def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["CalcRMSD"] = Options["--calcRMSD"]
OptionsInfo["UseBestRMSD"] = False
if re.match("^BestRMSD$", OptionsInfo["CalcRMSD"], re.I):
OptionsInfo["UseBestRMSD"] = True
OptionsInfo["MaxIters"] = int(Options["--maxIters"])
OptionsInfo["Mode"] = Options["--mode"]
OptionsInfo["RefFile"] = Options["--reffile"]
OptionsInfo["ProbeFile"] = Options["--probefile"]
# No need for any RDKit specific --outfileParams....
OptionsInfo["InfileParams"] = MiscUtil.ProcessOptionInfileParameters("--infileParams", Options["--infileParams"])
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["OutDelim"] = " "
if MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "csv"):
OptionsInfo["OutDelim"] = ","
elif MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "tsv txt"):
OptionsInfo["OutDelim"] = "\t"
else:
MiscUtil.PrintError("The file name specified , %s, for option \"--outfile\" is not valid. Supported file formats: csv tsv txt\n" % (OptionsInfo["Outfile"]))
def MoleculesWriter(FileName, **KeyWordArgs):
"""Set up a molecule writer.
Arguments:
FileName (str): Name of a file with complete path.
**KeyWordArgs (dictionary) : Parameter name and value pairs for writing and
processing molecules.
Returns:
RDKit object : Molecule writer.
Notes:
The file extension is used to determine type of the file and set up an appropriate
file writer.
"""
# Set default values for possible arguments...
WriterArgs = {
"Compute2DCoords": False,
"Kekulize": False,
"SMILESDelimiter": ' ',
"SMILESIsomeric": True,
"SMILESTitleLine": True,
"SMILESMolName": True
}
# Set specified values for possible arguments...
for Arg in WriterArgs:
if Arg in KeyWordArgs:
WriterArgs[Arg] = KeyWordArgs[Arg]
Writer = None
if MiscUtil.CheckFileExt(FileName, "sdf sd"):
Writer = Chem.SDWriter(FileName)
if WriterArgs["Kekulize"]:
Writer.SetKekulize(True)
elif MiscUtil.CheckFileExt(FileName, "pdb"):
Writer = Chem.PDBWriter(FileName)
elif MiscUtil.CheckFileExt(FileName, "smi"):
# Text for the name column in the title line. Blank indicates not to include name column
# in the output file...
NameHeader = 'Name' if WriterArgs["SMILESMolName"] else ''
Writer = Chem.SmilesWriter(FileName,
delimiter=WriterArgs["SMILESDelimiter"],
nameHeader=NameHeader,
includeHeader=WriterArgs["SMILESTitleLine"],
isomericSmiles=WriterArgs["SMILESIsomeric"],
kekuleSmiles=WriterArgs["Kekulize"])
else:
MiscUtil.PrintWarning(
"RDKitUtil.WriteMolecules: Non supported file type: %s" % FileName)
return Writer
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["Autocorr2DExclude"] = True
if not re.match("^Yes$", Options["--autocorr2DExclude"], re.I):
OptionsInfo["Autocorr2DExclude"] = False
OptionsInfo["FragmentCount"] = True
if not re.match("^Yes$", Options["--fragmentCount"], re.I):
OptionsInfo["FragmentCount"] = False
OptionsInfo["DescriptorNames"] = Options["--descriptorNames"]
OptionsInfo["Mode"] = Options["--mode"]
OptionsInfo["Infile"] = Options["--infile"]
OptionsInfo["InfileParams"] = MiscUtil.ProcessOptionInfileParameters(
"--infileParams", Options["--infileParams"], Options["--infile"])
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["OutfileParams"] = MiscUtil.ProcessOptionOutfileParameters(
"--outfileParams", Options["--outfileParams"], Options["--infile"],
