Small bugs fixed

molsysmt/build/define_new_chain.py

@@ -21,7 +21,7 @@ def define_new_chain(molecular_system, selection='all', chain_id=None, chain_nam
             chain_name = 'A'
 
         set(molecular_system, element='atom', selection='all', chain_index=0, skip_digestion=True)
-        set(molecular_system, element='chain', selection=0, chain_id=chain_id, chain_name=chain_name, skip_digestion=True)
+        set(molecular_system, element='chain', selection='all', chain_id=[chain_id], chain_name=[chain_name], skip_digestion=True)
 
     else:
 

molsysmt/data/_make/chicken_villin_HP35.py

@@ -14,7 +14,6 @@
 
 files_to_be_purged = [
         'pdb/1vii.pdb',
-        'mmtf/1vii.mmtf',
         'h5msm/chicken_villin_HP35.h5msm',
         'h5msm/chicken_villin_HP35_solvated.h5msm',
         'dcd/traj_chicken_villin_HP35.dcd',
@@ -35,9 +34,9 @@
 msm.convert('pdb_id:1vii', to_form='1vii.pdb')
 msm.convert('pdb_id:1vii', to_form='1vii.bcif')
 msm.convert('pdb_id:1vii', to_form='1vii.bcif.gz')
-shutil.move('1vii.pdb', Path(data_dir, 'bcif/1vii.pdb'))
-shutil.move('1vii.bcif', Path(data_dir, 'mmtf/1vii.bcif'))
-shutil.move('1vii.bcif.gz', Path(data_dir, 'mmtf/1vii.bcif.gz'))
+shutil.move('1vii.pdb', Path(data_dir, 'pdb/1vii.pdb'))
+shutil.move('1vii.bcif', Path(data_dir, 'bcif/1vii.bcif'))
+shutil.move('1vii.bcif.gz', Path(data_dir, 'bcif_gz/1vii.bcif.gz'))
 
 
 # vacuum

molsysmt/form/molsysmt_Topology/set.py

@@ -56,8 +56,13 @@ def set_chain_index_to_atom(item, indices='all', value=None, skip_digestion=Fals
     if is_all(indices):
         if len(value)==1:
             item.atoms.chain_index=value[0]
+            n_chains = 1
         else:
             item.atoms.chain_index=value
+            n_chains = np.unique(value).shape[0]
+        if n_chains!=item.chains.shape[0]:
+            item.reset_chains(n_chains=n_chains)
+            item.rebuild_chains(redefine_ids=True, redefine_types=True, redefine_names=True)
     else:
         item.atoms.iloc[indices, 4]=value
 

molsysmt/native/topology.py

@@ -666,6 +666,7 @@ def rebuild_molecules(self, redefine_indices=True, redefine_ids=True, redefine_n
     def rebuild_chains(self, redefine_ids=True, redefine_types=True, redefine_names=True):
 
         from molsysmt.element.molecule import _singular_molecule_type_to_plural
+        from molsysmt.element.chain import all_chain_names
 
         if redefine_ids:
 
@@ -720,23 +721,7 @@ def rebuild_chains(self, redefine_ids=True, redefine_types=True, redefine_names=
 
         if redefine_names:
 
-            alphabet = string.ascii_uppercase
-            chain_name_list = []
-            ii = 0
-            while len(chain_name_list) < self.chains.shape[0]:
-                if ii < len(alphabet):
-                    chain_name_list.append(alphabet[ii])
-                else:
-                    for first_letter in alphabet:
-                        for second_letter in alphabet:
-                            chain_name_list.append(first_letter + second_letter)
-                            if len(chain_name_list) >= self.chains.shape[0]:
-                                break
-                        if len(chain_name_list) >= self.chains.shape[0]:
-                            break
-                ii += 1
-
-            self.chains["chain_name"]=np.array(chain_name_list[:self.chains.shape[0]], dtype=object)
+            self.chains["chain_name"]=np.array(all_chain_names[:self.chains.shape[0]], dtype=object)
 
 
     def rebuild_entities(self, redefine_indices=True, redefine_ids=True, redefine_names=True, redefine_types=True):

