initial commit

PDBbuilder.py

@@ -0,0 +1,121 @@
+# https://bioinformatics.stackexchange.com/questions/19570/read-pdb-file-extract-dihedral-angles-modify-dihedral-angles-reconstruct-cart#
+# ^ reference for this code 
+
+
+from Bio import PDB
+import math
+
+from Bio.PDB import PDBIO
+import Bio.PDB.internal_coords as ic
+
+class ChainSelect(PDB.Select):
+    def accept_chain(self, chain):
+        if chain.id == 'A':
+            return True
+        else:
+            return False
+
+def pdb_from_dihedral_angles(structure: PDB.Structure.Structure,
+                             output_path: str,
+                             phi_angles, 
+                             psi_angles):
+    # Internally calculate dihedral angles for the structure 
+    structure.atom_to_internal_coordinates()
+
+    # Assume we care about the first chain only
+    # internal_coords extends the chain class to include dihedral angles (and other info)
+    chain: ic.IC_Chain = list(structure.get_chains())[0].internal_coord
+
+    # Dictionary of all dihedral angles in the chain
+    all_angles = chain.dihedra
+
+    # Find the phi and psi dihedral angles
+    # key[i]: ic.AtomKey
+    # key[i].akl[3]: gives the atom name - //kind of confusing representation
+    phi_keys = [k for k in all_angles.keys() if k[0].akl[3] == 'C' and 
+                                                k[1].akl[3] == 'N' and
+                                                k[2].akl[3] == 'CA' and
+                                                k[3].akl[3] == 'C']
+    psi_keys = [k for k in all_angles.keys() if k[0].akl[3] == 'N' and 
+                                                k[1].akl[3] == 'CA' and
+                                                k[2].akl[3] == 'C' and
+                                                k[3].akl[3] == 'N']
+
+
+    assert(len(phi_keys) == len(phi_angles))
+    assert(len(psi_keys) == len(psi_angles))
+
+    # Update phi angles
+    # Note that angles are stored as degrees in ic
+    phi_angles_degrees = list(map(math.degrees, phi_angles))
+    for i, k in enumerate(phi_keys):
+        all_angles[k].angle = phi_angles_degrees[i]
+
+    # Update psi angles
+    psi_angles_degrees = list(map(math.degrees, psi_angles))
+    for i, k in enumerate(psi_keys):
+        all_angles[k].angle = psi_angles_degrees[i]
+
+    # Now that the dihedral angles have been changed, need to recompute cartesian coords              
+    structure.internal_to_atom_coordinates()
+
+
+
+
+    # Write PDB file
+    io = PDBIO()
+    io.set_structure(structure)
+    io.save(output_path,  ChainSelect()) 
+
+
+parser = PDB.PDBParser()
+structure = parser.get_structure("1A3N", "data/1A3N.pdb")
+pdb_from_dihedral_angles(structure, "output/n1A3N.pdb", [0] * 140, [0] * 140)
+
+# structure.atom_to_internal_coordinates()
+
+# chain = list(structure.get_chains())[0]
+# ic_chain: PDB.internal_coords.IC_Chain = chain.internal_coord
+# d:  Dict[Tuple[PDB.internal_coords.AtomKey, 
+#                PDB.internal_coords.AtomKey,
+#                PDB.internal_coords.AtomKey,
+#                PDB.internal_coords.AtomKey],
+#                PDB.internal_coords.Dihedron] = ic_chain.dihedra
+
+
+
+# cnt = 1
+# for key in d:
+
+
+#     if w == 'N':
+#         if key[1].akl[3] == 'CA':
+#             if key[2].akl[3] == 'C':
+#                 if key[3].akl[3] == 'N':
+
+#                     print ('\n',cnt,' :   ',  [x.akl[3] for x in key], d[key].angle)
+
+#                     d[key].angle += 45
+
+#                     cnt += 1
+
+# cnt = 1
+# for key in d:
+
+
+#     if key[0].akl[3] == 'N':
+#         if key[1].akl[3] == 'CA':
+#             if key[2].akl[3] == 'C':
+#                 if key[3].akl[3] == 'N':
+
+#                     print ('\n',cnt,' :   ',  [x.akl[3] for x in key], d[key].angle)
+
+#                     cnt += 1
+
+# structure.internal_to_atom_coordinates(verbose = True)
+
+# io = PDBIO()
+
+# io.set_structure(structure)
+
+# io.save('output/atom_coord.pdb',  preserve_atom_numbering=True) 

