public void TestLogFileName(
string logDirectory,
string logFileNameBase,
string expectedBaseName)
{
var fileStatsLogger = new SimpleFileStatsLogger
{
LogFileBaseName = logFileNameBase,
LogDirectoryPath = logDirectory,
LogMessagesToFile = true
};
var fileToFind = ProcessFilesOrDirectoriesBase.GetAppPath();
fileStatsLogger.ProcessFile(fileToFind);
Console.WriteLine();
Console.WriteLine("Log file path: " + fileStatsLogger.LogFilePath);
var logFileSuffix = expectedBaseName + "_" + DateTime.Now.ToString("yyyy-MM-dd") + ".txt";
if (!fileStatsLogger.LogFilePath.EndsWith(logFileSuffix))
{
Assert.Fail("Unexpected log file name; does not end with " + logFileSuffix);
}
}
private static void ShowProgramHelp()
{
try
{
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"This program can be used to split apart a protein FASTA file into a number of sections. " +
"Although the splitting is random, each section will have a nearly identical number of residues."));
Console.WriteLine();
Console.WriteLine("Program syntax:");
Console.WriteLine(Path.GetFileName(ProcessFilesOrDirectoriesBase.GetAppPath()) +
" /I:SourceFastaFile [/O:OutputDirectoryPath]");
Console.WriteLine(" [/N:SplitCount] [/MB:TargetSizeMB] [/P:ParameterFilePath] ");
Console.WriteLine(" [/S:[MaxLevel]] [/A:AlternateOutputDirectoryPath] [/R] [/L]");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The input file path can contain the wildcard character * and should point to a FASTA file. " +
"The output directory switch is optional. " +
"If omitted, the output file will be created in the same directory as the input file."));
Console.WriteLine();
Console.WriteLine("Use /N to define the number of parts to split the input file into.");
Console.WriteLine("For example, /N:10 will split the input FASTA file into 10 parts");
Console.WriteLine();
Console.WriteLine("Alternatively, use /MB to specify the size of the split FASTA files, in MB (minimum {0} MB)", SplitterOptions.MINIMUM_TARGET_FILE_SIZE_MB);
Console.WriteLine("For example, /MB:100 will create separate FASTA files that are each ~100 MB in size");
Console.WriteLine();
Console.WriteLine("If both /N and /MB are specified, /N will be ignored");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The parameter file path is optional. " +
"If included, it should point to a valid XML parameter file."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /S to process all valid files in the input directory and subdirectories. " +
"Include a number after /S (like /S:2) to limit the level of subdirectories to examine. " +
"When using /S, you can redirect the output of the results using /A. " +
"When using /S, you can use /R to re-create the input directory hierarchy in the alternate output directory (if defined)."));
Console.WriteLine("Use /L to log messages to a file.");
Console.WriteLine();
Console.WriteLine("Program written by Matthew Monroe for the Department of Energy (PNNL, Richland, WA) in 2010");
Console.WriteLine("Version: " + GetAppVersion());
Console.WriteLine();
Console.WriteLine("E-mail: [email protected] or [email protected]");
Console.WriteLine("Website: https://omics.pnl.gov/ or https://panomics.pnnl.gov/");
Console.WriteLine();
// Delay for 750 msec in case the user double clicked this file from within Windows Explorer (or started the program via a shortcut)
Thread.Sleep(750);
}
catch (Exception ex)
{
Console.WriteLine("Error displaying the program syntax: " + ex.Message);
}
}
private static void ShowSyntax(string errorMessage = "")
{
Console.WriteLine();
if (!string.IsNullOrWhiteSpace(errorMessage))
{
ConsoleMsgUtils.ShowErrorCustom("Error: " + errorMessage, false);
Console.WriteLine();
}
var exeName = Path.GetFileName(ProcessFilesOrDirectoriesBase.GetAppPath());
ConsoleWriteWrapped("This program implements a protein parsimony algorithm for grouping proteins with similar peptides.");
Console.WriteLine();
Console.WriteLine("Program syntax #1:");
Console.WriteLine(exeName + " InputFilePath.txt [OutputFilePath]");
Console.WriteLine();
ConsoleWriteWrapped("The input file is a tab delimited text file with columns Protein and Peptide " +
