private static Database databaseSetUp(String fasta_file_name)
{
FastaFile f = Loader.parseFasta(fasta_file_name);
DigestedFastaFile df = PerformDigestion.performDigest(f, GlobalVar.NUM_MISSED_CLEAVAGES);
int numberOfProteinsInFasta = f.getAccessionToFullSequence().Count;
int numberOfPeptidesInDigestedFasta = df.getDigestedPeptideArray().Count;
log.Info("Fasta file: " + fasta_file_name);
log.Info("Num missed cleavages: " + GlobalVar.NUM_MISSED_CLEAVAGES);
log.Info("Number of proteins: " + numberOfProteinsInFasta);
log.Info("Number of peptides: " + numberOfPeptidesInDigestedFasta);
log.Debug("Constructing graph...");
Database g;
if (GlobalVar.isSimulationForFeatureExtraction == true)
{
g = new Database(f, df, true, false);
}
else
{
g = new Database(f, df, true, true);
}
log.Debug(g);
return(g);
}
//depricated
public static String GenerateConcacenatedDecoyFasta_MimicCometInternal(String fastaFile, String outputFilePath)
{
StreamWriter sw = new StreamWriter(outputFilePath);
DigestedFastaFile df = PerformDigestion.performDigest(fastaFile, GlobalVar.NUM_MISSED_CLEAVAGES, false);
List <DigestedPeptide> targetSequences = df.getDigestedPeptideArray();
String line;
foreach (DigestedPeptide targetSeq in targetSequences)
{
//write the target sequence
line = ">" + targetSeq.getAccession();
sw.WriteLine(line);
line = targetSeq.getSequence();
sw.WriteLine(line);
//write the decoy sequence
line = ">" + GlobalVar.DecoyPrefix + targetSeq.getAccession();
sw.WriteLine(line);
line = ReverseSequence_keepCTerm(targetSeq.getSequence());
sw.WriteLine(line);
}
sw.Close();
return(outputFilePath);
}
public static DigestedFastaFile performDigest(String fastaFilePath, int numMissedCleavages, Boolean keepFile)
{
if (GlobalVar.useChainsawComputedFile)
{
return(Loader.parseDigestedFasta(InputFileOrganizer.ChainSawResult));
}
// These are the output file paths
String outputTSVFile = fastaFilePath + "_digestedPeptides.tsv";
String outputIndexFile = fastaFilePath + ".index";
/* Peptide chainsaw parameters */
String chainsaw = InputFileOrganizer.ChainSaw; // tool location
//String enzyme = "Trypsin/P";
String enzyme = "Trypsin";
String specificity = "fully";
int minimumPeptideLength = GlobalVar.MinimumPeptideLength;
int maximumPeptideLength = 200;
// minimum and maximum peptide length is what typically is analyzed well by the
// mass spectrometer
// This is the chainsaw command to be run on the terminal
String chainsawCommand = chainsaw + " -c " + enzyme + " -s " + specificity + " -m " + minimumPeptideLength
+ " -M " + maximumPeptideLength + " -n " + numMissedCleavages + " " + fastaFilePath;
log.Info("Digesting database using ChainSaw");
// perform in-silico digestion
String chainsawOutput = ExecuteShellCommand.executeCommand(chainsawCommand);
log.Info(chainsawCommand);
log.Debug(chainsawOutput);
// parse new tsv file
DigestedFastaFile df = Loader.parseDigestedFasta(outputTSVFile);
// this tool automatically outputs file in the same folder as the input database, move file to output folder,
if (keepFile)
{
ExecuteShellCommand.executeCommand("move " + outputTSVFile + " " + InputFileOrganizer.preExperimentFilesFolder);
InputFileOrganizer.ChainSawResult = InputFileOrganizer.preExperimentFilesFolder + "\\" + IOUtils.getBaseName(outputTSVFile);
}
else
{
ExecuteShellCommand.executeCommand("rm " + outputTSVFile);
}
//ExecuteShellCommand.executeCommand("rm " + outputIndexFile);
return(df);
}
public Database(FastaFile fastaFile, DigestedFastaFile digestedFastaFile, bool _includeCarbamidoModification,
bool _includeRetentionTime, double _retentionTimeWindow)
{
includeCarbamidoModification = _includeCarbamidoModification;
includeRetentionTime = _includeRetentionTime;
retentionTimeWindow = _retentionTimeWindow;
log.Debug("Constructing graph...");
SequenceToPeptide = new Dictionary <String, Peptide>();
peptides = new List <Peptide>();
AccesstionToProtein = fastaFile.getAccessionToFullSequence();
addPeptides(digestedFastaFile.getDigestedPeptideArray());
log.Debug("Done constructing graph.");
}
public static Database loadExclusionDatabase(FastaFile fasta, DigestedFastaFile digestedFasta)
{
return(new Database(fasta, digestedFasta));
}
public Database(FastaFile fastaFile, DigestedFastaFile digestedFastaFile, bool _includeCarbamidoModification,
bool _includeRetentionTime) : this(fastaFile, digestedFastaFile, _includeCarbamidoModification, _includeRetentionTime,
DEFAULT_RETENTION_TIME_WINDOW)
{
}
public Database(FastaFile fastaFile, DigestedFastaFile digestedFastaFile) :
this(fastaFile, digestedFastaFile, DEFAULT_INCLUDE_CARBAMIDO_MODIFICATION, DEFAULT_INCLUDE_RETENTION_TIME)
{
}
