From 0256efada856a2d672d6d79b5e82a9c833d32f80 Mon Sep 17 00:00:00 2001
From: Tana Tandaric <127224945+bananatana@users.noreply.github.com>
Date: Thu, 18 Apr 2024 11:26:22 +0200
Subject: [PATCH] added (de)protonated AA

added ASH, GLH, LYN, ARN.
---
 aminoAcids.py | 33 ++++++++++++++++++++++++++++++++-
 protein.py    | 14 +++++++++++---
 2 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/aminoAcids.py b/aminoAcids.py
index 8d91b36..cfe90ee 100644
--- a/aminoAcids.py
+++ b/aminoAcids.py
@@ -8,11 +8,15 @@ def __init__(self):
         self.codes321 = {
             'ALA': 'A',
             'ARG': 'R',
+            'ARN': 'R',
             'ASN': 'N',           
             'ASP': 'D',
+            'ASH': 'D',
             'CYS': 'C',
+            'CYX': 'C',
             'GLN': 'Q',
             'GLU': 'E',
+            'GLH': 'E',
             'GLY': 'G',
             'HIS': 'H',
             'HIE': 'H',
@@ -21,6 +25,7 @@ def __init__(self):
             'ILE': 'I',
             'LEU': 'L',
             'LYS': 'K',
+            'LYN': 'K',
             'MET': 'M',
             'PHE': 'F',
             'PRO': 'P',
@@ -69,6 +74,11 @@ def __init__(self):
                 O = 1,
                 C = 6,
                 ),
+            'ARN': Counter(
+                N = 4,
+                O = 1,
+                C = 6,
+                ),
             'ASN': Counter(
                 N = 2,
                 O = 2,
@@ -79,12 +89,23 @@ def __init__(self):
                 O = 3,
                 C = 4
             ),
+            'ASH': Counter(
+                N = 1,
+                O = 3,
+                C = 4
+            ),
             'CYS': Counter(
                 N = 1,
                 O = 1,
                 C = 3,
                 S = 1
             ),
+            'CYX': Counter(
+                N = 1,
+                O = 1,
+                C = 3,
+                S = 1
+            ),
             'GLN': Counter(
                 N = 2,
                 O = 2,
@@ -95,6 +116,11 @@ def __init__(self):
                 O = 3,
                 C = 5
             ),
+            'GLH': Counter(
+                N = 1,
+                O = 3,
+                C = 5
+            ),
             'GLY': Counter(
                 N = 1,
                 O = 1,
@@ -135,6 +161,11 @@ def __init__(self):
                 O = 1,
                 C = 6
             ),
+            'LYN': Counter(
+                N = 2,
+                O = 1,
+                C = 6
+            ),
             'MET': Counter(
                 N = 1,
                 O = 1,
@@ -176,4 +207,4 @@ def __init__(self):
                 O = 1,
                 C = 5
             )
-        }
\ No newline at end of file
+        }
diff --git a/protein.py b/protein.py
index 6040629..acb382e 100644
--- a/protein.py
+++ b/protein.py
@@ -29,8 +29,8 @@
 
 class System(object):
     def __init__(self, **kwargs):
-        protein_res_names = ["ALA", "ARG", "ASN", "ASP", "CYS", "CYX", "GLN", "GLU", "GLY", "HIS", 
-                             "HIE", "HID", "HIP", "HISE", "HISD", "HISH", "ILE", "LEU", "LYS", 
+        protein_res_names = ["ALA", "ARG","ARN", "ASN", "ASP", "ASH", "CYS", "CYX", "GLN", "GLH", "GLU", "GLY", "HIS", 
+                             "HIE", "HID", "HIP", "HISE", "HISD", "HISH", "ILE", "LEU", "LYS", "LYN", 
                              "MET", "PHE", "PRO", "SER", "THR", "TRP", "TYR", "VAL", ]
 
         self.pdb = kwargs["pdb"]
@@ -249,7 +249,7 @@ def __init__(self, *args, **kwargs):
 
     def _setRes(self):
         """
-        Change Histidines and Cysteins in pdb to the format preferred by gromacs.
+        Change Histidines and Cysteins and Protonated ASP and GLU and Deprotonated LYS pdb to the format preferred by gromacs.
         """
         tgt = open(self.pdb.replace(".pdb", "-his.pdb"), "w")
         self.pdb_his = tgt.name
@@ -264,6 +264,14 @@ def _setRes(self):
                     tgt.write(line.replace('HIP ','HISH'))
                 elif line.split()[3] == "CYX":
                     tgt.write(line.replace('CYX ','CYS '))
+                elif line.split()[3] == "ASH":
+                    tgt.write(line.replace('ASH ','ASPH'))
+                elif line.split()[3] == "ASH":
+                    tgt.write(line.replace('GLH ','GLUH'))
+                elif line.split()[3] == "LYN":
+                    tgt.write(line.replace('LYN ','LYSN'))
+                elif line.split()[3] == "ARN":
+                    tgt.write(line.replace('ARN ','ARGN'))
                 else:
                     tgt.write(line)
             else: