List of usage examples for com.mongodb MongoClient getDatabase
public MongoDatabase getDatabase(final String databaseName)
From source file:module.script.epimed_ontology.UpdateFetalAdultOvary.java
License:Open Source License
public UpdateFetalAdultOvary() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); ClTopologyDao topologyDao = new ClTopologyDao(session); ClTopology adultOvary = topologyDao.find("C56.9"); ClTopology fetalOvary = topologyDao.find("E56.9"); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); MongoCollection<Document> collectionSample = db.getCollection("sample"); Bson filters = Filters.and(Filters.eq("exp_group.id_topology", "C56.9"), // ovary Filters.eq("exp_group.id_tissue_stage", 1) // adult );// w w w .j a v a 2s .c o m List<Document> samples = collectionSample.find(filters).into(new ArrayList<Document>()); for (Document sample : samples) { Document expgroup = sample.get("exp_group", Document.class); expgroup.append("id_topology", adultOvary.getIdTopology()); expgroup.append("topology", adultOvary.getName()); sample.append("exp_group", expgroup); collectionSample.updateOne(Filters.eq("_id", sample.getString("_id")), new Document("$set", sample)); } System.out.println(samples.size()); // === Commit transaction === // session.getTransaction().commit(); session.getTransaction().rollback(); if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.ImportArrayExpress1733.java
License:Open Source License
public ImportArrayExpress1733() { // ===== Connection ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); MongoCollection<Document> collectionSeries = db.getCollection("series"); MongoCollection<Document> collectionSamples = db.getCollection("samples"); // ===== Pattern ===== String patternText = "\\[[\\p{Print}\\p{Space}]+\\]"; ;//from w w w . j a v a 2 s . c o m Pattern pattern = Pattern.compile(patternText); // ===== Series ===== for (String accession : listAccessions) { List<String> accessionAsList = new ArrayList<String>(); accessionAsList.add(accession); String urlString = "https://www.ebi.ac.uk/arrayexpress/files/" + accession + "/" + accession + ".idf.txt"; System.out.println(urlString); String text = webService.loadUrl(urlString); String[] parts = text.split(lineSeparator); List<String> dataSeries = new ArrayList<String>(Arrays.asList(parts)); AESeries series = new AESeries(dataSeries); System.out.println(series); // ===== Check if already imported as a GSE ===== boolean isGseFound = false; String gseNumber = null; for (String secondaryAccession : series.getListAccessions()) { if (secondaryAccession.startsWith("GSE")) { gseNumber = secondaryAccession; Document gse = db.getCollection("series").find(Filters.eq("_id", secondaryAccession)).first(); isGseFound = gse != null; } } int nbImportedSamples = 0; if (!isGseFound) { // ===== Create Mongo series ===== Document docSeries = mongoService.createSeries(accession, series.getTitle(), null, series.getSubmissionDate(), series.getSubmissionDate()); if (series.getListAccessions() != null && !series.getListAccessions().isEmpty()) { docSeries.put("secondary_accessions", series.getListAccessions()); } if (false) { UpdateResult updateResult = collectionSeries.updateOne(Filters.eq("_id", accession), new Document("$set", docSeries)); if (updateResult.getMatchedCount() == 0) { collectionSeries.insertOne(docSeries); } } System.out.println(docSeries); // ===== Import clinical data ===== String url = "https://www.ebi.ac.uk/arrayexpress/files/" + accession + "/" + series.getSdrf(); System.out.println(url); String clindata = webService.loadUrl(url); String[] clinparts = clindata.split(lineSeparator); List<String> data = new ArrayList<String>(Arrays.asList(clinparts)); // ===== Recognize samples ===== List<String> header = this.createHeader(data.get(0), pattern); System.out.println(header); for (int i = 1; i < data.size(); i++) { Integer nbSamples = data.size() - 1; Map<String, Object> mapParameters = this.createMapParameters(data.get(i), header); String idSample = this.createIdSample(mapParameters); if (idSample == null) { System.err.println("ERROR: idSample is not recongnized for " + accession); System.out.println("Line " + i); System.out.println(mapParameters); mongoClient.close(); System.exit(0); } else { if (formatIdSample) { idSample = "E-MTAB-2836" + "-" + idSample; idSample = idSample.trim().replaceAll(" ", "-"); } } idSample = idSample.split(" ")[0].trim(); // === Organism === String organism = (String) mapParameters.get("organism"); if (organism == null || organism.isEmpty()) { organism = defaultOrganism; } // === Platform === String platform = (String) mapParameters.get("LIBRARY_STRATEGY"); if (platform != null && !platform.isEmpty()) { platform = platform.toLowerCase().trim(); } else { platform = defaultPlatform; } Document docSampleExist = collectionSamples.find(Filters.eq("_id", idSample)).first(); boolean docAlreadyExist = docSampleExist != null; System.out.println("docAlreadyExist " + docAlreadyExist); // === Delete old if already exist === if (docAlreadyExist) { List<String> listSeries = (List<String>) docSampleExist.get("series"); Set<String> setSeries = new HashSet<String>(); listSeries.add(accession); setSeries.addAll(listSeries); listSeries.clear(); listSeries.addAll(setSeries); docSampleExist.append("series", listSeries); System.out.println(docSampleExist); if (commit) { collectionSamples.deleteOne(eq("_id", docSampleExist.get("_id"))); collectionSamples.insertOne(docSampleExist); } } } } else { System.out.println("GEO accession " + gseNumber + " corresponding to " + accession + " exists already. Skip import."); } System.out.println("Number of imported samples: " + nbImportedSamples); } mongoClient.close(); }
From source file:module.script.ImportSupplementaryGSE20711.java
License:Open Source License
public ImportSupplementaryGSE20711() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); MongoCollection<Document> collection = db.getCollection("samples"); // ===== Excel data loader ===== String inputfile = this.getInputDirectory() + this.getDirSeparator() + "GSE20711_emmm0003-0726-SD2.xlsx"; System.out.println("LOADING \t " + inputfile); ExcelService excelService = new ExcelService(); excelService.load(inputfile);//from www .j a v a2s . c o m String gseNumber = "GSE20711"; for (int i = 0; i < excelService.getData().size(); i++) { List<Object> dataLine = excelService.getData().get(i); String bcString = (String) dataLine.get(0); bcString = bcString.replaceAll("BC", ""); Integer bcNumber = Integer.parseInt(bcString); Document docSample = collection .find(Filters .and(Filters.in("series", gseNumber), Filters.eq("exp_group.sample_title", "Breast tumor from patient P_" + bcNumber + " (expression data)"))) .first(); System.out.println("-------------------------------------------"); System.out.println(dataLine); System.out.println(docSample); } if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.ImportSupplementaryGSE25219.java
License:Open Source License
@SuppressWarnings({ "unused", "unchecked" }) public ImportSupplementaryGSE25219() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); MongoCollection<Document> collection = db.getCollection("samples"); // ===== Excel data loader ===== String inputfile = this.getInputDirectory() + this.getDirSeparator() + "NIHMS321722-supplement-7.xlsx"; System.out.println("LOADING \t " + inputfile); ExcelService excelService = new ExcelService(); excelService.load(inputfile);/*from w w w . j a va 2 s. c o m*/ // ===== Format raw data into data structures ====== List<Map<String, String>> listMap = new ArrayList<Map<String, String>>(); List<String> headerMap = new ArrayList<String>(); Map<String, String> mapBrain = new HashMap<String, String>(); for (int i = 0; i < excelService.getData().size(); i++) { List<Object> dataLine = excelService.getData().get(i); String brainCode = (String) dataLine.get(0); if (brainCode != null) { mapBrain = new HashMap<String, String>(); } // Existing brain code if (dataLine != null && dataLine.size() > 2 && dataLine.get(1) != null && dataLine.get(2) != null) { // System.out.println(dataLine.get(1) + " = " + dataLine.get(2)); mapBrain.put(dataLine.get(1).toString().trim(), dataLine.get(2).toString().trim()); } if (brainCode != null) { // New Brain code // System.out.println("brain code " + brainCode); headerMap.add(brainCode); listMap.add(mapBrain); } } // ===== Recognize data ===== for (int i = 0; i < headerMap.size(); i++) { System.out.println("----------------------------"); String code = headerMap.get(i); System.out.println(i + " " + code); Map<String, String> map = listMap.get(i); Map<String, String> updatedMap = new HashMap<String, String>(); for (Map.Entry<String, String> entry : map.entrySet()) { String key = entry.getKey(); String value = entry.getValue(); if (!key.toLowerCase().equals("age") // && !key.toLowerCase().equals("ethnicity") // && !key.toLowerCase().equals("sex") && !value.toLowerCase().equals("no data")) { updatedMap.put(key, value); } // System.out.println(key + " -> " + value); } List<Document> listDocuments = collection .find(Filters.and(Filters.eq("exp_group.main_gse_number", "GSE25219"), Filters.eq("parameters.brain code", code))) .into(new ArrayList<Document>()); System.out.println("Number of corresponding Mongo documents " + listDocuments.size()); System.out.println(updatedMap); for (int j = 0; j < listDocuments.size(); j++) { Document doc = listDocuments.get(j); Document parameters = (Document) doc.get("parameters"); parameters.putAll(updatedMap); System.out.println("\t" + parameters); // Update Mongo document doc.put("parameters", parameters); doc.put("analyzed", true); UpdateResult updateResult = collection.updateOne(Filters.eq("_id", doc.get("_id")), new Document("$set", doc)); } } if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.pro12.CreatePro12.java
License:Open Source License
@SuppressWarnings({ "unchecked" }) public CreatePro12() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); // MongoDatabase db = mongoClient.getDatabase("geo"); MongoCollection<Document> collectionSeries = db.getCollection("series"); Date submissionDate = null;//from w ww. jav a 2 s. c o m try { submissionDate = dateFormat.parse("2010-01-01"); } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); } List<String> platforms = new ArrayList<String>(); platforms.add("GPL570"); Document docSeries = new Document(); docSeries.append("_id", "PRO12").append("title", "Project 12: Reference tissues and cell lines") .append("platforms", platforms).append("submission_date", submissionDate) .append("last_update", submissionDate).append("import_date", new Date()); System.out.println(docSeries); collectionSeries.insertOne(docSeries); if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.pro12.TransferPro12.java
License:Open Source License
@SuppressWarnings({ "unchecked" }) public TransferPro12() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); MongoCollection<Document> collection = db.getCollection("samples"); String sql = "select id_sample from epimed_prod.om_sample join epimed_prod.om_sample_series using (id_sample) " + "join epimed_prod.om_series using (id_series) where id_series='PRO12'"; List<String> list = session.createSQLQuery(sql).list(); Document pro12 = new Document(); pro12.append("series", "PRO12"); for (String gsmNumber : list) { Document doc = collection.find(Filters.eq("_id", gsmNumber)).first(); System.out.println("-----------------------------"); System.out.println(gsmNumber + " " + doc); if (doc != null) { // Update Mongo document collection.updateOne(Filters.eq("_id", gsmNumber), new Document("$push", pro12)); }//from ww w .ja v a 2 s . c o m } if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.proallchen.CreateProallChen.java
License:Open Source License
public CreateProallChen() { // ===== Session PostgreSQL ===== SessionFactory sessionFactory = HibernateUtil .buildSessionFactory("config/epimed_semantic.hibernate.cfg.xml"); Session session = sessionFactory.openSession(); // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); // MongoDatabase db = mongoClient.getDatabase("geo"); MongoCollection<Document> collectionSeries = db.getCollection("series"); Date submissionDate = null;//from w ww . j a v a 2 s .c o m try { submissionDate = dateFormat.parse("2016-05-13"); } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); } // List<String> platforms = new ArrayList<String>(); // platforms.add("GPL570"); Document docSeries = new Document(); docSeries.append("_id", "PROALL_CHEN") .append("title", "Genomic Profiling of Adult and Pediatric B-cell Acute Lymphoblastic Leukemia") .append("platforms", null).append("submission_date", submissionDate) .append("last_update", submissionDate).append("import_date", new Date()); System.out.println(docSeries); collectionSeries.insertOne(docSeries); if (session.isOpen()) { session.close(); } sessionFactory.close(); mongoClient.close(); }
From source file:module.script.proallchen.ImportProallChenOriginal.java
License:Open Source License
