diff --git a/biochemist-python/_config.yml b/biochemist-python/_config.yml index 5ec209e..d776b26 100755 --- a/biochemist-python/_config.yml +++ b/biochemist-python/_config.yml @@ -8,6 +8,9 @@ author: The Molecular Sciences Software Institute # See https://jupyterbook.org/content/execute.html execute: execute_notebooks: force + exclude_patterns: + - "EC_class_ligands_search.ipynb" + - 'binding_site_investigation.ipynb' # Define the name of the latex output file for PDF builds latex: diff --git a/biochemist-python/chapters/EC_class_ligands_search.ipynb b/biochemist-python/chapters/EC_class_ligands_search.ipynb index 879c287..27f9ff9 100644 --- a/biochemist-python/chapters/EC_class_ligands_search.ipynb +++ b/biochemist-python/chapters/EC_class_ligands_search.ipynb @@ -92,7 +92,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "7f7f7135", "metadata": {}, "outputs": [], @@ -116,10 +116,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "e331ecd9", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "['1AQ7', '1AUJ', '1AZ8', '1BJV', '1BTW', '1BTX', '1BTZ', '1C1S', '1C1T', '1C2D']\n" + ] + }, + { + "data": { + "text/plain": [ + "180" + ] + }, + "execution_count": 2, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# There will be three components to the query, which will be labeled q1, q2 and q3.\n", "\n", @@ -165,10 +183,28 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "b4d77b9e", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There are 112 ligands for EC Number 3.4.21.4 in this list. Here is a list of the first 10 ligands.\n" + ] + }, + { + "data": { + "text/plain": [ + "['0CA', '0CB', '0KV', '0ZG', '0ZW', '0ZX', '0ZY', '10U', '11U', '12U']" + ] + }, + "execution_count": 3, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "molResultL = list(query(\"mol_definition\"))\n", "print(\"There are\",len(molResultL), \"ligands for EC Number\", ECnumber, \"in this list. Here is a list of the first 10 ligands.\")\n", @@ -203,7 +239,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "ffb3d082", "metadata": {}, "outputs": [], @@ -214,7 +250,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "9cbf3513", "metadata": {}, "outputs": [], @@ -226,10 +262,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "b7043e37", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "200" + ] + }, + "execution_count": 6, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "# check to see that the file downloaded properly. A status code of 200 means everything is okay.\n", "\n", @@ -238,7 +285,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "096a56da", "metadata": {}, "outputs": [], @@ -254,10 +301,146 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "c9d9c2e4", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "@MOLECULE\n", + "11U\n", + " 59 61 0 0 0\n", + "SMALL\n", + "NO_CHARGES\n", + "\n", + "@ATOM\n", + " 1 C1 2.4220 0.4070 0.3360 C.2 1 11U_ideal 0.0000\n", + " 2 O1 2.0060 -0.6420 0.7800 O.2 1 11U_ideal 0.0000\n", + " 3 C2 3.8690 0.5350 -0.0630 C.3 1 11U_ideal 0.0000\n", + " 4 N1 4.5590 -0.7380 0.1810 N.3 1 11U_ideal 0.0000\n", + " 5 C3 5.9760 -0.6510 -0.1970 C.3 1 11U_ideal 0.0000\n", + " 6 C4 6.7790 -0.0680 0.9670 C.3 1 11U_ideal 0.0000\n", + " 7 C5 8.2550 0.0240 0.5730 C.3 1 11U_ideal 0.0000\n", + " 8 C6 8.7810 -1.3740 0.2400 C.3 1 11U_ideal 0.0000\n", + " 9 C7 7.9780 -1.9570 -0.9250 C.3 1 11U_ideal 0.0000\n", + " 10 C8 6.5020 -2.0480 -0.5310 C.3 1 11U_ideal 