List of usage examples for org.apache.commons.io FilenameUtils getFullPath
public static String getFullPath(String filename)
From source file:DIA_Umpire_Quant.DIA_Umpire_LCMSIDGen.java
/** * @param args the command line arguments */// w w w .jav a 2 s . c o m public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println("DIA-Umpire LCMSID geneartor (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length != 1) { System.out.println( "command format error, the correct format should be: java -jar -Xmx10G DIA_Umpire_LCMSIDGen.jar diaumpire_module.params"); return; } try { ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_lcmsidgen.log"); } catch (Exception e) { } Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + args[0]); BufferedReader reader = new BufferedReader(new FileReader(args[0])); String line = ""; String WorkFolder = ""; int NoCPUs = 2; TandemParam tandemPara = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); HashMap<String, File> AssignFiles = new HashMap<>(); //<editor-fold defaultstate="collapsed" desc="Reading parameter file"> while ((line = reader.readLine()) != null) { line = line.trim(); Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==File list begin")) { do { line = reader.readLine(); line = line.trim(); if (line.equals("==File list end")) { continue; } else if (!"".equals(line)) { File newfile = new File(line); if (newfile.exists()) { AssignFiles.put(newfile.getAbsolutePath(), newfile); } else { Logger.getRootLogger().info("File: " + newfile + " does not exist."); } } } while (!line.equals("==File list end")); } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); String value = line.split("=")[1].trim(); switch (type) { case "Path": { WorkFolder = value; break; } case "path": { WorkFolder = value; break; } case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "DecoyPrefix": { if (!"".equals(value)) { tandemPara.DecoyPrefix = value; } break; } case "PeptideFDR": { tandemPara.PepFDR = Float.parseFloat(value); break; } } } } //</editor-fold> //Initialize PTM manager using compomics library PTMManager.GetInstance(); //Generate DIA file list ArrayList<DIAPack> FileList = new ArrayList<>(); File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("The path : " + WorkFolder + " cannot be found."); System.exit(1); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && (fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && (fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); } //process each DIA file to genearate untargeted identifications for (File fileEntry : AssignFiles.values()) { String mzXMLFile = fileEntry.getAbsolutePath(); if (mzXMLFile.toLowerCase().endsWith(".mzxml") | mzXMLFile.toLowerCase().endsWith(".mzml")) { long time = System.currentTimeMillis(); DIAPack DiaFile = new DIAPack(mzXMLFile, NoCPUs); FileList.add(DiaFile); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + mzXMLFile); if (!DiaFile.LoadDIASetting()) { Logger.getRootLogger().info("Loading DIA setting failed, job is incomplete"); System.exit(1); } if (!DiaFile.LoadParams()) { Logger.getRootLogger().info("Loading parameters failed, job is incomplete"); System.exit(1); } Logger.getRootLogger().info("Loading identification results " + mzXMLFile + "...."); DiaFile.ParsePepXML(tandemPara, null); DiaFile.BuildStructure(); if (!DiaFile.MS1FeatureMap.ReadPeakCluster()) { Logger.getRootLogger().info("Loading peak and structure failed, job is incomplete"); System.exit(1); } DiaFile.MS1FeatureMap.ClearMonoisotopicPeakOfCluster(); //Generate mapping between index of precursor feature and pseudo MS/MS scan index DiaFile.GenerateClusterScanNomapping(); //Doing quantification DiaFile.AssignQuant(); DiaFile.ClearStructure(); DiaFile.IDsummary.ReduceMemoryUsage(); time = System.currentTimeMillis() - time; Logger.getRootLogger().info(mzXMLFile + " processed time:" + String.format("%d hour, %d min, %d sec", TimeUnit.MILLISECONDS.toHours(time), TimeUnit.MILLISECONDS.toMinutes(time) - TimeUnit.HOURS.toMinutes(TimeUnit.MILLISECONDS.toHours(time)), TimeUnit.MILLISECONDS.toSeconds(time) - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(time)))); } Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); } }
From source file:DIA_Umpire_To_Skyline.DIA_Umpire_To_Skyline.java
/** * @param args the command line arguments *//* ww w. jav a2s . c om*/ public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println("DIA-Umpire_To_Skyline (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length < 1) { System.out.println( "command format error, it should be like: java -jar -Xmx20G DIA_Umpire_To_Skyline.jar Path NoThreads"); System.out.println("command : java -jar -Xmx20G DIA_Umpire_To_Skyline.jar Path [Option]\n"); System.out.println("\nOptions"); System.out.println("\t-t\tNo. of threads, Ex: -t4 (using four threads, default value)"); System.out.println( "\t-cP\tPath of msconvert.exe for mzXML conversion, Ex: -cP (using four threads, default value)"); return; } try { ConsoleLogger.SetConsoleLogger(Level.DEBUG); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_to_skyline.log"); } catch (Exception e) { System.out.println("Logger initialization failed"); } Logger.getRootLogger().info("Path:" + args[0]); String msconvertpath = "C:/inetpub/tpp-bin/msconvert"; String WorkFolder = args[0]; int NoCPUs = 4; for (int i = 1; i < args.length; i++) { if (args[i].startsWith("-")) { if (args[i].startsWith("-cP")) { msconvertpath = args[i].substring(3); Logger.getRootLogger().info("MSConvert path: " + msconvertpath); } if (args[i].startsWith("-t")) { NoCPUs = Integer.parseInt(args[i].substring(2)); Logger.getRootLogger().info("No. of threads: " + NoCPUs); } } } HashMap<String, File> AssignFiles = new HashMap<>(); try { File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("Path: " + folder.getAbsolutePath() + " cannot be found."); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); } ExecutorService executorPool = null; executorPool = Executors.newFixedThreadPool(3); for (File fileEntry : AssignFiles.values()) { String mzXMLFile = fileEntry.getAbsolutePath(); FileThread thread = new FileThread(mzXMLFile, NoCPUs, msconvertpath); executorPool.execute(thread); } executorPool.shutdown(); try { executorPool.awaitTermination(Long.MAX_VALUE, TimeUnit.NANOSECONDS); } catch (InterruptedException e) { Logger.getRootLogger().info("interrupted.."); } } catch (Exception e) { Logger.getRootLogger().error(e.getMessage()); throw e; } Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); }
From source file:DIA_Umpire_Quant.DIA_Umpire_ExtLibSearch.java
/** * @param args the command line arguments *//*from ww w . j a va 2s .c o m*/ public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println("DIA-Umpire targeted re-extraction analysis using external library (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length != 1) { System.out.println( "command format error, the correct format should be: java -jar -Xmx10G DIA_Umpire_ExtLibSearch.jar diaumpire_module.params"); return; } try { ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_extlibsearch.log"); } catch (Exception e) { } Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + args[0]); BufferedReader reader = new BufferedReader(new FileReader(args[0])); String line = ""; String WorkFolder = ""; int NoCPUs = 2; String ExternalLibPath = ""; String ExternalLibDecoyTag = "DECOY"; float ExtProbThreshold = 0.99f; float RTWindow_Ext = -1f; TandemParam tandemPara = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); HashMap<String, File> AssignFiles = new HashMap<>(); //<editor-fold defaultstate="collapsed" desc="Reading parameter file"> while ((line = reader.readLine()) != null) { line = line.trim(); Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==File list begin")) { do { line = reader.readLine(); line = line.trim(); if (line.equals("==File list end")) { continue; } else if (!"".equals(line)) { File newfile = new File(line); if (newfile.exists()) { AssignFiles.put(newfile.getAbsolutePath(), newfile); } else { Logger.getRootLogger().info("File: " + newfile + " does not exist."); } } } while (!line.equals("==File list end")); } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); String value = line.split("=")[1].trim(); switch (type) { case "Path": { WorkFolder = value; break; } case "path": { WorkFolder = value; break; } case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "Fasta": { tandemPara.FastaPath = value; break; } case "DecoyPrefix": { if (!"".equals(value)) { tandemPara.DecoyPrefix = value; } break; } case "ExternalLibPath": { ExternalLibPath = value; break; } case "ExtProbThreshold": { ExtProbThreshold = Float.parseFloat(value); break; } case "RTWindow_Ext": { RTWindow_Ext = Float.parseFloat(value); break; } case "ExternalLibDecoyTag": { ExternalLibDecoyTag = value; if (ExternalLibDecoyTag.endsWith("_")) { ExternalLibDecoyTag = ExternalLibDecoyTag.substring(0, ExternalLibDecoyTag.length() - 1); } break; } } } } //</editor-fold> //Initialize PTM manager using compomics library PTMManager.GetInstance(); //Check if the fasta file can be found if (!new File(tandemPara.FastaPath).exists()) { Logger.getRootLogger().info("Fasta file :" + tandemPara.FastaPath + " cannot be found, the process will be terminated, please check."); System.exit(1); } //Generate DIA file list ArrayList<DIAPack> FileList = new ArrayList<>(); File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("The path : " + WorkFolder + " cannot be found."); System.exit(1); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && (fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && (fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); } for (File fileEntry : AssignFiles.values()) { String mzXMLFile = fileEntry.getAbsolutePath(); if (mzXMLFile.toLowerCase().endsWith(".mzxml") | mzXMLFile.toLowerCase().endsWith(".mzml")) { DIAPack DiaFile = new DIAPack(mzXMLFile, NoCPUs); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + mzXMLFile); if (!DiaFile.LoadDIASetting()) { Logger.getRootLogger().info("Loading DIA setting failed, job is incomplete"); System.exit(1); } if (!DiaFile.LoadParams()) { Logger.getRootLogger().info("Loading parameters failed, job is incomplete"); System.exit(1); } Logger.getRootLogger().info("Loading identification results " + mzXMLFile + "...."); //If the serialization file for ID file existed if (DiaFile.ReadSerializedLCMSID()) { DiaFile.IDsummary.ReduceMemoryUsage(); DiaFile.IDsummary.FastaPath = tandemPara.FastaPath; FileList.add(DiaFile); } } } //<editor-fold defaultstate="collapsed" desc="Targeted re-extraction using external library"> //External library search Logger.getRootLogger().info("Targeted extraction using external library"); //Read exteranl library FragmentLibManager ExlibManager = FragmentLibManager.ReadFragmentLibSerialization(WorkFolder, FilenameUtils.getBaseName(ExternalLibPath)); if (ExlibManager == null) { ExlibManager = new FragmentLibManager(FilenameUtils.getBaseName(ExternalLibPath)); //Import traML file ExlibManager.ImportFragLibByTraML(ExternalLibPath, ExternalLibDecoyTag); //Check if there are decoy spectra ExlibManager.CheckDecoys(); //ExlibManager.ImportFragLibBySPTXT(ExternalLibPath); ExlibManager.WriteFragmentLibSerialization(WorkFolder); } Logger.getRootLogger() .info("No. of peptide ions in external lib:" + ExlibManager.PeptideFragmentLib.size()); for (DIAPack diafile : FileList) { if (diafile.IDsummary == null) { diafile.ReadSerializedLCMSID(); } //Generate RT mapping RTMappingExtLib RTmap = new RTMappingExtLib(diafile.IDsummary, ExlibManager, diafile.GetParameter()); RTmap.GenerateModel(); RTmap.GenerateMappedPepIon(); diafile.BuildStructure(); diafile.MS1FeatureMap.ReadPeakCluster(); diafile.GenerateMassCalibrationRTMap(); //Perform targeted re-extraction diafile.TargetedExtractionQuant(false, ExlibManager, ExtProbThreshold, RTWindow_Ext); diafile.MS1FeatureMap.ClearAllPeaks(); diafile.IDsummary.ReduceMemoryUsage(); //Remove target IDs below the defined probability threshold diafile.IDsummary.RemoveLowProbMappedIon(ExtProbThreshold); diafile.ExportID(); diafile.ClearStructure(); Logger.getRootLogger().info("Peptide ions: " + diafile.IDsummary.GetPepIonList().size() + " Mapped ions: " + diafile.IDsummary.GetMappedPepIonList().size()); } //</editor-fold> Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); }
From source file:DIA_Umpire_Quant.DIA_Umpire_IntLibSearch.java
/** * @param args the command line arguments *//*from w w w. j a v a 2 s . c om*/ public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println("DIA-Umpire targeted re-extraction analysis using internal library (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length != 1) { System.out.println( "command format error, the correct format should be : java -jar -Xmx10G DIA_Umpire_IntLibSearch.jar diaumpire_module.params"); return; } try { ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_intlibsearch.log"); } catch (Exception e) { } Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + args[0]); BufferedReader reader = new BufferedReader(new FileReader(args[0])); String line = ""; String WorkFolder = ""; int NoCPUs = 2; String InternalLibID = ""; float ProbThreshold = 0.99f; float RTWindow_Int = -1f; float Freq = 0f; int TopNFrag = 6; TandemParam tandemPara = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); HashMap<String, File> AssignFiles = new HashMap<>(); //<editor-fold defaultstate="collapsed" desc="Reading parameter file"> while ((line = reader.readLine()) != null) { line = line.trim(); Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==File list begin")) { do { line = reader.readLine(); line = line.trim(); if (line.equals("==File list end")) { continue; } else if (!"".equals(line)) { File newfile = new File(line); if (newfile.exists()) { AssignFiles.put(newfile.getAbsolutePath(), newfile); } else { Logger.getRootLogger().info("File: " + newfile + " does not exist."); } } } while (!line.equals("==File list end")); } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); String value = line.split("=")[1].trim(); switch (type) { case "Path": { WorkFolder = value; break; } case "path": { WorkFolder = value; break; } case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "InternalLibID": { InternalLibID = value; break; } case "RTWindow_Int": { RTWindow_Int = Float.parseFloat(value); break; } case "ProbThreshold": { ProbThreshold = Float.parseFloat(value); break; } case "TopNFrag": { TopNFrag = Integer.parseInt(value); break; } case "Freq": { Freq = Float.parseFloat(value); break; } case "Fasta": { tandemPara.FastaPath = value; break; } } } } //</editor-fold> //Initialize PTM manager using compomics library PTMManager.GetInstance(); //Check if the fasta file can be found if (!new File(tandemPara.FastaPath).exists()) { Logger.getRootLogger().info("Fasta file :" + tandemPara.FastaPath + " cannot be found, the process will be terminated, please check."); System.exit(1); } //Generate DIA file list ArrayList<DIAPack> FileList = new ArrayList<>(); try { File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("The path : " + WorkFolder + " cannot be found."); System.exit(1); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && (fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && (fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); } for (File fileEntry : AssignFiles.values()) { String mzXMLFile = fileEntry.getAbsolutePath(); if (mzXMLFile.toLowerCase().endsWith(".mzxml") | mzXMLFile.toLowerCase().endsWith(".mzml")) { DIAPack DiaFile = new DIAPack(mzXMLFile, NoCPUs); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + mzXMLFile); if (!DiaFile.LoadDIASetting()) { Logger.getRootLogger().info("Loading DIA setting failed, job is incomplete"); System.exit(1); } if (!DiaFile.LoadParams()) { Logger.getRootLogger().info("Loading parameters failed, job is incomplete"); System.exit(1); } Logger.getRootLogger().info("Loading identification results " + mzXMLFile + "...."); //If the serialization file for ID file existed if (DiaFile.ReadSerializedLCMSID()) { DiaFile.IDsummary.ReduceMemoryUsage(); DiaFile.IDsummary.FastaPath = tandemPara.FastaPath; FileList.add(DiaFile); } } } //<editor-fold defaultstate="collapsed" desc="Targete re-extraction using internal library"> Logger.getRootLogger().info( "================================================================================================="); if (FileList.size() > 1) { Logger.getRootLogger().info("Targeted re-extraction using internal library"); FragmentLibManager libManager = FragmentLibManager.ReadFragmentLibSerialization(WorkFolder, InternalLibID); if (libManager == null) { Logger.getRootLogger().info("Building internal spectral library"); libManager = new FragmentLibManager(InternalLibID); ArrayList<LCMSID> LCMSIDList = new ArrayList<>(); for (DIAPack dia : FileList) { LCMSIDList.add(dia.IDsummary); } libManager.ImportFragLibTopFrag(LCMSIDList, Freq, TopNFrag); libManager.WriteFragmentLibSerialization(WorkFolder); } libManager.ReduceMemoryUsage(); Logger.getRootLogger() .info("Building retention time prediction model and generate candidate peptide list"); for (int i = 0; i < FileList.size(); i++) { FileList.get(i).IDsummary.ClearMappedPep(); } for (int i = 0; i < FileList.size(); i++) { for (int j = i + 1; j < FileList.size(); j++) { RTAlignedPepIonMapping alignment = new RTAlignedPepIonMapping(WorkFolder, FileList.get(i).GetParameter(), FileList.get(i).IDsummary, FileList.get(j).IDsummary); alignment.GenerateModel(); alignment.GenerateMappedPepIon(); } FileList.get(i).ExportID(); FileList.get(i).IDsummary = null; } Logger.getRootLogger().info("Targeted matching........"); for (DIAPack diafile : FileList) { if (diafile.IDsummary == null) { diafile.ReadSerializedLCMSID(); } if (!diafile.IDsummary.GetMappedPepIonList().isEmpty()) { diafile.UseMappedIon = true; diafile.FilterMappedIonByProb = false; diafile.BuildStructure(); diafile.MS1FeatureMap.ReadPeakCluster(); diafile.MS1FeatureMap.ClearMonoisotopicPeakOfCluster(); diafile.GenerateMassCalibrationRTMap(); diafile.TargetedExtractionQuant(false, libManager, ProbThreshold, RTWindow_Int); diafile.MS1FeatureMap.ClearAllPeaks(); diafile.IDsummary.ReduceMemoryUsage(); diafile.IDsummary.RemoveLowProbMappedIon(ProbThreshold); diafile.ExportID(); Logger.getRootLogger().info("Peptide ions: " + diafile.IDsummary.GetPepIonList().size() + " Mapped ions: " + diafile.IDsummary.GetMappedPepIonList().size()); diafile.ClearStructure(); } diafile.IDsummary = null; System.gc(); } Logger.getRootLogger().info( "================================================================================================="); } //</editor-fold> Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:DIA_Umpire_SE.DIA_Umpire_SE.java
