Examples of picard.illumina.parser.ReadStructure

picard.illumina.parser.ReadStructure
Describes the intended logical output structure of clusters of an Illumina run. (e.g. If the input data consists of 80 base clusters and we provide a read structure of "36T8B36T" then those bases should be split into 3 reads: read one should be 36 cycles of template, read two should be 8 cycles of barcode, read three should be another 36 cycle template read.) Note: In future releases, ReadStructures will be specified by clients of IlluminaDataProvider(currently read structures are detected by IlluminaDataProviderFactory via the structure of QSeq files). When working with QSeq formats, while the individual reads need not fall on QSeq end file boundaries the total number of cycles should equal the total number of cycles found in all end files for one tile. (e.g. if I have 80 reads and 3 end files per tile, those end files should have a total of 80 reads in them regardless of how many reads appear in each individual file) @author jburke@broadinstitute.org

        /**
         * In extract illumina barcodes we NEVER want to look at the template reads, therefore replace them with skips because
         * IlluminaDataProvider and its factory will not open these nor produce ClusterData with the template reads in them, thus reducing
         * the file IO and value copying done by the data provider
         */
        readStructure = new ReadStructure(READ_STRUCTURE.replaceAll("T", "S"));
        final IlluminaDataType[] datatypes = (MINIMUM_BASE_QUALITY > 0) ?
                new IlluminaDataType[]{IlluminaDataType.BaseCalls, IlluminaDataType.PF, IlluminaDataType.QualityScores} :
                new IlluminaDataType[]{IlluminaDataType.BaseCalls, IlluminaDataType.PF};
        factory = new IlluminaDataProviderFactory(BASECALLS_DIR, LANE, readStructure, bclQualityEvaluationStrategy, datatypes);

View Full Code Here

        IOUtil.assertDirectoryIsReadable(BASECALLS_DIR);
        if (OUTPUT == null) OUTPUT = new File(BASECALLS_DIR, String.format("LANE%s_basecalling_metrics", LANE));
        IOUtil.assertFileIsWritable(OUTPUT);


        final IlluminaDataProviderFactory factory;
        final ReadStructure readStructure = new ReadStructure(READ_STRUCTURE);
        final BclQualityEvaluationStrategy bclQualityEvaluationStrategy = new BclQualityEvaluationStrategy(BclQualityEvaluationStrategy.ILLUMINA_ALLEGED_MINIMUM_QUALITY);


        if (INPUT == null) {
            // TODO: Legacy support. Remove when INPUT is required, after all old workflows are through
            factory = new IlluminaDataProviderFactory(BASECALLS_DIR, LANE, readStructure, bclQualityEvaluationStrategy,

View Full Code Here

            metrics.SD_PCT_PF_CLUSTERS_PER_TILE = Double.valueOf(decFormat.format(laneToPctPfClusterHistogram.getStandardDeviationBinSize(meanPctPfClustersPerTile) * 100));


            metrics.TOTAL_CLUSTERS = (long) this.tileToClusterHistogram.getSumOfValues();
            metrics.PF_CLUSTERS    = (long) this.tileToPfClusterHistogram.getSumOfValues();
            
            final ReadStructure readStructure = new ReadStructure(READ_STRUCTURE);
            int templateBaseCountPerCluster = 0;
            for (int i = 0; i < readStructure.templates.length(); i++) templateBaseCountPerCluster += readStructure.templates.get(i).length;
            metrics.TOTAL_READS = metrics.TOTAL_CLUSTERS * readStructure.templates.length();
            metrics.PF_READS = metrics.PF_CLUSTERS * readStructure.templates.length();
            metrics.TOTAL_BASES = metrics.TOTAL_CLUSTERS * templateBaseCountPerCluster;

View Full Code Here

            barcodeSamWriterMap.put(null, buildSamFileWriter(OUTPUT, SAMPLE_ALIAS, LIBRARY_NAME, buildSamHeaderParameters(null)));
        } else {
            populateWritersFromLibraryParams();
        }


        readStructure = new ReadStructure(READ_STRUCTURE);


        final int numOutputRecords = readStructure.templates.length();


        basecallsConverter = new IlluminaBasecallsConverter<SAMRecordsForCluster>(BASECALLS_DIR, BARCODES_DIR, LANE, readStructure,
                barcodeSamWriterMap, true, MAX_READS_IN_RAM_PER_TILE/numOutputRecords, TMP_DIR, NUM_PROCESSORS, FORCE_GC,

