Examples with ColumnarStructureX edu.sdsc.mmtf.spark.utils.ColumnarStructureX used on opensource projects

Example 1 with ColumnarStructureX

use of edu.sdsc.mmtf.spark.utils.ColumnarStructureX in project mm-dev by sbl-sdsc.

the class StructureAligner method getAllVsAllAlignments.

/**
 * Calculates all vs. all structural alignments of protein chains using the
 * specified alignment algorithm. The input structures must contain single
 * protein chains.
 *
 * @param targets structures containing single protein chains
 * @param alignmentAlgorithm name of the algorithm
 * @return dataset with alignment metrics
 */
public static Dataset<Row> getAllVsAllAlignments(JavaPairRDD<String, StructureDataInterface> targets, String alignmentAlgorithm) {
    SparkSession session = SparkSession.builder().getOrCreate();
    JavaSparkContext sc = new JavaSparkContext(session.sparkContext());
    // create a list of chainName/ C Alpha coordinates
    List<Tuple2<String, Point3d[]>> chains = targets.mapValues(s -> new ColumnarStructureX(s, true).getcAlphaCoordinates()).collect();
    // create an RDD of all pair indices (0,1), (0,2), ..., (1,2), (1,3), ...
    JavaRDD<Tuple2<Integer, Integer>> pairs = getPairs(sc, chains.size());
    // calculate structural alignments for all pairs.
    // broadcast (copy) chains to all worker nodes for efficient processing.
    // for each pair there can be zero or more solutions, therefore we flatmap the pairs.
    JavaRDD<Row> rows = pairs.flatMap(new StructuralAlignmentMapper(sc.broadcast(chains), alignmentAlgorithm));
    // convert rows to a dataset
    return session.createDataFrame(rows, getSchema());
}

Example 2 with ColumnarStructureX

use of edu.sdsc.mmtf.spark.utils.ColumnarStructureX in project mm-dev by sbl-sdsc.

the class StructureAligner method getQueryVsAllAlignments.

/**
 * Calculates structural alignments between a query and a target set of protein chains
 * using the specified alignment algorithm. An input structures must contain single
 * protein chains.
 *
 * @param targets structures containing single protein chains
 * @param alignmentAlgorithm name of the algorithm
 * @return dataset with alignment metrics
 */
public static Dataset<Row> getQueryVsAllAlignments(JavaPairRDD<String, StructureDataInterface> queries, JavaPairRDD<String, StructureDataInterface> targets, String alignmentAlgorithm) {
    SparkSession session = SparkSession.builder().getOrCreate();
    // spark context should not be closed here
    @SuppressWarnings("resource") JavaSparkContext sc = new JavaSparkContext(session.sparkContext());
    List<Tuple2<String, Point3d[]>> chains = new ArrayList<>();
    // create a list of chainName/ C Alpha coordinates for query chains
    chains.addAll(queries.mapValues(s -> new ColumnarStructureX(s, true).getcAlphaCoordinates()).collect());
    int querySize = chains.size();
    // create a list of chainName/ C Alpha coordinates for target chains
    chains.addAll(targets.mapValues(s -> new ColumnarStructureX(s, true).getcAlphaCoordinates()).collect());
    // create an RDD with indices for all query - target pairs (q, t)
    List<Tuple2<Integer, Integer>> pairList = new ArrayList<>(chains.size());
    for (int q = 0; q < querySize; q++) {
        for (int t = querySize; t < chains.size(); t++) {
            pairList.add(new Tuple2<Integer, Integer>(q, t));
        }
    }
    JavaRDD<Tuple2<Integer, Integer>> pairs = sc.parallelize(pairList, NUM_TASKS * sc.defaultParallelism());
    // calculate structural alignments for all pairs.
    // the chains are broadcast (copied) to all worker nodes for efficient processing
    JavaRDD<Row> rows = pairs.flatMap(new StructuralAlignmentMapper(sc.broadcast(chains), alignmentAlgorithm));
    // convert rows to a dataset
    return session.createDataFrame(rows, getSchema());
}