Beispiel #1
0
  @Test
  public void testLoadSIF() throws Exception {
    String filepath = TestUtils.DATA_DIR + "sample/BRCA_sif.txt";
    List<String> expectedAttributeNames =
        Arrays.asList(
            "TCGA_EXPERIMENT",
            "TCGA_BATCH",
            "TUMOR_NORMAL",
            "BIRDSEED_GENDER",
            "LEVEL2_NOISE",
            "LEVEL3_SEGMENT_COUNT",
            "PURITY	PLOIDY",
            "DELTA",
            "CANCER_DNA_FRACTION",
            "SUBCLONAL_GENOME_FRACTION");

    tstLoadFi(filepath, 0, false); // Sample information file, shouldn't have tracks.

    Set<String> attrNames = new HashSet<String>(AttributeManager.getInstance().getAttributeNames());

    assertTrue(
        attrNames.size()
            >= expectedAttributeNames.size()); // Can be larger because of default attributes
    for (String name : expectedAttributeNames) {
      assertTrue(expectedAttributeNames.contains(name));
    }
  }
Beispiel #2
0
  /**
   * Test loading sample information file from a sql database, using a profile
   *
   * @throws Exception
   */
  @Test
  public void testLoadSampleInfoProfile() throws Exception {

    AttributeManager.getInstance().clearAllAttributes();
    String path = TestUtils.DATA_DIR + "sql/sampleinfo_brca_sif_profile.dbxml";

    int expectedTracks = 0;
    List<Track> tracks = trackLoader.load(new ResourceLocator(path), genome);
    assertEquals(expectedTracks, tracks.size());

    String[] attrNames =
        "TCGA_EXPERIMENT	TCGA_BATCH	TUMOR_NORMAL	BIRDSEED_GENDER	LEVEL2_NOISE	LEVEL3_SEGMENT_COUNT	PURITY	PLOIDY	DELTA	CANCER_DNA_FRACTION	SUBCLONAL_GENOME_FRACTION"
            .split("\\s+");
    Set<String> expAttrNames = new HashSet<String>(Arrays.asList(attrNames));
    List<String> actAttrNames = AttributeManager.getInstance().getAttributeNames();
    actAttrNames.remove("NAME");
    actAttrNames.remove("DATA TYPE");
    actAttrNames.remove("DATA FILE");
    assertEquals(actAttrNames.size(), expAttrNames.size());
    for (String attrName : actAttrNames) {
      assertTrue(expAttrNames.contains(attrName));
    }
  }
Beispiel #3
0
  /**
   * Switches on various attributes of locator (mainly locator path extension and whether the
   * locator is indexed) to call the appropriate loading method.
   *
   * @param locator
   * @param genome
   * @return
   */
  public List<Track> load(ResourceLocator locator, Genome genome) throws DataLoadException {

    final String path = locator.getPath().trim();
    log.info("Loading resource, path " + path);
    try {
      String typeString = locator.getTypeString();

      if (typeString.endsWith(".tbi")) {
        MessageUtils.showMessage(
            "<html><b>Error:</b>File type '.tbi' is not recognized.  If this is a 'tabix' index <br>"
                + " load the associated gzipped file, which should have an extension of '.gz'");
      }

      // This list will hold all new tracks created for this locator
      List<Track> newTracks = new ArrayList<Track>();