View Full Code Here

            LIBRARY_PARAMS = BARCODE_PARAMS;
        }


        final ArrayList<String> messages = new ArrayList<String>();


        readStructure = new ReadStructure(READ_STRUCTURE);
        if (!readStructure.barcodes.isEmpty()) {
            if (LIBRARY_PARAMS == null) {
                messages.add("BARCODE_PARAMS or LIBRARY_PARAMS is missing.  If READ_STRUCTURE contains a B (barcode)" +
                        " then either LIBRARY_PARAMS or BARCODE_PARAMS(deprecated) must be provided!");
            }

View Full Code Here

        new CheckIlluminaDirectory().instanceMainWithExit(argv);
    }


    @Override
    protected int doWork() {
        final ReadStructure readStructure = new ReadStructure(READ_STRUCTURE);
        if (DATA_TYPES.isEmpty()) {
            DATA_TYPES.addAll(Arrays.asList(IlluminaBasecallsConverter.DATA_TYPES_NO_BARCODE));
        }


        final List<Integer> failingLanes = new ArrayList<Integer>();

View Full Code Here

                readNameEncoder = new IlluminaReadNameEncoder(RUN_BARCODE);
                break;
        }
        
        final BclQualityEvaluationStrategy bclQualityEvaluationStrategy = new BclQualityEvaluationStrategy(MINIMUM_QUALITY);
        readStructure = new ReadStructure(READ_STRUCTURE);
        if (MULTIPLEX_PARAMS != null) {
            IOUtil.assertFileIsReadable(MULTIPLEX_PARAMS);
        }
        final boolean demultiplex;
        if (OUTPUT_PREFIX != null) {

View Full Code Here

                    "MULTIPLEX_PARAMS=" + libraryParams,
                    "MACHINE_NAME=machine1",
                    "FLOWCELL_BARCODE=abcdeACXX"
            });


            final ReadStructure readStructure = new ReadStructure(readStructureString);
            for (final File outputSam : outputPrefixes) {
                for (int i = 1; i <= readStructure.templates.length(); ++i) {
                    final String filename = outputSam.getName() + "." + i + ".fastq";
                    IOUtil.assertFilesEqual(new File(outputSam.getParentFile(), filename), new File(testDataDir, filename));
                }

View Full Code Here

        Assert.assertEquals(illuminaFields[1], "N");


        barcodeParser.close();


        // Tack on test of barcode-informed Illumina Basecall parsing
        final ReadStructure rs = new ReadStructure("25T8B25T");
        final IlluminaDataProviderFactory factory = new IlluminaDataProviderFactory(basecallsDir, lane, rs,
                new BclQualityEvaluationStrategy(BclQualityEvaluationStrategy.ILLUMINA_ALLEGED_MINIMUM_QUALITY),
                IlluminaDataType.BaseCalls, IlluminaDataType.QualityScores, IlluminaDataType.Barcodes);
        testParsing(factory, rs, metricOne, barcodePosition);
    }

View Full Code Here

        return outObjs;
    }


    @Test(dataProvider = "validReadStructures")
    public void testValidStructuresFromString(final String rsString, final List<ReadDescriptor> descriptors, final int numTemplates, final int numBarcodes, final int numSkips) {
        final ReadStructure readStructure = new ReadStructure(rsString);
        testReadStructure(readStructure, rsString, descriptors, numTemplates, numBarcodes, numSkips);
    }

View Full Code Here

0 1

TOP

Related Classes of picard.illumina.parser.ReadStructure

picard.illumina.CheckIlluminaDirectory

picard.illumina.CollectIlluminaBasecallingMetrics

picard.illumina.CollectIlluminaBasecallingMetrics$IlluminaMetricCounts

picard.illumina.ExtractIlluminaBarcodes

picard.illumina.ExtractIlluminaBarcodesTest

picard.illumina.IlluminaBasecallsToFastq

picard.illumina.IlluminaBasecallsToFastqTest

picard.illumina.IlluminaBasecallsToSam

picard.illumina.IlluminaLaneMetricsCollectorTest

picard.illumina.ReadStructureTest

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.