0.0000\n", + " 11 N2 1.5890 1.4580 0.1990 N.am 1 11U_ideal 0.0000\n", + " 12 C9 0.1600 1.4690 0.5420 C.3 1 11U_ideal 0.0000\n", + " 13 C10 -0.5770 0.4580 -0.2980 C.2 1 11U_ideal 0.0000\n", + " 14 O2 0.0270 -0.2120 -1.1080 O.2 1 11U_ideal 0.0000\n", + " 15 C11 -0.3710 2.8880 0.2460 C.3 1 11U_ideal 0.0000\n", + " 16 C12 0.9140 3.7560 0.2780 C.3 1 11U_ideal 0.0000\n", + " 17 C13 1.9600 2.7850 -0.3250 C.3 1 11U_ideal 0.0000\n", + " 18 N3 -1.9070 0.2990 -0.1490 N.am 1 11U_ideal 0.0000\n", + " 19 C14 -2.6230 -0.6850 -0.9660 C.3 1 11U_ideal 0.0000\n", + " 20 C15 -4.0860 -0.6660 -0.6070 C.ar 1 11U_ideal 0.0000\n", + " 21 C16 -4.5620 -1.4980 0.3910 C.ar 1 11U_ideal 0.0000\n", + " 22 C17 -5.9000 -1.4810 0.7270 C.ar 1 11U_ideal 0.0000\n", + " 23 C18 -6.7750 -0.6300 0.0520 C.ar 1 11U_ideal 0.0000\n", + " 24 C19 -8.2130 -0.6110 0.4050 C.2 1 11U_ideal 0.0000\n", + " 25 N4 -9.0280 0.1840 -0.2270 N.2 1 11U_ideal 0.0000\n", + " 26 N5 -8.6890 -1.4350 1.4020 N.pl3 1 11U_ideal 0.0000\n", + " 27 C20 -6.2910 0.2030 -0.9560 C.ar 1 11U_ideal 0.0000\n", + " 28 C21 -4.9490 0.1800 -1.2800 C.ar 1 11U_ideal 0.0000\n", + " 29 H1 3.9330 0.7860 -1.1220 H 1 11U_ideal 0.0000\n", + " 30 H2 4.3400 1.3220 0.5260 H 1 11U_ideal 0.0000\n", + " 31 H3 4.4590 -1.0250 1.1430 H 1 11U_ideal 0.0000\n", + " 32 H4 6.0800 -0.0050 -1.0690 H 1 11U_ideal 0.0000\n", + " 33 H5 6.4040 0.9280 1.2050 H 1 11U_ideal 0.0000\n", + " 34 H6 6.6750 -0.7130 1.8390 H 1 11U_ideal 0.0000\n", + " 35 H7 8.8270 0.4390 1.4030 H 1 11U_ideal 0.0000\n", + " 36 H8 8.3590 0.6690 -0.2990 H 1 11U_ideal 0.0000\n", + " 37 H9 8.6770 -2.0190 1.1120 H 1 11U_ideal 0.0000\n", + " 38 H10 9.8320 -1.3090 -0.0410 H 1 11U_ideal 0.0000\n", + " 39 H11 8.3530 -2.9520 -1.1620 H 1 11U_ideal 0.0000\n", + " 40 H12 8.0820 -1.3110 -1.7970 H 1 11U_ideal 0.0000\n", + " 41 H13 6.3980 -2.6930 0.3420 H 1 11U_ideal 0.0000\n", + " 42 H14 5.9300 -2.4630 -1.3600 H 1 11U_ideal 0.0000\n", + " 43 H15 0.0300 1.2400 1.6000 H 1 11U_ideal 0.0000\n", + " 44 H16 -1.0720 3.2080 1.0170 H 1 11U_ideal 0.0000\n", + " 45 H17 -0.8360 2.9240 -0.7390 H 1 11U_ideal 0.0000\n", + " 46 H18 1.1770 4.0280 1.3010 H 1 11U_ideal 0.0000\n", + " 47 H19 0.8020 4.6440 -0.3440 H 1 11U_ideal 0.0000\n", + " 48 H20 2.9630 3.0560 0.0040 H 1 11U_ideal 0.0000\n", + " 49 H21 1.9020 2.7930 -1.4130 H 1 11U_ideal 0.0000\n", + " 50 H22 -2.3900 0.8350 0.4990 H 1 11U_ideal 0.0000\n", + " 51 H23 -2.5040 -0.4370 -2.0200 H 1 11U_ideal 0.0000\n", + " 52 H24 -2.2160 -1.6780 -0.7780 H 1 11U_ideal 0.0000\n", + " 53 H25 -3.8840 -2.1590 0.9100 H 1 11U_ideal 0.0000\n", + " 54 H26 -6.2690 -2.1270 1.5090 H 1 11U_ideal 0.0000\n", + " 55 H27 -9.9700 0.1960 0.0040 H 1 11U_ideal 0.0000\n", + " 56 H28 -8.0820 -2.0270 1.8720 H 1 11U_ideal 0.0000\n", + " 57 H29 -9.6310 -1.4220 1.6330 H 1 11U_ideal 0.0000\n", + " 58 H30 -6.9630 0.8640 -1.4820 H 1 11U_ideal 0.0000\n", + " 59 H31 -4.5730 0.8240 -2.0610 H 1 11U_ideal 0.0000\n", + "@BOND\n", + " 1 1 11 am\n", + " 2 11 17 1\n", + " 3 11 12 1\n", + " 4 1 2 2\n", + " 5 1 3 1\n", + " 6 16 17 1\n", + " 7 15 16 1\n", + " 8 12 15 1\n", + " 9 12 13 1\n", + " 10 13 18 am\n", + " 11 13 14 2\n", + " 12 18 19 1\n", + " 13 19 20 1\n", + " 14 20 28 ar\n", + " 15 20 21 ar\n", + " 16 27 28 ar\n", + " 17 23 27 ar\n", + " 18 23 24 1\n", + " 19 22 23 ar\n", + " 20 24 25 2\n", + " 21 24 26 1\n", + " 22 21 22 ar\n", + " 23 3 4 1\n", + " 24 4 5 1\n", + " 25 5 10 1\n", + " 26 5 6 1\n", + " 27 9 10 1\n", + " 28 8 9 1\n", + " 