use of org.baderlab.csplugins.enrichmentmap.model.DataSetFiles 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());
}
use of org.baderlab.csplugins.enrichmentmap.model.DataSetFiles 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());
}
use of org.baderlab.csplugins.enrichmentmap.model.DataSetFiles in project EnrichmentMapApp by BaderLab.
the class LoadDavidResultTest method testLoadDavidResult_withoutexpression.
@Test
public void testLoadDavidResult_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);
//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 data set
//create a dataset
EMDataSet dataset = em.createDataSet(LegacySupport.DATASET1, Method.Specialized, files);
//create a DatasetTask
ParseDavidEnrichmentResults enrichmentResultsFilesTask = new ParseDavidEnrichmentResults(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 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 7 * 6 edges
assertEquals(11, baton.supplier().get().size());
//there should be a total of 366 genes
assertEquals(414, em.getNumberOfGenes());
//there should be 43 genes in the geneset "nucleolus"
assertEquals(114, em.getAllGeneSets().get("ACETYLATION").getGenes().size());
//make sure the dummy expression has values for all the genes
assertEquals(414, dataset.getExpressionSets().getNumGenes());
assertEquals(414, dataset.getDataSetGenes().size());
}
use of org.baderlab.csplugins.enrichmentmap.model.DataSetFiles in project EnrichmentMapApp by BaderLab.
the class FileReaderTest method testExpression1ReaderNormal.
@Test
public void testExpression1ReaderNormal(Provider<EnrichmentMapParameters> empFactory) throws Exception {
//load the test expression file
String testDataFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/Expressiontestfile.gct";
//create a new instance of the parameters
EnrichmentMapParameters params = empFactory.get();
//set expression file name
params.getFiles().get(LegacySupport.DATASET1).setExpressionFileName(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);
//in order to load expression data the genes have to be registered with the application
//make sure that the genes are empty
assertEquals(0, map.getNumberOfGenes());
//add the gene to the master list of genes
map.addGene("GLS");
map.addGene("PSMA1");
map.addGene("ZP1");
map.addGene("ZYX");
//make sure all four genes have been associated
assertEquals(4, map.getNumberOfGenes());
//load expression file
ExpressionFileReaderTask task = new ExpressionFileReaderTask(dataset);
task.run(taskMonitor);
//There was one more gene in the expression file that wasn't in the set of genes
//make sure it was was added
assertEquals(4, map.getNumberOfGenes());
assertEquals(4, map.getDataSet(LegacySupport.DATASET1).getExpressionSets().getNumGenes());
assertEquals(59, map.getDataSet(LegacySupport.DATASET1).getExpressionSets().getNumConditions());
assertEquals(0.008720342, map.getDataSet(LegacySupport.DATASET1).getExpressionSets().getMinExpression(), 0.0);
assertEquals(5.131481026, map.getDataSet(LegacySupport.DATASET1).getExpressionSets().getMaxExpression(), 0.0);
}
use of org.baderlab.csplugins.enrichmentmap.model.DataSetFiles in project EnrichmentMapApp by BaderLab.
the class FileReaderTest method testBingoEnrichmentsReader.
//test Bingo enrichment results
@Test
public void testBingoEnrichmentsReader(Provider<EnrichmentMapParameters> empFactory) throws Exception {
//load the test enrichment files - Bingo
String testDataFileName = "src/test/resources/org/baderlab/csplugins/enrichmentmap/BingoResults.bgo";
//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);
ParseBingoEnrichmentResults task = new ParseBingoEnrichmentResults(dataset);
task.run(taskMonitor);
//Get the enrichment
Map<String, EnrichmentResult> enrichments = map.getDataSet(LegacySupport.DATASET1).getEnrichments().getEnrichments();
assertEquals(74, enrichments.size());
//check p-values
assertEquals(0.0010354, ((GenericResult) enrichments.get("NUCLEOLAR PART")).getPvalue(), 0.0);
//check fdr value
assertEquals(0.047796, ((GenericResult) enrichments.get("NUCLEOLAR PART")).getFdrqvalue(), 0.0);
//check geneset siz
assertEquals(5, ((GenericResult) enrichments.get("NUCLEOLAR PART")).getGsSize());
//check p-values
assertEquals(0.0000000000016209, ((GenericResult) enrichments.get("NUCLEOLUS")).getPvalue(), 0.0);
//check fdr value
assertEquals(0.0000000042203, ((GenericResult) enrichments.get("NUCLEOLUS")).getFdrqvalue(), 0.0);
//check geneset siz
assertEquals(43, ((GenericResult) enrichments.get("NUCLEOLUS")).getGsSize());
}
Aggregations