Java SAMSequenceDictionary.addSequence方法代码示例

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@DataProvider(name="haplotypeMapForWriting")
public Object[][] haplotypeMapForWriting() {

    SAMFileHeader header = new SAMFileHeader();
    header.setSortOrder(SAMFileHeader.SortOrder.coordinate);
    SAMSequenceDictionary sd = new SAMSequenceDictionary();
    sd.addSequence(new SAMSequenceRecord("chr1", 101));
    sd.addSequence(new SAMSequenceRecord("chr2", 101));
    sd.addSequence(new SAMSequenceRecord("chr3", 101));
    header.setSequenceDictionary(sd);


    HaplotypeMap newMap = new HaplotypeMap(header);
    HaplotypeBlock t1 = new HaplotypeBlock(0.151560926);
    t1.addSnp(new Snp("snp2", "chr1", 83, (byte)'A', (byte)'G', .16, null));
    t1.addSnp(new Snp("snp1", "chr1", 51, (byte)'T', (byte)'C', 0.15, Collections.singletonList("SQNM_1CHIP_FingerprintAssays")));
    newMap.addHaplotype(t1);
    HaplotypeBlock t2 = new HaplotypeBlock(.02d);
    t2.addSnp(new Snp("snp3", "chr2", 24, (byte)'C', (byte)'A', .20, null));
    newMap.addHaplotype(t2);

    return new Object[][]{{newMap}};
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test
public void testCompareLocatables() throws Exception {
    final SAMSequenceDictionary dict = new SAMSequenceDictionary();
    dict.addSequence(new SAMSequenceRecord("1", 1000));
    dict.addSequence(new SAMSequenceRecord("2", 1000));
    final SimpleInterval chr1_1_100 = new SimpleInterval("1:1-100");
    final SimpleInterval chr1_5_100 = new SimpleInterval("1:5-100");
    final SimpleInterval chr2_1_100 = new SimpleInterval("2:1-100");

    // equal intervals comparison return 0
    Assert.assertEquals(IntervalUtils.compareLocatables(chr1_1_100, chr1_1_100, dict), 0);
    Assert.assertEquals(IntervalUtils.compareLocatables(chr1_5_100, chr1_5_100, dict), 0);
    Assert.assertEquals(IntervalUtils.compareLocatables(chr2_1_100, chr2_1_100, dict), 0);
    // first < second return negative
    Assert.assertTrue(IntervalUtils.compareLocatables(chr1_1_100, chr1_5_100, dict) < 0);
    Assert.assertTrue(IntervalUtils.compareLocatables(chr1_1_100, chr2_1_100, dict) < 0);
    Assert.assertTrue(IntervalUtils.compareLocatables(chr1_5_100, chr2_1_100, dict) < 0);
    // first > second return positive
    Assert.assertTrue(IntervalUtils.compareLocatables(chr2_1_100, chr1_1_100, dict) > 0);
    Assert.assertTrue(IntervalUtils.compareLocatables(chr2_1_100, chr1_5_100, dict) > 0);
    Assert.assertTrue(IntervalUtils.compareLocatables(chr1_5_100, chr1_1_100, dict) > 0);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@DataProvider
public Object[][] testLocatableOrderingData() {
    final SAMSequenceDictionary dict = new SAMSequenceDictionary();
    dict.addSequence(new SAMSequenceRecord("1", 1000));
    dict.addSequence(new SAMSequenceRecord("2", 1000));

    return new Object[][] {
            // first, second, dictionary, expectedIsBefore, expectedIsAfter, expectedContigComparison
            { new SimpleInterval("1", 1, 100), new SimpleInterval("1", 200, 300), dict, true, false, 0 },
            { new SimpleInterval("1", 1, 100), new SimpleInterval("1", 101, 200), dict, true, false, 0 },
            { new SimpleInterval("1", 1, 100), new SimpleInterval("1", 100, 200), dict, false, false, 0 },
            { new SimpleInterval("1", 1, 100), new SimpleInterval("1", 99, 200), dict, false, false, 0 },

            { new SimpleInterval("1", 200, 300), new SimpleInterval("1", 1, 100), dict, false, true, 0 },
            { new SimpleInterval("1", 101, 200), new SimpleInterval("1", 1, 100), dict, false, true, 0 },
            { new SimpleInterval("1", 100, 200), new SimpleInterval("1", 1, 100), dict, false, false, 0 },
            { new SimpleInterval("1", 99, 200), new SimpleInterval("1", 1, 100), dict, false, false, 0 },

