Merge pull request #2 from bio-hpc/essence-dock

Essence dock V1.1

Author: cmartinez-biohpc

MetaScreener/extra_metascreener/results/ESSENCE-Dock.sh

@@ -12,9 +12,29 @@ PURPLE='\033[00;35m'
 CYAN='\033[00;36m'
 
 ms_path=${PWD/metascreener*/}/metascreener
-simg="singularity exec --bind=${PWD} $ms_path/singularity/metascreener.simg"
+simg="singularity exec --bind=${PWD} $ms_path/singularity/ESSENCE-Dock.simg"
 extra_metascreener="$ms_path/MetaScreener/extra_metascreener"
 
+if [ ! -f "$ms_path/singularity/ESSENCE-Dock.simg" ]; then
+	echo "The required ESSENCE-Dock Singularity image doesn't seem to be present. Would you like to download it automatically? "
+	echo "(Y/y) Download Singularity image automatically"
+	echo "(N/n) Exit"
+	read -r answer
+	while [ "${answer,,}" != "y" ] && [ "${answer,,}" != "yes" ] && [ "${answer,,}" != "n" ] && [ "${answer,,}" != "no" ]; do
+		echo "Would you like to download the Singularity image automatically?"
+		echo "(Y/y) Download Singularity image automatically"
+		echo "(N/n) Exit" 
+		read -r answer 
+	done
+	if [ "${answer,,}" = "y" ] || [ "${answer,,}" = "yes" ]; then 
+		wget --no-check-certificate -r "https://drive.usercontent.google.com/download?id=1yN63r8sl26VMZJtdrAG4e_JQFFlb1eE8&confirm=t" -O ${ms_path}/singularity/ESSENCE-Dock.simg
+		echo "The Singularity image has been downloaded"
+	else 
+		echo "Exiting.. Please install the Singularity image and try again"
+		exit
+	fi	
+fi
+
 printHelp(){
 	printf "${GREEN} %6s ${CYAN}%5s ${NONE}%-s \n" "-$1 )" "[ $2 ]" "$3"
 }
@@ -32,6 +52,8 @@ function help()
 	printHelp "np | no-postprocessing | raw" "O" "Skip post-processing of the best results, so no PSE or PLIP interactions are generated. Post-processing is performed by default"
 	printHelp "n | nc" "O" "Amount of compounds to include in the final PyMol Session. Default is 50"
 	printHelp "cl | cluster" "O" "String with options to launch in the cluster. Important: Always accompany this flag with an argument! For example: \"-p standard --time 12:00:00 ...\""
+	printHelp "c | cpus" "O" "Number of CPUs to use"
+	printHelp "t | timeout" "O" "Max time spent processing per compound"
 	printHelp "s | silent" "O" "Silent Mode: Don't show the progression of the ESSENCE-Dock consensus calculations. Only works without the -cl flag: silent mode disabled by default"
 	printHelp "ns | nosilent" "O" "No Silent Mode: Show the progression of the ESSENCE-Dock consensus calculations. Only works with the -cl flag: silent mode enabled by default"
 	printHelp "sc | skip-cleanup" "O" "Skip the cleanup: intermediate files will not be removed"
@@ -53,7 +75,8 @@ skipcleanup=false
 cluster_opt=sequential
 input_dirs=0
 debug=false
-
+CPUS=1
+timeoutLimit=3
 # Parameters
 while (( $# ))
 	do
@@ -86,7 +109,9 @@ while (( $# ))
 					--SKIP-CLEANUP | -SKIP-CLEANUP | -SC)  skipcleanup=true;;
 					--NOSILENT | -NOSILENT | -NS)  CLsilent=false;;
 					--NO-POSTPROCESSING | -NO-POSTPROCESSING | -RAW | -NP)  noPostProcessing=true;;
-					--CLUSTER | -CLUSTER| -CL)  cluster_opt=$2;;
+					--CLUSTER | -CLUSTER | -CL)  cluster_opt=$2;;
+					--CPUS | -CPU | -C)  CPUS=$2;;
+					--TIMEOUT | -TIMEOUT | -T)  timeoutLimit=$2;;
 					--HELP | -HELP | -H) help
 			esac
 		fi
@@ -122,16 +147,16 @@ else
 fi
 