Options["--outfile"])
OptionsInfo["Overwrite"] = Options["--overwrite"]
TextOutFileMode = False
TextOutFileDelim = ""
if MiscUtil.CheckFileExt(Options["--outfile"], "csv"):
TextOutFileMode = True
TextOutFileDelim = ","
elif MiscUtil.CheckFileExt(Options["--outfile"], "tsv txt"):
TextOutFileMode = True
TextOutFileDelim = "\t"
OptionsInfo["TextOutFileMode"] = TextOutFileMode
OptionsInfo["TextOutFileDelim"] = TextOutFileDelim
OptionsInfo["MPMode"] = True if re.match("^yes$", Options["--mp"],
re.I) else False
OptionsInfo["MPParams"] = MiscUtil.ProcessOptionMultiprocessingParameters(
"--mpParams", Options["--mpParams"])
OptionsInfo["Precision"] = int(Options["--precision"])
OptionsInfo["SMILESOut"] = False
if re.match("^Yes$", Options["--smilesOut"], re.I):
OptionsInfo["SMILESOut"] = True
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["Addhydrogens"] = True if re.match(
"^Yes$", Options["--addHydrogens"], re.I) else False
OptionsInfo["Infiles"] = Options["--infiles"]
OptionsInfo["InfilesNames"] = Options["--infilesNames"]
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["OutDelim"] = " "
if MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "csv"):
OptionsInfo["OutDelim"] = ","
elif MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "tsv txt"):
OptionsInfo["OutDelim"] = "\t"
else:
MiscUtil.PrintError(
"The file name specified , %s, for option \"--outfile\" is not valid. Supported file formats: csv tsv txt\n"
% (OptionsInfo["Outfile"]))
OptionsInfo["KeepInorganics"] = True if re.match(
"^Yes$", Options["--keepInorganics"], re.I) else False
OptionsInfo["KeepLigands"] = True if re.match(
"^Yes$", Options["--keepLigands"], re.I) else False
OptionsInfo["KeepSolvents"] = True if re.match(
"^Yes$", Options["--keepSolvents"], re.I) else False
ProcessKeepSelectionOptions()
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["Quiet"] = 1 if re.match("^Yes$", Options["--quiet"],
re.I) else 0
OptionsInfo["Precision"] = int(Options["--precision"])
OptionsInfo["Mode"] = Options["--mode"]
ProcessSpecifiedPropertyNames()
RetrieveInfilesInfo()
OptionsInfo["ChainIDs"] = Options["--chainIDs"]
OptionsInfo["AllChains"] = True if re.match("^All$", Options["--chainIDs"],
re.I) else False
ProcessChainIDs()
def DrawMolecules():
"""Draw molecules"""
Infile = OptionsInfo["Infile"]
Outfile = OptionsInfo["Outfile"]
# Read molecules...
MiscUtil.PrintInfo("\nReading file %s..." % Infile)
ValidMols, MolCount, ValidMolCount = RDKitUtil.ReadAndValidateMolecules(
Infile, **OptionsInfo["InfileParams"])
MiscUtil.PrintInfo("Total number of molecules: %d" % MolCount)
MiscUtil.PrintInfo("Number of valid molecules: %d" % ValidMolCount)
MiscUtil.PrintInfo("Number of ignored molecules: %d" %
(MolCount - ValidMolCount))
# Compute 2D coordinates...
if OptionsInfo["Compute2DCoords"]:
MiscUtil.PrintInfo("\nComputing 2D coordinates...")
for Mol in ValidMols:
AllChem.Compute2DCoords(Mol)
MiscUtil.PrintInfo("Generating image grid...")
# Setup atoms lists for highlighting atoms and bonds...
AtomLists = SetupAtomListsToHighlight(ValidMols)
BondLists = None
# Set up legends...
MolNames = None
if OptionsInfo["ShowMolName"]:
MolNames = []
MolCount = 0
for Mol in ValidMols:
MolCount += 1
MolName = RDKitUtil.GetMolName(Mol, MolCount)
MolNames.append(MolName)
