Merge pull request #186 from StollLab/issue89

Issue89

Author: mtessmer

src/chilife/RotamerEnsemble.py

@@ -17,7 +17,7 @@
 import chilife.io as io
 import chilife.scoring as scoring
 
-from .globals import SUPPORTED_RESIDUES, nataa_codes, dihedral_defs
+from .globals import SUPPORTED_RESIDUES, nataa_codes, dihedral_defs, ralt_prot_states
 from .scoring import get_lj_rep, GAS_CONST
 from .numba_utils import get_sasa as nu_getsasa
 from .alignment_methods import alignment_methods, parse_backbone, local_mx, global_mx
@@ -263,6 +263,21 @@ def from_mda(cls, residue, **kwargs):
         """
 
         res = residue.resname
+
+
+        if kwargs.get('use_H', False) and res in ralt_prot_states:
+            if res != 'HIS':
+                res = ralt_prot_states[res].get(len(residue.atoms), res)
+            elif len(residue.atoms) == 18:
+                res = 'HIP'
+            elif len([x for x in residue.atoms.names if 'HE' in x]) == 2:
+                res = 'HIE'
+            elif len([x for x in residue.atoms.names if 'HD' in x]) == 2:
+                res = 'HID'
+            else:
+                res = 'HIS'
+
+
         site = residue.resid
         chain = residue.segid
         protein = residue.universe

src/chilife/data/dihedral_defs.toml

@@ -1,13 +1,20 @@
 ARG = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "NE"], ["CG", "CD", "NE", "CZ"], ["CD", "NE", "CZ", "NH1"]]
 ASN = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "OD1"]]
 ASP = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "OD1"]]
+ASH = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "OD1"]]
 CYS = [["N", "CA", "CB", "SG"]]
+CYM = [["N", "CA", "CB", "SG"]]
 GLN = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "OE1"]]
 GLU = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "OE1"]]
+GLH = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "OE1"]]
 HIS = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "ND1"]]
+HID = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "ND1"]]
+HIE = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "ND1"]]
+HIP = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "ND1"]]
 ILE = [["N", "CA", "CB", "CG1"], ["CA", "CB", "CG1", "CD1"]]
 LEU = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD1"]]
 LYS = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "CE"], ["CG", "CD", "CE", "NZ"]]
+LYN = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"], ["CB", "CG", "CD", "CE"], ["CG", "CD", "CE", "NZ"]]
 MET = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "SD"], ["CB", "CG", "SD", "CE"]]
 PHE = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD1"]]
 PRO = [["N", "CA", "CB", "CG"], ["CA", "CB", "CG", "CD"]]

src/chilife/data/rotamer_libraries/residue_internal_coords/ash_ic.pkl

@@ -7,6 +7,11 @@
 residue_pdbs = pdb_directory.glob('*.pdb')
 
 for pdb in residue_pdbs:
+
+    new_path = Path(pdb.stem + '_ic.pkl')
+    if new_path.exists():
+        continue
+
     print(pdb.stem)
 
     srtd = chilife.sort_pdb(pdb)