/** * @param args the command line arguments DIA_Umpire parameterfile *//*from w ww. jav a2 s . c o m*/ public static void main(String[] args) throws InterruptedException, FileNotFoundException, ExecutionException, IOException, ParserConfigurationException, DataFormatException, SAXException, Exception { System.out.println( "================================================================================================="); System.out.println( "DIA-Umpire singal extraction analysis (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length < 2 || args.length > 3) { System.out.println( "command format error, the correct format is: java -jar -Xmx8G DIA_Umpire_SE.jar mzMXL_file diaumpire_se.params"); System.out.println( "To fix DIA setting, use : java -jar -Xmx8G DIA_Umpire_SE.jar mzMXL_file diaumpire_se.params -f"); return; } try { //Define logger level for console ConsoleLogger.SetConsoleLogger(Level.INFO); //Define logger level and file path for text log file ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_se.log"); } catch (Exception e) { } boolean Fix = false; boolean Resume = false; if (args.length == 3 && args[2].equals("-f")) { Fix = true; } String parameterfile = args[1]; String MSFilePath = args[0]; Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + parameterfile); Logger.getRootLogger().info("Spectra file:" + MSFilePath); BufferedReader reader = new BufferedReader(new FileReader(parameterfile)); String line = ""; InstrumentParameter param = new InstrumentParameter(InstrumentParameter.InstrumentType.TOF5600); param.DetermineBGByID = false; param.EstimateBG = true; int NoCPUs = 2; SpectralDataType.DataType dataType = SpectralDataType.DataType.DIA_F_Window; String WindowType = ""; int WindowSize = 25; ArrayList<XYData> WindowList = new ArrayList<>(); boolean ExportPrecursorPeak = false; boolean ExportFragmentPeak = false; //<editor-fold defaultstate="collapsed" desc="Read parameter file"> while ((line = reader.readLine()) != null) { Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==window setting begin")) { while (!(line = reader.readLine()).equals("==window setting end")) { if (!"".equals(line)) { WindowList.add(new XYData(Float.parseFloat(line.split("\t")[0]), Float.parseFloat(line.split("\t")[1]))); } } continue; } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); if (type.startsWith("para.")) { type = type.replace("para.", "SE."); } String value = line.split("=")[1].trim(); switch (type) { case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "ExportPrecursorPeak": { ExportPrecursorPeak = Boolean.parseBoolean(value); break; } case "ExportFragmentPeak": { ExportFragmentPeak = Boolean.parseBoolean(value); break; } //<editor-fold defaultstate="collapsed" desc="instrument parameters"> case "RPmax": { param.PrecursorRank = Integer.parseInt(value); break; } case "RFmax": { param.FragmentRank = Integer.parseInt(value); break; } case "CorrThreshold": { param.CorrThreshold = Float.parseFloat(value); break; } case "DeltaApex": { param.ApexDelta = Float.parseFloat(value); break; } case "RTOverlap": { param.RTOverlapThreshold = Float.parseFloat(value); break; } case "BoostComplementaryIon": { param.BoostComplementaryIon = Boolean.parseBoolean(value); break; } case "AdjustFragIntensity": { param.AdjustFragIntensity = Boolean.parseBoolean(value); break; } case "SE.MS1PPM": { param.MS1PPM = Float.parseFloat(value); break; } case "SE.MS2PPM": { param.MS2PPM = Float.parseFloat(value); break; } case "SE.SN": { param.SNThreshold = Float.parseFloat(value); break; } case "SE.MS2SN": { param.MS2SNThreshold = Float.parseFloat(value); break; } case "SE.MinMSIntensity": { param.MinMSIntensity = Float.parseFloat(value); break; } case "SE.MinMSMSIntensity": { param.MinMSMSIntensity = Float.parseFloat(value); break; } case "SE.MinRTRange": { param.MinRTRange = Float.parseFloat(value); break; } case "SE.MaxNoPeakCluster": { param.MaxNoPeakCluster = Integer.parseInt(value); param.MaxMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinNoPeakCluster": { param.MinNoPeakCluster = Integer.parseInt(value); param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinMS2NoPeakCluster": { param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MaxCurveRTRange": { param.MaxCurveRTRange = Float.parseFloat(value); break; } case "SE.Resolution": { param.Resolution = Integer.parseInt(value); break; } case "SE.RTtol": { param.RTtol = Float.parseFloat(value); break; } case "SE.NoPeakPerMin": { param.NoPeakPerMin = Integer.parseInt(value); break; } case "SE.StartCharge": { param.StartCharge = Integer.parseInt(value); break; } case "SE.EndCharge": { param.EndCharge = Integer.parseInt(value); break; } case "SE.MS2StartCharge": { param.MS2StartCharge = Integer.parseInt(value); break; } case "SE.MS2EndCharge": { param.MS2EndCharge = Integer.parseInt(value); break; } case "SE.NoMissedScan": { param.NoMissedScan = Integer.parseInt(value); break; } case "SE.Denoise": { param.Denoise = Boolean.valueOf(value); break; } case "SE.EstimateBG": { param.EstimateBG = Boolean.valueOf(value); break; } case "SE.RemoveGroupedPeaks": { param.RemoveGroupedPeaks = Boolean.valueOf(value); break; } case "SE.MinFrag": { param.MinFrag = Integer.parseInt(value); break; } case "SE.IsoPattern": { param.IsoPattern = Float.valueOf(value); break; } case "SE.StartRT": { param.startRT = Float.valueOf(value); break; } case "SE.EndRT": { param.endRT = Float.valueOf(value); break; } case "SE.RemoveGroupedPeaksRTOverlap": { param.RemoveGroupedPeaksRTOverlap = Float.valueOf(value); break; } case "SE.RemoveGroupedPeaksCorr": { param.RemoveGroupedPeaksCorr = Float.valueOf(value); break; } case "SE.MinMZ": { param.MinMZ = Float.valueOf(value); break; } case "SE.MinPrecursorMass": { param.MinPrecursorMass = Float.valueOf(value); break; } case "SE.MaxPrecursorMass": { param.MaxPrecursorMass = Float.valueOf(value); break; } case "SE.IsoCorrThreshold": { param.IsoCorrThreshold = Float.valueOf(value); break; } case "SE.MassDefectFilter": { param.MassDefectFilter = Boolean.parseBoolean(value); break; } case "SE.MassDefectOffset": { param.MassDefectOffset = Float.valueOf(value); break; } //</editor-fold>//</editor-fold> case "WindowType": { WindowType = value; switch (WindowType) { case "SWATH": { dataType = SpectralDataType.DataType.DIA_F_Window; break; } case "V_SWATH": { dataType = SpectralDataType.DataType.DIA_V_Window; break; } case "MSX": { dataType = SpectralDataType.DataType.MSX; break; } case "MSE": { dataType = SpectralDataType.DataType.MSe; break; } } break; } case "WindowSize": { WindowSize = Integer.parseInt(value); break; } } } } //</editor-fold> try { File MSFile = new File(MSFilePath); if (MSFile.exists()) { long time = System.currentTimeMillis(); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + MSFilePath + "...."); //Initialize a DIA file data structure DIAPack DiaFile = new DIAPack(MSFile.getAbsolutePath(), NoCPUs); DiaFile.Resume = Resume; DiaFile.SetDataType(dataType); DiaFile.SetParameter(param); //Set DIA isolation window setting if (dataType == SpectralDataType.DataType.DIA_F_Window) { DiaFile.SetWindowSize(WindowSize); } else if (dataType == SpectralDataType.DataType.DIA_V_Window) { for (XYData window : WindowList) { DiaFile.AddVariableWindow(window); } } DiaFile.SaveDIASetting(); DiaFile.SaveParams(); if (Fix) { DiaFile.FixScanidx(); return; } DiaFile.ExportPrecursorPeak = ExportPrecursorPeak; DiaFile.ExportFragmentPeak = ExportFragmentPeak; Logger.getRootLogger().info("Module A: Signal extraction"); //Start DIA signal extraction process to generate pseudo MS/MS files DiaFile.process(); time = System.currentTimeMillis() - time; Logger.getRootLogger().info(MSFilePath + " processed time:" + String.format("%d hour, %d min, %d sec", TimeUnit.MILLISECONDS.toHours(time), TimeUnit.MILLISECONDS.toMinutes(time) - TimeUnit.HOURS.toMinutes(TimeUnit.MILLISECONDS.toHours(time)), TimeUnit.MILLISECONDS.toSeconds(time) - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(time)))); } else { throw new RuntimeException("file: " + MSFile + "? does not exist!"); } Logger.getRootLogger().info("Job complete"); Logger.getRootLogger().info( "================================================================================================="); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:DIA_Umpire_Quant.DIA_Umpire_ProtQuant.java
