use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class SequenceFilePairConcatenator method concatenateFiles.
/**
* {@inheritDoc}
*/
@Override
public SequenceFilePair concatenateFiles(List<? extends SequencingObject> toConcatenate, String filename) throws ConcatenateException {
// create the filenames with F/R for the forward and reverse files
String forwardName = filename + "_R1.fastq";
String reverseName = filename + "_R2.fastq";
Path forwardFile;
Path reverseFile;
try {
// create a temp directory for the new files
Path tempDirectory = Files.createTempDirectory(null);
forwardFile = tempDirectory.resolve(forwardName);
reverseFile = tempDirectory.resolve(reverseName);
// create temp files
forwardFile = Files.createFile(forwardFile);
reverseFile = Files.createFile(reverseFile);
} catch (IOException e) {
throw new ConcatenateException("Could not create temporary files", e);
}
// for each file concatenate the forward and reverse files
for (SequencingObject f : toConcatenate) {
SequenceFilePair pair = (SequenceFilePair) f;
SequenceFile forwardSequenceFile = pair.getForwardSequenceFile();
SequenceFile reverseSequenceFile = pair.getReverseSequenceFile();
appendToFile(forwardFile, forwardSequenceFile);
appendToFile(reverseFile, reverseSequenceFile);
}
// create new SequenceFiles
SequenceFile forward = new SequenceFile(forwardFile);
SequenceFile reverse = new SequenceFile(reverseFile);
// create the new pair
SequenceFilePair sequenceFilePair = new SequenceFilePair(forward, reverse);
return sequenceFilePair;
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class SequenceFilePairRemoteRepositoryImpl method setRemoteStatus.
/**
* {@inheritDoc}
*/
@Override
protected <T extends IridaResourceSupport> T setRemoteStatus(T entity, RemoteAPI api) {
entity = super.setRemoteStatus(entity, api);
SequenceFilePair pair = (SequenceFilePair) entity;
pair.getFiles().forEach(f -> super.setRemoteStatus(f, api));
return entity;
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class RESTSampleSequenceFilesController method addNewSequenceFilePairToSample.
/**
* Add a pair of {@link SequenceFile}s to a {@link Sample}
*
* @param sampleId
* The {@link Sample} id to add to
* @param file1
* The first multipart file
* @param fileResource1
* The metadata for the first file
* @param file2
* The second multipart file
* @param fileResource2
* the metadata for the second file
* @param response
* a reference to the servlet response.
* @return Response containing the locations for the created files
* @throws IOException
* if we can't write the files to disk
*/
@RequestMapping(value = "/api/samples/{sampleId}/pairs", method = RequestMethod.POST, consumes = MediaType.MULTIPART_FORM_DATA_VALUE)
public ModelMap addNewSequenceFilePairToSample(@PathVariable Long sampleId, @RequestPart("file1") MultipartFile file1, @RequestPart(value = "parameters1") SequenceFileResource fileResource1, @RequestPart("file2") MultipartFile file2, @RequestPart(value = "parameters2") SequenceFileResource fileResource2, HttpServletResponse response) throws IOException {
logger.debug("Adding pair of sequence files to sample " + sampleId);
logger.trace("First uploaded file size: " + file1.getSize() + " bytes");
logger.trace("Second uploaded file size: " + file2.getSize() + " bytes");
ModelMap modelMap = new ModelMap();
// confirm that a relationship exists between the project and the sample
Sample sample = sampleService.read(sampleId);
logger.trace("Read sample " + sampleId);
// create temp files
Path temp1 = Files.createTempDirectory(null);
Path target1 = temp1.resolve(file1.getOriginalFilename());
Path temp2 = Files.createTempDirectory(null);
Path target2 = temp2.resolve(file2.getOriginalFilename());
// transfer the files to temp directories
file1.transferTo(target1.toFile());
file2.transferTo(target2.toFile());
// create the model objects
SequenceFile sf1 = fileResource1.getResource();
SequenceFile sf2 = fileResource2.getResource();
sf1.setFile(target1);
sf2.setFile(target2);
// get the sequencing run
SequencingRun sequencingRun = null;
if (!Objects.equal(fileResource1.getMiseqRunId(), fileResource2.getMiseqRunId())) {
throw new IllegalArgumentException("Cannot upload a pair of files from different sequencing runs");
}
Long runId = fileResource1.getMiseqRunId();
SequenceFilePair sequenceFilePair = new SequenceFilePair(sf1, sf2);
if (runId != null) {
sequencingRun = miseqRunService.read(runId);
sequenceFilePair.setSequencingRun(sequencingRun);
logger.trace("Added sequencing run to files" + runId);
}
// add the files and join
SampleSequencingObjectJoin createSequencingObjectInSample = sequencingObjectService.createSequencingObjectInSample(sequenceFilePair, sample);
// clean up the temporary files.