public ImportProallChenOriginal() { // ===== Connection ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); // ===== Samples ====== MongoCollection<Document> collectionSamples = db.getCollection("samples"); // ===== Excel data loader ===== String inputfile = this.getInputDirectory() + this.getDirSeparator() + "PROALL_CHEN_clinical.xlsx"; System.out.println("LOADING \t " + inputfile); ExcelService excelService = new ExcelService(); excelService.load(inputfile);//from www. j a v a2 s . co m System.out.println(excelService.getHeader()); String idSeries = "PROALL_CHEN"; List<String> listSeries = new ArrayList<String>(); listSeries.add(idSeries); for (int i = 0; i < excelService.getData().size(); i++) { List<Object> line = excelService.getData().get(i); String idSample = "ESM" + line.get(0); System.out.println(idSample + " " + line); Document docSample = collectionSamples.find(Filters.eq("_id", idSample.trim())).first(); System.out.println(docSample); Document parameters = (Document) docSample.get("parameters"); for (int j = 0; j < excelService.getHeader().size(); j++) { String header = (String) excelService.getHeader().get(j); Object value = line.get(j); // System.out.println(header + " = " + value); parameters.append(header, value); } System.out.println(parameters); // Update Mongo document docSample.put("parameters", parameters); UpdateResult updateResult = collectionSamples.updateOne(Filters.eq("_id", docSample.get("_id")), new Document("$set", docSample)); } mongoClient.close(); }
From source file:module.script.proallchen.ImportProallChenSupplementary.java
License:Open Source License
public ImportProallChenSupplementary() { // ===== Connection ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); // ===== Samples ====== MongoCollection<Document> collectionSamples = db.getCollection("samples"); // ===== Excel data loader ===== String inputfile = this.getInputDirectory() + this.getDirSeparator() + "DB_ALL_JIN_RNASEC_clinical_data_supplementary.xlsx"; System.out.println("LOADING \t " + inputfile); ExcelService excelService = new ExcelService(); excelService.load(inputfile);/*w ww. jav a 2 s .co m*/ System.out.println(excelService.getHeader()); String idSeries = "PROALL_CHEN"; List<String> listSeries = new ArrayList<String>(); listSeries.add(idSeries); for (int i = 0; i < excelService.getData().size(); i++) { List<Object> line = excelService.getData().get(i); String idSample = "ESM" + line.get(0); System.out.println(idSample + " " + line); // ===== Sample Document ===== Document docSample = new Document(); docSample.append("_id", idSample).append("main_gse_number", idSeries).append("series", listSeries) .append("organism", "Homo sapiens").append("submission_date", today) .append("last_update", today).append("import_date", today).append("analyzed", false); // ===== Mandatory parameters ===== Document expGroup = generateExpGroup(idSeries, idSample); docSample.append("exp_group", expGroup); // ===== Supplementary parameters ===== Document parameters = new Document(); parameters.append("id_sample", idSample); // === Attributes === for (int j = 0; j < excelService.getHeader().size(); j++) { String header = (String) excelService.getHeader().get(j); Object value = line.get(j); // System.out.println(header + " = " + value); parameters.append(header, value); } docSample.append("parameters", parameters); System.out.println(docSample); // === Delete if already exist === collectionSamples.deleteOne(eq("_id", idSample)); // ===== Insert data ===== collectionSamples.insertOne(docSample); } mongoClient.close(); }
From source file:module.script.probcp.CreateProbcp.java
License:Open Source License
@SuppressWarnings({ "unchecked" }) public CreateProbcp() { // ===== Session Mongo ===== MongoClient mongoClient = MongoUtil.buildMongoClient(); MongoDatabase db = mongoClient.getDatabase("epimed_experiments"); // MongoDatabase db = mongoClient.getDatabase("geo"); MongoCollection<Document> collectionSeries = db.getCollection("series"); Date submissionDate = null;/*from ww w.ja v a 2 s .c om*/ try { submissionDate = dateFormat.parse("2017-03-20"); } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); } List<String> platforms = new ArrayList<String>(); platforms.add("proteomics"); Document docSeries = new Document(); docSeries.append("_id", "PROBCP").append("title", "Breast cancer proteomics").append("platforms", platforms) .append("submission_date", submissionDate).append("last_update", submissionDate) .append("import_date", new Date()); System.out.println(docSeries); collectionSeries.insertOne(docSeries); mongoClient.close(); }