20240801 complete fred docking

science/20240403_multi_pose_docking_v2/20240430_analyze_cross_docking_results/scripts/analyzed_data/results.csv

@@ -0,0 +1,43 @@
+Bootstraps,StructureChoice,StructureChoice_Choose_N,Score,Score_Choose_N,EvaluationMetric,EvaluationMetric_Cutoff,Split,N_Per_Split,PoseSelection,PoseSelection_Choose_N,Min,Max,CI_Upper,CI_Lower,Total,Fraction
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,1,Default,1,0.0,0.6666666666666666,0.6323529411764706,0.014705882352941176,204,0.4617009803921568
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,5,Default,1,0.5853658536585366,0.8585365853658536,0.824390243902439,0.6536585365853659,205,0.7545268292682926
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,10,Default,1,0.5804878048780487,0.8926829268292683,0.8634146341463415,0.7268292682926829,205,0.8134634146341465
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,15,Default,1,0.6780487804878049,0.9073170731707317,0.8829268292682927,0.7609756097560976,205,0.8386731707317074
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,20,Default,1,0.7463414634146341,0.9073170731707317,0.8926829268292683,0.7804878048780488,205,0.8525707317073172
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,25,Default,1,0.751219512195122,0.9170731707317074,0.8975609756097561,0.7951219512195122,205,0.8604097560975611
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,30,Default,1,0.7804878048780488,0.9219512195121952,0.9073170731707317,0.8048780487804879,205,0.866487804878049
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,35,Default,1,0.7707317073170732,0.9219512195121952,0.9073170731707317,0.8097560975609757,205,0.8716682926829269
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,40,Default,1,0.7658536585365854,0.926829268292683,0.9121951219512195,0.8195121951219512,205,0.8756439024390245
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,45,Default,1,0.7804878048780488,0.9219512195121952,0.9121951219512195,0.824390243902439,205,0.8790829268292685
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,50,Default,1,0.7951219512195122,0.9317073170731708,0.9121951219512195,0.8292682926829268,205,0.8809853658536588
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,55,Default,1,0.8146341463414634,0.9317073170731708,0.9170731707317074,0.8439024390243902,205,0.884429268292683
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,60,Default,1,0.8146341463414634,0.9317073170731708,0.9170731707317074,0.8439024390243902,205,0.8852878048780489
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,65,Default,1,0.8097560975609757,0.9365853658536586,0.9219512195121952,0.8439024390243902,205,0.887639024390244
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,70,Default,1,0.8146341463414634,0.9317073170731708,0.9170731707317074,0.8536585365853658,205,0.8892243902439027
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,75,Default,1,0.824390243902439,0.9365853658536586,0.9219512195121952,0.8536585365853658,205,0.8916146341463416
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,80,Default,1,0.8390243902439024,0.9317073170731708,0.9219512195121952,0.8536585365853658,205,0.8916195121951221
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,85,Default,1,0.8292682926829268,0.9365853658536586,0.9219512195121952,0.8585365853658536,205,0.8937756097560977
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,90,Default,1,0.8390243902439024,0.9414634146341463,0.926829268292683,0.8585365853658536,205,0.8949609756097564
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,95,Default,1,0.848780487804878,0.9463414634146341,0.9219512195121952,0.8634146341463415,205,0.894907317073171
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,100,Default,1,0.848780487804878,0.9414634146341463,0.9219512195121952,0.8634146341463415,205,0.8969317073170733
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,105,Default,1,0.848780487804878,0.9317073170731708,0.9219512195121952,0.8682926829268293,205,0.8976585365853662
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,110,Default,1,0.8439024390243902,0.9414634146341463,0.926829268292683,0.8682926829268293,205,0.8995707317073173
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,115,Default,1,0.848780487804878,0.9414634146341463,0.926829268292683,0.8731707317073171,205,0.8990439024390245
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,120,Default,1,0.8536585365853658,0.9463414634146341,0.9219512195121952,0.8731707317073171,205,0.9007121951219514
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,125,Default,1,0.8585365853658536,0.9365853658536586,0.926829268292683,0.8731707317073171,205,0.9010439024390247
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,130,Default,1,0.8585365853658536,0.9414634146341463,0.926829268292683,0.8731707317073171,205,0.9012634146341466
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,135,Default,1,0.8585365853658536,0.9414634146341463,0.926829268292683,0.8780487804878049,205,0.9027024390243905
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,140,Default,1,0.8634146341463415,0.9414634146341463,0.926829268292683,0.8780487804878049,205,0.9025902439024391
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,145,Default,1,0.8536585365853658,0.9365853658536586,0.926829268292683,0.8829268292682927,205,0.9041219512195123
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,150,Default,1,0.8682926829268293,0.9317073170731708,0.926829268292683,0.8829268292682927,205,0.9052000000000002
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,155,Default,1,0.8634146341463415,0.9317073170731708,0.926829268292683,0.8829268292682927,205,0.9050926829268294
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,160,Default,1,0.8682926829268293,0.9365853658536586,0.9219512195121952,0.8829268292682927,205,0.9064878048780489
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,165,Default,1,0.8682926829268293,0.9365853658536586,0.926829268292683,0.8878048780487805,205,0.9069463414634149
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,170,Default,1,0.8731707317073171,0.9365853658536586,0.926829268292683,0.8878048780487805,205,0.9079219512195122
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,175,Default,1,0.8731707317073171,0.9365853658536586,0.926829268292683,0.8926829268292683,205,0.9083804878048782
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,180,Default,1,0.8829268292682927,0.9365853658536586,0.926829268292683,0.8926829268292683,205,0.9088390243902441
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,185,Default,1,0.8780487804878049,0.9365853658536586,0.926829268292683,0.8926829268292683,205,0.9096585365853662
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,190,Default,1,0.8829268292682927,0.9317073170731708,0.926829268292683,0.8975609756097561,205,0.9103268292682929
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,195,Default,1,0.8829268292682927,0.9317073170731708,0.926829268292683,0.8975609756097561,205,0.9116390243902441
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,200,Default,1,0.8926829268292683,0.9317073170731708,0.9219512195121952,0.8975609756097561,205,0.9116536585365856
+1000,Dock_to_All,All,POSIT_Probability,1,RMSD,2.0,RandomSplit,205,Default,1,0.9170731707317074,0.9170731707317074,0.9170731707317074,0.9170731707317074,205,0.9170731707317077

