fix linting

Author: ajfriedman22

ensemble_md/replica_exchange_EE.py

@@ -460,7 +460,7 @@ def set_params(self, analysis):
                 self.modify_coords_fn = self.default_coords_fn
             elif self.modify_coords == 'number':
                 if self.resname_select is None or self.resname_transform is None:
-                    raise ParameterError('resname_select and resname_transform options must be filled in if using the change number function')
+                    raise ParameterError('resname_select and resname_transform options must be filled in if using the change number function')  # noqa: E501
                 # Read file
                 input_file = gmx_parser.read_top(self.top[-1], self.resname_transform)
                 # Determine the atom names corresponding to the atom numbers
@@ -1765,7 +1765,7 @@ def process_top(self):
                 start_line, atom_name, atom_num, state = coordinate_swap.get_names(input_file, resname)
 
                 # Determine the connectivity of all atoms
-                connect_1, connect_2 = [], [] # Atom 1 and atom 2 which are connected and which state they are dummy atoms  # noqa: E501
+                connect_1, connect_2 = [], []  # Atom 1 and atom 2 which are connected and which state they are dummy atoms  # noqa: E501
                 for l, line in enumerate(input_file[start_line:]):  # noqa: E741
                     line_sep = line.split(' ')
                     if line_sep[0] == ';':
@@ -1845,8 +1845,8 @@ def change_num(self, molA_file_name, molB_file_name, swap_index):
         molA_new = open(molA_new_file_name, 'w')
 
         # Step 2: Determine how many of the molecule of interest are present in each system
-        numA, listA, trans_listA = coordinate_swap.deter_num_molecule(molA_file_name, self.resname_select, self.resname_transform)
-        numB, listB, trans_listB = coordinate_swap.deter_num_molecule(molB_file_name, self.resname_select, self.resname_transform)
+        numA, listA, trans_listA = coordinate_swap.deter_num_molecule(molA_file_name, self.resname_select, self.resname_transform)  # noqa: E501
+        numB, listB, trans_listB = coordinate_swap.deter_num_molecule(molB_file_name, self.resname_select, self.resname_transform)  # noqa: E501
 
         # Step 3: Fix break if present for solvated systems only
         if len(molA.topology.select('water')) != 0:
@@ -1862,7 +1862,7 @@ def change_num(self, molA_file_name, molB_file_name, swap_index):
                 molB = coordinate_swap.fix_break(molB, self.resname_transform, B_dimensions, connection_map[connection_map['Resname'] == self.resname_transform], self.verbose, resid)  # noqa: E501
 
         # Step 3: Setup the coordinate DF for the molecules
-        name, resid, resname, swap = [],[],[],[]
+        name, resid, resname, swap = [], [], [], []
         for i in listA:
             for n in self.atom_names:
                 name.append(n)
@@ -1887,7 +1887,7 @@ def change_num(self, molA_file_name, molB_file_name, swap_index):
                 resid.append(i)
                 resname.append(self.resname_transform)
                 swap.append('A2B')
-        df_atom_swap = pd.DataFrame({'Name': name, 'Resid': resid, 'Resname': resname,'Swap': swap})
+        df_atom_swap = pd.DataFrame({'Name': name, 'Resid': resid, 'Resname': resname, 'Swap': swap})
 
         # Step 4: Determine coordinates of all residues of interest  # noqa: E501
         df_atom_swap = coordinate_swap.get_miss_coord_by_num(molB, molA, self.resname_select, self.resname_transform, 'A2B', np.array(listB+trans_listB), listA, trans_listA, self.atom_names, df_atom_swap)  # noqa: E501
@@ -1917,7 +1917,7 @@ def change_num(self, molA_file_name, molB_file_name, swap_index):
         while line_start < len(molA_file):
             if line_start is not None:
                 # Print up until we reach the residue to modify
-                line_start, atom_num_restart = coordinate_swap.write_unmodified(line_start, molA_file, molB_new,resname_opt, atom_num_restart, preamble_legth, molA_coords, resnum_restart)  # noqa: E501
+                line_start, atom_num_restart = coordinate_swap.write_unmodified(line_start, molA_file, molB_new, resname_opt, atom_num_restart, preamble_legth, molA_coords, resnum_restart)  # noqa: E501
             else:
                 break
 
@@ -1957,4 +1957,4 @@ def change_num(self, molA_file_name, molB_file_name, swap_index):
 
         # Rename temp files
         os.rename('A_hybrid_swap.gro', molB_dir + '/confout.gro')
-        os.rename('B_hybrid_swap.gro', molA_dir + '/confout.gro')
+        os.rename('B_hybrid_swap.gro', molA_dir + '/confout.gro')

ensemble_md/utils/coordinate_swap.py

@@ -21,6 +21,7 @@
 from itertools import product
 import random
 
+
 def get_dimensions(file):
     """
     Determines the dimensions of the cubic box based on the input GRO file.
@@ -120,7 +121,7 @@ def fix_break(mol, resname, box_dimensions, atom_connect_all, verbose, resid=Non
     atom_pairs = []
     for atoms in atom_connect:
         if resid is not None:
-            atom_pairs.append(list(mol_top.select(f"resname {resname} and resid {resid-1} and (name {atoms[0]} or name {atoms[1]})")))
+            atom_pairs.append(list(mol_top.select(f"resname {resname} and resid {resid-1} and (name {atoms[0]} or name {atoms[1]})")))  # noqa: E501
         else:
             atom_pairs.append(list(mol_top.select(f"resname {resname} and (name {atoms[0]} or name {atoms[1]})")))
 