 if [ -d $out ];then
-	while [ "$input" != "Y" ] && [ "$input" != "y" ] && [ "$input" != "N" ] && [ "$input" != "n" ] ; do
-		echo "CreateFile: The directory ${folder_experiment} already exists. To continue you must delete this directory. Do you want to delete it? "
+	while [ "${input,,}" != "y" ] && [ "${input,,}" != "yes" ] && [ "${input,,}" != "n" ] && [ "${input,,}" != "no" ]; do
+		echo "The output directory ${out} already exists. To continue you must delete this directory. Do you want to delete it? "
 		echo "(Y/y) Delete folder"
 		echo "(N/n) Exit"
 		read  input
 	done
-	if [ "$input" == "Y" ] || [ "$input" == "y" ];then
+	if [ "${input,,}" == "y" ] || [ "${input,,}" == "yes" ];then
 		rm -r ${out}
 		mkdir ${out}
-	elif [ "$input" == "n" ] || [ "$input" == "N" ];then
+	elif [ "${input,,}" == "n" ] || [ "${input,,}" == "no" ];then
 		exit
 	fi
 	else
@@ -143,7 +168,7 @@ cross="${simg} python ${extra_metascreener}/results/cross/ESSENCE-Dock_cross.py
 
 # Execute the commands
 if [[ "$cluster_opt" == "sequential" ]];then
-	join="${simg} python3 ${extra_metascreener}/results/join/ESSENCE-Dock_Consensus.py -o ${out} -r ${receptor} -dd ${DiffDockPath} -f ${lst} -s ${silent} -n ${numberOfCompounds} -raw ${noPostProcessing}"
+	join="${simg} python ${extra_metascreener}/results/join/ESSENCE-Dock_Consensus.py -o ${out} -r ${receptor} -dd ${DiffDockPath} -f ${lst} -s ${silent} -n ${numberOfCompounds} -raw ${noPostProcessing} -c ${CPUS} -t ${timeoutLimit}"
 	echo "Preparing docking runs for ESSENCE-Dock Consensus.."
 	if $debug; then
 		echo -e "\e[0;34m[DEBUG]  Full Command:\n${cross}\e[0m"
@@ -176,7 +201,7 @@ if [[ "$cluster_opt" == "sequential" ]];then
 	fi
 
 else
-	join="${simg} python3 ${extra_metascreener}/results/join/ESSENCE-Dock_Consensus.py -o ${out} -r ${receptor} -dd ${DiffDockPath} -f ${lst} -s ${CLsilent} -n ${numberOfCompounds} -raw ${noPostProcessing}"
+	join="${simg} python ${extra_metascreener}/results/join/ESSENCE-Dock_Consensus.py -o ${out} -r ${receptor} -dd ${DiffDockPath} -f ${lst} -s ${CLsilent} -n ${numberOfCompounds} -raw ${noPostProcessing} -c ${CPUS} -t ${timeoutLimit}"
 	receptorName="${receptor##*/}" 
 	mkdir "$out/job_data/"
 	name_job="${out}/job_data/ESSENCE-Dock_Consensus_${receptorName%.*}.sh"

MetaScreener/extra_metascreener/results/cross/ESSENCE-Dock_cross.py

@@ -9,83 +9,85 @@
 
 import argparse
 import os
-from collections import OrderedDict
 import time
+from collections import OrderedDict
 
 parser = argparse.ArgumentParser()
-parser.add_argument('folder', type=str, nargs='+', help='Folders to process')
-parser.add_argument('-o', '--output', default='', type=str, help='name of output file')
+parser.add_argument("folder", type=str, nargs="+", help="Folders to process")
+parser.add_argument("-o", "--output", default="", type=str, help="name of output file")
 
 args = parser.parse_args()
 
 all_molecules = set()
 