"(column order does not matter; extra columns are ignored)");
Console.WriteLine();
ConsoleWriteWrapped("If the output file path is not defined, it will be created in the same location " +
"as the input file, but with '_parsimony' added to the filename");
Console.WriteLine();
Console.WriteLine("Program syntax #2:");
Console.WriteLine(exeName + " SQLiteDatabase.db3 [TableName]");
Console.WriteLine();
ConsoleWriteWrapped("If the input is a SQLite database file (extension .db, .db3, .sqlite, or\a.sqlite3), " +
"proteins and peptides will be read from the specified table, or\afrom " +
"T_Row_Metadata if TableName is not provided. The table must have columns " +
"Protein and Peptide. Results will be written to tables " +
Runner.PARSIMONY_GROUPING_TABLE + " and " + Runner.PARSIMONY_GROUP_MEMBERS_TABLE);
Console.WriteLine();
Console.WriteLine("Program written by Josh Aldrich for the Department of Energy (PNNL, Richland, WA)");
Console.WriteLine("Version: " + ProcessFilesOrDirectoriesBase.GetAppVersion(PROGRAM_DATE));
Console.WriteLine();
Console.WriteLine("E-mail: [email protected]");
Console.WriteLine("Website: https://github.com/PNNL-Comp-Mass-Spec/ or https://panomics.pnnl.gov/ or https://www.pnnl.gov/integrative-omics or ");
Console.WriteLine(" https://github.com/PNNL-Comp-Mass-Spec");
}
private static void ShowProgramHelp()
{
try
{
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"This program merges the contents of a tab-delimited peptide hit results file " +
"(e.g. from X!Tandem or MS-GF+) with the corresponding MASIC results files, " +
"appending the relevant MASIC stats for each peptide hit result, " +
"writing the merged data to a new tab-delimited text file."));
Console.WriteLine();
Console.WriteLine("It also supports TSV files, e.g. as created by the MzidToTsvConverter");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"If the input directory includes a MASIC _ReporterIons.txt file, " +
"the reporter ion intensities will also be included in the new text file."));
Console.WriteLine();
Console.WriteLine("Program syntax:"
+ Environment.NewLine + Path.GetFileName(ProcessFilesOrDirectoriesBase.GetAppPath()));
Console.WriteLine(" InputFilePathSpec [/M:MASICResultsDirectoryPath] [/O:OutputDirectoryPath]");
Console.WriteLine(" [/N:ScanNumberColumn] [/C] [/Mage] [/Append]");
Console.WriteLine(" [/DartID]");
Console.WriteLine(" [/S:[MaxLevel]] [/A:AlternateOutputDirectoryPath] [/R]");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The input file should be a tab-delimited file where one column has scan numbers. " +
"By default, this program assumes the second column has scan number, but the " +
"/N switch can be used to change this (see below)."));
Console.WriteLine();
Console.WriteLine("Common input files are:");
Console.WriteLine("- Peptide Hit Results Processor (https://github.com/PNNL-Comp-Mass-Spec/PHRP) tab-delimited files");
Console.WriteLine(" - MS-GF+ syn/fht file (_msgfplus_syn.txt or _msgfplus_fht.txt)");
Console.WriteLine(" - SEQUEST Synopsis or First-Hits file (_syn.txt or _fht.txt)");
Console.WriteLine(" - XTandem _xt.txt file");
Console.WriteLine("- MzidToTSVConverter (https://github.com/PNNL-Comp-Mass-Spec/Mzid-To-Tsv-Converter) .TSV files");
Console.WriteLine(" - This is a tab-delimited text file created from a .mzid file (e.g. from MS-GF+)");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"If the MASIC result files are not in the same directory as the input file, " +
"use /M to define the path to the correct directory."));
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The output directory switch is optional. " +
"If omitted, the output file will be created in the same directory as the input file"));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /N to change the column number that contains scan number in the input file. " +
"The default is 2 (meaning /N:2)."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"When reading data with _ReporterIons.txt files, you can use /C to specify " +
"that a separate output file be created for each collision mode type " + "in the input file (typically PQD, CID, and ETD)."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /Mage to specify that the input file is a results file from Mage Extractor. " +
