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

Example 11 with StructureDataInterface

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

the class SwissModelDatasetToStructure method main.

public static void main(String[] args) throws IOException {
    SparkSession spark = SparkSession.builder().master("local[*]").appName(SwissModelDatasetToStructure.class.getSimpleName()).getOrCreate();
    JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
    List<String> uniProtIds = Arrays.asList("P36575", "P24539", "O00244", "P18846", "Q9UII2");
    Dataset<Row> ds = SwissModelDataset.getSwissModels(uniProtIds);
    ds.show();
    ds = ds.filter("qmean > -2.5 AND coverage > 0.5");
    List<String> urls = ds.select("coordinates").as(Encoders.STRING()).collectAsList();
    System.out.println(urls);
    JavaPairRDD<String, StructureDataInterface> models = MmtfImporter.downloadSwissModelsByUrls(urls, sc);
    models.foreach(t -> System.out.println(t._2.getEntitySequence(0)));
    spark.close();
}

Example 12 with StructureDataInterface

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

the class TestRosettaMmtf method main.

/**
 * Test: Read MMTF-Hadoop Sequence file.
 *
 * @param args args[0] <path-to-mmtf-haddop-sequence-file>
 *
 * @throws FileNotFoundException
 */
public static void main(String[] args) throws FileNotFoundException {
    // instantiate Spark
    // TODO set to local[1] !!!!
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName("TestSwissModelMmtf");
    JavaSparkContext sc = new JavaSparkContext(conf);
    long start = System.nanoTime();
    // read PDB files recursively starting the specified directory
    JavaPairRDD<String, StructureDataInterface> structures = MmtfReader.readSequenceFile(args[0], sc);
    // total:  639 structures
    // structures = structures.filter(new ContainsDnaChain()); //  ?
    // structures = structures.filter(new ContainsLProteinChain()); // 639?
    // structures = structures.filter(new ContainsGroup("ZN")); // 0
    // structures = structures.filter(new ContainsGroup("ATP")); //
    // debug: print structure data
    // structures.foreach(t -> TraverseStructureHierarchy.demo(t._2));
    // structures.foreach(t -> System.out.println(t._1));
    System.out.println(structures.map(t -> t._2.getNumEntities()).reduce((a, b) -> a + b));
    System.out.println("Number of structures read: " + structures.count());
    long end = System.nanoTime();
    System.out.println("Time: " + (end - start) / 1E9 + " sec.");
    // close Spark
    sc.close();
}

Example 13 with StructureDataInterface

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

the class SecondaryStructureExtractor method getSecStructFractions.

private static Row getSecStructFractions(Tuple2<String, StructureDataInterface> t) throws Exception {
    String key = t._1;
    StructureDataInterface structure = t._2;
    if (t._2.getNumChains() != 1) {
        throw new IllegalArgumentException("This method can only be applied to single polymer chain.");
    }
    StringBuilder dsspQ8 = new StringBuilder(structure.getEntitySequence(0).length());
    StringBuilder dsspQ3 = new StringBuilder(structure.getEntitySequence(0).length());
    float helix = 0;
    float sheet = 0;
    float coil = 0;
    int dsspIndex = 0;
    int structureIndex = 0;
    int seqIndex;
    for (int code : structure.getSecStructList()) {
        seqIndex = structure.getGroupSequenceIndices()[structureIndex++];
        while (dsspIndex < seqIndex) {
            dsspQ8.append("X");
            dsspQ3.append("X");
            dsspIndex++;
        }
        dsspQ8.append(DsspSecondaryStructure.getDsspCode(code).getOneLetterCode());
        dsspIndex++;
        switch(DsspSecondaryStructure.getQ3Code(code)) {
            case ALPHA_HELIX:
                helix++;
                dsspQ3.append("H");
                break;
            case EXTENDED:
                sheet++;
                dsspQ3.append("E");
                break;
            case COIL:
                coil++;
                dsspQ3.append("C");
                break;
            default:
                break;
        }
    }
    while (dsspIndex < structure.getEntitySequence(0).length()) {
        dsspQ8.append("X");
        dsspQ3.append("X");
        dsspIndex++;
    }
    int n = structure.getSecStructList().length;
    helix /= n;
    sheet /= n;
    coil /= n;
    return RowFactory.create(key, structure.getEntitySequence(0), helix, sheet, coil, dsspQ8.toString(), dsspQ3.toString());
}

Example 14 with StructureDataInterface

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

the class AtpInteractionAnalysis method main.