29 7 8 1\n", + " 30 6 7 1\n", + " 31 3 29 1\n", + " 32 3 30 1\n", + " 33 17 48 1\n", + " 34 17 49 1\n", + " 35 16 46 1\n", + " 36 16 47 1\n", + " 37 15 44 1\n", + " 38 15 45 1\n", + " 39 12 43 1\n", + " 40 18 50 1\n", + " 41 19 51 1\n", + " 42 19 52 1\n", + " 43 28 59 1\n", + " 44 27 58 1\n", + " 45 25 55 1\n", + " 46 26 56 1\n", + " 47 26 57 1\n", + " 48 22 54 1\n", + " 49 21 53 1\n", + " 50 4 31 1\n", + " 51 5 32 1\n", + " 52 10 41 1\n", + " 53 10 42 1\n", + " 54 9 39 1\n", + " 55 9 40 1\n", + " 56 8 37 1\n", + " 57 8 38 1\n", + " 58 7 35 1\n", + " 59 7 36 1\n", + " 60 6 33 1\n", + " 61 6 34 1\n", + "\n" + ] + } + ], "source": [ "# Now we use these commands to read the file and make sure it downloaded properly. As an alternative, we\n", "# could go to the ligands folder in our Jupyter desktop and click on res11U.mol2 to make sure it looks correct.\n", @@ -290,7 +473,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "id": "b85d927b", "metadata": {}, "outputs": [], @@ -330,10 +513,29 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "id": "8b9106d8", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "There are 173 structures from EC Number 1.1.1.1 that have bound ligands with molecular weights between 400 and 700).\n", + "There are 11 unique ligands for structures with EC Number 1.1.1.1 in this list. Here is a list of the 11 ligands.\n" + ] + }, + { + "data": { + "text/plain": [ + "['022', 'APR', 'CHD', 'CND', 'COD', 'NAD', 'NAI', 'NAJ', 'PAD', 'TAD', 'WKZ']" + ] + }, + "execution_count": 10, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "### Solution\n", "\n", diff --git a/biochemist-python/chapters/binding_site_investigation.ipynb b/biochemist-python/chapters/binding_site_investigation.ipynb index 98cb79f..0e886df 100644 --- a/biochemist-python/chapters/binding_site_investigation.ipynb +++ b/biochemist-python/chapters/binding_site_investigation.ipynb @@ -30,10 +30,21 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 1, "id": "084d041c-6d26-4136-a3ff-2f5586c5ea26", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "200" + ] + }, + "execution_count": 1, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "import os # for making directories\n", "import requests\n", @@ -57,7 +68,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 2, "id": "97d0596a-533f-4aa8-afb5-bb9d182788fd", "metadata": {}, "outputs": [], @@ -81,7 +92,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 3, "id": "1266c266-ab03-4aa9-b4b5-d097cbc9d5cf", "metadata": {}, "outputs": [], @@ -128,10 +139,23 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 4, "id": "30aa1905-a77c-4b67-aeef-bd22f6123af2", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "b99491671e01419ea6e9dd4d41e4527f", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "import MDAnalysis as mda\n", "import nglview as nv\n", @@ -149,10 +173,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 5, "id": "22eab29a-8893-40e1-9b7c-8c82410c6998", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "2401aa6c72574b7daf42ea1fa5b8be4b", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "NGLWidget()" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "view = nv.show_mdanalysis(u)\n", "view" @@ -172,7 +211,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 6, "id": "59398872-79e2-4b19-a6a1-2a11305cb003", "metadata": {}, "outputs": [], @@ -193,10 +232,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 