sandbox/Tests.ipynb

@@ -18,7 +18,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bb0e9bda4b2a4a9eb6e171ee76c6ea86",
+       "model_id": "ea2e8c1e89bc4d219d42d82c9108c88f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -35,54 +35,158 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a673846b-5259-4acc-a751-9a9df5ba7a46",
+   "execution_count": 2,
+   "id": "e4442462-d13a-4102-831e-53432b0b04de",
    "metadata": {},
    "outputs": [],
    "source": [
-    "molecular_system = msm.build.build_peptide('AlaValPro', to_form='molsysmt.MolSys')"
+    "molsys_1 = msm.convert(systems['alanine dipeptide']['alanine_dipeptide.h5msm'], to_form='molsysmt.MolSys')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "3cde5516-66de-4705-8539-ea9814f7ab2c",
+   "execution_count": 3,
+   "id": "48649be7-9724-48f0-9f73-1c8ad9f577d2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "temp_molecular_system = msm.convert(molecular_system, to_form='pdbfixer.PDBFixer')"
+    "molsys_2 = msm.structure.translate(molsys_1, translation='[0.5, 0.0, 0.0] nm')"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "1b6627fa-c6cc-4262-a51c-ec50ed919840",
+   "execution_count": 4,
+   "id": "588d98cf-50f6-4a99-a562-d207ffb7e869",
    "metadata": {},
    "outputs": [],
    "source": [
-    "msm.select(temp_molecular_system, selection='component_type in [\"peptide\", \"protein\"]')"
+    "molsys_merged = msm.merge([molsys_1, molsys_2], keep_ids=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "b13310ce-2b0b-429c-a6e7-b0a53074d34c",
+   "execution_count": 5,
+   "id": "038cd459-facb-47d5-ae4f-26deefc4a9e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "msm.build.define_new_chain(molsys_merged)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8aa9e648-9c87-4701-bba5-3bf2d5aff9d9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>chain_id</th>\n",
+       "      <th>chain_name</th>\n",
+       "      <th>chain_type</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0</td>\n",
+       "      <td>A</td>\n",
+       "      <td>system</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   chain_id chain_name chain_type\n",
+       "0         0          A     system"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "molsys_merged.topology.chains"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "0d985652-a9f6-4617-b92e-c7fef89f24f6",
    "metadata": {},
    "outputs": [],
    "source": [
-    "msm.get(temp_molecular_system, element='component', selection='component_type in [\"peptide\", \"protein\"]',\n",
-    "                                     atom_index=True)"
+    "view = msm.view(molsys_merged, viewer='NGLView')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "4eff5af0-50ea-4c4a-a6b9-73c21170159e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "comparison = msm.compare(view, molsys_merged, attribute_type='topological',\n",
+    "             coordinates=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ddbf7195-e17f-43b4-a70a-8074f72d7ee5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "comparison"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a15ccef9-8872-4d86-83be-10c624e7a4d1",
+   "id": "9c305a1e-1f6c-4ecf-8138-0f55ade00df8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "msm.get(molecular_system, element='component', selection='component_type in [\"peptide\", \"protein\"]',\n",
-    "                                     atom_index=True)"
+    "    molsys_1 = msm.convert(systems['alanine dipeptide']['alanine_dipeptide.h5msm'], to_form='molsysmt.MolSys')\n",
+    "    molsys_2 = msm.structure.translate(molsys_1, translation='[0.5, 0.0, 0.0] nm')\n",
+    "    molsys_merged = msm.merge([molsys_1, molsys_2], keep_ids=False)\n",
+    "    msm.build.define_new_chain(molsys_merged, selection='all', chain_id=0, chain_name='A')\n",
+    "    view = msm.view(molsys_merged, viewer='NGLView')\n",
+    "    comparison = msm.compare(view, molsys_merged, attribute_type='topological',\n",
+    "            coordinates=True)\n",
+    "    assert comparison\n"
    ]
   }
  ],

tests/basic/convert/one_to_one/test_convert_from_file_mmtf.py

@@ -16,12 +16,6 @@ def test_file_mmtf_to_molsysmt_MolSys_1():
     form = msm.get_form(molsys)
     assert 'molsysmt.MolSys'==form
 
-def test_file_mmtf_to_molsysmt_MolSys_2():
-    molsys = systems['chicken villin HP35']['1vii.mmtf']
-    molsys = msm.convert(molsys, to_form='molsysmt.MolSys')
-    form = msm.get_form(molsys)
-    assert 'molsysmt.MolSys'==form
-
 #def test_file_mmtf_to_string_aminoacids1():
 #    molsys = tests_systems['T4 lysozyme L99A']['181l.mmtf']
 #    molsys = msm.convert(molsys, to_form='string:aminoacids1')

tests/basic/convert/one_to_one/test_convert_from_string_pdb_id.py

@@ -21,11 +21,17 @@ def test_string_pdb_id_to_file_pdb():
     os.remove(molsys)
     assert 'file:pdb'==form
 
-def test_string_pdb_id_to_file_mmtf():
-    molsys = msm.convert('pdb_id:181l', to_form='181l.mmtf')
+def test_string_pdb_id_to_file_bcif():
+    molsys = msm.convert('pdb_id:181l', to_form='181l.bcif')
     form = msm.get_form(molsys)
     os.remove(molsys)
-    assert 'file:mmtf'==form
+    assert 'file:bcif'==form
+
+def test_string_pdb_id_to_file_bcif_gz():
+    molsys = msm.convert('pdb_id:181l', to_form='181l.bcif.gz')
+    form = msm.get_form(molsys)
+    os.remove(molsys)
+    assert 'file:bcif.gz'==form
 
 def test_string_pdb_id_to_mdtraj_Trajectory():
     molsys = msm.convert('pdb_id:181l', to_form='mdtraj.Trajectory')

tests/basic/test_is_composed_of.py

@@ -31,6 +31,6 @@ def test_is_composed_of_5():
     assert output == False
 
 def test_is_composed_of_6():
-    output = msm.is_composed_of(molsys, ions=2, waters=1483, peptides=1)
+    output = msm.is_composed_of(molsys, ions=2, waters=1283, peptides=1)
     assert output == True
 

tests/basic/view/test_view_molsysmt_MolSys_with_NGLView.py

@@ -35,7 +35,7 @@ def test_view_molsyst_MolSys_with_NGLView_3():
     molsys_1 = msm.convert(systems['alanine dipeptide']['alanine_dipeptide.h5msm'], to_form='molsysmt.MolSys')
     molsys_2 = msm.structure.translate(molsys_1, translation='[0.5, 0.0, 0.0] nm')
     molsys_merged = msm.merge([molsys_1, molsys_2], keep_ids=False)
-    msm.build.define_new_chain(molsys_merged)
+    msm.build.define_new_chain(molsys_merged, selection='all', chain_id=0, chain_name='A')
     view = msm.view(molsys_merged, viewer='NGLView')
     comparison = msm.compare(view, molsys_merged, attribute_type='topological',
             coordinates=True)