In process

molsysmt/element/group/small_molecule/make_amino_acids_db.py → molsysmt/data/databases/make_amino_acids_db.py

@@ -41,10 +41,17 @@
 
     aux_dict['name']=key['_chem_comp']['name']
     aux_dict['three_letter_code']=key['_chem_comp']['three_letter_code']
+    aux_dict['formal_charge']=float(key['_chem_comp']['pdbx_formal_charge'])
     aux_dict['atom_name']=key['_chem_comp_atom']['atom_id']
     aux_dict['alt_atom_name']=key['_chem_comp_atom']['alt_atom_id']
     aux_dict['atom_type']=key['_chem_comp_atom']['type_symbol']
-    aux_dict['charge']=[float(ii) for ii in key['_chem_comp_atom']['charge']]
+    try:
+        charge = []
+        for ii in key['_chem_comp_atom']['charge']:
+            charge.append(float(ii))
+        aux_dict['charge']=charge
+    except:
+        aux_dict['charge']=[]
     if '_chem_comp_bond' in key:
         aux_dict['bonds']=[[ii,jj] for ii,jj in zip(key['_chem_comp_bond']['atom_id_1'],
                                                     key['_chem_comp_bond']['atom_id_2'])]
@@ -56,7 +63,18 @@
 #with open('small_molecules_db.pkl', 'wb') as fff:
 #    pickle.dump(output, fff)
 
+split_output = {}
+for name,value in output.items():
+    if name[0] not in split_output:
+        split_output[name[0]]={}
+    split_output[name[0]][name]=value
+
 import gzip
-with gzip.open('amino_acids_db.pkl.gz', 'wb', compresslevel=9) as fff:
-    pickle.dump(output, fff)
+
+for file_name, aux_output in split_output.items():
+    with gzip.open('amino_acids/'+file_name+'.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(aux_output, fff)
+
+with gzip.open('amino_acids/group_names.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(list(output.keys()), fff)
 

molsysmt/element/group/small_molecule/make_small_molecule_db.py → molsysmt/data/databases/make_ions_db.py

@@ -21,20 +21,34 @@
     data += types_dict[ii]
 data.remove('UNL')
 
+# quito iones
+ions = []
+for value in data:
+    key = cif_entries[value]
+    if key['_chem_comp']['name'].endswith(' ION"') or key['_chem_comp']['name'].endswith(' ion"'):
+        ions.append(value)
+
 output = {}
 
-for value in data:
+for value in ions:
 
     key = cif_entries[value]
 
     aux_dict={}
 
     aux_dict['name']=key['_chem_comp']['name']
     aux_dict['three_letter_code']=key['_chem_comp']['three_letter_code']
+    aux_dict['formal_charge']=float(key['_chem_comp']['pdbx_formal_charge'])
     aux_dict['atom_name']=key['_chem_comp_atom']['atom_id']
     aux_dict['alt_atom_name']=key['_chem_comp_atom']['alt_atom_id']
     aux_dict['atom_type']=key['_chem_comp_atom']['type_symbol']
-    aux_dict['charge']=[float(ii) for ii in key['_chem_comp_atom']['charge']]
+    try:
+        charge = []
+        for ii in key['_chem_comp_atom']['charge']:
+            charge.append(float(ii))
+        aux_dict['charge']=charge
+    except:
+        aux_dict['charge']=[]
     if '_chem_comp_bond' in key:
         aux_dict['bonds']=[[ii,jj] for ii,jj in zip(key['_chem_comp_bond']['atom_id_1'],
                                                     key['_chem_comp_bond']['atom_id_2'])]
@@ -46,7 +60,19 @@
 #with open('small_molecules_db.pkl', 'wb') as fff:
 #    pickle.dump(output, fff)
 
+split_output = {}
+for name,value in output.items():
+    if name[0] not in split_output:
+        split_output[name[0]]={}
+    split_output[name[0]][name]=value
+
 import gzip
-with gzip.open('small_molecules_db.pkl.gz', 'wb', compresslevel=9) as fff:
-    pickle.dump(output, fff)
+
+for file_name, aux_output in split_output.items():
+    with gzip.open('ions/'+file_name+'.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(aux_output, fff)
+
+with gzip.open('ions/group_names.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(list(output.keys()), fff)
+
 

