use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class SequencingObjectServiceTest method testCreateSequenceFilePairInSampleWrongType.
@Test(expected = IllegalArgumentException.class)
public void testCreateSequenceFilePairInSampleWrongType() throws IOException {
Sample s = new Sample();
SequencingRun run = new MiseqRun(LayoutType.SINGLE_END, "workflow");
SequenceFilePair so = TestDataFactory.constructSequenceFilePair();
so.setSequencingRun(run);
when(repository.save(so)).thenReturn(so);
service.createSequencingObjectInSample(so, s);
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class AnalysisWorkspaceServiceGalaxyTest method testGetAnalysisResultsSuccessMultiSample.
/**
* Tests successfully getting analysis results from Galaxy where there's
* multiple samples but workflow should have only accepted single sample (no
* label on name).
*
* @throws IridaWorkflowNotFoundException
* @throws IOException
* @throws ExecutionManagerException
* @throws IridaWorkflowAnalysisTypeException
*/
@Test
public void testGetAnalysisResultsSuccessMultiSample() throws IridaWorkflowNotFoundException, IridaWorkflowAnalysisTypeException, ExecutionManagerException, IOException {
Set<SingleEndSequenceFile> singleFiles = Sets.newHashSet(sampleSingleSequenceFileMap.values());
Set<SequenceFilePair> pairedFiles = Sets.newHashSet(sampleSequenceFilePairMap.values());
submission = AnalysisSubmission.builder(workflowId).name("my analysis").inputFiles(pairedInputFiles).referenceFile(referenceFile).build();
submission.setRemoteWorkflowId(WORKFLOW_ID);
submission.setRemoteAnalysisId(HISTORY_ID);
when(sequencingObjectService.getSequencingObjectsOfTypeForAnalysisSubmission(submission, SingleEndSequenceFile.class)).thenReturn(singleFiles);
when(sequencingObjectService.getSequencingObjectsOfTypeForAnalysisSubmission(submission, SequenceFilePair.class)).thenReturn(pairedFiles);
when(iridaWorkflowsService.getIridaWorkflow(workflowId)).thenReturn(iridaWorkflowSingle);
when(galaxyHistoriesService.getDatasetForFileInHistory(output1Filename, HISTORY_ID)).thenReturn(output1Dataset);
when(galaxyHistoriesService.getDatasetForFileInHistory(output2Filename, HISTORY_ID)).thenReturn(output2Dataset);
when(sequencingObjectService.getUniqueSamplesForSequencingObjects(singleFiles)).thenReturn(sampleSingleSequenceFileMap);
when(sequencingObjectService.getUniqueSamplesForSequencingObjects(pairedFiles)).thenReturn(sampleSequenceFilePairMap);
Analysis analysis = workflowPreparation.getAnalysisResults(submission);
assertNotNull("analysis is not valid", analysis);
assertEquals("invalid number of output files", 2, analysis.getAnalysisOutputFiles().size());
assertEquals("missing output file for analysis", Paths.get("output1.txt"), analysis.getAnalysisOutputFile("output1").getFile().getFileName());
// labels should now not have sample associated with them.
assertEquals("missing label for analysis output file", "output1.txt", analysis.getAnalysisOutputFile("output1").getLabel());
assertEquals("missing output file for analysis", "output2.txt", analysis.getAnalysisOutputFile("output2").getLabel());
verify(galaxyHistoriesService).getDatasetForFileInHistory("output1.txt", HISTORY_ID);
verify(galaxyHistoriesService).getDatasetForFileInHistory("output2.txt", HISTORY_ID);
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class AnalysisWorkspaceServiceGalaxyTest method testGetAnalysisResultsSuccessSinglePairedEnd.
/**
* Tests successfully getting analysis results from Galaxy with
* single/paired end input files.