7, "id": "ec313913-e6a6-49de-99f5-88a8b2d5f029", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "e76e61ee77e54089b97cc13e88d4ba18", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "NGLWidget()" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "view_binding_site(protein, ligand)" ] @@ -230,7 +284,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 8, "id": "16e2bad0-0fab-437c-8e6b-f66c1a622b3a", "metadata": {}, "outputs": [], @@ -250,20 +304,50 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 9, "id": "43598dd2-503b-47f3-816d-e20039ced662", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "39f72e25876f4a59a5451baa0beb88fd", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "NGLWidget()" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "view_binding_site(protein, ligand_A)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 10, "id": "92c18c8c-a728-4d57-af48-b5551fab49f8", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "86508b08ae76439f89976b8e570328a8", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + "NGLWidget()" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], "source": [ "view_binding_site(protein, ligand_B)" ] @@ -302,10 +386,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 11, "id": "d8f9ec87-1510-4e54-bdcb-9b53b689c9f6", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/janash/miniconda3/envs/iqb-2024/lib/python3.11/site-packages/MDAnalysis/coordinates/PDB.py:1153: UserWarning: Found no information for attr: 'formalcharges' Using default value of '0'\n", + " warnings.warn(\"Found no information for attr: '{}'\"\n" + ] + } + ], "source": [ "protein.write(f\"pdb/protein_{pdb_id}.pdb\")\n", "ligand_A.write(f\"pdb/ligand_A.pdb\")" @@ -329,22 +422,125 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 12, "id": "e8ce5142-5c21-4fac-b0c8-656f848efad8", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "INFO:PDB2PQR v3.6.2: biomolecular structure conversion software.\n", + "INFO:Please cite: Jurrus E, et al. Improvements to the APBS biomolecular solvation software suite. Protein Sci 27 112-128 (2018).\n", + "INFO:Please cite: Dolinsky TJ, et al. PDB2PQR: expanding and upgrading automated preparation of biomolecular structures for molecular simulations. Nucleic Acids Res 35 W522-W525 (2007).\n", + "INFO:Checking and transforming input arguments.\n", + "INFO:Loading topology files.\n", + "INFO:Loading molecule: pdb/protein_2zq2.pdb\n", + "ERROR:Error parsing line: invalid literal for int() with base 10: ''\n", + "ERROR:\n", + "ERROR:Truncating remaining errors for record type:REMARK\n", + "WARNING:Warning: pdb/protein_2zq2.pdb is a non-standard PDB file.\n", + "\n", + "ERROR:['REMARK']\n", + "INFO:Setting up molecule.\n", + "INFO:Created biomolecule object with 223 residues and 1625 atoms.\n", + "WARNING:Multiple occupancies found: N in SER A 61.\n", + "WARNING:Multiple occupancies found: CA in SER A 61.\n", + "WARNING:Multiple occupancies found: C in SER A 61.\n", + "WARNING:Multiple occupancies found: O in SER A 61.\n", + "WARNING:Multiple occupancies found: CB in SER A 61.\n", + "WARNING:Multiple occupancies found: OG in SER A 61.\n", + "WARNING:Multiple occupancies found in SER A 61. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in SER A 113.\n", + "WARNING:Multiple occupancies found: CA in SER A 113.\n", + "WARNING:Multiple occupancies found: C in SER A 113.\n", + "WARNING:Multiple occupancies found: O in SER A 113.