/** * @param args the command line arguments *///from w w w . j a va 2 s.c o m public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println( "DIA-Umpire protein quantitation module (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length != 1) { System.out.println( "command format error, the correct format should be: java -jar -Xmx10G DIA_Umpire_PortQuant.jar diaumpire_module.params"); return; } try { ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_orotquant.log"); } catch (Exception e) { } Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + args[0]); BufferedReader reader = new BufferedReader(new FileReader(args[0])); String line = ""; String WorkFolder = ""; int NoCPUs = 2; String Combined_Prot = ""; boolean DefaultProtFiltering = true; float Freq = 0f; int TopNPep = 6; int TopNFrag = 6; String FilterWeight = "GW"; float MinWeight = 0.9f; TandemParam tandemPara = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); HashMap<String, File> AssignFiles = new HashMap<>(); boolean ExportSaint = false; boolean SAINT_MS1 = false; boolean SAINT_MS2 = true; HashMap<String, String[]> BaitList = new HashMap<>(); HashMap<String, String> BaitName = new HashMap<>(); HashMap<String, String[]> ControlList = new HashMap<>(); HashMap<String, String> ControlName = new HashMap<>(); //<editor-fold defaultstate="collapsed" desc="Reading parameter file"> while ((line = reader.readLine()) != null) { line = line.trim(); Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==File list begin")) { do { line = reader.readLine(); line = line.trim(); if (line.equals("==File list end")) { continue; } else if (!"".equals(line)) { File newfile = new File(line); if (newfile.exists()) { AssignFiles.put(newfile.getAbsolutePath(), newfile); } else { Logger.getRootLogger().info("File: " + newfile + " does not exist."); } } } while (!line.equals("==File list end")); } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); String value = line.split("=")[1].trim(); switch (type) { case "Path": { WorkFolder = value; break; } case "path": { WorkFolder = value; break; } case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "Fasta": { tandemPara.FastaPath = value; break; } case "Combined_Prot": { Combined_Prot = value; break; } case "DefaultProtFiltering": { DefaultProtFiltering = Boolean.parseBoolean(value); break; } case "DecoyPrefix": { if (!"".equals(value)) { tandemPara.DecoyPrefix = value; } break; } case "ProteinFDR": { tandemPara.ProtFDR = Float.parseFloat(value); break; } case "FilterWeight": { FilterWeight = value; break; } case "MinWeight": { MinWeight = Float.parseFloat(value); break; } case "TopNFrag": { TopNFrag = Integer.parseInt(value); break; } case "TopNPep": { TopNPep = Integer.parseInt(value); break; } case "Freq": { Freq = Float.parseFloat(value); break; } //<editor-fold defaultstate="collapsed" desc="SaintOutput"> case "ExportSaintInput": { ExportSaint = Boolean.parseBoolean(value); break; } case "QuantitationType": { switch (value) { case "MS1": { SAINT_MS1 = true; SAINT_MS2 = false; break; } case "MS2": { SAINT_MS1 = false; SAINT_MS2 = true; break; } case "BOTH": { SAINT_MS1 = true; SAINT_MS2 = true; break; } } break; } // case "BaitInputFile": { // SaintBaitFile = value; // break; // } // case "PreyInputFile": { // SaintPreyFile = value; // break; // } // case "InterationInputFile": { // SaintInteractionFile = value; // break; // } default: { if (type.startsWith("BaitName_")) { BaitName.put(type.substring(9), value); } if (type.startsWith("BaitFile_")) { BaitList.put(type.substring(9), value.split("\t")); } if (type.startsWith("ControlName_")) { ControlName.put(type.substring(12), value); } if (type.startsWith("ControlFile_")) { ControlList.put(type.substring(12), value.split("\t")); } break; } //</editor-fold> } } } //</editor-fold> //Initialize PTM manager using compomics library PTMManager.GetInstance(); //Check if the fasta file can be found if (!new File(tandemPara.FastaPath).exists()) { Logger.getRootLogger().info("Fasta file :" + tandemPara.FastaPath + " cannot be found, the process will be terminated, please check."); System.exit(1); } //Check if the prot.xml file can be found if (!new File(Combined_Prot).exists()) { Logger.getRootLogger().info("ProtXML file: " + Combined_Prot + " cannot be found, the export protein summary table will be empty."); } LCMSID protID = null; //Parse prot.xml and generate protein master list given an FDR if (Combined_Prot != null && !Combined_Prot.equals("")) { protID = LCMSID.ReadLCMSIDSerialization(Combined_Prot); if (!"".equals(Combined_Prot) && protID == null) { protID = new LCMSID(Combined_Prot, tandemPara.DecoyPrefix, tandemPara.FastaPath); ProtXMLParser protxmlparser = new ProtXMLParser(protID, Combined_Prot, 0f); //Use DIA-Umpire default protein FDR calculation if (DefaultProtFiltering) { protID.RemoveLowLocalPWProtein(0.8f); protID.RemoveLowMaxIniProbProtein(0.9f); protID.FilterByProteinDecoyFDRUsingMaxIniProb(tandemPara.DecoyPrefix, tandemPara.ProtFDR); } //Get protein FDR calculation without other filtering else { protID.FilterByProteinDecoyFDRUsingLocalPW(tandemPara.DecoyPrefix, tandemPara.ProtFDR); } protID.LoadSequence(); protID.WriteLCMSIDSerialization(Combined_Prot); } Logger.getRootLogger().info("Protein No.:" + protID.ProteinList.size()); } HashMap<String, HashMap<String, FragmentPeak>> IDSummaryFragments = new HashMap<>(); //Generate DIA file list ArrayList<DIAPack> FileList = new ArrayList<>(); try { File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("The path : " + WorkFolder + " cannot be found."); System.exit(1); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && (fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && (fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); } for (File fileEntry : AssignFiles.values()) { String mzXMLFile = fileEntry.getAbsolutePath(); if (mzXMLFile.toLowerCase().endsWith(".mzxml") | mzXMLFile.toLowerCase().endsWith(".mzml")) { DIAPack DiaFile = new DIAPack(mzXMLFile, NoCPUs); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + mzXMLFile); if (!DiaFile.LoadDIASetting()) { Logger.getRootLogger().info("Loading DIA setting failed, job is incomplete"); System.exit(1); } if (!DiaFile.LoadParams()) { Logger.getRootLogger().info("Loading parameters failed, job is incomplete"); System.exit(1); } Logger.getRootLogger().info("Loading identification results " + mzXMLFile + "...."); //If the serialization file for ID file existed if (DiaFile.ReadSerializedLCMSID()) { DiaFile.IDsummary.ReduceMemoryUsage(); DiaFile.IDsummary.ClearAssignPeakCluster(); FileList.add(DiaFile); HashMap<String, FragmentPeak> FragMap = new HashMap<>(); IDSummaryFragments.put(FilenameUtils.getBaseName(mzXMLFile), FragMap); } } } //<editor-fold defaultstate="collapsed" desc="Peptide and fragment selection"> Logger.getRootLogger().info("Peptide and fragment selection across the whole dataset"); ArrayList<LCMSID> SummaryList = new ArrayList<>(); for (DIAPack diafile : FileList) { if (protID != null) { //Generate protein list according to mapping of peptide ions for each DIA file to the master protein list diafile.IDsummary.GenerateProteinByRefIDByPepSeq(protID, true); diafile.IDsummary.ReMapProPep(); } if ("GW".equals(FilterWeight)) { diafile.IDsummary.SetFilterByGroupWeight(); } else if ("PepW".equals(FilterWeight)) { diafile.IDsummary.SetFilterByWeight(); } SummaryList.add(diafile.IDsummary); } FragmentSelection fragselection = new FragmentSelection(SummaryList); fragselection.freqPercent = Freq; fragselection.GeneratePepFragScoreMap(); fragselection.GenerateTopFragMap(TopNFrag); fragselection.GenerateProtPepScoreMap(MinWeight); fragselection.GenerateTopPepMap(TopNPep); //</editor-fold> //<editor-fold defaultstate="collapsed" desc="Writing general reports"> ExportTable export = new ExportTable(WorkFolder, SummaryList, IDSummaryFragments, protID, fragselection); export.Export(TopNPep, TopNFrag, Freq); //</editor-fold> //<editor-fold defaultstate="collapsed" desc="//<editor-fold defaultstate="collapsed" desc="Generate SAINT input files"> if (ExportSaint && protID != null) { HashMap<String, DIAPack> Filemap = new HashMap<>(); for (DIAPack DIAfile : FileList) { Filemap.put(DIAfile.GetBaseName(), DIAfile); } FileWriter baitfile = new FileWriter(WorkFolder + "SAINT_Bait_" + DateTimeTag.GetTag() + ".txt"); FileWriter preyfile = new FileWriter(WorkFolder + "SAINT_Prey_" + DateTimeTag.GetTag() + ".txt"); FileWriter interactionfileMS1 = null; FileWriter interactionfileMS2 = null; if (SAINT_MS1) { interactionfileMS1 = new FileWriter( WorkFolder + "SAINT_Interaction_MS1_" + DateTimeTag.GetTag() + ".txt"); } if (SAINT_MS2) { interactionfileMS2 = new FileWriter( WorkFolder + "SAINT_Interaction_MS2_" + DateTimeTag.GetTag() + ".txt"); } HashMap<String, String> PreyID = new HashMap<>(); for (String samplekey : ControlName.keySet()) { String name = ControlName.get(samplekey); for (String file : ControlList.get(samplekey)) { baitfile.write(FilenameUtils.getBaseName(file) + "\t" + name + "\t" + "C\n"); LCMSID IDsummary = Filemap.get(FilenameUtils.getBaseName(file)).IDsummary; if (SAINT_MS1) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS1, file, name, PreyID, 1); } if (SAINT_MS2) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS2, file, name, PreyID, 2); } } } for (String samplekey : BaitName.keySet()) { String name = BaitName.get(samplekey); for (String file : BaitList.get(samplekey)) { baitfile.write(FilenameUtils.getBaseName(file) + "\t" + name + "\t" + "T\n"); LCMSID IDsummary = Filemap.get(FilenameUtils.getBaseName(file)).IDsummary; if (SAINT_MS1) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS1, file, name, PreyID, 1); } if (SAINT_MS2) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS2, file, name, PreyID, 2); } } } baitfile.close(); if (SAINT_MS1) { interactionfileMS1.close(); } if (SAINT_MS2) { interactionfileMS2.close(); } for (String AccNo : PreyID.keySet()) { preyfile.write(AccNo + "\t" + PreyID.get(AccNo) + "\n"); } preyfile.close(); } //</editor-fold> Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:ms1quant.MS1Quant.java
