
#!/usr/bin/env python
import os
import sys
import json
from BiochemPy import Compounds, Reactions
#Load Compounds
CompoundsHelper = Compounds()
Compounds_Dict = CompoundsHelper.loadCompounds()
MS_Aliases_Dict = CompoundsHelper.loadMSAliases(["MetaCyc", "PlantCyc"])
for cpd in MS_Aliases_Dict:
if ('PlantCyc' not in MS_Aliases_Dict[cpd]):
MS_Aliases_Dict[cpd]['PlantCyc'] = []
if ('MetaCyc' not in MS_Aliases_Dict[cpd]):
MS_Aliases_Dict[cpd]['MetaCyc'] = []
print("\t".join([
cpd, "|".join(MS_Aliases_Dict[cpd]['PlantCyc']),
"|".join(MS_Aliases_Dict[cpd]["MetaCyc"])
]))
#Load Reactions
ReactionsHelper = Reactions()
Reactions_Dict = ReactionsHelper.loadReactions()
MS_Aliases_Dict = ReactionsHelper.loadMSAliases(["MetaCyc", "PlantCyc"])
for rxn in MS_Aliases_Dict:
if ('PlantCyc' not in MS_Aliases_Dict[rxn]):
MS_Aliases_Dict[rxn]['PlantCyc'] = []
if ('MetaCyc' not in MS_Aliases_Dict[rxn]):