Examples with EMDataSet org.baderlab.csplugins.enrichmentmap.model.EMDataSet used on opensource projects

Example 36 with EMDataSet

use of org.baderlab.csplugins.enrichmentmap.model.EMDataSet in project EnrichmentMapApp by BaderLab.

the class FileReaderTest method testDavidEnrichmentsReader.

//test David enrichment results reader
@Test
public void testDavidEnrichmentsReader(Provider<EnrichmentMapParameters> empFactory) throws Exception {
    //load the test enrichment files - Bingo
    String testDataFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/DavidResults.txt";
    //create a new instance of the parameters
    EnrichmentMapParameters params = empFactory.get();
    //set enrichment file name 
    params.getFiles().get(LegacySupport.DATASET1).setEnrichmentFileName1(testDataFileName);
    //Create a new Enrichment map
    EnrichmentMap map = new EnrichmentMap(params.getCreationParameters(), serviceRegistrar);
    //get the default dataset
    Method method = EnrichmentMapParameters.stringToMethod(params.getMethod());
    DataSetFiles files = params.getFiles().get(LegacySupport.DATASET1);
    EMDataSet dataset = map.createDataSet(LegacySupport.DATASET1, method, files);
    ParseDavidEnrichmentResults task = new ParseDavidEnrichmentResults(dataset);
    task.run(taskMonitor);
    //Get the enrichment
    Map<String, EnrichmentResult> enrichments = map.getDataSet(LegacySupport.DATASET1).getEnrichments().getEnrichments();
    assertEquals(215, enrichments.size());
    //check p-values
    assertEquals(0.00000005210169741980237, ((GenericResult) enrichments.get("GO:0031974~MEMBRANE-ENCLOSED LUMEN")).getPvalue(), 0.0);
    //check fdr value
    assertEquals(0.000016724505445320226, ((GenericResult) enrichments.get("GO:0031974~MEMBRANE-ENCLOSED LUMEN")).getFdrqvalue(), 0.0);
    //check geneset siz
    assertEquals(95, ((GenericResult) enrichments.get("GO:0031974~MEMBRANE-ENCLOSED LUMEN")).getGsSize());
    //check p-values
    assertEquals(0.0009179741851709047, ((GenericResult) enrichments.get(((String) "domain:Leucine-zipper").toUpperCase())).getPvalue(), 0.0);
    //check fdr value
    assertEquals(0.46717397126592464, ((GenericResult) enrichments.get(((String) "domain:Leucine-zipper").toUpperCase())).getFdrqvalue(), 0.0);
    //check geneset siz
    assertEquals(11, ((GenericResult) enrichments.get(((String) "domain:Leucine-zipper").toUpperCase())).getGsSize());
}

Example 37 with EMDataSet

use of org.baderlab.csplugins.enrichmentmap.model.EMDataSet in project EnrichmentMapApp by BaderLab.

the class FileReaderTest method testGMTFileReader.

@Test
public void testGMTFileReader(Provider<EnrichmentMapParameters> empFactory) throws Exception {
    String testDataFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/Genesetstestfile.gmt";
    //create a new instance of the parameters
    EnrichmentMapParameters params = empFactory.get();
    //set gmt file name 
    params.getFiles().get(LegacySupport.DATASET1).setGMTFileName(testDataFileName);
    //Create a new Enrichment map
    EnrichmentMap map = new EnrichmentMap(params.getCreationParameters(), serviceRegistrar);
    //get the default dataset
    Method method = EnrichmentMapParameters.stringToMethod(params.getMethod());
    DataSetFiles files = params.getFiles().get(LegacySupport.DATASET1);
    EMDataSet dataset = map.createDataSet(LegacySupport.DATASET1, method, files);
    //set up task
    GMTFileReaderTask task = new GMTFileReaderTask(dataset);
    task.run(taskMonitor);
    //test to make sure that the file loaded in 10 genesets with a total of 75 genes
    assertEquals(10, map.getAllGeneSets().size());
    assertEquals(75, map.getNumberOfGenes());
}

Example 38 with EMDataSet

use of org.baderlab.csplugins.enrichmentmap.model.EMDataSet in project EnrichmentMapApp by BaderLab.

the class LoadBingoResultsTest method testLoadBingoResult_withoutexpression.