*
* @throws IridaWorkflowNotFoundException
* @throws IOException
* @throws ExecutionManagerException
* @throws IridaWorkflowAnalysisTypeException
*/
@Test
public void testGetAnalysisResultsSuccessSinglePairedEnd() throws IridaWorkflowNotFoundException, IridaWorkflowAnalysisTypeException, ExecutionManagerException, IOException {
Set<SingleEndSequenceFile> singleFiles = Sets.newHashSet(sampleSingleSequenceFileMap.values());
Set<SequenceFilePair> pairedFiles = Sets.newHashSet(sampleSequenceFilePairMap.values());
Set<SequencingObject> joinedFiles = Sets.newHashSet(singleFiles);
joinedFiles.addAll(pairedFiles);
Map<Sample, SequencingObject> joinedMap = Maps.newHashMap(sampleSingleSequenceFileMap);
joinedMap.putAll(sampleSequenceFilePairMap);
submission = AnalysisSubmission.builder(workflowIdMultiSamples).name("my analysis").inputFiles(singleInputFiles).inputFiles(pairedInputFiles).referenceFile(referenceFile).build();
submission.setRemoteWorkflowId(WORKFLOW_ID);
submission.setRemoteAnalysisId(HISTORY_ID);
when(sequencingObjectService.getSequencingObjectsForAnalysisSubmission(submission)).thenReturn(joinedFiles);
when(iridaWorkflowsService.getIridaWorkflow(workflowIdMultiSamples)).thenReturn(iridaWorkflowSinglePairedMultipleSamples);
when(galaxyHistoriesService.getDatasetForFileInHistory(output1Filename, HISTORY_ID)).thenReturn(output1Dataset);
when(galaxyHistoriesService.getDatasetForFileInHistory(output2Filename, HISTORY_ID)).thenReturn(output2Dataset);
when(sequencingObjectService.getUniqueSamplesForSequencingObjects(joinedFiles)).thenReturn(joinedMap);
Analysis analysis = workflowPreparation.getAnalysisResults(submission);
assertNotNull("analysis is not valid", analysis);
assertEquals("invalid number of output files", 2, analysis.getAnalysisOutputFiles().size());
assertEquals("missing output file for analysis", Paths.get("output1.txt"), analysis.getAnalysisOutputFile("output1").getFile().getFileName());
// labels should now not have sample associated with them.
assertEquals("missing label for analysis output file", "output1.txt", analysis.getAnalysisOutputFile("output1").getLabel());
assertEquals("missing output file for analysis", "output2.txt", analysis.getAnalysisOutputFile("output2").getLabel());
verify(galaxyHistoriesService).getDatasetForFileInHistory("output1.txt", HISTORY_ID);
verify(galaxyHistoriesService).getDatasetForFileInHistory("output2.txt", HISTORY_ID);
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class AnalysisWorkspaceServiceGalaxyTest method testPrepareAnalysisFilesPairedSuccess.
/**
* Tests out successfully to preparing an analysis with paired files
*
* @throws ExecutionManagerException
* @throws IridaWorkflowException
*/
@SuppressWarnings("unchecked")
@Test
public void testPrepareAnalysisFilesPairedSuccess() throws ExecutionManagerException, IridaWorkflowException {
Set<SequenceFilePair> pairedFiles = Sets.newHashSet(sampleSequenceFilePairMap.values());
submission = AnalysisSubmission.builder(workflowId).name("my analysis").inputFiles(Sets.newHashSet(pairedFiles)).referenceFile(referenceFile).build();
submission.setRemoteAnalysisId(HISTORY_ID);
submission.setRemoteWorkflowId(WORKFLOW_ID);
when(sequencingObjectService.getSequencingObjectsOfTypeForAnalysisSubmission(submission, SequenceFilePair.class)).thenReturn(pairedFiles);
when(iridaWorkflowsService.getIridaWorkflow(workflowId)).thenReturn(iridaWorkflowPaired);
when(galaxyHistoriesService.findById(HISTORY_ID)).thenReturn(workflowHistory);