Project.toml

@@ -0,0 +1,35 @@
+name = "TorusEvol"
+uuid = "bb045c0a-7050-477d-931f-b94f09181689"
+authors = ["Stefan Manolache <[email protected]>"]
+version = "0.1.0"
+
+[deps]
+Bio3DView = "99c8bb3a-9d13-5280-9740-b4880ed9c598"
+BioAlignments = "00701ae9-d1dc-5365-b64a-a3a3ebf5695e"
+BioSequences = "7e6ae17a-c86d-528c-b3b9-7f778a29fe59"
+BioStructures = "de9282ab-8554-53be-b2d6-f6c222edabfc"
+BioSymbols = "3c28c6f8-a34d-59c4-9654-267d177fcfa9"
+Blink = "ad839575-38b3-5650-b840-f874b8c74a25"
+CSV = "336ed68f-0bac-5ca0-87d4-7b16caf5d00b"
+DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
+DataStructures = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
+DelimitedFiles = "8bb1440f-4735-579b-a4ab-409b98df4dab"
+Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
+DistributionsAD = "ced4e74d-a319-5a8a-b0ac-84af2272839c"
+FastaIO = "a0c94c4b-ebed-5953-b5fc-82fe598ac79f"
+Formatting = "59287772-0a20-5a39-b81b-1366585eb4c0"
+HypothesisTests = "09f84164-cd44-5f33-b23f-e6b0d136a0d5"
+IJulia = "7073ff75-c697-5162-941a-fcdaad2a7d2a"
+LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
+LogExpFunctions = "2ab3a3ac-af41-5b50-aa03-7779005ae688"
+MCMCChains = "c7f686f2-ff18-58e9-bc7b-31028e88f75d"
+Memoization = "6fafb56a-5788-4b4e-91ca-c0cea6611c73"
+OffsetArrays = "6fe1bfb0-de20-5000-8ca7-80f57d26f881"
+PDMats = "90014a1f-27ba-587c-ab20-58faa44d9150"
+Plots = "91a5bcdd-55d7-5caf-9e0b-520d859cae80"
+StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
+StatsPlots = "f3b207a7-027a-5e70-b257-86293d7955fd"
+SubstitutionModels = "8365b1bb-bd83-58ee-a267-f2965fc81c73"
+Turing = "fce5fe82-541a-59a6-adf8-730c64b5f9a0"
+WebIO = "0f1e0344-ec1d-5b48-a673-e5cf874b6c29"
+Zygote = "e88e6eb3-aa80-5325-afca-941959d7151f"

