List of usage examples for java.lang Float parseFloat
public static float parseFloat(String s) throws NumberFormatException
From source file:DIA_Umpire_Quant.DIA_Umpire_ExtLibSearch.java
/** * @param args the command line arguments *///from w ww .ja v a 2 s . 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:apps.LuceneQuery.java
public static void main(String[] args) { Options options = new Options(); options.addOption("d", null, true, "index directory"); options.addOption("i", null, true, "input file"); options.addOption("s", null, true, "stop word file"); options.addOption("n", null, true, "max # of results"); options.addOption("o", null, true, "a TREC-style output file"); options.addOption("r", null, true, "an optional QREL file, if specified," + "we save results only for queries for which we find at least one relevant entry."); options.addOption("prob", null, true, "question sampling probability"); options.addOption("max_query_qty", null, true, "a maximum number of queries to run"); options.addOption("bm25_b", null, true, "BM25 parameter: b"); options.addOption("bm25_k1", null, true, "BM25 parameter: k1"); options.addOption("bm25fixed", null, false, "use the fixed BM25 similarity"); options.addOption("seed", null, true, "random seed"); Joiner commaJoin = Joiner.on(','); Joiner spaceJoin = Joiner.on(' '); options.addOption("source_type", null, true, "query source type: " + commaJoin.join(SourceFactory.getQuerySourceList())); CommandLineParser parser = new org.apache.commons.cli.GnuParser(); QrelReader qrels = null;//from w ww . j ava2 s . c om try { CommandLine cmd = parser.parse(options, args); String indexDir = null; if (cmd.hasOption("d")) { indexDir = cmd.getOptionValue("d"); } else { Usage("Specify 'index directory'", options); } String inputFileName = null; if (cmd.hasOption("i")) { inputFileName = cmd.getOptionValue("i"); } else { Usage("Specify 'input file'", options); } DictNoComments stopWords = null; if (cmd.hasOption("s")) { String stopWordFileName = cmd.getOptionValue("s"); stopWords = new DictNoComments(new File(stopWordFileName), true /* lowercasing */); System.out.println("Using the stopword file: " + stopWordFileName); } String sourceName = cmd.getOptionValue("source_type"); if (sourceName == null) Usage("Specify document source type", options); int numRet = 100; if (cmd.hasOption("n")) { numRet = Integer.parseInt(cmd.getOptionValue("n")); System.out.println("Retrieving at most " + numRet + " candidate entries."); } String trecOutFileName = null; if (cmd.hasOption("o")) { trecOutFileName = cmd.getOptionValue("o"); } else { Usage("Specify 'a TREC-style output file'", options); } double fProb = 1.0f; if (cmd.hasOption("prob")) { try { fProb = Double.parseDouble(cmd.getOptionValue("prob")); } catch (NumberFormatException e) { Usage("Wrong format for 'question sampling probability'", options); } } if (fProb <= 0 || fProb > 1) { Usage("Question sampling probability should be >0 and <=1", options); } System.out.println("Sample the following fraction of questions: " + fProb); float bm25_k1 = UtilConst.BM25_K1_DEFAULT, bm25_b = UtilConst.BM25_B_DEFAULT; if (cmd.hasOption("bm25_k1")) { try { bm25_k1 = Float.parseFloat(cmd.getOptionValue("bm25_k1")); } catch (NumberFormatException e) { Usage("Wrong format for 'bm25_k1'", options); } } if (cmd.hasOption("bm25_b")) { try { bm25_b = Float.parseFloat(cmd.getOptionValue("bm25_b")); } catch (NumberFormatException e) { Usage("Wrong format for 'bm25_b'", options); } } long seed = 0; String tmpl = cmd.getOptionValue("seed"); if (tmpl != null) seed = Long.parseLong(tmpl); System.out.println("Using seed: " + seed); Random randGen = new Random(seed); System.out.println(String.format("BM25 parameters k1=%f b=%f ", bm25_k1, bm25_b)); boolean useFixedBM25 = cmd.hasOption("bm25fixed"); EnglishAnalyzer analyzer = new EnglishAnalyzer(); Similarity similarity = null; if (useFixedBM25) { System.out.println(String.format("Using fixed BM25Simlarity, k1=%f b=%f", bm25_k1, bm25_b)); similarity = new BM25SimilarityFix(bm25_k1, bm25_b); } else { System.out.println(String.format("Using Lucene BM25Similarity, k1=%f b=%f", bm25_k1, bm25_b)); similarity = new BM25Similarity(bm25_k1, bm25_b); } int maxQueryQty = Integer.MAX_VALUE; if (cmd.hasOption("max_query_qty")) { try { maxQueryQty = Integer.parseInt(cmd.getOptionValue("max_query_qty")); } catch (NumberFormatException e) { Usage("Wrong format for 'max_query_qty'", options); } } System.out.println(String.format("Executing at most %d queries", maxQueryQty)); if (cmd.hasOption("r")) { String qrelFile = cmd.getOptionValue("r"); System.out.println("Using the qrel file: '" + qrelFile + "', queries not returning a relevant entry will be ignored."); qrels = new QrelReader(qrelFile); } System.out.println(String.format("Using indexing directory %s", indexDir)); LuceneCandidateProvider candProvider = new LuceneCandidateProvider(indexDir, analyzer, similarity); TextCleaner textCleaner = new TextCleaner(stopWords); QuerySource inpQuerySource = SourceFactory.createQuerySource(sourceName, inputFileName); QueryEntry inpQuery = null; BufferedWriter trecOutFile = new BufferedWriter(new FileWriter(new File(trecOutFileName))); int questNum = 0, questQty = 0; long totalTimeMS = 0; while ((inpQuery = inpQuerySource.next()) != null) { if (questQty >= maxQueryQty) break; ++questNum; String queryID = inpQuery.mQueryId; if (randGen.nextDouble() <= fProb) { ++questQty; String tokQuery = spaceJoin.join(textCleaner.cleanUp(inpQuery.mQueryText)); String query = TextCleaner.luceneSafeCleanUp(tokQuery).trim(); ResEntry[] results = null; if (query.isEmpty()) { results = new ResEntry[0]; System.out.println(String.format("WARNING, empty query id = '%s'", inpQuery.mQueryId)); } else { try { long start = System.currentTimeMillis(); results = candProvider.getCandidates(questNum, query, numRet); long end = System.currentTimeMillis(); long searchTimeMS = end - start; totalTimeMS += searchTimeMS; System.out.println(String.format( "Obtained results for the query # %d (answered %d queries), queryID %s the search took %d ms, we asked for max %d entries got %d", questNum, questQty, queryID, searchTimeMS, numRet, results.length)); } catch (ParseException e) { e.printStackTrace(); System.err.println( "Error parsing query: " + query + " orig question is :" + inpQuery.mQueryText); System.exit(1); } } boolean bSave = true; if (qrels != null) { boolean bOk = false; for (ResEntry r : results) { String label = qrels.get(queryID, r.mDocId); if (candProvider.isRelevLabel(label, 1)) { bOk = true; break; } } if (!bOk) bSave = false; } // System.out.println(String.format("Ranking results the query # %d queryId='%s' save results? %b", // questNum, queryID, bSave)); if (bSave) { saveTrecResults(queryID, results, trecOutFile, TREC_RUN, numRet); } } if (questNum % 1000 == 0) System.out.println(String.format("Proccessed %d questions", questNum)); } System.out.println(String.format("Proccessed %d questions, the search took %f MS on average", questQty, (float) totalTimeMS / questQty)); trecOutFile.close(); } catch (ParseException e) { e.printStackTrace(); Usage("Cannot parse arguments: " + e, options); } catch (Exception e) { System.err.println("Terminating due to an exception: " + e); System.exit(1); } }
From source file:fr.iphc.grid.jobmanager.JobManager.java
/** * @param args//from ww w.j av a2 s .c om */ public static void main(String[] args) throws Exception { JobManager command = new JobManager(); CommandLine line = command.parse(args); ArrayList<File> JdlList = new ArrayList<File>(); Global.getOutputexecutor = Executors.newFixedThreadPool(10); Initialize init = new Initialize(); String SetupFile = "setup_vigrid.xml"; if (line.hasOption(OPT_SETUP)) { SetupFile = line.getOptionValue(OPT_SETUP); } if ((new File(SetupFile).isFile())) { init.GlobalSetup(SetupFile); } // Init Job if (line.hasOption(OPT_JOB)) { File file = new File(line.getOptionValue(OPT_JOB)); if ((file.isFile())) { JdlList.add(file); } else { System.err.println("The file " + file + " doesn't exist"); System.exit(-1); } } else { File file = new File(line.getOptionValue(OPT_FILEJOB)); if ((file.isFile())) { JdlList = init.InitJdl(file); } else { System.err.println("The file " + file + " doesn't exist"); System.exit(-1); } } if (line.hasOption(OPT_WAIT)) { Global.TIMEOUTWAIT = Integer.parseInt(line.getOptionValue(OPT_WAIT)); } if (line.hasOption(OPT_RUN)) { Global.TIMEOUTRUN = Integer.parseInt(line.getOptionValue(OPT_RUN)); } if (line.hasOption(OPT_END)) { Global.TIMEOUTEND = Integer.parseInt(line.getOptionValue(OPT_END)); } if (line.hasOption(OPT_LOGDISPLAY)) { Global.SEUILDISPLAYLOG = Float.parseFloat(line.getOptionValue(OPT_LOGDISPLAY)); } init.InitJob(JdlList); // Init Url Ce if (line.hasOption(OPT_QUEUE)) { Global.file = new File(line.getOptionValue(OPT_QUEUE)); } if (line.hasOption(OPT_BAD)) { Global.BadCe = new File(line.getOptionValue(OPT_BAD)); } if (line.hasOption(OPT_OPTIMIZETIMEOUTRUN)) { Global.OPTTIMEOUTRUN = false; } if (line.hasOption(OPT_CWD)) { File theDir = new File(line.getOptionValue(OPT_CWD)); if (!theDir.exists()) { if (!theDir.mkdirs()) { System.err.println("Working directory create failed: " + line.getOptionValue(OPT_CWD)); System.exit(-1); } } Global.Cwd = line.getOptionValue(OPT_CWD); } else { Global.Cwd = System.getProperty("user.dir"); } if (!(new File(Global.Cwd)).canWrite()) { System.err.println(" Write permission denied : " + Global.Cwd); System.exit(-1); } System.out.println("Current working directory : " + Global.Cwd); Date start = new Date(); init.PrintGlobalSetup(); init.InitUrl(Global.file); init.InitSosCe(); init.rmLoadFailed(Global.Cwd + "/loadFailed.txt"); System.out.println("CE: " + Global.ListUrl.size() + " Nb JOB: " + Global.ListJob.size() + " " + new Date()); if (Global.ListJob.size() < 6) { // pour obtenir rapport de 0.8 Global.OPTTIMEOUTRUN = false; } // check if we can connect to the grid try { SessionFactory.createSession(true); } catch (NoSuccessException e) { System.err.println("Could not connect to the grid at all (" + e.getMessage() + ")"); System.err.println("Aborting"); System.exit(0); } // Launch Tread Job JobThread st = new JobThread(Global.ListJob, Global.ListUrl); st.start(); LoggingThread logst = new LoggingThread(Global.ListJob, Global.ListUrl, Global.SEUILDISPLAYLOG); logst.start(); // create Thread Hook intercept kill +CNTL+C Thread hook = new Thread() { public void run() { try { for (Jdl job : Global.ListJob) { if (job.getJobId() != null) { JobThread.jobCancel(job.getJobId()); } } } catch (Exception e) { System.err.println("Thread Hook:\n" + e.getMessage()); } // give it a change to display final job state try { sleep(5000); } catch (InterruptedException e) { e.printStackTrace(); } } }; Runtime.getRuntime().addShutdownHook(hook); // Integer timer = 180 * 60 * 1000; Date now = new Date(); // Boolean Fin = false; while ((!Global.END) && ((now.getTime() - start.getTime()) < Global.TIMEOUTEND * 60 * 1000)) { // TOEND // en // minutes now = new Date(); // int mb = 1024*1024; // Getting the runtime reference from system // Runtime runtime = Runtime.getRuntime(); // System.out.println("##### Heap utilization statistics [MB] // #####"); // Print used memory // System.out.println("Used Memory:" // + (runtime.totalMemory() - runtime.freeMemory()) / mb); // Print free memory // System.out.println("Free Memory:" // + runtime.freeMemory() / mb); // Print total available memory // System.out.println("Total Memory:" + runtime.totalMemory() / mb); // Print Maximum available memory // System.out.println("Max Memory:" + runtime.maxMemory() / mb); // // System.out.println("NB: "+nb_end); // if ((float)(runtime.totalMemory() - // runtime.freeMemory())/(float)runtime.maxMemory() > (float)0.3){ // System.out.println ("GC: "+(float)(runtime.totalMemory() - // runtime.freeMemory())/runtime.maxMemory()); // System.gc(); // }; sleep(15 * 1000); // in ms // System.gc(); // Fin=true; // for (Jdl job : Global.ListJob) { // if (job.getJob() != null) { // System.out.println("JOB: "+job.getId()+"\t"+job.getStatus()); // if (job.getStatus().compareTo("END")==0){ // ((JobImpl) job.getJob()).postStagingAndCleanup(); // System.out.println("END JOB: "+job.getId()); // job.setStatus("END"); // } // if (job.getStatus().compareTo("END")!