@Test
public void testLoadBingoResult_withoutexpression() throws Exception {
    //for a dataset we require genesets, an expression file (optional), enrichment results
    String testBingoResultsFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/bingo_output/12Hr_topgenes.bgo";
    DataSetFiles files = new DataSetFiles();
    files.setEnrichmentFileName1(testBingoResultsFileName);
    //set the method to Bingo
    double pvalue = 0.00005;
    // 5.0 X 10-8
    double qvaule = 0.00000005;
    double similarityCutoff = 0.25;
    EMCreationParameters params = new EMCreationParameters("EM1_", pvalue, qvaule, NESFilter.ALL, Optional.empty(), SimilarityMetric.JACCARD, similarityCutoff, 0.5);
    //create an new enrichment Map
    EnrichmentMap em = new EnrichmentMap(params, serviceRegistrar);
    EMDataSet dataset = em.createDataSet(LegacySupport.DATASET1, Method.Specialized, files);
    ParseBingoEnrichmentResults enrichmentResultsFilesTask = new ParseBingoEnrichmentResults(dataset);
    enrichmentResultsFilesTask.run(taskMonitor);
    CreateDummyExpressionTask dummyExpressionTask = new CreateDummyExpressionTask(dataset);
    dummyExpressionTask.run(taskMonitor);
    em.filterGenesets();
    InitializeGenesetsOfInterestTask genesets_init = new InitializeGenesetsOfInterestTask(em);
    genesets_init.run(taskMonitor);
    Baton<Map<SimilarityKey, GenesetSimilarity>> baton = new Baton<>();
    ComputeSimilarityTaskParallel similarities = new ComputeSimilarityTaskParallel(em, baton.consumer());
    similarities.run(taskMonitor);
    //check to see if the dataset loaded - there should be 74 genesets
    assertEquals(74, dataset.getSetOfGeneSets().getGeneSets().size());
    //there should also be 74 enrichments (the genesets are built from the bgo file)
    assertEquals(74, dataset.getEnrichments().getEnrichments().size());
    //there should be 11 genesets in the enrichments of interest
    assertEquals(5, dataset.getGeneSetsOfInterest().getGeneSets().size());
    //there should be 6 edges
    assertEquals(6, baton.supplier().get().size());
    //there should be a total of 366 genes
    assertEquals(446, em.getNumberOfGenes());
    //there should be 43 genes in the geneset "nucleolus"
    assertEquals(43, em.getAllGeneSets().get("NUCLEOLUS").getGenes().size());
    //make sure the dummy expression has values for all the genes
    assertEquals(446, dataset.getExpressionSets().getNumGenes());
    assertEquals(446, dataset.getDataSetGenes().size());
}

Example 39 with EMDataSet

use of org.baderlab.csplugins.enrichmentmap.model.EMDataSet in project EnrichmentMapApp by BaderLab.

the class LoadDatasetTaskTest method testLoadDataset1GSEAResult_withexpression.

@Test
public void testLoadDataset1GSEAResult_withexpression() throws Exception {
    //for a dataset we require genesets, an expression file (optional), enrichment results
    String testGMTFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/LoadDataset/gs_apop_mouse.gmt";
    String testExpressionFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/LoadDataset/Expressiontestfile.gct";
    String testGSEAResults1FileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/LoadDataset/GSEA_enrichments1.xls";
    String testGSEAResults2FileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/LoadDataset/GSEA_enrichments2.xls";
    DataSetFiles files = new DataSetFiles();
    files.setGMTFileName(testGMTFileName);
    files.setExpressionFileName(testExpressionFileName);
    files.setEnrichmentFileName1(testGSEAResults1FileName);
    files.setEnrichmentFileName2(testGSEAResults2FileName);
    EMCreationParameters params = new EMCreationParameters("EM1_", 0.1, 0.1, NESFilter.ALL, Optional.empty(), SimilarityMetric.JACCARD, 0.1, 0.1);
    //create an new enrichment Map
    EnrichmentMap em = new EnrichmentMap(params, serviceRegistrar);
    //create a dataset
    EMDataSet dataset = em.createDataSet(LegacySupport.DATASET1, Method.Generic, files);
    //load Data
    GMTFileReaderTask task = new GMTFileReaderTask(dataset);
    task.run(taskMonitor);
    ParseGSEAEnrichmentResults enrichmentResultsFilesTask = new ParseGSEAEnrichmentResults(dataset);
    enrichmentResultsFilesTask.run(taskMonitor);
    //load expression file
    ExpressionFileReaderTask exptask = new ExpressionFileReaderTask(dataset);
    exptask.run(taskMonitor);
    //check to see if the dataset loaded
    assertEquals(193, dataset.getSetOfGeneSets().getGeneSets().size());
    assertEquals(14, dataset.getEnrichments().getEnrichments().size());
    assertEquals(41, dataset.getDataSetGenes().size());
    assertEquals(41, dataset.getExpressionSets().getNumGenes());
}

Example 40 with EMDataSet

use of org.baderlab.csplugins.enrichmentmap.model.EMDataSet in project EnrichmentMapApp by BaderLab.

the class LoadDavidResultTest method testLoad2DavidResult_withoutexpression.

