fix: profile and localizing

config/config.yaml

@@ -1,61 +1,64 @@
-# NOTE: All paths should be fully qualified paths
+#Name your experiment here
+EXPERIMENT_NAME: "test"
 
-# Path to raw ligand data | DATABASE/DATASET/file
-INPUT_DIR: "/lustre/project/m2_jgu-smitt/data/raw"
+# NOTE: All paths are relative to the workflow directory (or --directory if specified)
 
+# Path to raw ligand data | DATABASE/DATASET/file
 # if you want to manually upload target pdb file upload these to in a subfolder of the input dir called "/PDB/receptor"
 
-
-# Path to output prepared target proteins
-PREPARED_DATA_DIR: "/lustre/project/m2_jgu-smitt/data/prepared"
-
-# Path to energy minimized ligand files
-PREPARED_LIGAND_DIR: "/lustre/project/m2_jgu-smitt/data/minimized"
-
-# Path to scratch directory
-TEMP_DATA_DIR: "/lustre/scratch/m2_jgu-smitt"
-
-# Path where docking results are stored
-OUTPUT_DIR: "/lustre/project/m2_jgu-smitt/<FOLDER>"
-
-# Number of best results to be displayed (0<value<=1: percentage )
+# Percentage of best results to be considered for display and re-screening (0<value<=1: percentage )
+#TODO: change the wording
 RESULT_NUMBER: "10"
 
-# Specify cutoff value for rescreening
+# Specify cutoff value for rescreening (in kcal/mol)
 CUTOFF_VALUE: "-8"
 
 #Specify name for local uploaded data
-#  note: this will be ignored, if a 'DATABASE' (see below) is specified
+#  NOTE: this will be ignored, if a 'DATABASE' (see below) is specified
 LOC_DATA: ["DATASET"]
 
-#Path to folder which contains compounds
-#  Here, a full qualified path should be indicated.
-#  note: this will be ignored, if a 'DATABASE' (see below) is specified
-LOCAL_INPUT_DIR: "<LOCAL_INPUT_DIR>"
-
-#Specify database to use   ZINC usees and downloads compounds from ZINC database, others read local input from LOCAL_INPUT_DIR
-
-DATABASE: ["ZINC"]
-
-#    First letter is the molecular weight bin - a measure of size - horizontal axis, left to right, online. A: 200 D, B: 250, C:300, D: 325, E:350, F: 375
-#    Second letter is the logP bin - a measure of polarity - vertical axis, top to bottom, online.
-#    The third letter is reactivity : A=anodyne. B=Bother (e.g. chromophores) C=clean (but pains ok), E=mild reactivity ok, G=reactive ok, I = hot chemistry ok
-#    The fourth letter is purchasability: A and B = in stock, C = in stock via agent, D = make on demand, E = boutique (expensive), F=annotated (not for sale)
-#    The fifth letter is pH range: R = ref (7.4), M = mid (near 7.4), L = low (around 6.4), H=high (around 8.4).
-#    The sixth and last dimension is net molecular charge. Here we follow the convention of InChIkeys.
-#        Thus. N = neutral, M = minus 1, L = minus 2 (or greater). O = plus 1, P = plus 2 (or greater).
+# Path to folder which contains compounds
+#   Here, a full qualified path should be indicated.
+#   NOTE: this will be ignored, if a 'DATABASE' (see above) is specified
+LOCAL_INPUT_DIR: ""
+
+# Specify "ZINC" to obtain compounds from the ZINC database.
+# Otherwise read local input from the LOCAL_INPUT_DIR, above.
+#TODO: unlist DATABASE
+DATABASE: "ZINC"
+
+# Specify a ZINC mirror site. Options are:
+#   - files.docking.org
+#   - ftp.uni-mainz.de/mirror/zink20/
+#ZINC_MIRROR: "ftp.uni-mainz.de/mirror/zink20/"
+ZINC_MIRROR: "files.docking.org"
+
+# Select the part of the ZINC database for screening. This section follows the ZINC notation and is
+# outlined, here:
+#   - the 1st letter is the molecular weight bin - a measure of size - horizontal axis, 
+#     left to right, as shown on the ZINC webpage. A: 200 D, B: 250, C:300, D: 325, E:350, F: 375
+#   - the 2nd letter is the logP bin - a measure of polarity - vertical axis, top to bottom, 
+#     as shown on the ZINC webpage.
+#   - the 3rd letter defines reactivity : A=anodyne, B=Bother (e.g. chromophores),
+#     C=clean (but pains ok), E=mild reactivity ok, G=reactive ok, I = hot chemistry ok
+#   - the 4th letter notes purchasability: A and B = in stock, C = in stock via agent, 
+#     D = make on demand, E = boutique (expensive), F=annotated (not for sale)
+#   - the 5th letter defines pH range: R = ref (7.4), M = mid (near 7.4), L = low (around 6.4), 
+#     H=high (around 8.4).
+#   - the 6th and last dimension is net molecular charge. Here we follow the convention of InChIkeys.
+#     Thus. N = neutral, M = minus 1, L = minus 2 (or greater). O = plus 1, P = plus 2 (or greater).
 
