Merge pull request #6 from HITS-MCM/version-1.1

Version 1.1
HITS-MCM · Jan 10, 2021 · e0561c3 · e0561c3
2 parents 3f0d3eb + 284a57d
commit e0561c3
Show file tree

Hide file tree

Showing 14 changed files with 797 additions and 288 deletions.
diff --git a/Data/Complete-PDB-Validation-Set.zip b/Data/Complete-PDB-Validation-Set.zip
diff --git a/baseline.txt → Data/baseline.txt b/baseline.txt → Data/baseline.txt
diff --git a/IFP_generation_examples_Analysis.ipynb b/IFP_generation_examples_Analysis.ipynb
diff --git a/IFP_generation_examples_PDB.ipynb b/IFP_generation_examples_PDB.ipynb
@@ -95,7 +95,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "965f29b5c3304b41ad90d31e933767e2",
+       "model_id": "6e71168883194b14bfe00afc13119b3b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -110,7 +110,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "RDKit WARNING: [09:00:26] Enabling RDKit 2019.09.3 jupyter extensions\n"
+      "RDKit WARNING: [17:20:31] Enabling RDKit 2019.09.3 jupyter extensions\n"
      ]
     }
    ],
@@ -241,11 +241,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Start HB analysis 09:00:31.010103\n",
-      "Start WB analysis 09:00:31.453852\n",
-      "Start collecting IFPs:  09:00:33.115897\n",
-      "Start building IFP table:  09:00:38.396874\n",
-      "IFP database is ready  09:00:38.400871\n"
+      "Start HB analysis 17:20:35.994626\n",
+      "Start WB analysis 17:20:36.830144\n",
+      "Start collecting IFPs:  17:20:40.802862\n",
+      "Start building IFP table:  17:20:46.395648\n",
+      "IFP database is ready  17:20:46.399646\n"
      ]
     }
    ],
@@ -368,7 +368,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f5d6cc6f0fd941a8bdc51058633d6a56",
+       "model_id": "7abeec6497ce46eeab7000b7e8d5179f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -415,7 +415,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "274cd53e0e4e4fab9b7d3709e3efe9df",
+       "model_id": "444bb88e33c648799f0407d09b9159d5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -457,11 +457,11 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Start HB analysis 09:01:04.490783\n",
-      "Start WB analysis 09:01:07.829875\n",
-      "Start collecting IFPs:  09:01:35.889706\n",
-      "Start building IFP table:  09:03:28.889941\n",
-      "IFP database is ready  09:03:28.940912\n"
+      "Start HB analysis 17:21:13.827890\n",
+      "Start WB analysis 17:21:17.652695\n",
+      "Start collecting IFPs:  17:22:04.597717\n",
+      "Start building IFP table:  17:23:40.905384\n",
+      "IFP database is ready  17:23:40.967349\n"
      ]
     },
     {
@@ -2499,7 +2499,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3cb5f0e397f7431a93f091083ed2c1a2",
+       "model_id": "f9f7b2ee1a4043ef94d1db9749d42f18",
        "version_major": 2,
        "version_minor": 0
       },
@@ -2560,17 +2560,17 @@
      "output_type": "stream",
      "text": [
       "{'Donor': ['O4', 'C6', 'N8', 'N10', 'C12'], 'Acceptor': ['C2', 'C6', 'N10', 'C19'], 'PosIonizable': ['C9', 'C6', 'C7', 'O4', 'C11'], 'Aromatic': ['O4', 'C7', 'C6', 'C9', 'C11', 'C12', 'H7', 'C31', 'H12', 'H9', 'C1', 'C2', 'N3', 'C11', 'C9', 'C5', 'N10', 'C21', 'C20', 'C18', 'C31', 'H7', 'C13', 'C16', 'C15', 'N14', 'C23', 'C24', 'C25', 'C26', 'C27', 'C28', 'C29', 'N30'], 'Hydrophobe': ['C5', 'C13', 'N14', 'C15', 'C16', 'C18', 'C20', 'C23', 'C24', 'C25', 'C26', 'C27', 'C28', 'C29', 'N30', 'C31', 'H12'], 'LumpedHydrophobe': ['C13', 'C16', 'C15', 'N14', 'C23', 'C24', 'C25', 'C26', 'C27', 'C28', 'C29', 'N30']}\n",