=0){ // Fin=false; // } // System.out.println("JOB: "+job.getId()+"\t"+job.getStatus() + // "\t"+job.getFail()+"\t"+job.getNodeCe()); // } // } // while ((Global.END==0) && ((new // Date().getTime()-start.getTime())<timer)){ } // Boolean end_load=false; // while (!end_load){ // end_load=true; // for(Jdl job:Global.ListJob){ // if (job.getStatus().equals("LOAD")){ // end_load=false; // } // } // } System.out.println("END JOB: " + now); st.halt(); logst.halt(); Iterator<Url> k = Global.ListUrl.iterator(); while (k.hasNext()) { Url url = k.next(); System.out.println("URL: " + url.getUrl()); } Iterator<Jdl> m = Global.ListJob.iterator(); while (m.hasNext()) { Jdl job = m.next(); System.out.println( "JOB: " + job.getId() + "\t" + job.getFail() + "\t" + job.getStatus() + "\t" + job.getNodeCe()); } System.out.println(start + " " + new Date()); System.exit(0); }
From source file:DIA_Umpire_Quant.DIA_Umpire_ProtQuant.java
/** * @param args the command line arguments *///www . j a va 2 s . c om 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:apps.quantification.LearnQuantificationSVMPerf.java
public static void main(String[] args) throws IOException { String cmdLineSyntax = LearnQuantificationSVMPerf.class.getName() + " [OPTIONS] <path to svm_perf_learn> <path to svm_perf_classify> <trainingIndexDirectory> <outputDirectory>"; Options options = new Options(); OptionBuilder.withArgName("f"); OptionBuilder.withDescription("Number of folds"); OptionBuilder.withLongOpt("f"); OptionBuilder.isRequired(true);/*from w ww . j a va 2 s.c o m*/ OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("c"); OptionBuilder.withDescription("The c value for svm_perf (default 0.01)"); OptionBuilder.withLongOpt("c"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("t"); OptionBuilder.withDescription("Path for temporary files"); OptionBuilder.withLongOpt("t"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("l"); OptionBuilder.withDescription("The loss function to optimize (default 2):\n" + " 0 Zero/one loss: 1 if vector of predictions contains error, 0 otherwise.\n" + " 1 F1: 100 minus the F1-score in percent.\n" + " 2 Errorrate: Percentage of errors in prediction vector.\n" + " 3 Prec/Rec Breakeven: 100 minus PRBEP in percent.\n" + " 4 Prec@p: 100 minus precision at p in percent.\n" + " 5 Rec@p: 100 minus recall at p in percent.\n" + " 10 ROCArea: Percentage of swapped pos/neg pairs (i.e. 100 - ROCArea)."); OptionBuilder.withLongOpt("l"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("w"); OptionBuilder.withDescription("Choice of structural learning algorithm (default 9):\n" + " 0: n-slack algorithm described in [2]\n" + " 1: n-slack algorithm with shrinking heuristic\n" + " 2: 1-slack algorithm (primal) described in [5]\n" + " 3: 1-slack algorithm (dual) described in [5]\n" + " 4: 1-slack algorithm (dual) with constraint cache [5]\n" + " 9: custom algorithm in svm_struct_learn_custom.c"); OptionBuilder.withLongOpt("w"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("p"); OptionBuilder.withDescription("The value of p used by the prec@p and rec@p loss functions (default 0)"); OptionBuilder.withLongOpt("p"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("v"); OptionBuilder.withDescription("Verbose output"); OptionBuilder.withLongOpt("v"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); OptionBuilder.withArgName("s"); OptionBuilder.withDescription("Don't delete temporary training file in svm_perf format (default: delete)"); OptionBuilder.withLongOpt("s"); OptionBuilder.isRequired(false); OptionBuilder.hasArg(false); options.addOption(OptionBuilder.create()); SvmPerfLearnerCustomizer classificationLearnerCustomizer = null; SvmPerfClassifierCustomizer classificationCustomizer = null; int folds = -1; GnuParser parser = new GnuParser(); String[] remainingArgs = null; try { CommandLine line = parser.parse(options, args); remainingArgs = line.getArgs(); classificationLearnerCustomizer = new SvmPerfLearnerCustomizer(remainingArgs[0]); classificationCustomizer = new SvmPerfClassifierCustomizer(remainingArgs[1]); folds = Integer.parseInt(line.getOptionValue("f")); if (line.hasOption("c")) classificationLearnerCustomizer.setC(Float.parseFloat(line.getOptionValue("c"))); if (line.hasOption("w")) classificationLearnerCustomizer.setW(Integer.parseInt(line.getOptionValue("w"))); if (line.hasOption("p")) classificationLearnerCustomizer.setP(Integer.parseInt(line.getOptionValue("p"))); if (line.hasOption("l")) classificationLearnerCustomizer.setL(Integer.parseInt(line.getOptionValue("l"))); if (line.hasOption("v")) classificationLearnerCustomizer.printSvmPerfOutput(true); if (line.hasOption("s")) classificationLearnerCustomizer.setDeleteTrainingFiles(false); if (line.hasOption("t")) { classificationLearnerCustomizer.setTempPath(line.getOptionValue("t")); classificationCustomizer.setTempPath(line.getOptionValue("t")); } } catch (Exception exp) { System.err.println("Parsing failed. Reason: " + exp.getMessage()); HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } assert (classificationLearnerCustomizer != null); if (remainingArgs.length != 4) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp(cmdLineSyntax, options); System.exit(-1); } String indexFile = remainingArgs[2]; File file = new File(indexFile); String indexName = file.getName(); String indexPath = file.getParent(); String outputPath = remainingArgs[3]; SvmPerfLearner classificationLearner = new SvmPerfLearner(); classificationLearner.setRuntimeCustomizer(classificationLearnerCustomizer); FileSystemStorageManager fssm = new FileSystemStorageManager(indexPath, false); fssm.open(); IIndex training = TroveReadWriteHelper.readIndex(fssm, indexName, TroveContentDBType.Full, TroveClassificationDBType.Full); final TextualProgressBar progressBar = new TextualProgressBar("Learning the quantifiers"); IOperationStatusListener status = new IOperationStatusListener() { @Override public void operationStatus(double percentage) { progressBar.signal((int) percentage); } }; QuantificationLearner quantificationLearner = new QuantificationLearner(folds, classificationLearner, classificationLearnerCustomizer, classificationCustomizer, ClassificationMode.PER_CATEGORY, new LogisticFunction(), status); IQuantifier[] quantifiers = quantificationLearner.learn(training); File executableFile = new File(classificationLearnerCustomizer.getSvmPerfLearnPath()); IDataManager classifierDataManager = new SvmPerfDataManager(new SvmPerfClassifierCustomizer( executableFile.getParentFile().getAbsolutePath() + Os.pathSeparator() + "svm_perf_classify")); String description = "_SVMPerf_C-" + classificationLearnerCustomizer.getC() + "_W-" + classificationLearnerCustomizer.getW() + "_L-" + classificationLearnerCustomizer.getL(); if (classificationLearnerCustomizer.getL() == 4 || classificationLearnerCustomizer.getL() == 5) description += "_P-" + classificationLearnerCustomizer.getP(); if (classificationLearnerCustomizer.getAdditionalParameters().length() > 0) description += "_" + classificationLearnerCustomizer.getAdditionalParameters(); String quantifierPrefix = indexName + "_Quantifier-" + folds + description; FileSystemStorageManager fssmo = new FileSystemStorageManager( outputPath + File.separatorChar + quantifierPrefix, true); fssmo.open(); QuantificationLearner.write(quantifiers, fssmo, classifierDataManager); fssmo.close(); BufferedWriter bfs = new BufferedWriter( new FileWriter(outputPath + File.separatorChar + quantifierPrefix + "_rates.txt")); TShortDoubleHashMap simpleTPRs = quantificationLearner.getSimpleTPRs(); TShortDoubleHashMap simpleFPRs = quantificationLearner.getSimpleFPRs(); TShortDoubleHashMap scaledTPRs = quantificationLearner.getScaledTPRs(); TShortDoubleHashMap scaledFPRs = quantificationLearner.getScaledFPRs(); ContingencyTableSet contingencyTableSet = quantificationLearner.getContingencyTableSet(); short[] cats = simpleTPRs.keys(); for (int i = 0; i < cats.length; ++i) { short cat = cats[i]; String catName = training.getCategoryDB().getCategoryName(cat); ContingencyTable contingencyTable = contingencyTableSet.getCategoryContingencyTable(cat); double simpleTPR = simpleTPRs.get(cat); double simpleFPR = simpleFPRs.get(cat); double scaledTPR = scaledTPRs.get(cat); double scaledFPR = scaledFPRs.get(cat); String line = quantifierPrefix + "\ttrain\tsimple\t" + catName + "\t" + cat + "\t" + contingencyTable.tp() + "\t" + contingencyTable.fp() + "\t" + contingencyTable.fn() + "\t" + contingencyTable.tn() + "\t" + simpleTPR + "\t" + simpleFPR + "\n"; bfs.write(line); line = quantifierPrefix + "\ttrain\tscaled\t" + catName + "\t" + cat + "\t" + contingencyTable.tp() + "\t" + contingencyTable.fp() + "\t" + contingencyTable.fn() + "\t" + contingencyTable.tn() + "\t" + scaledTPR + "\t" + scaledFPR + "\n"; bfs.write(line); } bfs.close(); }
From source file:it.unipd.dei.ims.falcon.CmdLine.java
public static void main(String[] args) { // last argument is always index path Options options = new Options(); // one of these actions has to be specified OptionGroup actionGroup = new OptionGroup(); actionGroup.addOption(new Option("i", true, "perform indexing")); // if dir, all files, else only one file actionGroup.addOption(new Option("q", true, "perform a single query")); actionGroup.addOption(new Option("b", false, "perform a query batch (read from stdin)")); actionGroup.setRequired(true);/*w w w. j a v a 2 s .com*/ options.addOptionGroup(actionGroup); // other options options.addOption(new Option("l", "segment-length", true, "length of a segment (# of chroma vectors)")); options.addOption( new Option("o", "segment-overlap", true, "overlap portion of a segment (# of chroma vectors)")); options.addOption(new Option("Q", "quantization-level", true, "quantization level for chroma vectors")); options.addOption(new Option("k", "min-kurtosis", true, "minimum kurtosis for indexing chroma vectors")); options.addOption(new Option("s", "sub-sampling", true, "sub-sampling of chroma features")); options.addOption(new Option("v", "verbose", false, "verbose output (including timing info)")); options.addOption(new Option("T", "transposition-estimator-strategy", true, "parametrization for the transposition estimator strategy")); options.addOption(new Option("t", "n-transp", true, "number of transposition; if not specified, no transposition is performed")); options.addOption(new Option("f", "force-transp", true, "force transposition by an amount of semitones")); options.addOption(new Option("p", "pruning", false, "enable query pruning; if -P is unspecified, use default strategy")); options.addOption(new Option("P", "pruning-custom", true, "custom query pruning strategy")); // parse HelpFormatter formatter = new HelpFormatter(); CommandLineParser parser = new PosixParser(); CommandLine cmd = null; try { cmd = parser.parse(options, args); if (cmd.getArgs().length != 1) throw new ParseException("no index path was specified"); } catch (ParseException ex) { System.err.println("ERROR - parsing command line:"); System.err.println(ex.getMessage()); formatter.printHelp("falcon -{i,q,b} [options] index_path", options); return; } // default values final float[] DEFAULT_TRANSPOSITION_ESTIMATOR_STRATEGY = new float[] { 0.65192807f, 0.0f, 0.0f, 0.0f, 0.3532628f, 0.4997167f, 0.0f, 0.41703504f, 0.0f, 0.16297342f, 0.0f, 0.0f }; final String DEFAULT_QUERY_PRUNING_STRATEGY = "ntf:0.340765*[0.001694,0.995720];ndf:0.344143*[0.007224,0.997113];" + "ncf:0.338766*[0.001601,0.995038];nmf:0.331577*[0.002352,0.997884];"; // TODO not the final one int hashes_per_segment = Integer.parseInt(cmd.getOptionValue("l", "150")); int overlap_per_segment = Integer.parseInt(cmd.getOptionValue("o", "50")); int nranks = Integer.parseInt(cmd.getOptionValue("Q", "3")); int subsampling = Integer.parseInt(cmd.getOptionValue("s", "1")); double minkurtosis = Float.parseFloat(cmd.getOptionValue("k", "-100.")); boolean verbose = cmd.hasOption("v"); int ntransp = Integer.parseInt(cmd.getOptionValue("t", "1")); TranspositionEstimator tpe = null; if (cmd.hasOption("t")) { if (cmd.hasOption("T")) { // TODO this if branch is yet to test Pattern p = Pattern.compile("\\d\\.\\d*"); LinkedList<Double> tokens = new LinkedList<Double>(); Matcher m = p.matcher(cmd.getOptionValue("T")); while (m.find()) tokens.addLast(new Double(cmd.getOptionValue("T").substring(m.start(), m.end()))); float[] strategy = new float[tokens.size()]; if (strategy.length != 12) { System.err.println("invalid transposition estimator strategy"); System.exit(1); } for (int i = 0; i < strategy.length; i++) strategy[i] = new Float(tokens.pollFirst()); } else { tpe = new TranspositionEstimator(DEFAULT_TRANSPOSITION_ESTIMATOR_STRATEGY); } } else if (cmd.hasOption("f")) { int[] transps = parseIntArray(cmd.getOptionValue("f")); tpe = new ForcedTranspositionEstimator(transps); ntransp = transps.length; } QueryPruningStrategy qpe = null; if (cmd.hasOption("p")) { if (cmd.hasOption("P")) { qpe = new StaticQueryPruningStrategy(cmd.getOptionValue("P")); } else { qpe = new StaticQueryPruningStrategy(DEFAULT_QUERY_PRUNING_STRATEGY); } } // action if (cmd.hasOption("i")) { try { Indexing.index(new File(cmd.getOptionValue("i")), new File(cmd.getArgs()[0]), hashes_per_segment, overlap_per_segment, subsampling, nranks, minkurtosis, tpe, verbose); } catch (IndexingException ex) { Logger.getLogger(CmdLine.class.getName()).log(Level.SEVERE, null, ex); } catch (IOException ex) { Logger.getLogger(CmdLine.class.getName()).log(Level.SEVERE, null, ex); } } if (cmd.hasOption("q")) { String queryfilepath = cmd.getOptionValue("q"); doQuery(cmd, queryfilepath, hashes_per_segment, overlap_per_segment, nranks, subsampling, tpe, ntransp, minkurtosis, qpe, verbose); } if (cmd.hasOption("b")) { try { long starttime = System.currentTimeMillis(); BufferedReader in = new BufferedReader(new InputStreamReader(System.in)); String line = null; while ((line = in.readLine()) != null && !line.trim().isEmpty()) doQuery(cmd, line, hashes_per_segment, overlap_per_segment, nranks, subsampling, tpe, ntransp, minkurtosis, qpe, verbose); in.close(); long endtime = System.currentTimeMillis(); System.out.println(String.format("total time: %ds", (endtime - starttime) / 1000)); } catch (IOException ex) { Logger.getLogger(CmdLine.class.getName()).log(Level.SEVERE, null, ex); } } }
From source file:edu.duke.igsp.gkde.Main.java
public static void main(String[] argv) throws Exception { Options opts = new Options(); opts.addOption("s", true, "wiggle track step (default=1)"); opts.addOption("l", true, "feature length (default=600)"); opts.addOption("f", true, "fragment size (default=estimated from data)"); // opts.addOption("b", true, "bandwidth (default=200)"); // opts.addOption("w", true, "window (default=3800"); opts.addOption("wg", true, "wg threshold set (defualt = calculated)"); opts.addOption("c", true, "genomic total read weight (defualt = calculated)"); opts.addOption("h", false, "print usage"); opts.addOption(OptionBuilder.withArgName("input dir").hasArg() .withDescription("input directory (default=current directory)").isRequired(false).create("d")); opts.addOption(OptionBuilder.withArgName("output dir").hasArg() .withDescription("output directory (default=current directory)").isRequired(false).create("o")); opts.addOption(OptionBuilder.withArgName("background dir").hasArg() .withDescription("background directory (default=none)").isRequired(false).create("b")); opts.addOption(OptionBuilder.withArgName("ploidy dir").hasArg() .withDescription("ploidy/input directory (default=none)").isRequired(false).create("p")); opts.addOption(OptionBuilder.withArgName("wig | bed | npf").hasArg() .withDescription("output format (default wig)").isRequired(false).create("of")); opts.addOption(OptionBuilder.withArgName("dnase | chip | faire | atac").hasArg() .withDescription("input data").isRequired(true).create("in")); opts.addOption(OptionBuilder.withArgName("weight clip").hasArg() .withDescription("weight clip value (default none)").isRequired(false).create("wc")); opts.addOption("t", true, "threshold (standard deviations) (default=4.0)"); // opts.addOption("r", true, "background ratio (default=2.0)"); opts.addOption("v", false, "verbose output"); CommandLineParser parser = new GnuParser(); int fragment_size = -1; int fragment_offset = 0; long featureLength = 600l; // float thresh = 2; float threshold = KDEChromosome.Settings.DEFAULT_THRESHOLD; int step = 1; boolean showHelp = false; boolean verbose = false; String inputDirectory = null; String backgroundDirectory = null; String ploidyDirectory = null; String[] files = null;// w w w .j a v a2s.c o m