@@ -380,7 +381,7 @@ def get_miss_coord(mol_align, mol_ref, name_align, name_ref, df_atom_swap, dir,
     return df_atom_swap
 
 
-def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir, np_target, list_ref, list_ref_trans, name_list, df_atom_swap):
+def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir, np_target, list_ref, list_ref_trans, name_list, df_atom_swap):  # noqa: E501
     """
     Gets coordinates for the missing atoms after the conformational swap
 
@@ -420,7 +421,7 @@ def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir,
         df_atom_swap['Y Coordinates'] = np.nan
         df_atom_swap['Z Coordinates'] = np.nan
 
-    # In the case where the target system has fewer of the molecule of interest then the reference just select molecule at random and use the coordinates
+    # In the case where the target system has fewer of the molecule of interest then the reference just select molecule at random and use the coordinates  # noqa: E501
     # Step 2: Determine which molecules will correspond to which after the swap
     if len(np_target) <= len(list_ref):
         adding_molecules = False
@@ -434,7 +435,7 @@ def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir,
     # Step 3: Get coordinates for each atom for molecules determined above
     np_target_remaining = copy.deepcopy(np_target)
     target_real = []
-    atom_counter = 0 # Keep track of when we move to the next resid number
+    atom_counter = 0  # Keep track of when we move to the next resid number
     for i, row in df_atom_swap[df_atom_swap['Swap'] == dir].iterrows():
         if row['Resname'] == select_name or adding_molecules is False:
             target_resid = int(row['Resid'])
@@ -450,7 +451,7 @@ def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir,
                 atom_counter += 1
             atomname = row['Name']
             atomid = mol_ref.topology.select(f'resid {ref_resid-1} and name {atomname}')[0]
-            coords = mol_ref.xyz[0,atomid,:]
+            coords = mol_ref.xyz[0, atomid, :]
 
             df_atom_swap.at[i, 'X Coordinates'] = coords[0]
             df_atom_swap.at[i, 'Y Coordinates'] = coords[1]
@@ -459,17 +460,14 @@ def get_miss_coord_by_num(mol_target, mol_ref, select_name, transform_name, dir,
     if adding_molecules is False:
         return df_atom_swap
 
-    # In the case where the target has more of a molecule than the reference we need to get new coordinates    
-    num_add = len(np_target) - len(list_ref)
-    added = 0
-    attempt = 0
+    # In the case where the target has more of a molecule than the reference we need to get new coordinates
     # Step 4: Align select atoms between the two systems
     while len(np_target_remaining) != 0:
         # Step 5: select coordinates for atom and add to DF
         sele_resid_add = np_target_remaining[0]
         np_target_remaining = np.delete(np_target_remaining, 0)
         for n, name in enumerate(name_list):
-            index_add = df_atom_swap[(df_atom_swap['Swap'] == dir) & (df_atom_swap['Resid'] == sele_resid_add) & (df_atom_swap['Name'] == name)].index[0]
+            index_add = df_atom_swap[(df_atom_swap['Swap'] == dir) & (df_atom_swap['Resid'] == sele_resid_add) & (df_atom_swap['Name'] == name)].index[0]  # noqa: E501
             index_traj = mol_target.topology.select(f'resid {sele_resid_add-1} and name {name}')[0]
             new_coords = mol_target.xyz[0, index_traj, :]
             if n == 0:
@@ -1102,7 +1100,7 @@ def get_names(input, resname):
         if line == '[ atoms ]\n':
             atom_section = True
         if line == '[ bonds ]\n':
-            start_line=l+2
+            start_line = l + 2
     return start_line, atom_name, np.array(atom_num), state
 
 
@@ -1241,7 +1239,6 @@ def _read_gro(side, resname_list, gro_list):
                 name.append(line[9:15].replace(' ', ''))
                 num.append(line[15:20])
 
-
     return name, num
 
 
@@ -1296,6 +1293,7 @@ def create_atom_map(gro_list, resname_list, swap_patterns):
     output_df.reindex()
     output_df.to_csv('atom_name_mapping.csv')
 
+
 def deter_num_molecule(gro, name, trans_name):
     """
     Determine the number of molecules with this name in the system
@@ -1331,4 +1329,4 @@ def deter_num_molecule(gro, name, trans_name):
             if num not in trans_res_mol:
                 trans_res_mol.append(num)
     num_mol = len(res_mol) + len(trans_res_mol)
-    return num_mol, res_mol, trans_res_mol
+    return num_mol, res_mol, trans_res_mol

ensemble_md/utils/gmx_parser.py

@@ -439,9 +439,9 @@ def deter_atom_order(mol_file, resname, resid=None):
     else:
         resname_list = resname
         resid_list = resid
-    
+
     atom_order_all = []
-    for resname_i, resid_i in zip(resname_list, resid_list):    
+    for resname_i, resid_i in zip(resname_list, resid_list):
         atom_order = []
         for line in mol_file:
             split_line = line.split(' ')