# Perform alignment to a common template...
PerformAlignment(ValidMols)
# Generate appropriate output files...
if MiscUtil.CheckFileExt(Outfile, "svg"):
GenerateSVGImageFile(ValidMols, MolNames, AtomLists, BondLists)
elif MiscUtil.CheckFileExt(Outfile, "html htm"):
GenerateHTMLTableFile(ValidMols, MolNames, AtomLists, BondLists)
else:
GenerateImageFile(ValidMols, MolNames, AtomLists, BondLists)
def ValidateOptions():
"""Validate option values"""
MiscUtil.ValidateOptionTextValue("-a, --autocorr2DExclude", Options["--autocorr2DExclude"], "yes no")
MiscUtil.ValidateOptionTextValue("-f, --fragmentCount", Options["--fragmentCount"], "yes no")
MiscUtil.ValidateOptionTextValue("-m, --mode", Options["--mode"], "2D 3D All FragmentCountOnly Specify")
if re.match("^Specify$", Options["--mode"], re.I):
if re.match("^none$", Options["--descriptorNames"], re.I):
MiscUtil.PrintError("The name(s) of molecular descriptors must be specified using \"-d, --descriptorNames\" option during \"Specify\" value of \"-m, --mode\" option.")
MiscUtil.ValidateOptionFilePath("-i, --infile", Options["--infile"])
MiscUtil.ValidateOptionFileExt("-i, --infile", Options["--infile"], "sdf sd mol smi csv tsv txt")
if re.match("^3D|All$", Options["--mode"], re.I):
if MiscUtil.CheckFileExt(Options["--infile"], "smi"):
MiscUtil.PrintError("The input SMILES file, %s, is not valid for \"3D or All\" value of \"-m, --mode\" option.")
MiscUtil.ValidateOptionFileExt("-o, --outfile", Options["--outfile"], "sdf sd csv tsv txt")
MiscUtil.ValidateOptionsOutputFileOverwrite("-o, --outfile", Options["--outfile"], "--overwrite", Options["--overwrite"])
MiscUtil.ValidateOptionsDistinctFileNames("-i, --infile", Options["--infile"], "-o, --outfile", Options["--outfile"])
MiscUtil.ValidateOptionIntegerValue("-p, --precision", Options["--precision"], {">": 0})
MiscUtil.ValidateOptionTextValue("-s, --smilesOut", Options["--smilesOut"], "yes no")
def GenerateImageFile(ValidMols, MolNames, AtomLists, BondLists):
"""Generate a non SVG image file."""
Outfile = OptionsInfo["Outfile"]
NumOfMolsPerRow = OptionsInfo["NumOfMolsPerRow"]
Width = OptionsInfo["MolImageWidth"]
Height = OptionsInfo["MolImageHeight"]
# Setup drawing options...
UpdatedDrawingOptions = DrawingOptions()
UpdatedDrawingOptions.atomLabelFontSize = int(
OptionsInfo["AtomLabelFontSize"])
UpdatedDrawingOptions.bondLineWidth = float(OptionsInfo["BondLineWidth"])
MolsImage = Draw.MolsToGridImage(ValidMols,
molsPerRow=NumOfMolsPerRow,
subImgSize=(Width, Height),
legends=MolNames,
highlightAtomLists=AtomLists,
highlightBondLists=BondLists,
useSVG=False,
kekulize=OptionsInfo["Kekulize"],
options=UpdatedDrawingOptions)
MiscUtil.PrintInfo("\nGenerating image file %s..." % Outfile)
if MiscUtil.CheckFileExt(Outfile, "pdf"):
if MolsImage.mode == 'RGBA':
MolsImage = MolsImage.convert('RGB')
MolsImage.save(Outfile)
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["Infile"] = Options["--infile"]
FileDir, FileName, FileExt = MiscUtil.ParseFileName(OptionsInfo["Infile"])
OptionsInfo["InfileRoot"] = FileName
OptionsInfo["Outfile"] = Options["--outfile"]
FileDir, FileName, FileExt = MiscUtil.ParseFileName(OptionsInfo["Outfile"])
OptionsInfo["OutfileRoot"] = FileName
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["OutDelim"] = " "
if MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "csv"):
OptionsInfo["OutDelim"] = ","
elif MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "tsv txt"):
OptionsInfo["OutDelim"] = "\t"
else:
MiscUtil.PrintError(
"The file name specified , %s, for option \"--outfile\" is not valid. Supported file formats: csv tsv txt\n"
% (OptionsInfo["Outfile"]))
OptionsInfo["OutMode"] = Options["--outMode"]
OptionsInfo["MultipleOutFiles"] = True if re.match(
"^MultipleFiles$", OptionsInfo["OutMode"], re.I) else False
OptionsInfo["OutChainID"] = True if re.match(
"^Yes$", Options["--outChainID"], re.I) else False
OptionsInfo["OutCategory"] = True if re.match(
"^Yes$", Options["--outCategory"], re.I) else False
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["Precision"] = int(Options["--precision"])
RetrieveInfileInfo()
OptionsInfo["ChainIDs"] = Options["--chainIDs"]
ProcessChainIDs()
SetupCategoryOutfiles()
def ProcessSpecifiedDescriptorNames():
"""Process and validate specified decriptor names."""
