Examples with StructureToPolymerChains edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains used on opensource projects

Example 16 with StructureToPolymerChains

use of edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains in project mmtf-spark by sbl-sdsc.

the class SecondaryStructureWord2VecEncoder method main.

/**
 * @param args outputFilePath outputFormat (json|parquet)
 * @throws IOException
 * @throws StructureException
 */
public static void main(String[] args) throws IOException {
    String path = MmtfReader.getMmtfReducedPath();
    if (args.length != 2) {
        System.err.println("Usage: " + SecondaryStructureWord2VecEncoder.class.getSimpleName() + " <outputFilePath> + <fileFormat>");
        System.exit(1);
    }
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(SecondaryStructureWord2VecEncoder.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // read MMTF Hadoop sequence file and create a non-redundant Pisces
    // subset set (<=20% seq. identity) of L-protein chains
    int sequenceIdentity = 20;
    double resolution = 3.0;
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.readSequenceFile(path, sc).flatMapToPair(new StructureToPolymerChains()).filter(new Pisces(sequenceIdentity, resolution));
    // get content
    int segmentLength = 11;
    Dataset<Row> data = SecondaryStructureSegmentExtractor.getDataset(pdb, segmentLength);
    // add Word2Vec encoded feature vector
    ProteinSequenceEncoder encoder = new ProteinSequenceEncoder(data);
    int n = 2;
    int windowSize = (segmentLength - 1) / 2;
    int vectorSize = 50;
    data = encoder.overlappingNgramWord2VecEncode(n, windowSize, vectorSize);
    data.printSchema();
    data.show(25, false);
    if (args[1].equals("json")) {
        // coalesce data into a single file
        data = data.coalesce(1);
    }
    data.write().mode("overwrite").format(args[1]).save(args[0]);
    long end = System.nanoTime();
    System.out.println(TimeUnit.NANOSECONDS.toSeconds(end - start) + " sec.");
}

Example 17 with StructureToPolymerChains

use of edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains in project mmtf-spark by sbl-sdsc.

the class DSSPDemo method main.

public static void main(String[] args) throws IOException {
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[1]").setAppName(CustomReportDemo.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // single protein chain
    List<String> pdbIds = Arrays.asList("1STP");
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.downloadFullMmtfFiles(pdbIds, sc).cache();
    pdb = pdb.flatMapToPair(new StructureToPolymerChains());
    Dataset<Row> ds = SecondaryStructureExtractor.getDataset(pdb);
    // show the schema of this dataset
    ds.printSchema();
    ds.show(2, false);
    long end = System.nanoTime();
    System.out.println("Time:     " + (end - start) / 1E9 + "sec.");
    sc.close();
}

Example 18 with StructureToPolymerChains

use of edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains in project mmtf-spark by sbl-sdsc.

the class SecondaryStructureElementDemo method main.

public static void main(String[] args) throws IOException {
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[1]").setAppName(CustomReportDemo.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // single protein chain
    List<String> pdbIds = Arrays.asList("1STP");
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.downloadReducedMmtfFiles(pdbIds, sc).cache();
    pdb = pdb.flatMapToPair(new StructureToPolymerChains()).filter(new ContainsLProteinChain());
    Dataset<Row> ds = SecondaryStructureElementExtractor.getDataset(pdb, "E", 6);
    // show the top 50 rows of this dataset
    ds.show(50, false);
    long end = System.nanoTime();
    System.out.println("Time: " + TimeUnit.NANOSECONDS.toSeconds(end - start) + " sec.");
    sc.close();
}

Example 19 with StructureToPolymerChains

use of edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains in project mmtf-spark by sbl-sdsc.

the class SecondaryStructureSegmentDemo method main.

public static void main(String[] args) throws IOException {
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(CustomReportDemo.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // single protein chain
    List<String> pdbIds = Arrays.asList("1STP");
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.downloadReducedMmtfFiles(pdbIds, sc).cache();
    pdb = pdb.flatMapToPair(new StructureToPolymerChains()).filter(new ContainsLProteinChain());
    int segmentLength = 25;
    Dataset<Row> ds = SecondaryStructureSegmentExtractor.getDataset(pdb, segmentLength);
    // show the top 50 rows of this dataset
    ds.show(50, false);
    long end = System.nanoTime();
    System.out.println("Time: " + TimeUnit.NANOSECONDS.toSeconds(end - start) + " sec.");
    sc.close();
}

Example 20 with StructureToPolymerChains

use of edu.sdsc.mmtf.spark.mappers.StructureToPolymerChains in project mmtf-spark by sbl-sdsc.

the class MmtfImporterTest method test3.

@Test
public void test3() throws IOException {
    Path p = Paths.get("./src/main/resources/files/test");
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfImporter.importPdbFiles(p.toString(), sc);
    assertTrue(pdb.count() == 1);
    pdb = pdb.flatMapToPair(new StructureToPolymerChains());
    assertEquals(8, pdb.count());
}