/**
 * @param args input arguments
 * @throws IOException
 */
public static void main(String[] args) throws IOException {
    String path = MmtfReader.getMmtfFullPath();
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(AtpInteractionAnalysis.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // read PDB in MMTF format
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.readSequenceFile(path, sc);
    // filter by sequence identity subset
    int sequenceIdentity = 20;
    double resolution = 2.0;
    pdb = pdb.filter(new Pisces(sequenceIdentity, resolution));
    // find ATP interactions within 3 Angstroms
    GroupInteractionExtractor finder = new GroupInteractionExtractor("ATP", 3);
    Dataset<Row> interactions = finder.getDataset(pdb).cache();
    // TODO add a line to only analyze interactions
    // with the oxygens in the terminal phosphate group of ATP
    // (O1G, O2G, O3G)
    // Tip: Google SQL LIKE
    interactions = interactions.filter("atom1 LIKE('O%G')");
    // show the data schema of the dataset and some data
    interactions.printSchema();
    interactions.show(20);
    long n = interactions.count();
    System.out.println("# interactions: " + n);
    System.out.println("Top interacting groups");
    Dataset<Row> topGroups = interactions.groupBy("residue2").count();
    topGroups.sort(// sort descending by count
    col("count").desc()).show(10);
    System.out.println("Top interacting group/atoms types");
    Dataset<Row> topGroupsAndAtoms = interactions.groupBy("residue2", "atom2").count();
    topGroupsAndAtoms.withColumn("frequency", // add column with frequency of occurrence
    col("count").divide(n)).sort(// sort descending
    col("frequency").desc()).show(10);
    long end = System.nanoTime();
    System.out.println("Time:     " + (end - start) / 1E9 + "sec.");
    sc.close();
}

Example 15 with StructureDataInterface

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

the class InteractionAnalysisAdvanced method main.

/**
 * @param args no input arguments
 * @throws IOException
 */
public static void main(String[] args) throws IOException {
    String path = MmtfReader.getMmtfFullPath();
    long start = System.nanoTime();
    SparkConf conf = new SparkConf().setMaster("local[*]").setAppName(InteractionAnalysisAdvanced.class.getSimpleName());
    JavaSparkContext sc = new JavaSparkContext(conf);
    // read PDB in MMTF format
    JavaPairRDD<String, StructureDataInterface> pdb = MmtfReader.readSequenceFile(path, sc);
    // get non-redundant subset
    pdb = pdb.filter(new Pisces(40, 2.5));
    // find Zinc interactions within 3 Angstroms
    GroupInteractionExtractor finder = new GroupInteractionExtractor("ZN", 3);
    Dataset<Row> interactions = finder.getDataset(pdb).cache();
    // show the data schema of the dataset and some data
    interactions.printSchema();
    interactions.show(20);
    long n = interactions.count();
    System.out.println("# interactions: " + n);
    System.out.println("Top interacting groups");
    Dataset<Row> topGroups = interactions.groupBy("residue2").count();
    topGroups.sort(// sort descending by count
    col("count").desc()).show(10);
    System.out.println("Top interacting group/atoms types");
    Dataset<Row> topGroupsAndAtoms = interactions.filter(// exclude carbon interactions
    "element2 != 'C'").groupBy("residue2", "atom2").count();
    topGroupsAndAtoms.withColumn("frequency", // add column with frequency of occurrence
    col("count").divide(n)).filter(// filter out occurrences < 1 %
    "frequency > 0.01").sort(// sort descending
    col("frequency").desc()).show(20);
    // TODO print the top 10 interacting elements
    System.out.println("Top interacting elements");
    Dataset<Row> topElements = interactions.filter(// exclude carbon interactions
    "element2 != 'C'").groupBy("element2").count();
    topElements.withColumn("frequency", col("count").divide(n)).filter(// filter out occurrences < 1 %
    "frequency > 0.01").sort(// sort descending
    col("frequency").desc()).show(10);
    interactions.groupBy("element2").avg("distance").sort("avg(distance)").show(10);
    // Aggregate multiple statistics
    // Note: import static org.apache.spark.sql.functions.* required!
    // e.g. org.apache.spark.sql.functions.avg
    // for a list of all available functions
    interactions.groupBy("element2").agg(count("distance"), avg("distance"), min("distance"), max("distance"), kurtosis("distance")).show(10);
    long end = System.nanoTime();
    System.out.println("Time:     " + (end - start) / 1E9 + "sec.");
    sc.close();
}