OptionsInfo["SpecifiedDescriptorNames"] = []
if not re.match("^(2D|3D|All|FragmentCountOnly|Specify)$", OptionsInfo["Mode"], re.I):
MiscUtil.PrintError("Mode value, %s, using \"-m, --mode\" option is not a valid value." % OptionsInfo["Mode"])
if re.match("^2D$", OptionsInfo["Mode"], re.I):
OptionsInfo["SpecifiedDescriptorNames"] = DescriptorNamesMap["2D"]["Names"]
if OptionsInfo["FragmentCount"]:
OptionsInfo["SpecifiedDescriptorNames"].extend(DescriptorNamesMap["FragmentCount"]["Names"])
return
elif re.match("^3D$", OptionsInfo["Mode"], re.I):
OptionsInfo["SpecifiedDescriptorNames"] = DescriptorNamesMap["3D"]["Names"]
return
elif re.match("^All$", OptionsInfo["Mode"], re.I):
OptionsInfo["SpecifiedDescriptorNames"] = DescriptorNamesMap["2D"]["Names"]
if OptionsInfo["FragmentCount"]:
OptionsInfo["SpecifiedDescriptorNames"].extend(DescriptorNamesMap["FragmentCount"]["Names"])
OptionsInfo["SpecifiedDescriptorNames"].extend(DescriptorNamesMap["3D"]["Names"])
return
elif re.match("^FragmentCountOnly$", OptionsInfo["Mode"], re.I):
OptionsInfo["SpecifiedDescriptorNames"] = DescriptorNamesMap["FragmentCount"]["Names"]
return
# Set up a canonical descriptor names map for checking specified names...
CanonicalNameMap = {}
for Name in DescriptorNamesMap["ComputeFunction"]:
CanonicalNameMap[Name.lower()] = Name
# Parse and validate specified names...
DescriptorNames = re.sub(" ", "", OptionsInfo["DescriptorNames"])
if not DescriptorNames:
MiscUtil.PrintError("No descriptor names specified for \"-d, --descriptorNames\" option")
SMILESInfile = MiscUtil.CheckFileExt(Options["--infile"], "smi")
Canonical3DNameMap = {}
if SMILESInfile:
for Name in DescriptorNamesMap["3D"]["Names"]:
Canonical3DNameMap[Name.lower()] = Name
SpecifiedDescriptorNames = []
for Name in DescriptorNames.split(","):
CanonicalName = Name.lower()
if CanonicalName in CanonicalNameMap:
SpecifiedDescriptorNames.append(CanonicalNameMap[CanonicalName])
else:
MiscUtil.PrintError("The descriptor name, %s, specified using \"-d, --descriptorNames\" option is not a valid name." % (Name))
if SMILESInfile:
if CanonicalName in Canonical3DNameMap:
MiscUtil.PrintError("The 3D descriptor name, %s, specified using \"-d, --descriptorNames\" option is not a valid for SMILES input file." % (Name))
if not len(SpecifiedDescriptorNames):
MiscUtil.PrintError("No valid descriptor name specified for \"-d, --descriptorNames\" option")
OptionsInfo["SpecifiedDescriptorNames"] = SpecifiedDescriptorNames
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["AlignMethod"] = Options["--alignMethod"].lower()
OptionsInfo["AlignMode"] = Options["--alignMode"]
OptionsInfo["Mode"] = Options["--mode"]
OptionsInfo["ProbeFiles"] = Options["--probefiles"]
OptionsInfo["ProbeFilesNames"] = Options["--probeFilesNames"]
OptionsInfo["RefFiles"] = Options["--reffiles"]
OptionsInfo["RefFilesNames"] = Options["--refFilesNames"]
RetrieveProbeFilesInfo()
RetrieveRefFilesInfo()
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["OutMatrix"] = True if re.match(
"^Yes$", Options["--outMatrix"], re.I) else False
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["OutDelim"] = " "
if MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "csv"):
OptionsInfo["OutDelim"] = ","
elif MiscUtil.CheckFileExt(OptionsInfo["Outfile"], "tsv txt"):
OptionsInfo["OutDelim"] = "\t"
else:
MiscUtil.PrintError(
"The file name specified , %s, for option \"--outfile\" is not valid. Supported file formats: csv tsv txt\n"
% (OptionsInfo["Outfile"]))
def ReadMolecules(FileName, **KeyWordArgs):
"""Read molecules from an input file without performing any validation
and creation of molecule objects.