molsysmt/data/databases/make_small_molecules_db.py

@@ -0,0 +1,81 @@
+# wget https://files.wwpdb.org/pub/pdb/data/monomers/components.cif
+
+from molsysmt.native import CIFFileHandler
+import pickle
+
+handler = CIFFileHandler('components.cif')
+cif_entries = handler.parse()
+
+types_dict = {}
+
+for ii in cif_entries:
+    jj = cif_entries[ii]['_chem_comp']['type']
+    if jj in types_dict:
+        types_dict[jj].append(ii)
+    else:
+        types_dict[jj] = [ii]
+
+types = ['NON-POLYMER', 'non-polymer', 'other']
+data = []
+for ii in types:
+    data += types_dict[ii]
+data.remove('UNL')
+
+# quito iones
+ions = []
+for value in data:
+    key = cif_entries[value]
+    if key['_chem_comp']['name'].endswith(' ION"') or key['_chem_comp']['name'].endswith(' ion"'):
+        ions.append(value)
+
+for ion in ions:
+    data.remove(ion)
+
+output = {}
+
+for value in data:
+
+    key = cif_entries[value]
+
+    aux_dict={}
+
+    aux_dict['name']=key['_chem_comp']['name']
+    aux_dict['three_letter_code']=key['_chem_comp']['three_letter_code']
+    aux_dict['formal_charge']=float(key['_chem_comp']['pdbx_formal_charge'])
+    aux_dict['atom_name']=key['_chem_comp_atom']['atom_id']
+    aux_dict['alt_atom_name']=key['_chem_comp_atom']['alt_atom_id']
+    aux_dict['atom_type']=key['_chem_comp_atom']['type_symbol']
+    try:
+        charge = []
+        for ii in key['_chem_comp_atom']['charge']:
+            charge.append(float(ii))
+        aux_dict['charge']=charge
+    except:
+        aux_dict['charge']=[]
+    if '_chem_comp_bond' in key:
+        aux_dict['bonds']=[[ii,jj] for ii,jj in zip(key['_chem_comp_bond']['atom_id_1'],
+                                                    key['_chem_comp_bond']['atom_id_2'])]
+    else:
+        aux_dict['bonds']=[]
+
+    output[value]=aux_dict
+
+#with open('small_molecules_db.pkl', 'wb') as fff:
+#    pickle.dump(output, fff)
+
+split_output = {}
+for name,value in output.items():
+    if name[0] not in split_output:
+        split_output[name[0]]={}
+    split_output[name[0]][name]=value
+
+import gzip
+
+for file_name, aux_output in split_output.items():
+    with gzip.open('small_molecules/'+file_name+'.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(aux_output, fff)
+
+with gzip.open('small_molecules/group_names.pkl.gz', 'wb', compresslevel=9) as fff:
+        pickle.dump(list(output.keys()), fff)
+
+

molsysmt/element/group/amino_acid/__init__.py

@@ -1,5 +1,5 @@
-from .names import names
 from .get_amino_acid_type_from_name import get_amino_acid_type_from_name
 from .get_1_letter_code_from_name import get_1_letter_code_from_name
 from .is_amino_acid import is_amino_acid
+from .group_names import group_names
 

molsysmt/element/group/amino_acid/group_names.py

@@ -0,0 +1,19 @@
+import pickle
+import sys
+import gzip
+
+if sys.version_info[1]==10:
+    from importlib.resources import files
+    def path(package, file):
+        return files(package).joinpath(file)
+elif sys.version_info[1] in (8,9):
+    from pathlib import PurePath
+    parent = PurePath(__file__).parent
+    def path(package, file):
+        data_dir = package.split('.')[-1]
+        return parent.joinpath('../data/'+data_dir+'/'+file).__str__()
+
+
+with gzip.open(path('molsysmt.data.databases.amino_acids','group_names.pkl.gz'), 'rb') as fff:
+    group_names = pickle.load(fff)
+

molsysmt/element/group/amino_acid/is_amino_acid.py

@@ -1,8 +1,8 @@
-from .get_amino_acid_type_from_name import name_to_type
+from .group_names import group_names
 
 def is_amino_acid(name):
     """
     To be written soon...
     """
-    return (name in name_to_type)
+    return (name in group_names)
 

molsysmt/element/group/ion/__init__.py

@@ -1,2 +1,2 @@
-from .ion_names import ion_names
 from .is_ion import is_ion
+from .group_names import group_names

molsysmt/element/group/small_molecule/small_molecule_names.py → molsysmt/element/group/ion/group_names.py

@@ -1,5 +1,6 @@
 import pickle
 import sys
+import gzip
 
 if sys.version_info[1]==10:
     from importlib.resources import files
@@ -13,6 +14,6 @@ def path(package, file):
         return parent.joinpath('../data/'+data_dir+'/'+file).__str__()
 
 
-with open(path('molsysmt.data.databases','components.pkl'), 'rb') as fff:
-    small_molecule_names = pickle.load(fff)
+with gzip.open(path('molsysmt.data.databases.ions','group_names.pkl.gz'), 'rb') as fff:
+    group_names = pickle.load(fff)
 

molsysmt/element/group/ion/is_ion.py

@@ -1,9 +1,9 @@
-from .ion_names import ion_names
+from .group_names import group_names
 
 def is_ion(name):
     """
     To be written soon...
     """
 
-    return (name in ion_names)
+    return (name in group_names)
 

molsysmt/element/group/small_molecule/__init__.py

@@ -1,2 +1,3 @@
-from .small_molecule_names import small_molecule_names
 from .is_small_molecule import is_small_molecule
+from .group_names import group_names
+

molsysmt/element/group/small_molecule/group_names.py

@@ -0,0 +1,19 @@
+import pickle
+import sys
+import gzip
+
+if sys.version_info[1]==10:
+    from importlib.resources import files
+    def path(package, file):
+        return files(package).joinpath(file)
+elif sys.version_info[1] in (8,9):
+    from pathlib import PurePath
+    parent = PurePath(__file__).parent
+    def path(package, file):
+        data_dir = package.split('.')[-1]
+        return parent.joinpath('../data/'+data_dir+'/'+file).__str__()
+
+
+with gzip.open(path('molsysmt.data.databases.small_molecules','group_names.pkl.gz'), 'rb') as fff:
+    group_names = pickle.load(fff)
+

molsysmt/element/group/small_molecule/is_small_molecule.py

@@ -1,9 +1,9 @@
-from .small_molecule_names import small_molecule_names
+from .group_names import group_names
 
 def is_small_molecule(name):
     """
     To be written soon...
     """
 
-    return (name in small_molecule_names)
+    return (name in group_names)