def readDockingResults(resFile):
fHandle = open(resFile)
result= {}
try:
header = fHandle.next().strip().split()
if "Ligand" not in header or "1_Energy" not in header:
raise
except:
errorMsg("Docking result file is in bad format")
return {}
for line in fHandle:
entry = dict(zip(header, line.strip().split()))
result[entry["Ligand"]] = float(entry["1_Energy"].replace(',','.'))
fHandle.close()
return result
for x in contactsBaseSet:
if x in chemBaseMolsDict:
baseSubset.append(chemBaseMolsDict[x])
for chemTrainSet, chemBaseSet in chemTreeWalkGenerator(contactsTrainSet, trainSubset, contactsBaseSet, baseSubset, minYesThreshold = args.yesPersChem, topPercent = args.chemTreshold):
for cName in chemBaseSet:
bestCompounds.add(cName)
#print('Best compounds')
#print(bestCompounds)
bestCompoundsList = list(bestCompounds)
bestCompoundsList.sort(key = lambda x: baseDockingResults[x])
for cName in bestCompoundsList[:args.maxcluster]:
#print(' ', cName, baseDockingResults[cName])
finalResult.add(cName)
#print("*******************")
else:
errorMsg('Methods are not implemented')
sys.exit(1)
finalResultList = list(finalResult)
finalResultList.sort(key = lambda x: baseDockingResults[x])
results = []
trainCompNames=getLongNames(chemTrainMolsDict)
for cName in finalResultList:
print(' ', cName, baseDockingResults[cName])
results.append({"id":cName.replace('ZINC', ''), "energy":baseDockingResults[cName], "score":scoreS[cName], "similarChem":getBestSimilarToMolset(chemBaseMolsDict[cName], chemTrainMolsDict, trainCompNames), "similarContacts":getBestSimilarToMolset(contactsBaseMolsDict[cName], contactsTrainMolsDict, trainCompNames)})
saveResults(args.outJson, results)
createHtmlReport(args.htmlreport, results, maxsimil=min(max(args.maxsimilar, 3), 10), maxOutComp = args.maxtop)