Arguments:
FileName (str): Name of a file with complete path.
**KeyWordArgs (dictionary) : Parameter name and value pairs for reading and
processing molecules.
Returns:
list : List of RDKit molecule objects.
Notes:
The file extension is used to determine type of the file and set up an appropriate
file reader.
"""
# Set default values for possible arguments...
ReaderArgs = {"Sanitize": True, "RemoveHydrogens": True, "StrictParsing": True, "SMILESDelimiter" : ' ', "SMILESColumn": 1, "SMILESNameColumn": 2, "SMILESTitleLine": True }
# Set specified values for possible arguments...
for Arg in ReaderArgs:
if Arg in KeyWordArgs:
ReaderArgs[Arg] = KeyWordArgs[Arg]
# Modify specific valeus for SMILES...
if MiscUtil.CheckFileExt(FileName, "smi csv tsv txt"):
Args = ["Sanitize", "SMILESTitleLine"]
for Arg in Args:
if ReaderArgs[Arg] is True:
ReaderArgs[Arg] = 1
else:
ReaderArgs[Arg] = 0
Mols = []
if MiscUtil.CheckFileExt(FileName, "sdf sd"):
return ReadMoleculesFromSDFile(FileName, ReaderArgs["Sanitize"], ReaderArgs["RemoveHydrogens"], ReaderArgs['StrictParsing'])
elif MiscUtil.CheckFileExt(FileName, "mol"):
return ReadMoleculesFromMolFile(FileName, ReaderArgs["Sanitize"], ReaderArgs["RemoveHydrogens"], ReaderArgs['StrictParsing'])
elif MiscUtil.CheckFileExt(FileName, "mol2"):
return ReadMoleculesFromMol2File(FileName, ReaderArgs["Sanitize"], ReaderArgs["RemoveHydrogens"])
elif MiscUtil.CheckFileExt(FileName, "pdb"):
return ReadMoleculesFromPDBFile(FileName, ReaderArgs["Sanitize"], ReaderArgs["RemoveHydrogens"])
elif MiscUtil.CheckFileExt(FileName, "smi txt csv tsv"):
SMILESColumnIndex = ReaderArgs["SMILESColumn"] - 1
SMILESNameColumnIndex = ReaderArgs["SMILESNameColumn"] - 1
return ReadMoleculesFromSMILESFile(FileName, ReaderArgs["SMILESDelimiter"], SMILESColumnIndex, SMILESNameColumnIndex, ReaderArgs["SMILESTitleLine"], ReaderArgs["Sanitize"])
else:
MiscUtil.PrintWarning("RDKitUtil.ReadMolecules: Non supported file type: %s" % FileName)
return Mols
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["ButinaSimilarityCutoff"] = float(Options["--butinaSimilarityCutoff"])
OptionsInfo["ButinaReordering"] = False
if re.match("^Yes$", Options["--butinaReordering"], re.I):
OptionsInfo["ButinaReordering"] = True
OptionsInfo["Fingerprints"] = Options["--fingerprints"]
OptionsInfo["FingerprintsType"] = Options["--fingerprintsType"]
OptionsInfo["ClusteringMethod"] = Options["--clusteringMethod"]
ProcessClusteringMethodParameter()
OptionsInfo["NumClusters"] = int(Options["--numClusters"])
OptionsInfo["Infile"] = Options["--infile"]
OptionsInfo["InfileParams"] = MiscUtil.ProcessOptionInfileParameters("--infileParams", Options["--infileParams"], Options["--infile"])
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["OutfileParams"] = MiscUtil.ProcessOptionOutfileParameters("--outfileParams", Options["--outfileParams"], Options["--infile"], Options["--outfile"])
OptionsInfo["Overwrite"] = Options["--overwrite"]