            { new SimpleInterval("1", 1, 100), new SimpleInterval("2", 1, 100), dict, true, false, -1 },
            { new SimpleInterval("1", 1, 100), new SimpleInterval("2", 101, 200), dict, true, false, -1 },
            { new SimpleInterval("1", 101, 200), new SimpleInterval("2", 1, 100), dict, true, false, -1 },
            { new SimpleInterval("2", 1, 100), new SimpleInterval("1", 1, 100), dict, false, true, 1 },
            { new SimpleInterval("2", 101, 200), new SimpleInterval("1", 1, 100), dict, false, true, 1 },
            { new SimpleInterval("2", 1, 100), new SimpleInterval("1", 101, 200), dict, false, true, 1 }
    };
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test
public void testMalformedAmbiguousQuerySucceeds() {
    final SAMSequenceDictionary sd = getAmbiguousSequenceDictionary();
    final String queryString = "contig:abc-dce";

    sd.addSequence(new SAMSequenceRecord("contig", 99));
    sd.addSequence(new SAMSequenceRecord(queryString, 99));

    // the query string matches as a full contig, but also has a prefix that matches the contig "contig". When
    // viewed as the latter, however, the start-end positions fail to parse as numbers. This resolves as a query
    // against the longer contig "contig:abc-dce", and logs a warning
    HashSet<SimpleInterval> expectedIntervals = new HashSet<>();
    expectedIntervals.add(new SimpleInterval(queryString, 1, 99));
    Assert.assertEquals(
            new HashSet<>(IntervalUtils.getResolvedIntervals(queryString, sd)),
            new HashSet<>(expectedIntervals));
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test
public void testTerminatingPlusSign() {
    // special case test for a query "prefix:+", where "prefix:" is a valid contig
    final SAMSequenceDictionary sd = getAmbiguousSequenceDictionary();
    final String contigPrefix = "prefix:";
    sd.addSequence(new SAMSequenceRecord(contigPrefix, 99));
    Assert.assertEquals(
            new HashSet<>(IntervalUtils.getResolvedIntervals(contigPrefix + "+", sd)),
            new HashSet<>());

    sd.addSequence(new SAMSequenceRecord(contigPrefix + "+", 99));
    HashSet<SimpleInterval> expectedIntervals = new HashSet<>();
    expectedIntervals.add(new SimpleInterval("prefix:+", 1, 99));
    Assert.assertEquals(
            new HashSet<>(IntervalUtils.getResolvedIntervals(contigPrefix + "+", sd)),
            expectedIntervals);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test
public void testContigHasColon() {
    SAMFileHeader header = new SAMFileHeader();
    header.setSortOrder(htsjdk.samtools.SAMFileHeader.SortOrder.coordinate);
    SAMSequenceDictionary dict = new SAMSequenceDictionary();
    SAMSequenceRecord rec = new SAMSequenceRecord("c:h:r1", 10);
    rec.setSequenceLength(10);
    dict.addSequence(rec);
    header.setSequenceDictionary(dict);

    final GenomeLocParser myGenomeLocParser = new GenomeLocParser(header.getSequenceDictionary());
    GenomeLoc loc = myGenomeLocParser.parseGenomeLoc("c:h:r1:4-5");
    assertEquals(0, loc.getContigIndex());
    assertEquals(loc.getStart(), 4);
    assertEquals(loc.getStop(), 5);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test(groups = "spark")
public void testDoSetPairFlags() {

    final JavaSparkContext ctx = SparkContextFactory.getTestSparkContext();
    final SAMSequenceDictionary seq = new SAMSequenceDictionary();
    seq.addSequence(new SAMSequenceRecord("test_seq", 1000));
    final SAMFileHeader header = new SAMFileHeader(seq);

    final List<GATKRead> readList = makeReadSet(header);
    final JavaRDD<GATKRead> reads = ctx.parallelize(readList);
    ;

    final List<GATKRead> result = PSFilter.setPairFlags(reads, 100).collect();

    Assert.assertEquals(result.size(), 6);
    for (final GATKRead read : result) {
        if (read.getName().equals("paired_1") || read.getName().equals("paired_2")) {
            Assert.assertTrue(read.isPaired());
        } else {
            Assert.assertFalse(read.isPaired());
        }
    }

}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
/**
 * Creates an artificial sam header, matching the parameters, chromosomes which will be labeled chr1, chr2, etc
 *
 * @param numberOfChromosomes the number of chromosomes to create
 * @param startingChromosome  the starting number for the chromosome (most likely set to 1)
 * @param chromosomeSize      the length of each chromosome
 * @return
 */
public static SAMFileHeader createArtificialSamHeader(int numberOfChromosomes, int startingChromosome, int chromosomeSize) {
    SAMFileHeader header = new SAMFileHeader();
    header.setSortOrder(htsjdk.samtools.SAMFileHeader.SortOrder.coordinate);
    SAMSequenceDictionary dict = new SAMSequenceDictionary();
    // make up some sequence records
    for (int x = startingChromosome; x < startingChromosome + numberOfChromosomes; x++) {
        SAMSequenceRecord rec = new SAMSequenceRecord("chr" + (x), chromosomeSize /* size */);
        rec.setSequenceLength(chromosomeSize);
        dict.addSequence(rec);
    }
    header.setSequenceDictionary(dict);
    return header;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
private SAMSequenceDictionary createDictionary(List<Chromosome> chromosomes) {
    SAMSequenceDictionary newDictionary = new SAMSequenceDictionary();
    for (Chromosome chromosome : chromosomes) {
        newDictionary.addSequence(new SAMSequenceRecord(chromosome.getName(), chromosome.getSize()));
    }
    return newDictionary;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
static SAMSequenceDictionary ReadDict(File fastafile) {
	SAMSequenceDictionary dict = new SAMSequenceDictionary();
	