/** * @param args the command line arguments MS1Quant parameterfile *//*from www .j av a2 s. c o m*/ public static void main(String[] args) throws Exception { BufferedReader reader = null; try { System.out.println( "================================================================================================="); System.out.println("Umpire MS1 quantification and feature detection analysis (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length < 3 || !args[1].startsWith("-mode")) { System.out .println("command : java -jar -Xmx10G MS1Quant.jar ms1quant.params -mode[1 or 2] [Option]"); System.out.println("\n-mode"); System.out.println("\t1:Single file mode--> mzXML_file PepXML_file"); System.out.println("\t\tEx: -mode1 file1.mzXML file1.pep.xml"); System.out.println( "\t2:Folder mode--> mzXML_Folder PepXML_Folder, all generated csv tables will be merged into a single csv file"); System.out.println("\t\tEx: -mode2 /data/mzxml/ /data/pepxml/"); System.out.println("\nOptions"); System.out.println( "\t-C\tNo of concurrent files to be processed (only for folder mode), Ex. -C5, default:1"); System.out.println("\t-p\tMinimum probability, Ex. -p0.9, default:0.9"); System.out.println("\t-ID\tDetect identified feature only"); System.out.println("\t-O\toutput folder, Ex. -O/data/"); return; } ConsoleLogger consoleLogger = new ConsoleLogger(); consoleLogger.SetConsoleLogger(Level.DEBUG); consoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "ms1quant_debug.log"); Logger logger = Logger.getRootLogger(); logger.debug("Command: " + Arrays.toString(args)); logger.info("MS1Quant version: " + UmpireInfo.GetInstance().Version); String parameterfile = args[0]; logger.info("Parameter file: " + parameterfile); File paramfile = new File(parameterfile); if (!paramfile.exists()) { logger.error("Parameter file " + paramfile.getAbsolutePath() + " cannot be found. The program will exit."); } reader = new BufferedReader(new FileReader(paramfile.getAbsolutePath())); String line = ""; InstrumentParameter param = new InstrumentParameter(InstrumentParameter.InstrumentType.TOF5600); int NoCPUs = 2; int NoFile = 1; param.DetermineBGByID = false; param.EstimateBG = true; //<editor-fold defaultstate="collapsed" desc="Read parameter file"> while ((line = reader.readLine()) != null) { if (!"".equals(line) && !line.startsWith("#")) { logger.info(line); //System.out.println(line); if (line.split("=").length < 2) { continue; } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); if (type.startsWith("para.")) { type = type.replace("para.", "SE."); } String value = line.split("=")[1].trim(); switch (type) { case "Thread": { NoCPUs = Integer.parseInt(value); break; } //<editor-fold defaultstate="collapsed" desc="instrument parameters"> case "SE.MS1PPM": { param.MS1PPM = Float.parseFloat(value); break; } case "SE.MS2PPM": { param.MS2PPM = Float.parseFloat(value); break; } case "SE.SN": { param.SNThreshold = Float.parseFloat(value); break; } case "SE.MS2SN": { param.MS2SNThreshold = Float.parseFloat(value); break; } case "SE.MinMSIntensity": { param.MinMSIntensity = Float.parseFloat(value); break; } case "SE.MinMSMSIntensity": { param.MinMSMSIntensity = Float.parseFloat(value); break; } case "SE.MinRTRange": { param.MinRTRange = Float.parseFloat(value); break; } case "SE.MaxNoPeakCluster": { param.MaxNoPeakCluster = Integer.parseInt(value); param.MaxMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinNoPeakCluster": { param.MinNoPeakCluster = Integer.parseInt(value); param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MinMS2NoPeakCluster": { param.MinMS2NoPeakCluster = Integer.parseInt(value); break; } case "SE.MaxCurveRTRange": { param.MaxCurveRTRange = Float.parseFloat(value); break; } case "SE.Resolution": { param.Resolution = Integer.parseInt(value); break; } case "SE.RTtol": { param.RTtol = Float.parseFloat(value); break; } case "SE.NoPeakPerMin": { param.NoPeakPerMin = Integer.parseInt(value); break; } case "SE.StartCharge": { param.StartCharge = Integer.parseInt(value); break; } case "SE.EndCharge": { param.EndCharge = Integer.parseInt(value); break; } case "SE.MS2StartCharge": { param.MS2StartCharge = Integer.parseInt(value); break; } case "SE.MS2EndCharge": { param.MS2EndCharge = Integer.parseInt(value); break; } case "SE.NoMissedScan": { param.NoMissedScan = Integer.parseInt(value); break; } case "SE.Denoise": { param.Denoise = Boolean.valueOf(value); break; } case "SE.EstimateBG": { param.EstimateBG = Boolean.valueOf(value); break; } case "SE.RemoveGroupedPeaks": { param.RemoveGroupedPeaks = Boolean.valueOf(value); break; } case "SE.MinFrag": { param.MinFrag = Integer.parseInt(value); break; } case "SE.IsoPattern": { param.IsoPattern = Float.valueOf(value); break; } case "SE.StartRT": { param.startRT = Float.valueOf(value); } case "SE.EndRT": { param.endRT = Float.valueOf(value); } //</editor-fold> } } } //</editor-fold> int mode = 1; if (args[1].equals("-mode2")) { mode = 2; } else if (args[1].equals("-mode1")) { mode = 1; } else { logger.error("-mode number not recongized. The program will exit."); } String mzXML = ""; String pepXML = ""; String mzXMLPath = ""; String pepXMLPath = ""; File mzXMLfile = null; File pepXMLfile = null; File mzXMLfolder = null; File pepXMLfolder = null; int idx = 0; if (mode == 1) { mzXML = args[2]; logger.info("Mode1 mzXML file: " + mzXML); mzXMLfile = new File(mzXML); if (!mzXMLfile.exists()) { logger.error("Mode1 mzXML file " + mzXMLfile.getAbsolutePath() + " cannot be found. The program will exit."); return; } pepXML = args[3]; logger.info("Mode1 pepXML file: " + pepXML); pepXMLfile = new File(pepXML); if (!pepXMLfile.exists()) { logger.error("Mode1 pepXML file " + pepXMLfile.getAbsolutePath() + " cannot be found. The program will exit."); return; } idx = 4; } else if (mode == 2) { mzXMLPath = args[2]; logger.info("Mode2 mzXML folder: " + mzXMLPath); mzXMLfolder = new File(mzXMLPath); if (!mzXMLfolder.exists()) { logger.error("Mode2 mzXML folder " + mzXMLfolder.getAbsolutePath() + " does not exist. The program will exit."); return; } pepXMLPath = args[3]; logger.info("Mode2 pepXML folder: " + pepXMLPath); pepXMLfolder = new File(pepXMLPath); if (!pepXMLfolder.exists()) { logger.error("Mode2 pepXML folder " + pepXMLfolder.getAbsolutePath() + " does not exist. The program will exit."); return; } idx = 4; } String outputfolder = ""; float MinProb = 0f; for (int i = idx; i < args.length; i++) { if (args[i].startsWith("-")) { if (args[i].equals("-ID")) { param.TargetIDOnly = true; logger.info("Detect ID feature only: true"); } if (args[i].startsWith("-O")) { outputfolder = args[i].substring(2); logger.info("Output folder: " + outputfolder); File outputfile = new File(outputfolder); if (!outputfolder.endsWith("\\") | outputfolder.endsWith("/")) { outputfolder += "/"; } if (!outputfile.exists()) { outputfile.mkdir(); } } if (args[i].startsWith("-C")) { try { NoFile = Integer.parseInt(args[i].substring(2)); logger.info("No of concurrent files: " + NoFile); } catch (Exception ex) { logger.error(args[i] + " is not a correct integer format, will process only one file at a time."); } } if (args[i].startsWith("-p")) { try { MinProb = Float.parseFloat(args[i].substring(2)); logger.info("probability threshold: " + MinProb); } catch (Exception ex) { logger.error(args[i] + " is not a correct format, will use 0 as threshold instead."); } } } } reader.close(); TandemParam tandemparam = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); PTMManager.GetInstance(); if (param.TargetIDOnly) { param.EstimateBG = false; param.ApexDelta = 1.5f; param.NoMissedScan = 10; param.MiniOverlapP = 0.2f; param.RemoveGroupedPeaks = false; param.CheckMonoIsotopicApex = false; param.DetectByCWT = false; param.FillGapByBK = false; param.IsoCorrThreshold = -1f; param.SmoothFactor = 3; } if (mode == 1) { logger.info("Processing " + mzXMLfile.getAbsolutePath() + "...."); long time = System.currentTimeMillis(); LCMSPeakMS1 LCMS1 = new LCMSPeakMS1(mzXMLfile.getAbsolutePath(), NoCPUs); LCMS1.SetParameter(param); LCMS1.Resume = false; if (!param.TargetIDOnly) { LCMS1.CreatePeakFolder(); } LCMS1.ExportPeakClusterTable = true; if (pepXMLfile.exists()) { tandemparam.InteractPepXMLPath = pepXMLfile.getAbsolutePath(); LCMS1.ParsePepXML(tandemparam, MinProb); logger.info("No. of PSMs included: " + LCMS1.IDsummary.PSMList.size()); logger.info("No. of Peptide ions included: " + LCMS1.IDsummary.GetPepIonList().size()); } if (param.TargetIDOnly) { LCMS1.SaveSerializationFile = false; } if (param.TargetIDOnly || !LCMS1.ReadPeakCluster()) { LCMS1.PeakClusterDetection(); } if (pepXMLfile.exists()) { LCMS1.AssignQuant(false); LCMS1.IDsummary.ExportPepID(outputfolder); } time = System.currentTimeMillis() - time; logger.info(LCMS1.ParentmzXMLName + " processed time:" + String.format("%d hour, %d min, %d sec", TimeUnit.MILLISECONDS.toHours(time), TimeUnit.MILLISECONDS.toMinutes(time) - TimeUnit.HOURS.toMinutes(TimeUnit.MILLISECONDS.toHours(time)), TimeUnit.MILLISECONDS.toSeconds(time) - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(time)))); LCMS1.BaseClearAllPeaks(); LCMS1.SetSpectrumParser(null); LCMS1.IDsummary = null; LCMS1 = null; System.gc(); } else if (mode == 2) { LCMSID IDsummary = new LCMSID("", "", ""); logger.info("Parsing all pepXML files in " + pepXMLPath + "...."); for (File file : pepXMLfolder.listFiles()) { if (file.getName().toLowerCase().endsWith("pep.xml") || file.getName().toLowerCase().endsWith("pepxml")) { PepXMLParser pepXMLParser = new PepXMLParser(IDsummary, file.getAbsolutePath(), MinProb); } } HashMap<String, LCMSID> LCMSIDMap = IDsummary.GetLCMSIDFileMap(); ExecutorService executorPool = null; executorPool = Executors.newFixedThreadPool(NoFile); logger.info("Processing all mzXML files in " + mzXMLPath + "...."); for (File file : mzXMLfolder.listFiles()) { if (file.getName().toLowerCase().endsWith("mzxml")) { LCMSID id = LCMSIDMap.get(FilenameUtils.getBaseName(file.getName())); if (id == null || id.PSMList == null) { logger.warn("No IDs found in :" + FilenameUtils.getBaseName(file.getName()) + ". Quantification for this file is skipped"); continue; } if (!id.PSMList.isEmpty()) { MS1TargetQuantThread thread = new MS1TargetQuantThread(file, id, NoCPUs, outputfolder, param); executorPool.execute(thread); } } } LCMSIDMap.clear(); LCMSIDMap = null; IDsummary = null; executorPool.shutdown(); try { executorPool.awaitTermination(Long.MAX_VALUE, TimeUnit.NANOSECONDS); } catch (InterruptedException e) { logger.info("interrupted.."); } if (outputfolder == null | outputfolder.equals("")) { outputfolder = mzXMLPath; } logger.info("Merging PSM files.."); File output = new File(outputfolder); FileWriter writer = new FileWriter(output.getAbsolutePath() + "/PSM_merge.csv"); boolean header = false; for (File csvfile : output.listFiles()) { if (csvfile.getName().toLowerCase().endsWith("_psms.csv")) { BufferedReader outreader = new BufferedReader(new FileReader(csvfile)); String outline = outreader.readLine(); if (!header) { writer.write(outline + "\n"); header = true; } while ((outline = outreader.readLine()) != null) { writer.write(outline + "\n"); } outreader.close(); csvfile.delete(); } } writer.close(); } logger.info("MS1 quant module is complete."); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:FDREstimator.ExportWithEstimatedFDR.java