OptionsInfo["OutFileMode"] = Options["--outfileMode"]
SingleOutFileMode = True
if not re.match("^SingleFile$", Options["--outfileMode"], re.I):
SingleOutFileMode = False
OptionsInfo["SingleOutFileMode"] = SingleOutFileMode
FileDir, FileName, FileExt = MiscUtil.ParseFileName(Options["--outfile"])
OptionsInfo["OutfileBasename"] = FileName
OptionsInfo["OutfileExt"] = FileExt
TextOutFileMode = False
TextOutFileDelim = ""
TextOutFileTitleLine = True
if MiscUtil.CheckFileExt(Options["--outfile"], "csv"):
TextOutFileMode = True
TextOutFileDelim = ","
elif MiscUtil.CheckFileExt(Options["--outfile"], "tsv txt"):
TextOutFileMode = True
TextOutFileDelim = "\t"
elif MiscUtil.CheckFileExt(Options["--outfile"], "smi"):
TextOutFileMode = True
TextOutFileDelim = OptionsInfo["OutfileParams"]["SMILESDelimiter"]
TextOutFileTitleLine = OptionsInfo["OutfileParams"]["SMILESTitleLine"]
OptionsInfo["TextOutFileMode"] = TextOutFileMode
OptionsInfo["TextOutFileDelim"] = TextOutFileDelim
OptionsInfo["TextOutFileTitleLine"] = TextOutFileTitleLine
OptionsInfo["SimilarityMetric"] = Options["--similarityMetric"]
ProcessSimilarityMetricParameter()
OptionsInfo["ParamsFingerprints"] = Options["--paramsFingerprints"]
ProcessFingerprintsParameters()
def ProcessOptions():
"""Process and validate command line arguments and options"""
MiscUtil.PrintInfo("Processing options...")
# Validate options...
ValidateOptions()
OptionsInfo["CoreScaffold"] = Options["--coreScaffold"]
OptionsInfo["Infile"] = Options["--infile"]
OptionsInfo["InfileParams"] = MiscUtil.ProcessOptionInfileParameters(
"--infileParams", Options["--infileParams"], Options["--infile"])
OptionsInfo["Outfile"] = Options["--outfile"]
OptionsInfo["OutfileParams"] = MiscUtil.ProcessOptionOutfileParameters(
"--outfileParams", Options["--outfileParams"], Options["--infile"],
Options["--outfile"])
TextOutFileMode = False
TextOutFileDelim = ""
if MiscUtil.CheckFileExt(Options["--outfile"], "csv"):
TextOutFileMode = True
TextOutFileDelim = ","
elif MiscUtil.CheckFileExt(Options["--outfile"], "tsv txt"):
TextOutFileMode = True
TextOutFileDelim = "\t"
OptionsInfo["TextOutFileMode"] = TextOutFileMode
OptionsInfo["TextOutFileDelim"] = TextOutFileDelim
TextOutQuote = False
if re.match("^auto$", Options["--quote"], re.I):
if MiscUtil.CheckFileExt(Options["--outfile"], "csv"):
TextOutQuote = True
else:
if re.match("^yes$", Options["--quote"], re.I):
TextOutQuote = True
OptionsInfo["TextOutQuote"] = TextOutQuote
OptionsInfo["Overwrite"] = Options["--overwrite"]
RemoveUnmatchedMode = False
UnmatchedOutfile = None
if re.match("^yes$", Options["--removeUnmatched"], re.I):
RemoveUnmatchedMode = True
FileDir, FileName, FileExt = MiscUtil.ParseFileName(
OptionsInfo["Outfile"])
UnmatchedOutfile = "%sUnmatched.%s" % (FileName, FileExt)
OptionsInfo["RemoveUnmatchedMode"] = RemoveUnmatchedMode
OptionsInfo["UnmatchedOutfile"] = UnmatchedOutfile
OptionsInfo["SpecifiedDecompositionParams"] = Options[
