Examples with StructureDataInterface org.rcsb.mmtf.api.StructureDataInterface used on opensource projects

Example 26 with StructureDataInterface

use of org.rcsb.mmtf.api.StructureDataInterface in project mmtf-spark by sbl-sdsc.

the class MapToBioAssembly method main.

public static void main(String[] args) {
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(CustomReportDemo.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    List<String> pdbIds = Arrays.asList("1HV4");
    JavaPairRDD<String, StructureDataInterface> bioassemblies = MmtfReader.downloadFullMmtfFiles(pdbIds, sc).flatMapToPair(new StructureToBioassembly());
    System.out.println("Number of bioassemblies for 1HV4: " + bioassemblies.count());
    sc.close();
}

Example 27 with StructureDataInterface

use of org.rcsb.mmtf.api.StructureDataInterface in project mmtf-spark by sbl-sdsc.

the class MapToBioAssembly2 method main.

public static void main(String[] args) throws FileNotFoundException, IOException {
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(CustomReportDemo.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    long start = System.nanoTime();
    // List<String> pdbIds = Arrays.asList("1HV4");
    // List<String> pdbIds = Arrays.asList("2HHB");
    // JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader
    // .downloadFullMmtfFiles(pdbIds, sc);
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.readFullSequenceFile(sc).filter(new Pisces(20, 3.0));
    // System.out.println("**** AU ****");
    // pdb.foreach(t -> TraverseStructureHierarchy.printStructureData(t._2));
    JavaPairRDD<String, StructureDataInterface> bioassemblies = pdb.flatMapToPair(new StructureToBioassembly2());
    System.out.println("Number of bioassemblies: " + bioassemblies.count());
    long end = System.nanoTime();
    System.out.println("time: " + (end - start) / 1E9 + " sec.");
    // System.out.println("**** BA ****");
    // bioassemblies.foreach(t -> TraverseStructureHierarchy.printStructureData(t._2));
    // bioassemblies.foreach(t -> TraverseStructureHierarchy.printChainEntityGroupAtomInfo(t._2));
    sc.close();
}

Example 28 with StructureDataInterface

use of org.rcsb.mmtf.api.StructureDataInterface in project mmtf-spark by sbl-sdsc.

the class RosettaToMmtfFull method main.

/**
 * Converts a directory containing Rosetta-style PDB files into an MMTF-Hadoop Sequence file.
 * The input directory is traversed recursively to find PDB files.
 *
 * <p> Example files from Gremlin website:
 * https://gremlin2.bakerlab.org/meta/aah4043_final.zip
 *
 * @param args args[0] <path-to-pdb_files>, args[1] <path-to-mmtf-hadoop-file>
 *
 * @throws FileNotFoundException
 */
public static void main(String[] args) throws FileNotFoundException {
    if (args.length != 2) {
        System.out.println("Usage: RosettaToMmtfFull <path-to-pdb_files> <path-to-mmtf-hadoop-file>");
    }
    // path to input directory
    String pdbPath = args[0];
    // path to output directory
    String mmtfPath = args[1];
    // instantiate Spark
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName("RosettaToMmtfFull");
    JavaSparkContext sc = new JavaSparkContext(conf);
    // read PDB files recursively starting the specified directory
    JavaPairRDD<String, StructureDataInterface> structures = MmtfImporter.importPdbFiles(pdbPath, sc);
    // save as an MMTF-Hadoop Sequence File
    MmtfWriter.writeSequenceFile(mmtfPath, sc, structures);
    // close Spark
    sc.close();
}

Example 29 with StructureDataInterface

use of org.rcsb.mmtf.api.StructureDataInterface in project mmtf-spark by sbl-sdsc.

the class TraverseStructureHierarchy method main.

public static void main(String[] args) {
    // instantiate Spark. Each Spark application needs these two lines of code.
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(ReadMmtfReduced.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // List<String> pdbIds = Arrays.asList("5UTV"); // multiple models
    // List<String> pdbIds = Arrays.asList("1BZ1"); // multiple protein chains
    // List<String> pdbIds = Arrays.asList("1STP"); // single protein chain
    // structure with 2 bioassemblies
    List<String> pdbIds = Arrays.asList("1HV4");
    // List<String> pdbIds = Arrays.asList("2NBK"); // single protein chain
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.downloadFullMmtfFiles(pdbIds, sc).cache();
    pdb.foreach(t -> TraverseStructureHierarchy.printAll(t._2));
}

Example 30 with StructureDataInterface

use of org.rcsb.mmtf.api.StructureDataInterface 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();
}