	try {
		BufferedReader reader = null;
		if(fastafile.getName().endsWith(".gz")) {
			reader = new BufferedReader(new FileReader(fastafile.getCanonicalPath().substring(0,fastafile.getCanonicalPath().lastIndexOf(".gz") ) +".fai"));
		}
		else {
			reader = new BufferedReader(new FileReader(fastafile.getCanonicalPath() +".fai"));
		}
		
	
		String line;
		String[] split;
		
		while((line = reader.readLine())!=null) {				
			split = line.split("\t");
			SAMSequenceRecord record = new SAMSequenceRecord(split[0], Integer.parseInt(split[1]));
			dict.addSequence(record);				
		}
		reader.close();
	}
	catch(Exception e){
		
		e.printStackTrace();
	}
		return dict;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
/** Get SamSequenceDictionary either from local file or from built-in resources.
 * If reading from resources, "genome" is the tag before '.genome'. E.g. 
 * 'hg19' will read file hg19.genome  
 * */
private boolean setSamSeqDictFromGenomeFile(String genome) throws IOException {

	SAMSequenceDictionary samSeqDict= new SAMSequenceDictionary();

	BufferedReader reader=null;
	try{
		// Attempt to read from resource
		InputStream res= Main.class.getResourceAsStream("/genomes/" + genome + ".genome");
		reader= new BufferedReader(new InputStreamReader(res));
	} catch (NullPointerException e){
		try{
			// Read from local file
			reader= new BufferedReader(new FileReader(new File(genome)));
		} catch (FileNotFoundException ex){
			return false; 
		}
	}
	
	String line = null;
	while ((line = reader.readLine()) != null) {
		if(line.trim().isEmpty() || line.trim().startsWith("#")){
			continue;
		}
		String[] chromLine= line.split("\t");
		SAMSequenceRecord sequenceRecord = new SAMSequenceRecord(chromLine[0], Integer.parseInt(chromLine[1]));
		samSeqDict.addSequence(sequenceRecord);
	}
	reader.close();
	this.setSamSeqDictSource(genome);
	this.setSamSeqDict(samSeqDict);
	return true;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
private GenomeLocParser createGenomeLocParser() {
    SAMSequenceDictionary dict = new SAMSequenceDictionary();
    for (Chromosome chr : GenomeManager.getInstance().getCurrentGenome().getChromosomes()) {
        dict.addSequence(new SAMSequenceRecord(chromoNameToStandard(chr.getName()), chr.getLength()));
    }
    return new GenomeLocParser(dict);
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
public static SAMSequenceDictionary getSequenceDictionary(Configuration conf) throws IOException {
    int counter = conf.getInt(dictionaryCount, 0);
    SAMSequenceDictionary dict = new SAMSequenceDictionary();
    for(int i = 0; i < counter; i++) {
        String seqName = conf.get(dictionarySequenceName + i);
        int seqLength = conf.getInt(dictionarySequenceLength + i, 0);
        SAMSequenceRecord seq = new SAMSequenceRecord(seqName, seqLength);
        dict.addSequence(seq);
    }
    return dict;
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test
public void testIsSequenceDictionaryFromIndexNegative() throws Exception {
    SAMSequenceDictionary dict = new SAMSequenceDictionary();
    dict.addSequence(new SAMSequenceRecord("1", 99));
    dict.addSequence(new SAMSequenceRecord("2", 99));
    Assert.assertFalse(IndexUtils.isSequenceDictionaryFromIndex(dict));
}
 

import htsjdk.samtools.SAMSequenceDictionary; //导入方法依赖的package包/类
@Test(expectedExceptions = NumberFormatException.class)
public void testMalformedQueryFail() {
    final SAMSequenceDictionary sd = getAmbiguousSequenceDictionary();
    sd.addSequence(new SAMSequenceRecord("contig:1-10", 99));
    sd.addSequence(new SAMSequenceRecord("contig", 99));
    IntervalUtils.getResolvedIntervals("contig:abc-dce", sd);
}