science/20240403_multi_pose_docking_v2/20240430_analyze_cross_docking_results/scripts/analyzed_data/settings.yml

@@ -0,0 +1,62 @@
+date_dict_path: /data/chodera/paynea/asapdiscovery-sars-retrospective/science/20240403_multi_pose_docking_v2/20240430_analyze_cross_docking_results/20240503_inputs_analysis/date_dict.json
+n_bootstraps: 1000
+n_per_split:
+- 1
+- 5
+- 10
+- 15
+- 20
+- 25
+- 30
+- 35
+- 40
+- 45
+- 50
+- 55
+- 60
+- 65
+- 70
+- 75
+- 80
+- 85
+- 90
+- 95
+- 100
+- 105
+- 110
+- 115
+- 120
+- 125
+- 130
+- 135
+- 140
+- 145
+- 150
+- 155
+- 160
+- 165
+- 170
+- 175
+- 180
+- 185
+- 190
+- 195
+- 200
+- 205
+n_poses:
+- 1
+- 2
+- 5
+- 10
+- 20
+- 50
+n_structures:
+- 1
+- 2
+- 5
+- 10
+pose_id_column: Pose_ID
+query_ligand_column: Query_Ligand
+reference_ligand_column: Reference_Ligand
+reference_structure_column: Reference_Structure
+rmsd_cutoff: 2.0

science/20240801_complete_fred_docking/README.md

@@ -0,0 +1,9 @@
+In order to compare the results we get from referenced-based docking to a more typical docking approach, I'd like to run complete cross-docking with FRED.
+
+
+Notes:
+I had to re-prep the fragalysis download because only 157 of the structures were getting recognized, it still won't recognize these three structures as being part of the cache:
+`{'Mpro-P0053_0A', 'Mpro-P0091_0A', 'Mpro-P2007_0A'}`
+See more in `cluster_scripts/analyze_missing_structures.ipynb`
+
+There isn't anything obvious about the structures to me so a deeper investigation would be needed. I'm just pushing ahead with the 202 that we have.