"This file will contain results from several analysis jobs; the first column " +
"in this file must be Job and the remaining columns must be the standard " +
"Synopsis or First-Hits columns supported by PHRPReader. " +
"In addition, the input directory must have a file named InputFile_metadata.txt " +
"(this file will have been auto-created by Mage Extractor)."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /Append to merge results from multiple datasets together as a single file; " +
"this is only applicable when the InputFilePathSpec includes a * wildcard and multiple files are matched. " +
"The merged results file will have DatasetID values of 1, 2, 3, etc. " +
"along with a second file mapping DatasetID to Dataset Name"));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /DartID to only list each peptide once per scan. " +
"The Protein column will list the first protein, while the " +
"Proteins column will be a comma separated list of all of the proteins. " +
"This format is compatible with DART-ID (https://www.ncbi.nlm.nih.gov/pubmed/31260443)"));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /S to process all valid files in the input directory and subdirectories. " +
"Include a number after /S (like /S:2) to limit the level of subdirectories to examine. " +
"When using /S, you can redirect the output of the results using /A to specify an alternate output directory. " +
"When using /S, you can use /R to re-create the input directory hierarchy in the alternate output directory (if defined)."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Program written by Matthew Monroe for the Department of Energy (PNNL, Richland, WA) in 2008; updated in 2019"));
Console.WriteLine("Version: " + GetAppVersion());
Console.WriteLine();
Console.WriteLine("E-mail: [email protected] or [email protected]");
Console.WriteLine("Website: https://omics.pnl.gov/ or https://panomics.pnnl.gov/");
Console.WriteLine();
// Delay for 750 msec in case the user double clicked this file from within Windows Explorer (or started the program via a shortcut)
System.Threading.Thread.Sleep(750);
}
catch (Exception ex)
{
ShowErrorMessage("Error displaying the program syntax: " + ex.Message);
}
}
private static void Main(string[] args)
{
try
{
if (args.Length == 0)
{
var exePath = ProcessFilesOrDirectoriesBase.GetAppPath();
Console.WriteLine("WriteFaimsXMLFromRawFile version " + GetAppVersion());
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"This program converts a Thermo .raw file with FAIMS scans into a series of .mzXML files, " +
"creating one .mzXML file for each FAIMS compensation voltage (CV) value in the .raw file."));
Console.WriteLine();
Console.WriteLine("Syntax:");
Console.WriteLine("{0} InstrumentFile.raw [Output_Directory_Path]", Path.GetFileName(exePath));
Console.WriteLine();
Console.WriteLine("Wild cards are supported, e.g. *.raw");
Console.WriteLine();
// ReSharper disable StringLiteralTypo
Console.WriteLine("Program written by Dain Brademan for the Joshua Coon Research Group (University of Wisconsin) in 2018");
Console.WriteLine("Converted to use ThermoFisher.CommonCore DLLs by Matthew Monroe for PNNL (Richland, WA) in 2020");
Console.WriteLine("E-mail: [email protected] or [email protected] or [email protected]");
Console.WriteLine("Website: https://github.com/PNNL-Comp-Mass-Spec/FAIMS-MzXML-Generator/releases or");
Console.WriteLine(" https://github.com/coongroup/FAIMS-MzXML-Generator");
// ReSharper restore StringLiteralTypo
return;
}
var inputFilePathSpec = args[0];
string outputDirectoryPath;
if (args.Length > 1)
{
outputDirectoryPath = args[1];
}
else
{
outputDirectoryPath = string.Empty;
}
var processor = new FAIMStoMzXMLProcessor();
RegisterEvents(processor);
processor.QuickCVLookup = false;
var success = processor.ProcessFiles(inputFilePathSpec, outputDirectoryPath);
if (success)
{
Console.WriteLine("Processing completed");
}
System.Threading.Thread.Sleep(750);
}
catch (Exception ex)
{
ConsoleMsgUtils.ShowError("Error in Program.Main", ex);
