Examples with ExperimentalMethods edu.sdsc.mmtf.spark.filters.ExperimentalMethods used on opensource projects

Example 1 with ExperimentalMethods

use of edu.sdsc.mmtf.spark.filters.ExperimentalMethods in project mmtf-spark by sbl-sdsc.

the class WriteMmtfCustom method main.

/**
 * @param args
 * @throws FileNotFoundException
 */
public static void main(String[] args) throws FileNotFoundException {
    String path = MmtfReader.getMmtfFullPath();
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(WriteMmtfCustom.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // read a 20% random sample of the PDB
    double fraction = 0.2;
    long seed = 123;
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.readSequenceFile(path, fraction, seed, sc);
    // retain high resolution X-ray structures
    pdb = pdb.filter(new ExperimentalMethods(ExperimentalMethods.X_RAY_DIFFRACTION)).filter(new Resolution(0, 2.0)).filter(new Rfree(0, 0.2));
    // coalesce this into 8 partitions to avoid creating many small files
    pdb = pdb.coalesce(8);
    // save this subset in a Hadoop Sequence file
    MmtfWriter.writeSequenceFile(path + "_xray", sc, pdb);
    System.out.println("# structures in custom set: " + pdb.count());
    long end = System.nanoTime();
    System.out.println("Time: " + (end - start) / 1E9 + "sec.");
    sc.close();
}

Example 2 with ExperimentalMethods

use of edu.sdsc.mmtf.spark.filters.ExperimentalMethods in project mmtf-spark by sbl-sdsc.

the class MapToTuple4 method main.

public static void main(String[] args) throws FileNotFoundException {
    String path = MmtfReader.getMmtfReducedPath();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(MapToTuple4.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // sample a small fraction of the PDB
    double fraction = 0.001;
    long seed = 123;
    // read PDB, use X-ray structures only, and create a Tuple with PDB ID,
    // resolution, r-free, and r-work
    MmtfReader.readSequenceFile(path, fraction, seed, sc).filter(new ExperimentalMethods(ExperimentalMethods.X_RAY_DIFFRACTION)).map(t -> new Tuple4<String, Float, Float, Float>(t._1, t._2.getResolution(), t._2.getRfree(), t._2.getRwork())).foreach(t -> System.out.println(t));
    sc.close();
}

Example 3 with ExperimentalMethods

use of edu.sdsc.mmtf.spark.filters.ExperimentalMethods in project mmtf-spark by sbl-sdsc.

the class FilterByExperimentalMethods method main.

public static void main(String[] args) throws FileNotFoundException {
    String path = MmtfReader.getMmtfReducedPath();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(FilterByExperimentalMethods.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    MmtfReader.readSequenceFile(path, // read MMTF hadoop sequence file
    sc).filter(new ExperimentalMethods(ExperimentalMethods.NEUTRON_DIFFRACTION)).filter(new ExperimentalMethods(ExperimentalMethods.X_RAY_DIFFRACTION)).keys().foreach(// print the keys (using a lambda expression)
    key -> System.out.println(key));
    sc.close();
}