String[] bgfiles = {}; String[] ipfiles = {}; String outputFormat = "wig"; String inputDataType = "dnase"; File outputDirectory = new File(System.getProperty("user.dir")); long bandwidth = 0l; long window = 0l; double ncuts = 0.0d; float temp_threshold = 0f; int weight_clip = 0; System.out.println("F-Seq Version 1.85"); try { CommandLine cmd = parser.parse(opts, argv); showHelp = (cmd.hasOption("h")); verbose = (cmd.hasOption("v")); if (cmd.hasOption("s")) step = Integer.parseInt(cmd.getOptionValue("s")); if (cmd.hasOption("f")) fragment_size = Integer.parseInt(cmd.getOptionValue("f")); if (cmd.hasOption("d")) //input directory inputDirectory = cmd.getOptionValue("d"); if (cmd.hasOption("b")) //background directory backgroundDirectory = cmd.getOptionValue("b"); if (cmd.hasOption("p")) //ploidy|input directory ploidyDirectory = cmd.getOptionValue("p"); if (cmd.hasOption("l")) // bandwidth featureLength = Long.parseLong(cmd.getOptionValue("l")); if (cmd.hasOption("of")) { // output format outputFormat = cmd.getOptionValue("of"); if (!outputFormat.equals("wig") && !outputFormat.equals("bed") && !outputFormat.equals("npf")) { System.out.println("Parameter error: output format must be 'wig' or 'bed'."); showHelp = true; } } if (cmd.hasOption("in")) { // input data type inputDataType = cmd.getOptionValue("in"); if (!inputDataType.equals("dnase") && !inputDataType.equals("chip") && !inputDataType.equals("faire") && !inputDataType.equals("atac")) { System.out.println( "Parameter error: input data type must be 'dnase', 'chip', 'faire', or 'atac'."); showHelp = true; } } if (cmd.hasOption("wc")) { // weight clip weight_clip = Integer.parseInt(cmd.getOptionValue("wc")); } if (cmd.hasOption("t")) { // threshold (standard deviations) threshold = Float.parseFloat(cmd.getOptionValue("t")); } if (cmd.hasOption("o")) { // output directory String out = cmd.getOptionValue("o"); outputDirectory = new File(out); if (!outputDirectory.exists() && !outputDirectory.isDirectory()) { System.out.println("Output directory '" + out + "' is not a valid directory."); showHelp = true; } } if (cmd.hasOption("wg")) temp_threshold = Float.parseFloat(cmd.getOptionValue("wg")); if (cmd.hasOption("c")) ncuts = Double.parseDouble(cmd.getOptionValue("c")); // TESTING ONLY // if(cmd.hasOption("w")) // window // window = Long.parseLong(cmd.getOptionValue("w")); //if(cmd.hasOption("b")) // window // bandwidth = Long.parseLong(cmd.getOptionValue("b")); files = cmd.getArgs(); // input files //bgfiles = cmd.getArgs(); // background files } catch (Exception e) { System.out.println("Error parsing arguments: " + e.getMessage()); e.printStackTrace(); showHelp = true; } if (showHelp || (inputDirectory == null && files.length == 0)) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("fseq [options]... [file(s)]...", opts); System.exit(1); } File[] pfiles = getFiles(inputDirectory, files); File[] background_files = getFiles(backgroundDirectory, bgfiles); File[] ploidy_files = getFiles(ploidyDirectory, ipfiles); KDEChromosome[] chrs = null; // assume all files are of the same type, if not we'll get parsing errors String path = pfiles[0].getPath(); String extension = path.substring(path.lastIndexOf('.')).toLowerCase(); System.out.println("Path: " + path + ", extension: " + extension); if (extension.equals(".bed")) { System.out.println("Parsing BED file."); chrs = BedReader.read(pfiles); } else if (extension.equals(".sam") || extension.equals(".bam")) { System.out.println("Parsing SAM/BAM file."); chrs = SamReader.read(pfiles, weight_clip); } //KDEChromosome[] input = BedReader.read(ifiles); //compute fragment offset if (fragment_size == -1) { fragment_size = wgShiftCalc(chrs); } fragment_offset = (int) (fragment_size / 2); if (ncuts == 0.0d) { for (int i = 0; i < chrs.length; ++i) { // computes the total read weight of all cuts on a chromosome ncuts += chrs[i].getTotalWeight(); } } KDEChromosome.Settings settings = null; if (bandwidth > 0 || window > 0) { settings = new KDEChromosome.Settings(bandwidth, window, threshold, fragment_offset, ncuts, inputDataType); } else { settings = new KDEChromosome.Settings(featureLength, threshold, fragment_offset, ncuts, inputDataType); } float wg_threshold = wgThreshold(settings, chrs); if (temp_threshold != 0f) { wg_threshold = temp_threshold; } //KDEChromosome.Settings bg_settings = null; //bg_settings = new KDEChromosome.Settings(featureLength*2, threshold, fragment_offset); //int background_size = 0; //int input_size = 0; //float bg_ratio = 0; //float sd = 0; if (verbose) { System.out.println("Settings: "); System.out.println("\twindow=" + (settings.window * 2)); System.out.println("\tbandwidth=" + (settings.bandwidth)); //System.out.println("\tfragment offset=" + (settings.offset)); System.out.println("\tthreshold = " + wg_threshold); System.out.println("\test. fragment size = " + fragment_size); System.out.println("\tsequence length = " + chrs[0].getSequenceLength()); } // if(backgroundDirectory != null) { // for(int i = 0; i < input.length; ++i) { // background_size += input[i].getLength(); // } // for(int i = 0; i < chrs.length; ++i) { // input_size += chrs[i].getLength(); // } // bg_ratio = (float)input_size/(float)background_size; // sd = computeSD(bg_settings, input); // //System.out.println("Sample Ratio: " + bg_ratio); // //System.out.println("Input Size: " + input_size); // //System.out.println("Background Size: " + background_size); // //System.out.println("Input standard deviation: " + (settings.threshold * (float)Math.sqrt((double)bg_ratio * (double)sd * (double)sd))); // //System.out.println("Data standard deviation: " + settings.threshold * computeSD(settings, chrs)); // } for (int i = 0; i < chrs.length; ++i) { if (chrs[i].getFirstPos() == chrs[i].getLastPos()) { System.out.println("Warning: " + chrs[i].getChromosome() + " has size zero. Skipping."); continue; } File ofile = Util.makeUniqueFileWithExtension(outputDirectory, chrs[i].getChromosome(), outputFormat); DensityWriter dw = null; if (outputFormat.equals("wig")) { dw = new WiggleDensityWriter(ofile, chrs[i].getChromosome(), chrs[i].getFirstPos(), step); } else { if (outputFormat.equals("npf")) { dw = new NpfDensityWriter(ofile, chrs[i].getChromosome(), chrs[i].getFirstPos(), step); } else { dw = new BedDensityWriter(ofile, chrs[i].getChromosome(), chrs[i].getFirstPos(), step); } } //Function takes all? or new function for each? // if(backgroundDirectory != null) { // boolean hit = false; // for(int j = 0; j < background_files.length; ++j) { // if(background_files[j].getName().equals(chrs[i].getChromosome() + ".bff")) { // System.out.println("Running background on Chromosome " + chrs[i].getChromosome()); // chrs[i].runBG(settings, dw, verbose, wg_threshold, background_files[j]); // hit = true; // } // } // if(!hit) // System.out.println("No background for Chromosome " + chrs[i].getChromosome()); // } else { // if(ploidyDirectory !=) // chrs[i].run(settings, dw, verbose, wg_threshold); // } chrs[i].run(settings, dw, verbose, wg_threshold, background_files, ploidy_files); dw.close(); } //kde.showGraph(); }
From source file:de.prozesskraft.ptest.Fingerprint.java
public static void main(String[] args) throws org.apache.commons.cli.ParseException, IOException { // try// w w w. java2s .c o m // { // if (args.length != 3) // { // System.out.println("Please specify processdefinition file (xml) and an outputfilename"); // } // // } // catch (ArrayIndexOutOfBoundsException e) // { // System.out.println("***ArrayIndexOutOfBoundsException: Please specify processdefinition.xml, openoffice_template.od*, newfile_for_processdefinitions.odt\n" + e.toString()); // } /*---------------------------- get options from ini-file ----------------------------*/ File inifile = new java.io.File( WhereAmI.getInstallDirectoryAbsolutePath(Fingerprint.class) + "/" + "../etc/ptest-fingerprint.ini"); if (inifile.exists()) { try { ini = new Ini(inifile); } catch (InvalidFileFormatException e1) { // TODO Auto-generated catch block e1.printStackTrace(); } catch (IOException e1) { // TODO Auto-generated catch block e1.printStackTrace(); } } else { System.err.println("ini file does not exist: " + inifile.getAbsolutePath()); System.exit(1); } /*---------------------------- create boolean options ----------------------------*/ Option ohelp = new Option("help", "print this message"); Option ov = new Option("v", "prints version and build-date"); /*---------------------------- create argument options ----------------------------*/ Option opath = OptionBuilder.withArgName("PATH").hasArg() .withDescription( "[mandatory; default: .] the root path for the tree you want to make a fingerprint from.") // .isRequired() .create("path"); Option osizetol = OptionBuilder.withArgName("FLOAT").hasArg().withDescription( "[optional; default: 0.02] the sizeTolerance (as factor in percent) of all file entries will be set to this value. [0.0 < sizetol < 1.0]") // .isRequired() .create("sizetol"); Option omd5 = OptionBuilder.withArgName("no|yes").hasArg() .withDescription("[optional; default: yes] should be the md5sum of files determined? no|yes") // .isRequired() .create("md5"); Option oignore = OptionBuilder.withArgName("STRING").hasArgs() .withDescription("[optional] path-pattern that should be ignored when creating the fingerprint") // .isRequired() .create("ignore"); Option oignorefile = OptionBuilder.withArgName("FILE").hasArg().withDescription( "[optional] file with path-patterns (one per line) that should be ignored when creating the fingerprint") // .isRequired() .create("ignorefile"); Option ooutput = OptionBuilder.withArgName("FILE").hasArg() .withDescription("[mandatory; default: <path>/fingerprint.xml] fingerprint file") // .isRequired() .create("output"); Option of = new Option("f", "[optional] force overwrite fingerprint file if it already exists"); /*---------------------------- create options object ----------------------------*/ Options options = new Options(); options.addOption(ohelp); options.addOption(ov); options.addOption(opath); options.addOption(osizetol); options.addOption(omd5); options.addOption(oignore); options.addOption(oignorefile); options.addOption(ooutput); options.addOption(of); /*---------------------------- create the parser ----------------------------*/ CommandLineParser parser = new GnuParser(); try { // parse the command line arguments commandline = parser.parse(options, args); } catch (Exception exp) { // oops, something went wrong System.err.println("Parsing failed. Reason: " + exp.getMessage()); exiter(); } /*---------------------------- usage/help ----------------------------*/ if (commandline.hasOption("help")) { HelpFormatter formatter = new HelpFormatter(); formatter.printHelp("fingerprint", options); System.exit(0); } else if (commandline.hasOption("v")) { System.out.println("web: " + web); System.out.println("author: " + author); System.out.println("version:" + version); System.out.println("date: " + date); System.exit(0); } /*---------------------------- ueberpruefen ob eine schlechte kombination von parametern angegeben wurde ----------------------------*/ String path = ""; String sizetol = ""; boolean md5 = false; Float sizetolFloat = null; String output = ""; java.io.File ignorefile = null; ArrayList<String> ignore = new ArrayList<String>(); if (!(commandline.hasOption("path"))) { System.err.println("setting default for -path=."); path = "."; } else { path = commandline.getOptionValue("path"); } if (!