/** * @param args the command line arguments *//*from w w w .j av a 2 s.c om*/ public static void main(String[] args) throws ParserConfigurationException, SAXException, IOException, ClassNotFoundException, XmlPullParserException, InterruptedException, SQLException { System.out.println( "================================================================================================="); System.out.println("Umpire search result parser(version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length == 0) { System.out.println( "command : java -jar -Xmx1G Umpire-SearchResultParser.jar [Options] [Combined ProtXML file] [PepXML files...]"); System.out.println(""); System.out.println("ProtXML extension: *.prot.xml or *.ProtXML"); System.out.println("PepXML extension: *.pep.xml or *.PepXML"); System.out.println("\nOptions"); System.out.println("\t-MP\tMin protein parsing probability\tex: -MP0.1f (default: -1, no filtering)"); System.out.println("\t-Mp\tMin PSM parsing probability\tex: -Mp0.1f (default: -1, no filtering)"); System.out.println("\t-fP\tProtein FDR\tex: -fP0.01 (default: 0.01, no filtering: -1)"); System.out.println("\t-fp\tPeptide FDR\tex: -fp0.05 (default: 0.01, no filtering: -1)"); System.out.println("\t-d\tDecoy tag prefix\tex: -dDECOY (default: rev_)"); System.out.println( "\t-C\t(0 or 1) Correct mass diff derived from isotope error\tex:-C0 (default:0, no correction)"); System.out.println("\t-fa\tFasta file"); System.out.println("\t-N\tOutput filename"); System.out.println( "\t-pt\tInitial protein probability filtering threshold\tex: -pt0.5 (default: 0.5, no filtering : -1)"); System.out.println( "\t-rf\tR factor threshold, proteins with protein probablity less than the threshold will be used to estimate the R factor \n\t\tex: -rf0.2 (default: 0.2, do not use R factor: -1)"); return; } ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "parser_debug.log"); float protFDR = 0.01f; float pepFDR = 0.01f; float MinpepProb = -1f; float MinprotProb = -1f; boolean CorrectMassDiff = false; String DecoyTag = "rev_"; String Fasta = ""; String Outputname = ""; float protprob = 0.5f; float rfthreshold = 0.2f; String ProtXML = ""; ArrayList<String> PepXML = new ArrayList<>(); for (int i = 0; i < args.length; i++) { if (args[i].startsWith("-")) { if (args[i].startsWith("-fP")) { protFDR = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("Protein FDR: " + protFDR); } if (args[i].startsWith("-fp")) { pepFDR = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("Peptide FDR: " + pepFDR); } if (args[i].startsWith("-MP")) { MinprotProb = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("Min protein parsing probability: " + MinprotProb); } if (args[i].startsWith("-Mp")) { MinpepProb = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("Min PSM parsing probability: " + MinpepProb); } if (args[i].startsWith("-d")) { DecoyTag = args[i].substring(2); Logger.getRootLogger().info("Decoy tag: " + DecoyTag); } if (args[i].startsWith("-fa")) { Fasta = args[i].substring(3); Logger.getRootLogger().info("Fasta file: " + Fasta); } if (args[i].startsWith("-N")) { Outputname = args[i].substring(2); Logger.getRootLogger().info("Output filename: " + Outputname); } if (args[i].startsWith("-C")) { if (args[i].substring(2).equals("1")) { CorrectMassDiff = true; } Logger.getRootLogger().info("Correct mass diff: " + CorrectMassDiff); } if (args[i].startsWith("-pt")) { protprob = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("Initial protein probablity filtering threshold: " + protprob); } if (args[i].startsWith("-rf")) { rfthreshold = Float.parseFloat(args[i].substring(3)); Logger.getRootLogger().info("R factor threshold: " + rfthreshold); } } if (args[i].endsWith(".pep.xml") || args[i].endsWith(".PepXML")) { PepXML.add(args[i]); } if (args[i].endsWith(".prot.xml") || args[i].endsWith(".ProtXML")) { ProtXML = args[i]; } } if (!Outputname.equals("")) { Outputname = Outputname + "_"; } Outputname = Outputname + MSUmpire.Utility.DateTimeTag.GetTag(); LCMSID lcmsid = new LCMSID(Outputname, DecoyTag, Fasta); for (String pepxml : PepXML) { LCMSID pepxmlid = new LCMSID(pepxml, DecoyTag, Fasta); PepXMLParser pepxmlparser = new PepXMLParser(pepxmlid, pepxml, MinpepProb, CorrectMassDiff); if (pepFDR != -1f) { pepxmlid.FilterByPepDecoyFDR(DecoyTag, pepFDR); } Logger.getRootLogger().info("peptide No.:" + pepxmlid.GetPepIonList().size() + "; Peptide level threshold: " + pepxmlid.PepProbThreshold); for (PepIonID pepID : pepxmlid.GetPepIonList().values()) { lcmsid.AddPeptideID(pepID); } } if (!"".equals(ProtXML)) { ProtXMLParser protxmlparser = new ProtXMLParser(lcmsid, ProtXML, MinprotProb); lcmsid.DecoyTag = DecoyTag; if (protprob != -1f) { lcmsid.RemoveLowLocalPWProtein(protprob); } float rf = 1f; if (rfthreshold != -1f) { rf = lcmsid.GetRFactor(rfthreshold); } if (protFDR != -1f) { lcmsid.FilterByProteinDecoyFDRUsingMaxIniProb(lcmsid.DecoyTag, protFDR / rf); } if (!"".equals(Fasta)) { lcmsid.LoadSequence(); } lcmsid.ReMapProPep(); lcmsid.ExportProtID(); } lcmsid.CreateInstanceForAllPepIon(); lcmsid.ExportPepID(); Logger.getRootLogger().info("Protein No.:" + lcmsid.ProteinList.size() + "; All peptide ions.:" + lcmsid.GetPepIonList().size()); }
From source file:DIA_Umpire_Quant.DIA_Umpire_Quant.java
/** * @param args the command line arguments *//*from www .j av a 2s . c om*/ public static void main(String[] args) throws FileNotFoundException, IOException, Exception { System.out.println( "================================================================================================="); System.out.println("DIA-Umpire quantitation with targeted re-extraction analysis (version: " + UmpireInfo.GetInstance().Version + ")"); if (args.length != 1) { System.out.println( "command format error, it should be like: java -jar -Xmx10G DIA_Umpire_Quant.jar diaumpire_quant.params"); return; } try { ConsoleLogger.SetConsoleLogger(Level.INFO); ConsoleLogger.SetFileLogger(Level.DEBUG, FilenameUtils.getFullPath(args[0]) + "diaumpire_quant.log"); } catch (Exception e) { } try { Logger.getRootLogger().info("Version: " + UmpireInfo.GetInstance().Version); Logger.getRootLogger().info("Parameter file:" + args[0]); BufferedReader reader = new BufferedReader(new FileReader(args[0])); String line = ""; String WorkFolder = ""; int NoCPUs = 2; String UserMod = ""; String Combined_Prot = ""; String InternalLibID = ""; String ExternalLibPath = ""; String ExternalLibDecoyTag = "DECOY"; boolean DefaultProtFiltering = true; boolean DataSetLevelPepFDR = false; float ProbThreshold = 0.99f; float ExtProbThreshold = 0.99f; float Freq = 0f; int TopNPep = 6; int TopNFrag = 6; float MinFragMz = 200f; String FilterWeight = "GW"; float MinWeight = 0.9f; float RTWindow_Int = -1f; float RTWindow_Ext = -1f; TandemParam tandemPara = new TandemParam(DBSearchParam.SearchInstrumentType.TOF5600); HashMap<String, File> AssignFiles = new HashMap<>(); boolean InternalLibSearch = false; boolean ExternalLibSearch = false; boolean ExportSaint = false; boolean SAINT_MS1 = false; boolean SAINT_MS2 = true; HashMap<String, String[]> BaitList = new HashMap<>(); HashMap<String, String> BaitName = new HashMap<>(); HashMap<String, String[]> ControlList = new HashMap<>(); HashMap<String, String> ControlName = new HashMap<>(); //<editor-fold defaultstate="collapsed" desc="Reading parameter file"> while ((line = reader.readLine()) != null) { line = line.trim(); Logger.getRootLogger().info(line); if (!"".equals(line) && !line.startsWith("#")) { //System.out.println(line); if (line.equals("==File list begin")) { do { line = reader.readLine(); line = line.trim(); if (line.equals("==File list end")) { continue; } else if (!"".equals(line)) { File newfile = new File(line); if (newfile.exists()) { AssignFiles.put(newfile.getAbsolutePath(), newfile); } else { Logger.getRootLogger().info("File: " + newfile + " does not exist."); } } } while (!line.equals("==File list end")); } if (line.split("=").length < 2) { continue; } String type = line.split("=")[0].trim(); String value = line.split("=")[1].trim(); switch (type) { case "TargetedExtraction": { InternalLibSearch = Boolean.parseBoolean(value); break; } case "InternalLibSearch": { InternalLibSearch = Boolean.parseBoolean(value); break; } case "ExternalLibSearch": { ExternalLibSearch = Boolean.parseBoolean(value); break; } case "Path": { WorkFolder = value; break; } case "path": { WorkFolder = value; break; } case "Thread": { NoCPUs = Integer.parseInt(value); break; } case "Fasta": { tandemPara.FastaPath = value; break; } case "Combined_Prot": { Combined_Prot = value; break; } case "DefaultProtFiltering": { DefaultProtFiltering = Boolean.parseBoolean(value); break; } case "DecoyPrefix": { if (!"".equals(value)) { tandemPara.DecoyPrefix = value; } break; } case "UserMod": { UserMod = value; break; } case "ProteinFDR": { tandemPara.ProtFDR = Float.parseFloat(value); break; } case "PeptideFDR": { tandemPara.PepFDR = Float.parseFloat(value); break; } case "DataSetLevelPepFDR": { DataSetLevelPepFDR = Boolean.parseBoolean(value); break; } case "InternalLibID": { InternalLibID = value; break; } case "ExternalLibPath": { ExternalLibPath = value; break; } case "ExtProbThreshold": { ExtProbThreshold = Float.parseFloat(value); break; } case "RTWindow_Int": { RTWindow_Int = Float.parseFloat(value); break; } case "RTWindow_Ext": { RTWindow_Ext = Float.parseFloat(value); break; } case "ExternalLibDecoyTag": { ExternalLibDecoyTag = value; if (ExternalLibDecoyTag.endsWith("_")) { ExternalLibDecoyTag = ExternalLibDecoyTag.substring(0, ExternalLibDecoyTag.length() - 1); } break; } case "ProbThreshold": { ProbThreshold = Float.parseFloat(value); break; } case "ReSearchProb": { //ReSearchProb = Float.parseFloat(value); break; } case "FilterWeight": { FilterWeight = value; break; } case "MinWeight": { MinWeight = Float.parseFloat(value); break; } case "TopNFrag": { TopNFrag = Integer.parseInt(value); break; } case "TopNPep": { TopNPep = Integer.parseInt(value); break; } case "Freq": { Freq = Float.parseFloat(value); break; } case "MinFragMz": { MinFragMz = Float.parseFloat(value); break; } //<editor-fold defaultstate="collapsed" desc="SaintOutput"> case "ExportSaintInput": { ExportSaint = Boolean.parseBoolean(value); break; } case "QuantitationType": { switch (value) { case "MS1": { SAINT_MS1 = true; SAINT_MS2 = false; break; } case "MS2": { SAINT_MS1 = false; SAINT_MS2 = true; break; } case "BOTH": { SAINT_MS1 = true; SAINT_MS2 = true; break; } } break; } // case "BaitInputFile": { // SaintBaitFile = value; // break; // } // case "PreyInputFile": { // SaintPreyFile = value; // break; // } // case "InterationInputFile": { // SaintInteractionFile = value; // break; // } default: { if (type.startsWith("BaitName_")) { BaitName.put(type.substring(9), value); } if (type.startsWith("BaitFile_")) { BaitList.put(type.substring(9), value.split("\t")); } if (type.startsWith("ControlName_")) { ControlName.put(type.substring(12), value); } if (type.startsWith("ControlFile_")) { ControlList.put(type.substring(12), value.split("\t")); } break; } //</editor-fold> } } } //</editor-fold> //Initialize PTM manager using compomics library PTMManager.GetInstance(); if (!UserMod.equals("")) { PTMManager.GetInstance().ImportUserMod(UserMod); } //Check if the fasta file can be found if (!new File(tandemPara.FastaPath).exists()) { Logger.getRootLogger().info("Fasta file :" + tandemPara.FastaPath + " cannot be found, the process will be terminated, please check."); System.exit(1); } //Check if the prot.xml file can be found if (!new File(Combined_Prot).exists()) { Logger.getRootLogger().info("ProtXML file: " + Combined_Prot + " cannot be found, the export protein summary table will be empty."); } LCMSID protID = null; //Parse prot.xml and generate protein master list given an FDR if (Combined_Prot != null && !Combined_Prot.equals("")) { protID = LCMSID.ReadLCMSIDSerialization(Combined_Prot); if (!"".equals(Combined_Prot) && protID == null) { protID = new LCMSID(Combined_Prot, tandemPara.DecoyPrefix, tandemPara.FastaPath); ProtXMLParser protxmlparser = new ProtXMLParser(protID, Combined_Prot, 0f); //Use DIA-Umpire default protein FDR calculation if (DefaultProtFiltering) { protID.RemoveLowLocalPWProtein(0.8f); protID.RemoveLowMaxIniProbProtein(0.9f); protID.FilterByProteinDecoyFDRUsingMaxIniProb(tandemPara.DecoyPrefix, tandemPara.ProtFDR); } //Get protein FDR calculation without other filtering else { protID.FilterByProteinDecoyFDRUsingLocalPW(tandemPara.DecoyPrefix, tandemPara.ProtFDR); } protID.LoadSequence(); protID.WriteLCMSIDSerialization(Combined_Prot); } Logger.getRootLogger().info("Protein No.:" + protID.ProteinList.size()); } HashMap<String, HashMap<String, FragmentPeak>> IDSummaryFragments = new HashMap<>(); //Generate DIA file list ArrayList<DIAPack> FileList = new ArrayList<>(); File folder = new File(WorkFolder); if (!folder.exists()) { Logger.getRootLogger().info("The path : " + WorkFolder + " cannot be found."); System.exit(1); } for (final File fileEntry : folder.listFiles()) { if (fileEntry.isFile() && (fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry.getAbsolutePath(), fileEntry); } if (fileEntry.isDirectory()) { for (final File fileEntry2 : fileEntry.listFiles()) { if (fileEntry2.isFile() && (fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzxml") | fileEntry2.getAbsolutePath().toLowerCase().endsWith(".mzml")) && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q1.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q2.mzxml") && !fileEntry2.getAbsolutePath().toLowerCase().endsWith("q3.mzxml")) { AssignFiles.put(fileEntry2.getAbsolutePath(), fileEntry2); } } } } Logger.getRootLogger().info("No. of files assigned :" + AssignFiles.size()); for (File fileEntry : AssignFiles.values()) { Logger.getRootLogger().info(fileEntry.getAbsolutePath()); String mzXMLFile = fileEntry.getAbsolutePath(); if (mzXMLFile.toLowerCase().endsWith(".mzxml") | mzXMLFile.toLowerCase().endsWith(".mzml")) { DIAPack DiaFile = new DIAPack(mzXMLFile, NoCPUs); FileList.add(DiaFile); HashMap<String, FragmentPeak> FragMap = new HashMap<>(); IDSummaryFragments.put(FilenameUtils.getBaseName(mzXMLFile), FragMap); Logger.getRootLogger().info( "================================================================================================="); Logger.getRootLogger().info("Processing " + mzXMLFile); if (!DiaFile.LoadDIASetting()) { Logger.getRootLogger().info("Loading DIA setting failed, job is incomplete"); System.exit(1); } if (!DiaFile.LoadParams()) { Logger.getRootLogger().info("Loading parameters failed, job is incomplete"); System.exit(1); } } } LCMSID combinePepID = null; if (DataSetLevelPepFDR) { combinePepID = LCMSID.ReadLCMSIDSerialization(WorkFolder + "combinePepID.SerFS"); if (combinePepID == null) { FDR_DataSetLevel fdr = new FDR_DataSetLevel(); fdr.GeneratePepIonList(FileList, tandemPara, WorkFolder + "combinePepID.SerFS"); combinePepID = fdr.combineID; combinePepID.WriteLCMSIDSerialization(WorkFolder + "combinePepID.SerFS"); } } //process each DIA file for quantification based on untargeted identifications for (DIAPack DiaFile : FileList) { long time = System.currentTimeMillis(); Logger.getRootLogger().info("Loading identification results " + DiaFile.Filename + "...."); //If the LCMSID serialization is found if (!DiaFile.ReadSerializedLCMSID()) { DiaFile.ParsePepXML(tandemPara, combinePepID); DiaFile.BuildStructure(); if (!DiaFile.MS1FeatureMap.ReadPeakCluster()) { Logger.getRootLogger().info("Loading peak and structure failed, job is incomplete"); System.exit(1); } DiaFile.MS1FeatureMap.ClearMonoisotopicPeakOfCluster(); //Generate mapping between index of precursor feature and pseudo MS/MS scan index DiaFile.GenerateClusterScanNomapping(); //Doing quantification DiaFile.AssignQuant(); DiaFile.ClearStructure(); } DiaFile.IDsummary.ReduceMemoryUsage(); time = System.currentTimeMillis() - time; Logger.getRootLogger().info(DiaFile.Filename + " processed time:" + String.format("%d hour, %d min, %d sec", TimeUnit.MILLISECONDS.toHours(time), TimeUnit.MILLISECONDS.toMinutes(time) - TimeUnit.HOURS.toMinutes(TimeUnit.MILLISECONDS.toHours(time)), TimeUnit.MILLISECONDS.toSeconds(time) - TimeUnit.MINUTES.toSeconds(TimeUnit.MILLISECONDS.toMinutes(time)))); } //<editor-fold defaultstate="collapsed" desc="Targete re-extraction using internal library"> Logger.getRootLogger().info( "================================================================================================="); if (InternalLibSearch && FileList.size() > 1) { Logger.getRootLogger().info("Module C: Targeted extraction using internal library"); FragmentLibManager libManager = FragmentLibManager.ReadFragmentLibSerialization(WorkFolder, InternalLibID); if (libManager == null) { Logger.getRootLogger().info("Building internal spectral library"); libManager = new FragmentLibManager(InternalLibID); ArrayList<LCMSID> LCMSIDList = new ArrayList<>(); for (DIAPack dia : FileList) { LCMSIDList.add(dia.IDsummary); } libManager.ImportFragLibTopFrag(LCMSIDList, Freq, TopNFrag); libManager.WriteFragmentLibSerialization(WorkFolder); } libManager.ReduceMemoryUsage(); Logger.getRootLogger() .info("Building retention time prediction model and generate candidate peptide list"); for (int i = 0; i < FileList.size(); i++) { FileList.get(i).IDsummary.ClearMappedPep(); } for (int i = 0; i < FileList.size(); i++) { for (int j = i + 1; j < FileList.size(); j++) { RTAlignedPepIonMapping alignment = new