      String dbUrl = locator.getDBUrl();
      LoadHandler handler = getTrackLoaderHandler(typeString);
      if (dbUrl != null) {
        this.loadFromDatabase(locator, newTracks, genome);
      } else if (typeString.endsWith(".dbxml")) {
        loadFromDBProfile(locator, newTracks);
      } else if (typeString.endsWith(".gmt")) {
        loadGMT(locator);
      } else if (typeString.equals("das")) {
        loadDASResource(locator, newTracks);
      } else if (typeString.endsWith(".vcf.list")) {
        loadVCFListFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".trio")) {
        loadTrioData(locator);
      } else if (typeString.endsWith("varlist")) {
        VariantListManager.loadVariants(locator);
      } else if (typeString.endsWith("samplepathmap")) {
        VariantListManager.loadSamplePathMap(locator);
      } else if (typeString.endsWith(".rnai.gct")) {
        loadRnaiGctFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".gct")
          || typeString.endsWith("res")
          || typeString.endsWith("tab")) {
        loadGctFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".gbk") || typeString.endsWith(".gb")) {
        loadGbkFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".cn")
          || typeString.endsWith(".xcn")
          || typeString.endsWith(".snp")
          || typeString.endsWith(".igv")
          || typeString.endsWith(".loh")) {
        loadIGVFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".cbs")
          || typeString.endsWith(".seg")
          || typeString.endsWith("glad")
          || typeString.endsWith("birdseye_canary_calls")
          || typeString.endsWith(".seg.zip")) {
        loadSegFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".gistic")) {
        loadGisticFile(locator, newTracks);
      } else if (typeString.endsWith(".gs")) {
        loadRNAiGeneScoreFile(locator, newTracks, RNAIGeneScoreParser.Type.GENE_SCORE, genome);
      } else if (typeString.endsWith(".riger")) {
        loadRNAiGeneScoreFile(locator, newTracks, RNAIGeneScoreParser.Type.POOLED, genome);
      } else if (typeString.endsWith(".hp")) {
        loadRNAiHPScoreFile(locator);
      } else if (typeString.contains(".tabblastn") || typeString.endsWith(".orthologs")) {
        loadSyntentyMapping(locator, newTracks);
      } else if (typeString.endsWith(".sam")
          || typeString.endsWith(".bam")
          || typeString.endsWith(".cram")
          || typeString.endsWith(".sam.list")
          || typeString.endsWith(".bam.list")
          || typeString.endsWith(".aligned")
          || typeString.endsWith(".sai")
          || typeString.endsWith(".bai")
          || typeString.equals("alist")
          || typeString.equals(Ga4ghAPIHelper.RESOURCE_TYPE)) {
        loadAlignmentsTrack(locator, newTracks, genome);
      } else if (typeString.endsWith(".wig")
          || typeString.endsWith(".bedgraph")
          || typeString.endsWith(".bdg")
          || typeString.endsWith("cpg.txt")
          || typeString.endsWith(".expr")) {
        loadWigFile(locator, newTracks, genome);
      } else if (typeString.endsWith("fpkm_tracking")
          || typeString.endsWith("gene_exp.diff")
          || typeString.endsWith("cds_exp.diff")) {
        loadCufflinksFile(locator, newTracks, genome);
      } else if (typeString.contains(".dranger")) {
        loadDRangerFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".ewig.tdf") || (typeString.endsWith(".ewig.ibf"))) {
        loadEwigIBFFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".bw")
          || typeString.endsWith(".bb")
          || typeString.endsWith(".bigwig")
          || typeString.endsWith(".bigbed")) {
        loadBWFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".ibf") || typeString.endsWith(".tdf")) {
        loadTDFFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".counts")) {
        loadGobyCountsArchive(locator, newTracks, genome);
      } else if (WiggleParser.isWiggle(locator)) {
        loadWigFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".maf")) {
        loadMultipleAlignmentTrack(locator, newTracks, genome);
      } else if (typeString.endsWith(".maf.dict")) {
        loadMultipleAlignmentTrack(locator, newTracks, genome);
      } else if (typeString.contains(".peak.bin")) {
        loadPeakTrack(locator, newTracks, genome);
      } else if (typeString.endsWith("mage-tab")
          || ExpressionFileParser.parsableMAGE_TAB(locator)) {
        locator.setDescription("MAGE_TAB");
        loadGctFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".bp")) {
        loadBasePairFile(locator, newTracks, genome);
      } else if (GWASParser.isGWASFile(typeString)) {
        loadGWASFile(locator, newTracks, genome);
      } else if (GobyAlignmentQueryReader.supportsFileType(path)) {
        loadAlignmentsTrack(locator, newTracks, genome);
      } else if (typeString.endsWith(".list")) {
        // This should be deprecated
        loadListFile(locator, newTracks, genome);
      } else if (typeString.endsWith(".smap")) {
        loadSMAPFile(locator, newTracks, genome);
      } else if (CodecFactory.hasCodec(locator, genome) && !forceNotTribble(typeString)) {
        loadTribbleFile(locator, newTracks, genome);
      } else if (handler != null) {
        // Custom loader specified
        log.info(String.format("Loading %s with %s", path, handler));
        handler.load(path, newTracks);
      } else if (AttributeManager.isSampleInfoFile(locator)) {
        // This might be a sample information file.
        AttributeManager.getInstance().loadSampleInfo(locator);
      } else {
        MessageUtils.showMessage("<html>Unknown file type: " + path + "<br>Check file extension");
      }

      // Track line
      TrackProperties tp = null;
      String trackLine = locator.getTrackLine();
      if (trackLine != null) {
        tp = new TrackProperties();
        ParsingUtils.parseTrackLine(trackLine, tp);
      }

      for (Track track : newTracks) {

        if (locator.getFeatureInfoURL() != null) {
          track.setUrl(locator.getFeatureInfoURL());
        }
        if (tp != null) {
          track.setProperties(tp);
        }
        if (locator.getColor() != null) {
          track.setColor(locator.getColor());
        }
        if (locator.getSampleId() != null) {
          track.setSampleId(locator.getSampleId());
        }
      }

      return newTracks;
    } catch (Exception e) {
      if (!NOLogExceptions.contains(e.getClass())) {
        log.error(e.getMessage(), e);
      }
      throw new DataLoadException(e.getMessage());
    }
  }