-      "Start HB analysis 09:03:39.984259\n",
-      "Start WB analysis 09:03:40.275094\n",
-      "Start collecting IFPs:  09:03:40.931716\n",
-      "Start building IFP table:  09:03:41.687284\n",
-      "IFP database is ready  09:03:41.689284\n",
+      "Start HB analysis 17:23:51.228455\n",
+      "Start WB analysis 17:23:51.448328\n",
+      "Start collecting IFPs:  17:23:52.024998\n",
+      "Start building IFP table:  17:23:53.113372\n",
+      "IFP database is ready  17:23:53.116371\n",
       "\n",
       " -------------------- Contacts found: --------------------\n",
       "\n",
       "Hydrophobic contacts:  ['HY_ASN51', 'HY_ALA55', 'HY_MET98', 'HY_LEU107', 'HY_ALA111', 'HY_PHE138', 'HY_THR184']\n",
       "\n",
-      "Aromatic contacts:  ['AR_PHE138', 'AR_TRP162', 'AR_PHE170']\n",
+      "Aromatic contacts:  ['AR_PHE22', 'AR_PHE138', 'AR_TYR139', 'AR_TRP162', 'AR_PHE170']\n",
       "\n",
       "Water Bridges:  ['WB_GLN23']\n",
       "\n",
@@ -2645,6 +2645,7 @@
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>time</th>\n",
+       "      <th>AR_PHE22</th>\n",
        "      <th>WB_GLN23</th>\n",
        "      <th>HY_ASN51</th>\n",
        "      <th>HY_ALA55</th>\n",
@@ -2653,6 +2654,7 @@
        "      <th>HY_ALA111</th>\n",
        "      <th>AR_PHE138</th>\n",
        "      <th>HY_PHE138</th>\n",
+       "      <th>AR_TYR139</th>\n",
        "      <th>AR_TRP162</th>\n",
        "      <th>AR_PHE170</th>\n",
        "      <th>HY_THR184</th>\n",
@@ -2674,18 +2676,23 @@
        "      <td>1</td>\n",
        "      <td>1</td>\n",
        "      <td>1</td>\n",
+       "      <td>1</td>\n",
+       "      <td>1</td>\n",
        "      <td>6</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "text/plain": [
-       "   time  WB_GLN23  HY_ASN51  HY_ALA55  HY_MET98  HY_LEU107  HY_ALA111  \\\n",
-       "0     0         1         1         1         1          1          1   \n",
+       "   time  AR_PHE22  WB_GLN23  HY_ASN51  HY_ALA55  HY_MET98  HY_LEU107  \\\n",
+       "0     0         1         1         1         1         1          1   \n",
        "\n",
-       "   AR_PHE138  HY_PHE138  AR_TRP162  AR_PHE170  HY_THR184  WAT  \n",
-       "0          1          1          1          1          1    6  "
+       "   HY_ALA111  AR_PHE138  HY_PHE138  AR_TYR139  AR_TRP162  AR_PHE170  \\\n",
+       "0          1          1          1          1          1          1   \n",
+       "\n",
+       "   HY_THR184  WAT  \n",
+       "0          1    6  "
       ]
      },
      "execution_count": 15,
@@ -2715,13 +2722,13 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Showing residues:   23 51 55 98 107 111 138 138 162 170 184  \n"
+      "Showing residues:   22 23 51 55 98 107 111 138 138 139 162 170 184  \n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7c7a5452feab42d7b19746f244f76bbe",
+       "model_id": "907adf8122a34077910b18c965d839a1",
        "version_major": 2,
        "version_minor": 0
       },
@@ -2744,11 +2751,11 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "##### "
+   ]
   }
  ],
  "metadata": {

diff --git a/IFP_generation_examples_TRAJ.ipynb b/IFP_generation_examples_TRAJ.ipynb
diff --git a/README.md b/README.md
@@ -1,12 +1,12 @@
 # MD-IFP: MD trajectory analysis using protein-ligand Interaction Fingerprints
 ## A Python Workflow for the Generation and Analysis of Protein-Ligand Interaction Fingerprints from Molecular Dynamics trajectories
-### v.1.01
-### 03.05.2020
+### v.1.1
+### 19.09.2020
 