 ZINC_INPUT:
-  WEIGHT: ["A", "B"] #["C","D","E","F","G"]
-  LOGP:  ["A"] # ,"D","E","F","G", "H","I","J"]
+  WEIGHT: ["B", "C"] #["C","D","E","F","G"]
+  LOGP:  ["B", "C"] # ,"D","E","F","G", "H","I","J"]
   REACT: ["A"] #,"B"] # ,"C", "E", "G"]
-  PURCHASE: ["A"] #, "B"] #, "C", "D", "E"]
-  PH: ["M"]
-  CHARGE: ["N"] # ,"M","O","L","P"]
+  PURCHASE: ["B"] #, "B"] #, "C", "D", "E"]
+  PH: ["M", "R"]
+  CHARGE: ["P"] # ,"M","O","L","P"]
 
-#In case you don't want to download tranches from ZINC based on the paramters given above, a ZINC subset can be choosen. Otherwise set subset as TRANCHES
-# ex.
-SUBSET: "<SUBSET_NAME>"
+# In case you don't want to download tranches from ZINC based on the paramters given above, 
+# a ZINC subset can be choosen. Otherwise set subset as TRANCHES.
+SUBSET: "TRANCHES"
 
 #Specify ENAMINE collection
 ENAMINE_INPUT:
@@ -66,23 +69,21 @@ ENAMINE_INPUT:
 
 ENAMINE_URL: http://www.enamine.net/files/Stock_Screening_Collections/
 
+# Specify whether rescreening is desired ("TRUE" or "FALSE")
+# Rescreening will be performed on the top results as specified by 'RESULT_NUMBER' and 'CUTOFF_VALUE'
+# for the targets specified in 'RESCREENING_TARGETS', below.
 RESCREENING: "FALSE"
 
-# Specify target enzyme ID and chains format: ["PDB_ID, <CHAIN_1> <CHAIN_2]
-TARGETS: ["TARGET,A B C"]
+# Specify target PDB ID and chains in this format: ["PDB_ID, <CHAIN_1> <CHAIN_2], e.g.:
+TARGETS: ["7CWM, A B C"]
 
 # to be specified, if 'RESCREENING' is desired (RESCREENING: "TRUE")
-RESCREENING_TARGETS: ["TARGET1,A B C", "TARGET2,A B C", "TARGET3, A B C"]
-
+RESCREENING_TARGETS: ["6ACD, A B C", "6NB3, A B C", "7BNN, A B C"]
 
 TARGET_URL: https://files.rcsb.org/download
-GRID_DIR: "/<GRID_DIRECTORY>"
-
-#Name your experiment here or change it in the final json file
-
-EXPERIMENT_NAME: "<Name>"
+GRID_DIR: "GRID"
 
-#parameters for energy minimization
+# parameters for energy minimization
 ENERGY_MIN_ALGORITHM: 'cg'
 CONVERGENCE_CRITERIA: '1e-6'
 STEPS: '2500'

profiles/Mogon-NHR/config.yaml

@@ -1,14 +1,17 @@
 default-resources:
-    slurm_partition: smallcpu
+    executor: "slurm"
+    slurm_account: "nhr-zdvhpc"
+    slurm_partition: "smallcpu"
     mem_mb_per_cpu: 1800
     runtime: "30m"
     clusters: "mogonnhr"
 
 set-resources:
     docking:
       mem_mb_per_cpu: 3000
-      slurm_partition: parallel
-      ntasks: 512
+      slurm_partition: "parallel"
+      tasks: 512
+      runtime: 500
     energyMin:
       mem_mb: 350
       runtime: 90

workflow/Snakefile

@@ -5,31 +5,18 @@ from snakemake.utils import min_version
 
 min_version("7.19.1")  # this is where SLURM support was introduced
 
-INPUT_DIR = config["INPUT_DIR"]
-
-MIN_DIR = config["PREPARED_LIGAND_DIR"]
-
-PREPARED_DIR = config["PREPARED_DATA_DIR"]
-
-OUTPUT_DIR = config["OUTPUT_DIR"]
-
-TMP_DIR = config["TEMP_DATA_DIR"]
 