@Test
public void testLoad2DavidResult_withoutexpression() throws Exception {
    //for a dataset we require genesets, an expression file (optional), enrichment results
    String testDavidResultsFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/david_output/12hr_David_Output.txt";
    DataSetFiles files = new DataSetFiles();
    files.setEnrichmentFileName1(testDavidResultsFileName);
    //for a dataset we require genesets, an expression file (optional), enrichment results
    String testDavidResultsFileName2 = "src/test/resources/org/baderlab/csplugins/enrichmentmap/task/david_output/24hr_David_Output.txt";
    DataSetFiles files2 = new DataSetFiles();
    files2.setEnrichmentFileName1(testDavidResultsFileName2);
    //set the method to David
    double similarityCutoff = 0.25;
    double pvalue = 0.005;
    // 5.0 X 10-3
    double qvalue = 0.005;
    EMCreationParameters params = new EMCreationParameters("EM1_", pvalue, qvalue, NESFilter.ALL, Optional.empty(), SimilarityMetric.JACCARD, similarityCutoff, 0.5);
    //create an new enrichment Map
    EnrichmentMap em = new EnrichmentMap(params, serviceRegistrar);
    //Load first dataset
    //create a dataset
    EMDataSet dataset = em.createDataSet(LegacySupport.DATASET1, Method.Specialized, files);
    //create a DatasetTask
    ParseDavidEnrichmentResults enrichmentResultsFilesTask = new ParseDavidEnrichmentResults(dataset);
    enrichmentResultsFilesTask.run(taskMonitor);
    //Load second dataset
    //create a dataset
    EMDataSet dataset2 = em.createDataSet(LegacySupport.DATASET2, Method.Specialized, files2);
    //create a DatasetTask
    ParseDavidEnrichmentResults enrichmentResultsFiles2Task = new ParseDavidEnrichmentResults(dataset2);
    enrichmentResultsFiles2Task.run(taskMonitor);
    // check to see if the two datasets are distinct
    if (!((dataset.getDataSetGenes().containsAll(dataset2.getDataSetGenes())) && (dataset2.getDataSetGenes().containsAll(dataset.getDataSetGenes()))))
        em.setDistinctExpressionSets(true);
    CreateDummyExpressionTask dummyExpressionTask = new CreateDummyExpressionTask(dataset);
    dummyExpressionTask.run(taskMonitor);
    CreateDummyExpressionTask dummyExpressionTask2 = new CreateDummyExpressionTask(dataset2);
    dummyExpressionTask2.run(taskMonitor);
    em.filterGenesets();
    InitializeGenesetsOfInterestTask genesets_init = new InitializeGenesetsOfInterestTask(em);
    genesets_init.run(taskMonitor);
    // check to see if the dataset loaded - there should be 215 genesets
    assertEquals(215, dataset.getSetOfGeneSets().getGeneSets().size());
    // there should also be 215 enrichments (the genesets are built from the txt file)
    assertEquals(215, dataset.getEnrichments().getEnrichments().size());
    // there should be 7 genesets in the enrichments of interest
    assertEquals(7, dataset.getGeneSetsOfInterest().getGeneSets().size());
    // there should be 114 genes in the geneset "acetylation"
    assertEquals(114, em.getDataSet(LegacySupport.DATASET1).getSetOfGeneSets().getGeneSets().get("ACETYLATION").getGenes().size());
    //		assertEquals(114, em.getAllGenesets().get("ACETYLATION").getGenes().size());
    dataset2 = em.getDataSet(LegacySupport.DATASET2);
    // check the stats for dataset2
    // check to see if the dataset loaded - there should be 263 genesets
    assertEquals(263, dataset2.getSetOfGeneSets().getGeneSets().size());
    // there should also be 263 enrichments (the genesets are built from the bgo file)
    assertEquals(263, dataset2.getEnrichments().getEnrichments().size());
    // there should be 0 genesets in the enrichments of interest
    assertEquals(0, dataset2.getGeneSetsOfInterest().getGeneSets().size());
    // make sure the dummy expression has values for all the genes
    assertEquals(367, dataset2.getExpressionSets().getNumGenes());
    assertEquals(367, dataset2.getDataSetGenes().size());
    // there should be 20 edges (2 edges for every node because of the distinct expresison sets)
    // assertEquals((7*6),em.getGenesetSimilarity().size()); there should be a total of 366 genes
    assertEquals(661, em.getNumberOfGenes());
}