science/20240801_complete_fred_docking/cluster_scripts/analyze_missing_structures.ipynb

@@ -0,0 +1,142 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "initial_id",
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "df = pd.read_csv(\"/Users/alexpayne/Scientific_Projects/mers-drug-discovery/sars2-retrospective-analysis/1/docking_results_final.csv\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "f23acff9f7022de5",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "df.groupby([\"ligand_id\", \"in-silico_SARS-CoV-2-Mpro_docking-structure-POSIT_msk\"]).nunique()"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "5336d3511e3e0674",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "mol_ids = df.ligand_id.unique()"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "5e0d03b3e6a9a876",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "structure_id = set(df[\"in-silico_SARS-CoV-2-Mpro_docking-structure-POSIT_msk\"].unique())"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "44101b3c0f0823e7",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "len(structure_id)"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "5a1c8e1a867f6af1",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "from pathlib import Path"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "6c0172eef2b37a4f",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "xtal_dirs = set([xtal_dir.stem for xtal_dir in Path(\"/Users/alexpayne/Scientific_Projects/mers-drug-discovery/sars2-retrospective-analysis/mpro_fragalysis-04-01-24_p_series/aligned\").glob(\"Mpro*\")])"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "f0b749bacd3538a8",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [
+    "xtal_dirs - structure_id"
+   ],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "8a90582cd00a3a4e",
+   "execution_count": null
+  },
+  {
+   "cell_type": "code",
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   },
+   "id": "e39381b8e90365e2"
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

science/20240801_complete_fred_docking/cluster_scripts/copy_correct_p_series_structures.ipynb

@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38b88560-cfae-4977-9e73-a584490b4628",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "import shutil"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a7a2096e-65df-46d4-bf30-f77717fc53ab",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "correct_structures = Path(\"/home/paynea/asap-datasets/mpro_fragalysis-04-01-24_curated_cache\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e5b5f64f-af37-42d0-8d75-5b77005322b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "original = Path(\"/home/paynea/asap-datasets/mpro_fragalysis-04-01-24/aligned\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ee5f8148-0387-443c-8eab-11ca5778ce17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new = Path(\"/home/paynea/asap-datasets/mpro_fragalysis-04-01-24_p_series/aligned\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "04569019-2371-4625-bba9-62bfc5e84514",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prepped_dirs = [prepped_dir for prepped_dir in correct_structures.glob(\"Mpro*\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5a7955af-74fe-461a-bb52-64bdc49a477b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(prepped_dirs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db1bba21-fb3d-4171-930a-d459fa497602",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "frag_dirs = [prepped_dir.stem[:13] for prepped_dir in prepped_dirs]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9d859d75-26c2-4061-a32c-5a7041e1c61a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for prepped_dir in prepped_dirs:\n",
+    "    frag_name = prepped_dir.stem[:13]\n",
+    "    shutil.copytree(original / frag_name, new / frag_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4838b95d-1414-4b46-b66b-d9e723b12990",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python [conda env:asapdiscovery]",
+   "language": "python",
+   "name": "conda-env-asapdiscovery-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

science/20240801_complete_fred_docking/cluster_scripts/protein_prep.json

@@ -0,0 +1,20 @@
+{
+  "target": "SARS-CoV-2-Mpro",
+  "pdb_file": null,
+  "fragalysis_dir": "/lila/data/chodera/asap-datasets/mpro_fragalysis-04-01-24_p_series",
+  "structure_dir": null,
+  "cache_dir": "/lila/data/chodera/asap-datasets/mpro_fragalysis-04-01-24_curated_cache_p_series",
+  "save_to_cache": true,
+  "align": null,
+  "ref_chain": null,
+  "active_site_chain": null,
+  "seqres_yaml": null,
+  "loop_db": "/lila/home/kaminowb/.openeye/rcsb_spruce.loop_db",
+  "oe_active_site_residue": null,
+  "use_dask": true,
+  "dask_type": "local",
+  "dask_n_workers": null,
+  "logname": "",
+  "loglevel": 20,
+  "output_dir": "/lila/data/chodera/paynea/asapdiscovery-sars-retrospective/science/20240801_complete_fred_docking/cluster_scripts/fragalysis_prep_out"
+}