Examples with BioAssay ubic.gemma.model.expression.bioAssay.BioAssay used on opensource projects

Example 36 with BioAssay

use of ubic.gemma.model.expression.bioAssay.BioAssay in project Gemma by PavlidisLab.

the class ExpressionDataDoubleMatrixUtil method scalarDivideMatrix.

/**
 * Divide all values by the dividend
 *
 * @param matrix   matrix
 * @param dividend dividend
 * @throws IllegalArgumentException if dividend == 0.
 */
public static void scalarDivideMatrix(ExpressionDataDoubleMatrix matrix, double dividend) {
    if (dividend == 0)
        throw new IllegalArgumentException("Can't divide by zero");
    int columns = matrix.columns();
    for (ExpressionDataMatrixRowElement el : matrix.getRowElements()) {
        CompositeSequence del = el.getDesignElement();
        for (int i = 0; i < columns; i++) {
            BioAssay bm = matrix.getBioAssaysForColumn(i).iterator().next();
            double valA = matrix.get(del, bm);
            matrix.set(del, bm, valA / dividend);
        }
    }
}

Example 37 with BioAssay

use of ubic.gemma.model.expression.bioAssay.BioAssay in project Gemma by PavlidisLab.

the class ExpressionDataWriterUtils method constructBioAssayName.

/**
 * Constructs a bioassay name. This is useful when writing out data to a file.
 *
 * @param matrix           matrix
 * @param assayColumnIndex The column index in the matrix.
 * @return BA name
 */
public static String constructBioAssayName(ExpressionDataMatrix<?> matrix, int assayColumnIndex) {
    BioMaterial bioMaterialForColumn = matrix.getBioMaterialForColumn(assayColumnIndex);
    Collection<BioAssay> bioAssaysForColumn = matrix.getBioAssaysForColumn(assayColumnIndex);
    return constructBioAssayName(bioMaterialForColumn, bioAssaysForColumn);
}

Example 38 with BioAssay

use of ubic.gemma.model.expression.bioAssay.BioAssay in project Gemma by PavlidisLab.

the class BaseExpressionDataMatrix method getBioMaterialGroupsForAssays.

private void getBioMaterialGroupsForAssays(Map<BioMaterial, Collection<BioAssay>> bioMaterialMap, List<BioAssay> bioAssays) {
    for (BioAssay ba : bioAssays) {
        if (BaseExpressionDataMatrix.log.isDebugEnabled())
            BaseExpressionDataMatrix.log.debug("      " + ba);
        BioMaterial bm = ba.getSampleUsed();
        if (!bioMaterialMap.containsKey(bm)) {
            bioMaterialMap.put(bm, new HashSet<BioAssay>());
        }
        bioMaterialMap.get(bm).add(ba);
    }
}

Example 39 with BioAssay

use of ubic.gemma.model.expression.bioAssay.BioAssay in project Gemma by PavlidisLab.

the class BaseExpressionDataMatrix method getBestBioAssayDimension.

@Override
public BioAssayDimension getBestBioAssayDimension() {
    Collection<BioAssayDimension> dims = new HashSet<>(this.bioAssayDimensions.values());
    BioAssayDimension b = dims.iterator().next();
    if (dims.size() > 1) {
        /*
             * Special complication if there is more than one BioAssayDimension
             */
        int s = -1;
        Collection<BioMaterial> allBioMaterials = new HashSet<>();
        // find the largest BioAssayDimension
        for (BioAssayDimension bioAssayDimension : dims) {
            if (bioAssayDimension.getBioAssays().size() > s) {
                s = bioAssayDimension.getBioAssays().size();
                b = bioAssayDimension;
            }
            for (BioAssay ba : b.getBioAssays()) {
                allBioMaterials.add(ba.getSampleUsed());
            }
        }
        for (BioAssay ba : b.getBioAssays()) {
            if (!allBioMaterials.contains(ba.getSampleUsed())) {
                /*
                     * In rare cases none of the usual ones has all the samples.
                     *
                     * This can also happen if the data are not sample-matched or vector-merged
                     */
                throw new IllegalStateException("Could not find an appropriate BioAssayDimension to represent the data matrix; data might need to be matched or merged");
            }
        }
    }
    return b;
}

Example 40 with BioAssay

use of ubic.gemma.model.expression.bioAssay.BioAssay in project Gemma by PavlidisLab.

the class BaseExpressionDataMatrix method setUpColumnElements.