+
 def read_energies(input_dir):
-	dct = {}
-	with open(input_dir + "/Results_scoring.csv") as csv:
-		lines = csv.readlines()
-	for i, line in enumerate(lines[1:]):
-		lineSplit = line.strip().split(';')
-		compound = lineSplit[4]
-		if compound not in all_molecules:
-			all_molecules.add(compound)
-		energy = float(lineSplit[0])
-		path = str(lineSplit[-1])
-		dct[compound] = [str(i+1), energy, path]
-	return dct
-
-directories = ''
+    dct = {}
+    with open(input_dir + "/Results_scoring.csv") as csv:
+        lines = csv.readlines()
+    for i, line in enumerate(lines[1:]):
+        lineSplit = line.strip().split(";")
+        compound = lineSplit[4]
+        if compound not in all_molecules:
+            all_molecules.add(compound)
+        energy = float(lineSplit[0])
+        path = str(lineSplit[-1])
+        dct[compound] = [str(i + 1), energy, path]
+    return dct
+
+
+directories = ""
 all = OrderedDict()
-first_sw = ''
-name_out = ''
+first_sw = ""
+name_out = ""
 ORDER = False
 
 start = time.time()
 args.folder.sort()
 
 for dir in args.folder:
-	index = dir.find('VS_')
-	directories += '{} '.format(dir)
-	sw = dir.split("VS_")[-1].split("_")[0]
-	if (sw not in name_out):
-		name_out += '{}_'.format(sw)
-        
-	energies = read_energies(dir)
-	if len(energies) > 0:
-		if sw in all.keys():
-			all[sw].update(energies)
-		else:
-			all[sw] = energies
-	if first_sw == "":
-		first_sw = sw
+    index = dir.find("VS_")
+    directories += "{} ".format(dir)
+    sw = dir.split("VS_")[-1].split("_")[0]
+    if sw not in name_out:
+        name_out += "{}_".format(sw)
+
+    energies = read_energies(dir)
+    if len(energies) > 0:
+        if sw in all.keys():
+            all[sw].update(energies)
+        else:
+            all[sw] = energies
+    if first_sw == "":
+        first_sw = sw
 
 file_out = args.output
 
 header = " Rank ".join(all.keys()) + " Rank Molecule"
 header = ",".join(all.keys())
 
-#print("Writing preprocessed results to " + str(file_out))
-
-f_out = open(file_out, 'w')
-f_out.write('{}\n'.format(header))
-rank = 1;
+f_out = open(file_out, "w")
+f_out.write("{}\n".format(header))
+rank = 1
 
 if len(all) == 0:
-	print("No results have been found")
-	exit()
+    print("No results have been found")
+    exit()
 
 for molecule in all_molecules:
-	outputLine = ""
-	for sw in all.keys():
-		if all[sw].has_key(molecule):
-			result = all[sw][molecule]
-			outputLine += '{} {} {} '.format(result[0], result[1], result[2])
-		else:
-			outputLine += "-- -- -- "
-	outputLine += " " + molecule + "\n"          
-	f_out.write(outputLine)
-	rank += 1
+    outputLine = ""
+    for sw in all.keys():
+        if molecule in all[sw]:
+            result = all[sw][molecule]
+            outputLine += "{} {} {} ".format(result[0], result[1], result[2])
+        else:
+            outputLine += "-- -- -- "
+    outputLine += " " + molecule + "\n"
+    f_out.write(outputLine)
+    rank += 1
 f_out.close()
 
-print("Time to preprocess the individual docking calculations: %ss" % (round(time.time() - start, 2)))
-
+print(
+    "Time to preprocess the individual docking calculations: %ss"
+    % (round(time.time() - start, 2))
+)