RTAlignedPepIonMapping(WorkFolder, FileList.get(i).GetParameter(), FileList.get(i).IDsummary, FileList.get(j).IDsummary); alignment.GenerateModel(); alignment.GenerateMappedPepIon(); } FileList.get(i).ExportID(); FileList.get(i).IDsummary = null; } Logger.getRootLogger().info("Targeted matching........"); for (DIAPack diafile : FileList) { if (diafile.IDsummary == null) { diafile.ReadSerializedLCMSID(); } if (!diafile.IDsummary.GetMappedPepIonList().isEmpty()) { diafile.UseMappedIon = true; diafile.FilterMappedIonByProb = false; diafile.BuildStructure(); diafile.MS1FeatureMap.ReadPeakCluster(); diafile.MS1FeatureMap.ClearMonoisotopicPeakOfCluster(); diafile.GenerateMassCalibrationRTMap(); diafile.TargetedExtractionQuant(false, libManager, 1.1f, RTWindow_Int); diafile.MS1FeatureMap.ClearAllPeaks(); diafile.IDsummary.ReduceMemoryUsage(); diafile.IDsummary.RemoveLowProbMappedIon(ProbThreshold); diafile.ExportID(); Logger.getRootLogger().info("Peptide ions: " + diafile.IDsummary.GetPepIonList().size() + " Mapped ions: " + diafile.IDsummary.GetMappedPepIonList().size()); diafile.ClearStructure(); } diafile.IDsummary = null; System.gc(); } Logger.getRootLogger().info( "================================================================================================="); } //</editor-fold> //<editor-fold defaultstate="collapsed" desc="Targeted re-extraction using external library"> //External library search if (ExternalLibSearch) { Logger.getRootLogger().info("Module C: Targeted extraction using external library"); //Read exteranl library FragmentLibManager ExlibManager = FragmentLibManager.ReadFragmentLibSerialization(WorkFolder, FilenameUtils.getBaseName(ExternalLibPath)); if (ExlibManager == null) { ExlibManager = new FragmentLibManager(FilenameUtils.getBaseName(ExternalLibPath)); //Import traML file ExlibManager.ImportFragLibByTraML(ExternalLibPath, ExternalLibDecoyTag); //Check if there are decoy spectra ExlibManager.CheckDecoys(); //ExlibManager.ImportFragLibBySPTXT(ExternalLibPath); ExlibManager.WriteFragmentLibSerialization(WorkFolder); } Logger.getRootLogger() .info("No. of peptide ions in external lib:" + ExlibManager.PeptideFragmentLib.size()); for (DIAPack diafile : FileList) { if (diafile.IDsummary == null) { diafile.ReadSerializedLCMSID(); } //Generate RT mapping RTMappingExtLib RTmap = new RTMappingExtLib(diafile.IDsummary, ExlibManager, diafile.GetParameter()); RTmap.GenerateModel(); RTmap.GenerateMappedPepIon(); diafile.BuildStructure(); diafile.MS1FeatureMap.ReadPeakCluster(); diafile.GenerateMassCalibrationRTMap(); //Perform targeted re-extraction diafile.TargetedExtractionQuant(false, ExlibManager, ProbThreshold, RTWindow_Ext); diafile.MS1FeatureMap.ClearAllPeaks(); diafile.IDsummary.ReduceMemoryUsage(); //Remove target IDs below the defined probability threshold diafile.IDsummary.RemoveLowProbMappedIon(ExtProbThreshold); diafile.ExportID(); diafile.ClearStructure(); Logger.getRootLogger().info("Peptide ions: " + diafile.IDsummary.GetPepIonList().size() + " Mapped ions: " + diafile.IDsummary.GetMappedPepIonList().size()); } } //</editor-fold> //<editor-fold defaultstate="collapsed" desc="Peptide and fragment selection"> Logger.getRootLogger().info("Peptide and fragment selection across the whole dataset"); ArrayList<LCMSID> SummaryList = new ArrayList<>(); for (DIAPack diafile : FileList) { if (diafile.IDsummary == null) { diafile.ReadSerializedLCMSID(); diafile.IDsummary.ClearAssignPeakCluster(); //diafile.IDsummary.ClearPSMs(); } if (protID != null) { //Generate protein list according to mapping of peptide ions for each DIA file to the master protein list diafile.IDsummary.GenerateProteinByRefIDByPepSeq(protID, true); diafile.IDsummary.ReMapProPep(); } if ("GW".equals(FilterWeight)) { diafile.IDsummary.SetFilterByGroupWeight(); } else if ("PepW".equals(FilterWeight)) { diafile.IDsummary.SetFilterByWeight(); } SummaryList.add(diafile.IDsummary); } FragmentSelection fragselection = new FragmentSelection(SummaryList); fragselection.freqPercent = Freq; fragselection.MinFragMZ = MinFragMz; fragselection.GeneratePepFragScoreMap(); fragselection.GenerateTopFragMap(TopNFrag); fragselection.GenerateProtPepScoreMap(MinWeight); fragselection.GenerateTopPepMap(TopNPep); //</editor-fold> //<editor-fold defaultstate="collapsed" desc="Writing general reports"> ExportTable export = new ExportTable(WorkFolder, SummaryList, IDSummaryFragments, protID, fragselection); export.Export(TopNPep, TopNFrag, Freq); //</editor-fold> //<editor-fold defaultstate="collapsed" desc="//<editor-fold defaultstate="collapsed" desc="Generate SAINT input files"> if (ExportSaint && protID != null) { HashMap<String, DIAPack> Filemap = new HashMap<>(); for (DIAPack DIAfile : FileList) { Filemap.put(DIAfile.GetBaseName(), DIAfile); } FileWriter baitfile = new FileWriter(WorkFolder + "SAINT_Bait_" + DateTimeTag.GetTag() + ".txt"); FileWriter preyfile = new FileWriter(WorkFolder + "SAINT_Prey_" + DateTimeTag.GetTag() + ".txt"); FileWriter interactionfileMS1 = null; FileWriter interactionfileMS2 = null; if (SAINT_MS1) { interactionfileMS1 = new FileWriter( WorkFolder + "SAINT_Interaction_MS1_" + DateTimeTag.GetTag() + ".txt"); } if (SAINT_MS2) { interactionfileMS2 = new FileWriter( WorkFolder + "SAINT_Interaction_MS2_" + DateTimeTag.GetTag() + ".txt"); } HashMap<String, String> PreyID = new HashMap<>(); for (String samplekey : ControlName.keySet()) { String name = ControlName.get(samplekey); for (String file : ControlList.get(samplekey)) { baitfile.write(FilenameUtils.getBaseName(file) + "\t" + name + "\t" + "C\n"); LCMSID IDsummary = Filemap.get(FilenameUtils.getBaseName(file)).IDsummary; if (SAINT_MS1) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS1, file, name, PreyID, 1); } if (SAINT_MS2) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS2, file, name, PreyID, 2); } } } for (String samplekey : BaitName.keySet()) { String name = BaitName.get(samplekey); for (String file : BaitList.get(samplekey)) { baitfile.write(FilenameUtils.getBaseName(file) + "\t" + name + "\t" + "T\n"); LCMSID IDsummary = Filemap.get(FilenameUtils.getBaseName(file)).IDsummary; if (SAINT_MS1) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS1, file, name, PreyID, 1); } if (SAINT_MS2) { SaintOutput(protID, IDsummary, fragselection, interactionfileMS2, file, name, PreyID, 2); } } } baitfile.close(); if (SAINT_MS1) { interactionfileMS1.close(); } if (SAINT_MS2) { interactionfileMS2.close(); } for (String AccNo : PreyID.keySet()) { preyfile.write(AccNo + "\t" + PreyID.get(AccNo) + "\n"); } preyfile.close(); } //</editor-fold> Logger.getRootLogger().info("Job done"); Logger.getRootLogger().info( "================================================================================================="); } catch (Exception e) { Logger.getRootLogger().error(ExceptionUtils.getStackTrace(e)); throw e; } }
From source file:bboss.org.artofsolving.jodconverter.cli.Convert.java
public static void main(String[] arguments) throws ParseException, JSONException, IOException { CommandLineParser commandLineParser = new PosixParser(); CommandLine commandLine = commandLineParser.parse(OPTIONS, arguments); String outputFormat = null;/* www .ja va 2s .co m*/ if (commandLine.hasOption(OPTION_OUTPUT_FORMAT.getOpt())) { outputFormat = commandLine.getOptionValue(OPTION_OUTPUT_FORMAT.getOpt()); } int port = DEFAULT_OFFICE_PORT; if (commandLine.hasOption(OPTION_PORT.getOpt())) { port = Integer.parseInt(commandLine.getOptionValue(OPTION_PORT.getOpt())); } String[] fileNames = commandLine.getArgs(); if ((outputFormat == null && fileNames.length != 2) || fileNames.length < 1) { String syntax = "java -jar jodconverter-core.jar [options] input-file output-file\n" + "or [options] -o output-format input-file [input-file...]"; HelpFormatter helpFormatter = new HelpFormatter(); helpFormatter.printHelp(syntax, OPTIONS); System.exit(STATUS_INVALID_ARGUMENTS); } DocumentFormatRegistry registry; if (commandLine.hasOption(OPTION_REGISTRY.getOpt())) { File registryFile = new File(commandLine.getOptionValue(OPTION_REGISTRY.getOpt())); registry = new JsonDocumentFormatRegistry(FileUtils.readFileToString(registryFile)); } else { registry = new DefaultDocumentFormatRegistry(); } DefaultOfficeManagerConfiguration configuration = new DefaultOfficeManagerConfiguration(); configuration.setPortNumber(port); if (commandLine.hasOption(OPTION_TIMEOUT.getOpt())) { int timeout = Integer.parseInt(commandLine.getOptionValue(OPTION_TIMEOUT.getOpt())); configuration.setTaskExecutionTimeout(timeout * 1000); } if (commandLine.hasOption(OPTION_USER_PROFILE.getOpt())) { String templateProfileDir = commandLine.getOptionValue(OPTION_USER_PROFILE.getOpt()); configuration.setTemplateProfileDir(new File(templateProfileDir)); } OfficeManager officeManager = configuration.buildOfficeManager(); officeManager.start(); OfficeDocumentConverter converter = new OfficeDocumentConverter(officeManager, registry); try { if (outputFormat == null) { File inputFile = new File(fileNames[0]); File outputFile = new File(fileNames[1]); converter.convert(inputFile, outputFile); } else { for (int i = 0; i < fileNames.length; i++) { File inputFile = new File(fileNames[i]); String outputName = FilenameUtils.getBaseName(fileNames[i]) + "." + outputFormat; File outputFile = new File(FilenameUtils.getFullPath(fileNames[i]) + outputName); converter.convert(inputFile, outputFile); } } } finally { officeManager.stop(); } }