(commandline.hasOption("sizetol"))) { System.err.println("setting default for -sizetol=0.02"); sizetol = "0.02"; sizetolFloat = 0.02F; } else { sizetol = commandline.getOptionValue("sizetol"); sizetolFloat = Float.parseFloat(sizetol); if ((sizetolFloat > 1) || (sizetolFloat < 0)) { System.err.println("use only values >=0.0 and <1.0 for -sizetol"); System.exit(1); } } if (!(commandline.hasOption("md5"))) { System.err.println("setting default for -md5=yes"); md5 = true; } else if (commandline.getOptionValue("md5").equals("no")) { md5 = false; } else if (commandline.getOptionValue("md5").equals("yes")) { md5 = true; } else { System.err.println("use only values no|yes for -md5"); System.exit(1); } if (commandline.hasOption("ignore")) { ignore.addAll(Arrays.asList(commandline.getOptionValues("ignore"))); } if (commandline.hasOption("ignorefile")) { ignorefile = new java.io.File(commandline.getOptionValue("ignorefile")); if (!ignorefile.exists()) { System.err.println("warn: ignore file does not exist: " + ignorefile.getCanonicalPath()); } } if (!(commandline.hasOption("output"))) { System.err.println("setting default for -output=" + path + "/fingerprint.xml"); output = path + "/fingerprint.xml"; } else { output = commandline.getOptionValue("output"); } // wenn output bereits existiert -> abbruch java.io.File outputFile = new File(output); if (outputFile.exists()) { if (commandline.hasOption("f")) { outputFile.delete(); } else { System.err .println("error: output file (" + output + ") already exists. use -f to force overwrite."); System.exit(1); } } // if ( !( commandline.hasOption("output")) ) // { // System.err.println("option -output is mandatory."); // exiter(); // } /*---------------------------- die lizenz ueberpruefen und ggf abbrechen ----------------------------*/ // check for valid license ArrayList<String> allPortAtHost = new ArrayList<String>(); allPortAtHost.add(ini.get("license-server", "license-server-1")); allPortAtHost.add(ini.get("license-server", "license-server-2")); allPortAtHost.add(ini.get("license-server", "license-server-3")); MyLicense lic = new MyLicense(allPortAtHost, "1", "user-edition", "0.1"); // lizenz-logging ausgeben for (String actLine : (ArrayList<String>) lic.getLog()) { System.err.println(actLine); } // abbruch, wenn lizenz nicht valide if (!lic.isValid()) { System.exit(1); } /*---------------------------- die eigentliche business logic ----------------------------*/ Dir dir = new Dir(); dir.setBasepath(path); dir.setOutfilexml(output); // ignore file in ein Array lesen if ((ignorefile != null) && (ignorefile.exists())) { Scanner sc = new Scanner(ignorefile); while (sc.hasNextLine()) { ignore.add(sc.nextLine()); } sc.close(); } // // autoignore hinzufuegen // String autoIgnoreString = ini.get("autoignore", "autoignore"); // ignoreLines.addAll(Arrays.asList(autoIgnoreString.split(","))); // // debug // System.out.println("ignorefile content:"); // for(String actLine : ignore) // { // System.out.println("line: "+actLine); // } try { dir.genFingerprint(sizetolFloat, md5, ignore); } catch (NullPointerException e) { System.err.println("file/dir does not exist " + path); e.printStackTrace(); exiter(); } catch (IOException e) { e.printStackTrace(); exiter(); } System.out.println("writing to file: " + dir.getOutfilexml()); dir.writeXml(); }
From source file:uk.co.moonsit.rmi.GraphClient.java
@SuppressWarnings("SleepWhileInLoop") public static void main(String args[]) { Properties p = new Properties(); try {//ww w . j av a2 s . c o m p.load(new FileReader("graph.properties")); } catch (IOException ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } //String[] labels = p.getProperty("labels").split(","); GraphClient demo = null; int type = 0; boolean log = false; if (args[0].equals("-l")) { log = true; } switch (type) { case 0: try { System.setProperty("java.security.policy", "file:./client.policy"); if (System.getSecurityManager() == null) { System.setSecurityManager(new RMISecurityManager()); } String name = "GraphServer"; String host = p.getProperty("host"); System.out.println(host); Registry registry = LocateRegistry.getRegistry(host); String[] list = registry.list(); for (String s : list) { System.out.println(s); } GraphDataInterface gs = null; boolean bound = false; while (!bound) { try { gs = (GraphDataInterface) registry.lookup(name); bound = true; } catch (NotBoundException e) { System.err.println("GraphServer exception:" + e.toString()); Thread.sleep(500); } } @SuppressWarnings("null") String config = gs.getConfig(); System.out.println(config); /*float[] fs = gs.getValues(); for (float f : fs) { System.out.println(f); }*/ demo = new GraphClient(gs, 1000, 700, Float.parseFloat(p.getProperty("frequency")), log); demo.init(config); demo.run(); } catch (RemoteException e) { System.err.println("GraphClient exception:" + e.toString()); } catch (FileNotFoundException ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } catch (IOException ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } catch (Exception ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } finally { if (demo != null) { demo.close(); } } break; case 1: try { demo = new GraphClient(1000, 700, Float.parseFloat(p.getProperty("frequency"))); demo.init("A^B|Time|Error|-360|360"); demo.addData(0, 1, 100); demo.addData(0, 2, 200); demo.addData(1, 1, 50); demo.addData(1, 2, 450); } catch (FileNotFoundException ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } catch (IOException ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } catch (Exception ex) { Logger.getLogger(GraphClient.class.getName()).log(Level.SEVERE, null, ex); } break; } }
From source file:DIA_Umpire_Quant.DIA_Umpire_Quant.java
/** * @param args the command line arguments *///from w ww . 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 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; } }