 ## Associated publications: 
 1. IFP analysis of dissociation trajectories for 3 compounds of HSP90  reported in the paper 
 
-   D. B. Kokh, B. Doser, S. Richter, F. Ormersbach, X. Cheng , R.C. Wade  "A Workflow for Exploring Ligand Dissociation    from a Macromolecule: Efficient Random Acceleration Molecular Dynamics Simulation and Interaction Fingerprints Analysis of Ligand         Trajectories" J. Chem Phys.(2020) 158  doi: 10.1063/5.0019088; https://arxiv.org/abs/2006.11066
+   D. B. Kokh, B. Doser, S. Richter, F. Ormersbach, X. Cheng , R.C. Wade  "A Workflow for Exploring Ligand Dissociation    from a Macromolecule: Efficient Random Acceleration Molecular Dynamics Simulation and Interaction Fingerprints Analysis of Ligand         Trajectories" J. Chem Phys.(2020) 158  125102  doi: 10.1063/5.0019088; https://arxiv.org/abs/2006.11066
 
    was implemented in  __IFP_generation_examples_Analysis.ipynb__ 
 
@@ -33,11 +33,13 @@ Schloss-Wolfsbrunnenweg 35
 *This open source software code was developed in part in the __Human Brain Project__, funded from the European Union’s Horizon 2020 Framework Programme for Research and Innovation under Specific Grant Agreements  No. 785907 (Human Brain Project  SGA2).*
 
 ## __Packages requirements:__
-__Python 3.x__: we strongly reccomend to create conda envirenment (see https://docs.conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html)
+__Python 3.x__ 
 
-__Python Libraries:__ numpy;    pandas;  matplotlib;  seaborn; RDkit; sklearn;  scipy; ngview; (installation of ngview can be tricky, the following way may work: after installation of the Python envirenment - conda install -c conda-forge nglview=2.7.1 and then jupyter-nbextension enable nglview --py --sys-prefix)
-
-__MDAnalysis Version: 0.20.1__ (Important: an old module for H-bond analysis is currently used, it will be removed in version 2.0 )
+__Python Libraries:__ 
+   1. numpy;    pandas;  matplotlib;  seaborn; sklearn;  scipy; 
+   2. __RDkit__ 
+   3. __ngview__ - used for visualization (installation of ngview can be tricky, the following way may work: after installation of the Python envirenment - conda install -c conda-forge nglview=2.7.1 and then jupyter-nbextension enable nglview --py --sys-prefix). If you don't need visualization, you can skip this, but JN must be edited accordingly
+   4. __MDAnalysis Version: 0.20.1__ (Important: an old module for H-bond analysis is currently used, it will be removed in version 2.0 )
 
 __Chimera__ - only for the scripts used for preprocessing pdb files (structure protonation and generation of the ligand mol2 file); not required if protonation and mol2 file are already prepared by a user)
 
@@ -62,7 +64,8 @@ __chimera_hydrogen_mol2.py__  - generation of ligand mol2 file
        
 ## Application examples (folder Examples):
 
-   1. Generation of the IFP databease for a single MD trajectory of a protein-ligand complex
+   1. IFP.py - Generation of the IFP databease for a single MD trajectory of a protein-ligand complex
+   2. IFP_contacts_quickView.py  - generation of a plot with average IFPs extracted from a trajectory
 
 ## Test Examples as Python Jupyter Notebooks :
 
@@ -93,3 +96,6 @@ This example shows how RAMD dissociation trajectories can be analyzed using pre-
 
 *This plot illustrates ligand dissociation pathways in a graph representation derived from clustering ligand trajectories in IFP space and plotting them with respect to the ligand COM from the initial bound position.*
 
+### IV. __MD-IFP_test.ipynb:__
+
+JN designed for validation of the IFP sctipt on 40 PDB complexes (used in paper J. Chem. Phys. 2020)