\n", + "WARNING:Multiple occupancies found: CB in SER A 113.\n", + "WARNING:Multiple occupancies found: OG in SER A 113.\n", + "WARNING:Multiple occupancies found in SER A 113. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in SER A 122.\n", + "WARNING:Multiple occupancies found: CA in SER A 122.\n", + "WARNING:Multiple occupancies found: C in SER A 122.\n", + "WARNING:Multiple occupancies found: O in SER A 122.\n", + "WARNING:Multiple occupancies found: CB in SER A 122.\n", + "WARNING:Multiple occupancies found: OG in SER A 122.\n", + "WARNING:Multiple occupancies found in SER A 122. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in SER A 167.\n", + "WARNING:Multiple occupancies found: CA in SER A 167.\n", + "WARNING:Multiple occupancies found: C in SER A 167.\n", + "WARNING:Multiple occupancies found: O in SER A 167.\n", + "WARNING:Multiple occupancies found: CB in SER A 167.\n", + "WARNING:Multiple occupancies found: OG in SER A 167.\n", + "WARNING:Multiple occupancies found in SER A 167. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in SER A 170.\n", + "WARNING:Multiple occupancies found: CA in SER A 170.\n", + "WARNING:Multiple occupancies found: C in SER A 170.\n", + "WARNING:Multiple occupancies found: O in SER A 170.\n", + "WARNING:Multiple occupancies found: CB in SER A 170.\n", + "WARNING:Multiple occupancies found: OG in SER A 170.\n", + "WARNING:Multiple occupancies found in SER A 170. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in SER A 236.\n", + "WARNING:Multiple occupancies found: CA in SER A 236.\n", + "WARNING:Multiple occupancies found: C in SER A 236.\n", + "WARNING:Multiple occupancies found: O in SER A 236.\n", + "WARNING:Multiple occupancies found: CB in SER A 236.\n", + "WARNING:Multiple occupancies found: OG in SER A 236.\n", + "WARNING:Multiple occupancies found in SER A 236. At least one of the instances is being ignored.\n", + "WARNING:Multiple occupancies found: N in GLN A 240.\n", + "WARNING:Multiple occupancies found: CA in GLN A 240.\n", + "WARNING:Multiple occupancies found: C in GLN A 240.\n", + "WARNING:Multiple occupancies found: O in GLN A 240.\n", + "WARNING:Multiple occupancies found: CB in GLN A 240.\n", + "WARNING:Multiple occupancies found: CG in GLN A 240.\n", + "WARNING:Multiple occupancies found: CD in GLN A 240.\n", + "WARNING:Multiple occupancies found: OE1 in GLN A 240.\n", + "WARNING:Multiple occupancies found: NE2 in GLN A 240.\n", + "WARNING:Multiple occupancies found in GLN A 240. At least one of the instances is being ignored.\n", + "INFO:Setting termini states for biomolecule chains.\n", + "INFO:Loading forcefield.\n", + "INFO:Loading hydrogen topology definitions.\n", + "WARNING:Missing atom CG in residue LYS A 222\n", + "WARNING:Missing atom CD in residue LYS A 222\n", + "WARNING:Missing atom CE in residue LYS A 222\n", + "WARNING:Missing atom NZ in residue LYS A 222\n", + "WARNING:Missing atom CG in residue LYS A 222\n", + "WARNING:Missing atom CD in residue LYS A 222\n", + "WARNING:Missing atom CE in residue LYS A 222\n", + "WARNING:Missing atom NZ in residue LYS A 222\n", + "INFO:Attempting to repair 4 missing atoms in biomolecule.