}
}
private static void ShowProgramHelp()
{
try
{
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"This program reads in a .fasta or .txt file containing protein names and sequences (and optionally descriptions). " +
"The program also reads in a .txt file containing peptide sequences and protein names (though protein name is optional) " +
"then uses this information to compute the sequence coverage percent for each protein."));
Console.WriteLine();
Console.WriteLine("Program syntax:" + Environment.NewLine + Path.GetFileName(ProcessFilesOrDirectoriesBase.GetAppPath()));
Console.WriteLine(" /I:PeptideInputFilePath /R:ProteinInputFilePath [/O:OutputDirectoryName]");
Console.WriteLine(" [/P:ParameterFilePath] [/G] [/H] [/M] [/K] [/Debug] [/KeepDB]");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The input file path can contain the wildcard character *. If a wildcard is present, the same protein input file path " +
"will be used for each of the peptide input files matched."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The output directory name is optional. If omitted, the output files will be created in the same directory as the input file. " +
"If included, a subdirectory is created with the name OutputDirectoryName."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The parameter file path is optional. If included, it should point to a valid XML parameter file."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /G to ignore I/L differences when finding peptides in proteins or computing coverage."));
Console.WriteLine("Use /H to suppress (hide) the protein sequence in the _coverage.txt file.");
Console.WriteLine("Use /M to enable the creation of a protein to peptide mapping file.");
Console.WriteLine("Use /K to skip protein coverage computation steps");
Console.WriteLine();
Console.WriteLine("Use /Debug to keep the console open to see additional debug messages");
Console.WriteLine("Use /KeepDB to keep the SQLite database after processing (by default it is deleted)");
Console.WriteLine();
Console.WriteLine("Program written by Matthew Monroe and Nikša Blonder for the Department of Energy (PNNL, Richland, WA) in 2005");
Console.WriteLine("Version: " + GetAppVersion());
Console.WriteLine();
Console.WriteLine("E-mail: [email protected] or [email protected]");
Console.WriteLine("Website: https://omics.pnl.gov or https://panomics.pnl.gov/");
Console.WriteLine();
}
catch (Exception ex)
{
ShowErrorMessage("Error displaying the program syntax: " + ex.Message);
}
}
private static int Main(string[] args)
{
var exeName = System.Reflection.Assembly.GetEntryAssembly()?.GetName().Name;
var exePath = ProcessFilesOrDirectoriesBase.GetAppPath();
var cmdLineParser = new CommandLineParser <ThermoFAIMStoMzMLOptions>(exeName, GetAppVersion())
{
ProgramInfo = "This program converts a Thermo .raw file with FAIMS scans into a series of .mzML files, " +
"creating one .mzML file for each FAIMS compensation voltage (CV) value in the .raw file",
ContactInfo = "Program written by Matthew Monroe for PNNL (Richland, WA) in 2020" + Environment.NewLine +
"E-mail: [email protected] or [email protected]" + Environment.NewLine +
"Website: https://omics.pnl.gov/ or https://panomics.pnnl.gov/"
};
// Allow /Conf in addition to /ParamFile for specifying a text file with Key=Value options
cmdLineParser.AddParamFileKey("Conf");
cmdLineParser.UsageExamples.Add("Program syntax:" + Environment.NewLine + Path.GetFileName(exePath) + " " +
"/I:InputFileNameOrDirectoryPath [/O:OutputDirectoryName] " + Environment.NewLine +
"[/S] [/R:LevelsToRecurse] [/Preview] " + Environment.NewLine +
"[/IE] [/L] [/LogFile:LogFileName]");
var result = cmdLineParser.ParseArgs(args);
var options = result.ParsedResults;
if (!result.Success || !options.Validate())
{
// Delay for 750 msec in case the user double clicked this file from within Windows Explorer (or started the program via a shortcut)
System.Threading.Thread.Sleep(750);
return(-1);
}
try
{
var processor = new ThermoFAIMStoMzMLProcessor(options);
processor.DebugEvent += Processor_DebugEvent;
processor.ErrorEvent += Processor_ErrorEvent;