ProteinViewer.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "5c7b2f8e3a274d1c89c6ce833bbaac71",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "A Jupyter Widget"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<Chain id=A>\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "I/O operation on closed file",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[1;32mIn [1], line 11\u001b[0m\n\u001b[0;32m      8\u001b[0m chain \u001b[39m=\u001b[39m \u001b[39mlist\u001b[39m(structure\u001b[39m.\u001b[39mget_chains())[\u001b[39m0\u001b[39m]\n\u001b[0;32m      9\u001b[0m \u001b[39mprint\u001b[39m(chain)\n\u001b[1;32m---> 11\u001b[0m nv\u001b[39m.\u001b[39;49mshow_biopython(structure)\n",
+      "File \u001b[1;32mc:\\Users\\stefa\\Dropbox\\Jotun Hein - Part C Projects\\Manolache\\Code\\Evolutionary Toroidal Difussions\\TorusEvol\\.venv\\lib\\site-packages\\nglview\\show.py:452\u001b[0m, in \u001b[0;36mshow_biopython\u001b[1;34m(entity, **kwargs)\u001b[0m\n\u001b[0;32m    437\u001b[0m \u001b[39m'''Show NGL widget with Biopython structural entity.\u001b[39;00m\n\u001b[0;32m    438\u001b[0m \n\u001b[0;32m    439\u001b[0m \u001b[39mTakes a Structure, Model, Chain, Residue or Atom\u001b[39;00m\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    449\u001b[0m \u001b[39m... w\u001b[39;00m\n\u001b[0;32m    450\u001b[0m \u001b[39m'''\u001b[39;00m\n\u001b[0;32m    451\u001b[0m entity \u001b[39m=\u001b[39m BiopythonStructure(entity)\n\u001b[1;32m--> 452\u001b[0m \u001b[39mreturn\u001b[39;00m NGLWidget(entity, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n",
+      "File \u001b[1;32mc:\\Users\\stefa\\Dropbox\\Jotun Hein - Part C Projects\\Manolache\\Code\\Evolutionary Toroidal Difussions\\TorusEvol\\.venv\\lib\\site-packages\\nglview\\widget.py:245\u001b[0m, in \u001b[0;36mNGLWidget.__init__\u001b[1;34m(self, structure, representations, parameters, **kwargs)\u001b[0m\n\u001b[0;32m    243\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m    244\u001b[0m     \u001b[39mif\u001b[39;00m structure \u001b[39mis\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39mNone\u001b[39;00m:\n\u001b[1;32m--> 245\u001b[0m         \u001b[39mself\u001b[39m\u001b[39m.\u001b[39madd_structure(structure, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m    247\u001b[0m \u001b[39mif\u001b[39;00m representations:\n\u001b[0;32m    248\u001b[0m     \u001b[39m# If initial representations are provided,\u001b[39;00m\n\u001b[0;32m    249\u001b[0m     \u001b[39m# we need to set defaultRepresentation to False\u001b[39;00m\n\u001b[0;32m    250\u001b[0m     \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mrepresentations \u001b[39m=\u001b[39m representations\n",
+      "File \u001b[1;32mc:\\Users\\stefa\\Dropbox\\Jotun Hein - Part C Projects\\Manolache\\Code\\Evolutionary Toroidal Difussions\\TorusEvol\\.venv\\lib\\site-packages\\nglview\\widget.py:1113\u001b[0m, in \u001b[0;36mNGLWidget.add_structure\u001b[1;34m(self, structure, **kwargs)\u001b[0m\n\u001b[0;32m   1111\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(structure, Structure):\n\u001b[0;32m   1112\u001b[0m     \u001b[39mraise\u001b[39;00m \u001b[39mValueError\u001b[39;00m(\u001b[39mf\u001b[39m\u001b[39m'\u001b[39m\u001b[39m{\u001b[39;00mstructure\u001b[39m}\u001b[39;00m\u001b[39m is not an instance of Structure\u001b[39m\u001b[39m'\u001b[39m)\n\u001b[1;32m-> 1113\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_load_data(structure, \u001b[39m*\u001b[39m\u001b[39m*\u001b[39mkwargs)\n\u001b[0;32m   1114\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_ngl_component_ids\u001b[39m.\u001b[39mappend(structure\u001b[39m.\u001b[39mid)\n\u001b[0;32m   1115\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mn_components \u001b[39m>\u001b[39m \u001b[39m1\u001b[39m:\n",
+      "File \u001b[1;32mc:\\Users\\stefa\\Dropbox\\Jotun Hein - Part C Projects\\Manolache\\Code\\Evolutionary Toroidal Difussions\\TorusEvol\\.venv\\lib\\site-packages\\nglview\\widget.py:1231\u001b[0m, in \u001b[0;36mNGLWidget._load_data\u001b[1;34m(self, obj, **kwargs)\u001b[0m\n\u001b[0;32m   1229\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m is_url:\n\u001b[0;32m   1230\u001b[0m     \u001b[39mif\u001b[39;00m \u001b[39mhasattr\u001b[39m(obj, \u001b[39m'\u001b[39m\u001b[39mget_structure_string\u001b[39m\u001b[39m'\u001b[39m):\n\u001b[1;32m-> 1231\u001b[0m         blob \u001b[39m=\u001b[39m obj\u001b[39m.\u001b[39;49mget_structure_string()\n\u001b[0;32m   1232\u001b[0m         kwargs2[\u001b[39m'\u001b[39m\u001b[39mext\u001b[39m\u001b[39m'\u001b[39m] \u001b[39m=\u001b[39m obj\u001b[39m.\u001b[39mext\n\u001b[0;32m   1233\u001b[0m         passing_buffer \u001b[39m=\u001b[39m \u001b[39mTrue\u001b[39;00m\n",
+      "File \u001b[1;32mc:\\Users\\stefa\\Dropbox\\Jotun Hein - Part C Projects\\Manolache\\Code\\Evolutionary Toroidal Difussions\\TorusEvol\\.venv\\lib\\site-packages\\nglview\\adaptor.py:200\u001b[0m, in \u001b[0;36mBiopythonStructure.get_structure_string\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    198\u001b[0m io_str \u001b[39m=\u001b[39m StringIO()\n\u001b[0;32m    199\u001b[0m io_pdb\u001b[39m.\u001b[39msave(io_str)\n\u001b[1;32m--> 200\u001b[0m \u001b[39mreturn\u001b[39;00m io_str\u001b[39m.\u001b[39;49mgetvalue()\n",
+      "\u001b[1;31mValueError\u001b[0m: I/O operation on closed file"
+     ]
+    }
+   ],
+   "source": [
+    "import nglview as nv\n",
+    "from Bio.PDB import PDBParser\n",
+    "\n",
+    "parser = PDBParser()\n",
+    "\n",
+    "with open(\"data/m1A3N.pdb\") as handle:\n",
+    "    record = next(SeqIO.parse(handle, \"fasta\"))\n",
+    "    human_a = record.seq\n",
+    "    print(human_a)\n",
+    "structure = parser.get_structure(\"m1A3N\", \"m1A3N.pdb\")\n",
+    "\n",
+    "chain = list(structure.get_chains())[0]\n",
+    "print(chain)\n",
+    "\n",
+    "nv.show_biopython(structure)\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import nglview as nv\n",
+    "\n",
+    "\n",
+    "w = nv.show_structure_file(\"output/n1A3N.pdb\")\n",
+    "w.clear()\n",
+    "w.add_representation(\"backbone\")\n",
+    "\n",
+    "for i in range(10):\n",
+    "    if i % 2 == 0:\n",
+    "        w = nv.show_structure_file(\"output/n1A3N.pdb\")\n",
+    "    else:\n",
+    "        w = nv.show_structure_file(\"output/m1A3N.pdb\")\n",
+    "    w.clear()\n",
+    "    w.add_representation(\"backbone\")\n",
+    "    w"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "abbeed12461a445698b89c1caa5e72ec",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "A Jupyter Widget"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "u = nv.show_structure_file(\"output/n1A3N.pdb\")\n",
+    "u"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.9.6 ('.venv': venv)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.6 (tags/v3.9.6:db3ff76, Jun 28 2021, 15:26:21) [MSC v.1929 64 bit (AMD64)]"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "9f23c5b2d7923a9bf6ddcca76ea127105863b859cb6fc4879d608de940540fb9"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}