 LOCAL_INPUT = config["LOCAL_INPUT_DIR"]
-
 DATABASE = config["DATABASE"]
-
 SUBSET = config["SUBSET"]
-
 RESCREENING_TARGETS = config["RESCREENING_TARGETS"]
 
 
 def generateOutput(wildcards):
-    irods = path.join(OUTPUT_DIR, "results", "irods.json")
+    irods = path.join("results", "irods.json")
     if config["RESCREENING"] == "TRUE":
         out = expand(
             path.join(
-                OUTPUT_DIR,
                 "results",
                 "rescreening_{percentage}",
                 "{receptorID}",
@@ -40,54 +27,22 @@ def generateOutput(wildcards):
             combAll=combAll,
         )
         hist = expand(
-            path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
+            path.join("results", "{receptorID}_hist.png"),
             receptorID=config["TARGETS"][0].split(",")[0],
         )
-
         return hist + out + [irods]
-
     else:
         out = expand(
-            path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
+            path.join("results", "{receptorID}_{percentage}.csv"),
             receptorID=config["TARGETS"][0].split(",")[0],
             percentage=config["RESULT_NUMBER"],
         )
         hist = expand(
-            path.join(OUTPUT_DIR, "results", "{receptorID}_hist.png"),
+            path.join("results", "{receptorID}_hist.png"),
             receptorID=config["TARGETS"][0].split(",")[0],
         )
         return hist + out + [irods]
 
-
-localrules:
-    all,
-    generateIRODS,
-    dockingResultsTxt,
-    removeDuplicateLigands,
-    makeVenn,
-    prepareLigands2,
-    mergeDocking2,
-    bestLigands,
-    prepareSecondDocking,
-    convertMol2,
-    makeReceptorPDBQT,
-    mergeDocking,
-    mergeLocalInput,
-    split,
-    split2,
-    targetProtein,
-    getZINCdata,
-    getZINCSubsets,
-    gunzip,
-    ENAMINEdownload,
-    prepareReceptor,
-    prepareDocking,
-    prepareLibrary,
-    prepareGeometry,
-    makeHistogram,
-    cleanLigands,
-
-
 targetList = []  # get ProteinIDs from configfile for rescreening
 for i in config["RESCREENING_TARGETS"]:
     targetList.append(i.split(",")[0])
@@ -102,7 +57,6 @@ combAll = "_".join(targetList)  # combine all rescreening targets
 
 def getAllVenn(wildcards):
     path.join(
-        OUTPUT_DIR,
         "output",
         "rescreening",
         "{receptorID}",
@@ -114,7 +68,6 @@ def IRODSinput(wildcards):
     if config["RESCREENING"] == "TRUE":
         out = expand(
             path.join(
-                OUTPUT_DIR,
                 "results",
                 "rescreening_{percentage}",
                 "{receptorID}",
@@ -126,7 +79,7 @@ def IRODSinput(wildcards):
         )
     else:
         out = expand(
-            path.join(OUTPUT_DIR, "results", "{receptorID}_{percentage}.csv"),
+            path.join("results", "{receptorID}_{percentage}.csv"),
             receptorID=config["TARGETS"][0].split(",")[0],
             percentage=config["RESULT_NUMBER"],
         )
@@ -150,13 +103,14 @@ rule generateIRODS:
     input:
         IRODSinput,
     output:
-        path.join(OUTPUT_DIR, "results", "irods.json"),
+        path.join("results", "irods.json"),
     log:
         "logs/generateIRODS.log",
     script:
         "scripts/generateIRODS.py"
 
 
-include: "rules/analyse.smk"
-include: "rules/docking.smk"
 include: "rules/preparation.smk"
+include: "rules/docking.smk"
+include: "rules/analyse.smk"
+