"--decompositionParams"]
ProcessDecompositionParameters()
OptionsInfo["SpecifiedMCSParams"] = Options["--mcsParams"]
ProcessMCSParameters()
SMARTSOrSMILESCoreScaffold = ""
SMARTSOrSMILESCoreScaffoldList = []
if not re.match("^none$", Options["--smartsOrSmilesCoreScaffold"],
re.I) or len(Options["--smartsOrSmilesCoreScaffold"]):
if re.match("^(BySMARTS|BySMILES)$", Options["--coreScaffold"], re.I):
SMARTSOrSMILESCoreScaffold = re.sub(
" ", "", Options["--smartsOrSmilesCoreScaffold"])
if not SMARTSOrSMILESCoreScaffold:
MiscUtil.PrintError(
"A non empty value must be specified for \"-s, --smartsOrSmilesCoreScaffold\" during %s value of \"-c, --coreScaffold\" option "
% (Options["--coreScaffold"]))
SMARTSOrSMILESCoreScaffoldList = SMARTSOrSMILESCoreScaffold.split(
",")
OptionsInfo["SMARTSOrSMILESCoreScaffold"] = SMARTSOrSMILESCoreScaffold
OptionsInfo[
"SMARTSOrSMILESCoreScaffoldList"] = SMARTSOrSMILESCoreScaffoldList
def ValidateOptions():
"""Validate option values"""
MiscUtil.ValidateOptionTextValue("--compute2DCoords",
Options["--compute2DCoords"], "yes no")
MiscUtil.ValidateOptionTextValue("-m, --mode", Options["--mode"],
"RxnByName RxnBySMIRKS")
MiscUtil.ValidateOptionTextValue("-p, --prodMolNames",
Options["--prodMolNames"],
"UseReactants Sequential")
if not re.match("^auto$", Options["--rxnNamesFile"], re.I):
MiscUtil.ValidateOptionFilePath("--rxnNamesFile",
Options["--rxnNamesFile"])
MiscUtil.ValidateOptionFileExt("-o, --outfile", Options["--outfile"],
"sdf sd smi")
MiscUtil.ValidateOptionsOutputFileOverwrite("-o, --outfile",
Options["--outfile"],
"--overwrite",
Options["--overwrite"])
ReactantFiles = re.sub(" ", "", Options["--infiles"])
if not ReactantFiles:
MiscUtil.PrintError(
"No reactant files specified for \"-i, --infiles\" option")
# Validate file extensions...
for ReactantFile in ReactantFiles.split(","):
MiscUtil.ValidateOptionFilePath("-i, --infiles", ReactantFile)
MiscUtil.ValidateOptionFileExt("-i, --infiles", ReactantFile,
"sdf sd smi csv tsv txt")
MiscUtil.ValidateOptionsDistinctFileNames("-i, --infiles",
ReactantFile,
"-o, --outfile",
Options["--outfile"])
# Match file formats...
FirstFile = True
FirstFileFormat = ""
for ReactantFile in ReactantFiles.split(","):
FileFormat = ""
if MiscUtil.CheckFileExt(ReactantFile, "sdf sd"):
FileFormat = "SD"
elif MiscUtil.CheckFileExt(ReactantFile, "smi csv tsv txt"):
FileFormat = "SMILES"
else:
MiscUtil.PrintError(
"The file name specified , %s, for option \"-i, --infiles\" is not valid. Supported file formats: sdf sd smi csv tsv txt\n"
% ReactantFile)
if FirstFile:
FirstFile = False
FirstFileFormat = FileFormat
continue
if not re.match("^%s$" % FirstFileFormat, FileFormat, re.IGNORECASE):
MiscUtil.PrintError(
"All reactant file names - %s - specified using option \"-i, --infiles\" must have the same file format.\n"
% ReactantFiles)
MiscUtil.ValidateOptionTextValue("--sanitize", Options["--sanitize"],
"yes no")