when(galaxyLibrariesService.buildEmptyLibrary(any(GalaxyProjectName.class))).thenReturn(workflowLibrary);
when(sequencingObjectService.getUniqueSamplesForSequencingObjects(pairedFiles)).thenReturn(sampleSequenceFilePairMap);
when(galaxyHistoriesService.fileToHistory(refFile, InputFileType.FASTA, workflowHistory)).thenReturn(refDataset);
when(galaxyWorkflowService.getWorkflowDetails(WORKFLOW_ID)).thenReturn(workflowDetails);
when(analysisParameterServiceGalaxy.prepareAnalysisParameters(any(Map.class), any(IridaWorkflow.class))).thenReturn(new WorkflowInputsGalaxy(new WorkflowInputs()));
when(galaxyWorkflowService.getWorkflowInputId(workflowDetails, SEQUENCE_FILE_PAIRED_LABEL)).thenReturn(SEQUENCE_FILE_PAIRED_ID);
when(galaxyWorkflowService.getWorkflowInputId(workflowDetails, REFERENCE_FILE_LABEL)).thenReturn(REFERENCE_FILE_ID);
when(analysisCollectionServiceGalaxy.uploadSequenceFilesPaired(any(Map.class), eq(workflowHistory), eq(workflowLibrary))).thenReturn(collectionResponsePaired);
PreparedWorkflowGalaxy preparedWorkflow = workflowPreparation.prepareAnalysisFiles(submission);
assertEquals("preparedWorflow history id not equal to " + HISTORY_ID, HISTORY_ID, preparedWorkflow.getRemoteAnalysisId());
assertEquals("preparedWorkflow library is invalid", LIBRARY_ID, preparedWorkflow.getRemoteDataId());
assertNotNull("workflowInputs in preparedWorkflow is null", preparedWorkflow.getWorkflowInputs());
Map<String, WorkflowInput> workflowInputsMap = preparedWorkflow.getWorkflowInputs().getInputsObject().getInputs();
assertEquals("workflow inputs has invalid size", 2, workflowInputsMap.size());
assertTrue("workflow inputs should contain reference file entry", workflowInputsMap.containsKey(REFERENCE_FILE_ID));
assertTrue("workflow inputs should contain sequence file paired entry", workflowInputsMap.containsKey(SEQUENCE_FILE_PAIRED_ID));
verify(analysisCollectionServiceGalaxy, never()).uploadSequenceFilesSingleEnd(any(Map.class), any(History.class), any(Library.class));
verify(analysisCollectionServiceGalaxy).uploadSequenceFilesPaired(any(Map.class), any(History.class), any(Library.class));
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class AnalysisWorkspaceServiceGalaxy method prepareAnalysisFiles.
/**
* {@inheritDoc}
*/
@Override
public PreparedWorkflowGalaxy prepareAnalysisFiles(AnalysisSubmission analysisSubmission) throws ExecutionManagerException, IridaWorkflowException {
checkNotNull(analysisSubmission, "analysisSubmission is null");
checkNotNull(analysisSubmission.getRemoteAnalysisId(), "analysisId is null");
checkNotNull(analysisSubmission.getWorkflowId(), "workflowId is null");
checkNotNull(analysisSubmission.getRemoteWorkflowId(), "remoteWorkflowId is null");
IridaWorkflow iridaWorkflow = iridaWorkflowsService.getIridaWorkflow(analysisSubmission.getWorkflowId());
IridaWorkflowInput workflowInput = iridaWorkflow.getWorkflowDescription().getInputs();
Set<SingleEndSequenceFile> singleEndFiles = sequencingObjectService.getSequencingObjectsOfTypeForAnalysisSubmission(analysisSubmission, SingleEndSequenceFile.class);
Set<SequenceFilePair> pairedEndFiles = sequencingObjectService.getSequencingObjectsOfTypeForAnalysisSubmission(analysisSubmission, SequenceFilePair.class);
if (iridaWorkflow.getWorkflowDescription().requiresReference()) {
checkArgument(analysisSubmission.getReferenceFile().isPresent(), "workflow requires reference but none defined in submission");
} else {