processor.WarningEvent += Processor_WarningEvent;
processor.StatusEvent += Processor_MessageEvent;
processor.ProgressUpdate += Processor_ProgressUpdate;
bool success;
if (options.RecurseDirectories)
{
success = processor.ProcessFilesAndRecurseDirectories(
options.InputDataFilePath,
options.OutputDirectoryPath,
options.MaxLevelsToRecurse);
}
else
{
success = processor.ProcessFilesWildcard(
options.InputDataFilePath,
options.OutputDirectoryPath);
}
if (success)
{
return(0);
}
return(-1);
}
catch (Exception ex)
{
ShowErrorMessage("Error occurred in modMain->Main", ex);
return(-1);
}
}
private static void ShowProgramHelp()
{
try
{
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"This program will read a Thermo .RAW file, .mzML file, .mzXML file, or Agilent LC/MSD .CDF/.MGF file combo " +
"and create a selected ion chromatogram (SIC) for each parent ion. " +
"It also supports extracting reporter ion intensities (e.g. iTRAQ or TMT), " +
"and additional metadata from mass spectrometer data files."));
Console.WriteLine();
Console.WriteLine("Program syntax:" + Environment.NewLine + Path.GetFileName(ProcessFilesOrDirectoriesBase.GetAppPath()));
Console.WriteLine(" /I:InputFilePath.raw [/O:OutputDirectoryPath]");
Console.WriteLine(" [/P:ParamFilePath] [/D:DatasetID or DatasetLookupFilePath] ");
Console.WriteLine(" [/S:[MaxLevel]] [/A:AlternateOutputDirectoryPath] [/R]");
Console.WriteLine(" [/L:[LogFilePath]] [/LogDir:LogDirPath] [/SF:StatusFileName] [/Q]");
Console.WriteLine();
Console.WriteLine("The input file path can contain the wildcard character *");
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The output directory name is optional. " +
"If omitted, the output files will be created in the same directory as the input file. " +
"If included, then a subdirectory is created with the name OutputDirectoryName."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The parameter file switch /P is optional. " +
"If supplied, it should point to a valid MASIC XML parameter file. If omitted, defaults are used."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"The /D switch can be used to specify the Dataset ID of the input file; if omitted, 0 will be used"));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Alternatively, a lookup file can be specified with the /D switch (useful if processing multiple files using * or /S). " +
"The lookup file is a comma, space, or tab delimited file with two columns:" + Environment.NewLine + "Dataset Name and Dataset ID"));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /S to process all valid files in the input directory and subdirectories. " +
"Include a number after /S (like /S:2) to limit the level of subdirectories to examine."));
Console.WriteLine("When using /S, you can redirect the output of the results using /A.");
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"When using /S, you can use /R to re-create the input directory hierarchy in the alternate output directory (if defined)."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /L or /Log to specify that a log file should be created. " +
"Use /L:LogFilePath to specify the name (or full path) for the log file."));
Console.WriteLine();
Console.WriteLine(ConsoleMsgUtils.WrapParagraph(
"Use /SF to specify the name to use for the Masic Status file (default is " + clsMASICOptions.DEFAULT_MASIC_STATUS_FILE_NAME + ")."));
Console.WriteLine();
Console.WriteLine("The optional /Q switch will prevent the progress window from being shown");
Console.WriteLine();
Console.WriteLine("Program written by Matthew Monroe for the Department of Energy (PNNL, Richland, WA) in 2003");
Console.WriteLine("Version: " + GetAppVersion());
Console.WriteLine();
Console.WriteLine("E-mail: [email protected] or [email protected]");
Console.WriteLine("Website: https://omics.pnl.gov/ or https://panomics.pnnl.gov/");
Console.WriteLine();
// Delay for 750 msec in case the user double clicked this file from within Windows Explorer (or started the program via a shortcut)
Thread.Sleep(750);
}
catch (Exception ex)
{
ShowErrorMessage("Error displaying the program syntax: " + ex.Message);
}
}