/**
 * <p>
 * Note: In the current versions of Gemma, we require that there can be only a single BioAssayDimension. Thus this
 * code is overly complex. If an experiment has multiple BioAssayDimensions (due to multiple arrays), we merge the
 * vectors (e.g., needed in the last case shown below). However, the issue of having multiple "BioMaterials" per
 * "BioAssay" still exists.
 * <p>
 * Deals with the fact that the bioassay dimensions can vary in size, and don't even need to overlap in the
 * biomaterials used. In the case where there is a single BioAssayDimension this reduces to simply associating each
 * column with a bioassay (though we are forced to use an integer under the hood).
 * <p>
 * For example, in the following diagram "-" indicates a biomaterial, while "*" indicates a bioassay. Each row of
 * "*" indicates samples run on a different microarray design (a different bio assay material). In the examples we
 * assume there is just a single biomaterial dimension.
 * <pre>
 * ---------------
 * *****              -- only a few samples run on this platform
 *  **********        -- ditto
 *            ****    -- these samples were not run on any of the other platforms .
 * </pre>
 * <p>
 * A simpler case:
 * </p>
 * <pre>
 * ---------------
 * ***************
 * ***********
 * *******
 * </pre>
 * <p>
 * A more typical and easy case (one microarray design used):
 * </p>
 * <pre>
 * ----------------
 * ****************
 * </pre>
 * <p>
 * If every sample was run on two different array designs:
 * </p>
 * <pre>
 * ----------------
 * ****************
 * ****************
 * </pre>
 * <p>
 * Every sample was run on a different array design:
 * <pre>
 * -----------------------
 * ******
 *       *********
 *                ********
 * </pre>
 * <p>
 * Because there can be limited or no overlap between the bioassay dimensions, we cannot assume the dimensions of
 * the matrix will be defined by the longest BioAssayDimension. Note that later in processing, this possible lack of
 * overlap is fixed by sample matching or vector merging; this class has to deal with the general case.
 * </p>
 */
int setUpColumnElements() {
    BaseExpressionDataMatrix.log.debug("Setting up column elements");
    assert this.bioAssayDimensions != null && this.bioAssayDimensions.size() > 0 : "No bioAssayDimensions defined";
    Map<BioMaterial, Collection<BioAssay>> bioMaterialMap = new LinkedHashMap<>();
    for (BioAssayDimension dimension : this.bioAssayDimensions.values()) {
        List<BioAssay> bioAssays = dimension.getBioAssays();
        BaseExpressionDataMatrix.log.debug("Processing: " + dimension + " with " + bioAssays.size() + " assays");
        this.getBioMaterialGroupsForAssays(bioMaterialMap, bioAssays);
    }
    if (BaseExpressionDataMatrix.log.isDebugEnabled())
        BaseExpressionDataMatrix.log.debug(bioMaterialMap.size() + " biomaterialGroups (correspond to columns)");
    int column = 0;
    for (BioMaterial bioMaterial : bioMaterialMap.keySet()) {
        if (BaseExpressionDataMatrix.log.isDebugEnabled())
            BaseExpressionDataMatrix.log.debug("Column " + column + " **--->>>> " + bioMaterial);
        for (BioAssay assay : bioMaterialMap.get(bioMaterial)) {
            if (this.columnBioMaterialMap.containsKey(bioMaterial)) {
                int existingColumn = columnBioMaterialMap.get(bioMaterial);
                this.columnAssayMap.put(assay, existingColumn);
                if (BaseExpressionDataMatrix.log.isDebugEnabled())
                    BaseExpressionDataMatrix.log.debug(assay + " --> column " + existingColumn);
                if (columnBioAssayMapByInteger.get(existingColumn) == null) {
                    columnBioAssayMapByInteger.put(existingColumn, new HashSet<BioAssay>());
                }
                columnBioAssayMapByInteger.get(existingColumn).add(assay);
            } else {
                if (BaseExpressionDataMatrix.log.isDebugEnabled()) {
                    BaseExpressionDataMatrix.log.debug(bioMaterial + " --> column " + column);
                    BaseExpressionDataMatrix.log.debug(assay + " --> column " + column);
                }
                this.columnBioMaterialMap.put(bioMaterial, column);
                this.columnAssayMap.put(assay, column);
                if (columnBioAssayMapByInteger.get(column) == null) {
                    columnBioAssayMapByInteger.put(column, new HashSet<BioAssay>());
                }
                columnBioMaterialMapByInteger.put(column, bioMaterial);
                columnBioAssayMapByInteger.get(column).add(assay);
            }
        }
        column++;
    }
    if (BaseExpressionDataMatrix.log.isDebugEnabled()) {
        for (BioAssay o : this.columnAssayMap.keySet()) {
            BaseExpressionDataMatrix.log.debug(o + " " + this.columnAssayMap.get(o));
        }
    }
    assert bioMaterialMap.size() == columnBioMaterialMapByInteger.keySet().size();
    return columnBioMaterialMapByInteger.keySet().size();
}