checkArgument(!analysisSubmission.getReferenceFile().isPresent(), "workflow does not require a reference and a reference file is set in the submission");
}
if (!iridaWorkflow.getWorkflowDescription().acceptsSingleSequenceFiles()) {
checkArgument(singleEndFiles.isEmpty(), "workflow does not accept single sequence files, but single sequence files are passed as input to " + analysisSubmission);
}
if (!iridaWorkflow.getWorkflowDescription().acceptsPairedSequenceFiles()) {
checkArgument(pairedEndFiles.isEmpty(), "workflow does not accept paired sequence files, but paired sequence files are passed as input to " + analysisSubmission);
}
String temporaryLibraryName = AnalysisSubmission.class.getSimpleName() + "-" + UUID.randomUUID().toString();
History workflowHistory = galaxyHistoriesService.findById(analysisSubmission.getRemoteAnalysisId());
Library workflowLibrary = galaxyLibrariesService.buildEmptyLibrary(new GalaxyProjectName(temporaryLibraryName));
// get unique files for pairs and single files
Map<Sample, SingleEndSequenceFile> singleFiles = sequencingObjectService.getUniqueSamplesForSequencingObjects(singleEndFiles);
Map<Sample, SequenceFilePair> pairedFiles = sequencingObjectService.getUniqueSamplesForSequencingObjects(pairedEndFiles);
// check that there aren't common sample names between single and paired
if (samplesInCommon(singleFiles, pairedFiles)) {
throw new SampleAnalysisDuplicateException("Single and paired input files share a common sample for submission " + analysisSubmission);
}
String workflowId = analysisSubmission.getRemoteWorkflowId();
WorkflowDetails workflowDetails = galaxyWorkflowService.getWorkflowDetails(workflowId);
WorkflowInputsGalaxy workflowInputsGalaxy = analysisParameterServiceGalaxy.prepareAnalysisParameters(analysisSubmission.getInputParameters(), iridaWorkflow);
WorkflowInputs inputs = workflowInputsGalaxy.getInputsObject();
inputs.setDestination(new WorkflowInputs.ExistingHistory(workflowHistory.getId()));
inputs.setWorkflowId(workflowDetails.getId());
if (!singleFiles.isEmpty()) {
String sequenceFilesLabelSingle = workflowInput.getSequenceReadsSingle().get();
String workflowSequenceFileSingleInputId = galaxyWorkflowService.getWorkflowInputId(workflowDetails, sequenceFilesLabelSingle);
CollectionResponse collectionResponseSingle = analysisCollectionServiceGalaxy.uploadSequenceFilesSingleEnd(singleFiles, workflowHistory, workflowLibrary);
inputs.setInput(workflowSequenceFileSingleInputId, new WorkflowInputs.WorkflowInput(collectionResponseSingle.getId(), WorkflowInputs.InputSourceType.HDCA));
}
if (!pairedFiles.isEmpty()) {
String sequenceFilesLabelPaired = workflowInput.getSequenceReadsPaired().get();
String workflowSequenceFilePairedInputId = galaxyWorkflowService.getWorkflowInputId(workflowDetails, sequenceFilesLabelPaired);
CollectionResponse collectionResponsePaired = analysisCollectionServiceGalaxy.uploadSequenceFilesPaired(pairedFiles, workflowHistory, workflowLibrary);
inputs.setInput(workflowSequenceFilePairedInputId, new WorkflowInputs.WorkflowInput(collectionResponsePaired.getId(), WorkflowInputs.InputSourceType.HDCA));
}
String analysisId = workflowHistory.getId();
if (iridaWorkflow.getWorkflowDescription().requiresReference()) {
String referenceFileLabel = workflowInput.getReference().get();
prepareReferenceFile(analysisSubmission.getReferenceFile().get(), workflowHistory, referenceFileLabel, workflowDetails, inputs);
}
return new PreparedWorkflowGalaxy(analysisId, workflowLibrary.getId(), new WorkflowInputsGalaxy(inputs));
}
Aggregations