\n", + "WARNING:Missing atom CG in residue LYS A 222\n", + "WARNING:Missing atom CD in residue LYS A 222\n", + "WARNING:Missing atom CE in residue LYS A 222\n", + "WARNING:Missing atom NZ in residue LYS A 222\n", + "INFO:Added atom CG to residue LYS A 222 at coordinates 30.628, -3.449, -0.010\n", + "INFO:Added atom CD to residue LYS A 222 at coordinates 32.074, -3.541, -0.453\n", + "INFO:Added atom CE to residue LYS A 222 at coordinates 32.755, -2.198, -0.512\n", + "INFO:Added atom NZ to residue LYS A 222 at coordinates 34.167, -2.339, -0.950\n", + "INFO:Updating disulfide bridges.\n", + "INFO:Debumping biomolecule.\n", + "INFO:Adding hydrogens to biomolecule.\n", + "INFO:Debumping biomolecule (again).\n", + "INFO:Optimizing hydrogen bonds\n", + "INFO:Applying force field to biomolecule states.\n", + "INFO:Regenerating headers.\n", + "INFO:Regenerating PDB lines.\n", + "WARNING:Ignoring 390 header lines in output.\n", + "WARNING:Ignoring 390 header lines in output.\n" + ] + } + ], "source": [ "! pdb2pqr --pdb-output=pdb/protein_h.pdb --pH=7.4 pdb/protein_2zq2.pdb protein.pqr" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 13, "id": "bbd1951c-9d2e-4fff-a89d-3f1ccc39104f", "metadata": {}, "outputs": [], "source": [ - "protein = mda.Universe(\"pdb/protein_H.pdb\")" + "protein = mda.Universe(\"pdb/protein_h.pdb\")" ] }, { @@ -361,7 +557,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 14, "id": "3fe5109d-f0ef-446e-8caf-6f02aba50874", "metadata": {}, "outputs": [], @@ -378,10 +574,19 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 15, "id": "fb118dba-cbf6-4fe1-96bf-a07b1e2cb141", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "[17:18:26] WARNING: More than one matching pattern found - picking one\n", + "\n" + ] + } + ], "source": [ "ligand = AssignBondOrdersFromTemplate(template, pdb_ligand)\n", "\n", @@ -399,7 +604,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 16, "id": "f313c3f9-acc5-400b-af84-aafe86f33a57", "metadata": {}, "outputs": [], @@ -424,7 +629,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 17, "id": "8942f955-25d9-4f1b-b384-40b1bcb8919b", "metadata": {}, "outputs": [], @@ -437,17 +642,26 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 18, "id": "22e64eeb-0e80-405b-b7a4-2f7dca799219", "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/janash/miniconda3/envs/iqb-2024/lib/python3.11/site-packages/MDAnalysis/converters/RDKit.py:473: UserWarning: No `bonds` attribute in this AtomGroup. Guessing bonds based on atoms coordinates\n", + " warnings.warn(\n" + ] + } + ], "source": [ "protein_mol = plf.Molecule.from_mda(protein_h)" ] }, { "cell_type": "code", - "execution_count": null, + "execution_count": 19, "id": "d6dacd2e-79b8-4ef5-988d-b3882cf09e0b", "metadata": {}, "outputs": [], @@ -457,7 +671,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 20, "id": "6bea506e-6ab5-40df-9858-30de794d3462", "metadata": {}, "outputs": [], @@ -467,10 +681,25 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 21, "id": "49f738f2-0a32-42a9-9ffc-a6ee8a052065", "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "application/vnd.jupyter.widget-view+json": { + "model_id": "44c9a5ea8b784bb7bbb52e2d81408340", + "version_major": 2, + "version_minor": 0 + }, + "text/plain": [ + " 0%| | 0/1 [00:00" + ], + "text/plain": [ + "" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ "view = fp.plot_lignetwork(lig_list[0])\n", "view" ] + }, + { + "cell_type": "code", + "execution_count": null, + "id": "e8217646-90f1-496b-b902-9f15663d4324", + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { @@ -505,7 +901,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.1.undefined" + "version": "3.11.9" } }, "nbformat": 4,