Files.deleteIfExists(target1);
Files.deleteIfExists(temp1);
Files.deleteIfExists(target2);
Files.deleteIfExists(temp2);
logger.trace("Deleted temp files");
SequencingObject sequencingObject = createSequencingObjectInSample.getObject();
sequencingObject = addSequencingObjectLinks(sequencingObject, sampleId);
sequencingObject.add(linkTo(methodOn(RESTSampleSequenceFilesController.class).getSampleSequenceFiles(sampleId)).withRel(REL_SAMPLE_SEQUENCE_FILES));
// add location header
response.addHeader(HttpHeaders.LOCATION, sequencingObject.getLink("self").getHref());
// set the response status.
response.setStatus(HttpStatus.CREATED.value());
modelMap.addAttribute(RESTGenericController.RESOURCE_NAME, sequencingObject);
// respond to the client
return modelMap;
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class RESTSampleSequenceFilesController method addSequencingObjectLinks.
/**
* Add the links for a {@link SequencingObject} to its sample, self, to each
* individual {@link SequenceFile}
*
* @param sequencingObject {@link SequencingObject} to enhance
* @param sampleId ID of the {@link Sample} for the object
* @param <T> The subclass of {@link SequencingObject} being enhanced by this method
* @return the enhanced {@link SequencingObject}
*/
@SuppressWarnings("unchecked")
public static <T extends SequencingObject> T addSequencingObjectLinks(T sequencingObject, Long sampleId) {
String objectType = objectLabels.get(sequencingObject.getClass());
// link to self
sequencingObject.add(linkTo(methodOn(RESTSampleSequenceFilesController.class).readSequencingObject(sampleId, objectType, sequencingObject.getId())).withSelfRel());
// link to the sample
sequencingObject.add(linkTo(methodOn(RESTProjectSamplesController.class).getSample(sampleId)).withRel(RESTSampleSequenceFilesController.REL_SAMPLE));
// link to the individual files
for (SequenceFile file : sequencingObject.getFiles()) {
file.add(linkTo(methodOn(RESTSampleSequenceFilesController.class).readSequenceFileForSequencingObject(sampleId, objectType, sequencingObject.getId(), file.getId())).withSelfRel());
}
AnalysisSubmission automatedAssembly = sequencingObject.getAutomatedAssembly();
if (automatedAssembly != null) {
sequencingObject.add(linkTo(methodOn(RESTAnalysisSubmissionController.class).getResource(automatedAssembly.getId())).withRel(REL_AUTOMATED_ASSEMBLY));
}
AnalysisSubmission sistrTyping = sequencingObject.getSistrTyping();
if (sistrTyping != null) {
sequencingObject.add(linkTo(methodOn(RESTAnalysisSubmissionController.class).getResource(sistrTyping.getId())).withRel(REL_SISTR_TYPING));
}
// if it's a pair, add forward/reverse links
if (sequencingObject instanceof SequenceFilePair) {
sequencingObject = (T) addSequenceFilePairLinks((SequenceFilePair) sequencingObject, sampleId);
}
return sequencingObject;
}
use of ca.corefacility.bioinformatics.irida.model.sequenceFile.SequenceFilePair in project irida by phac-nml.
the class SNVPhylAnalysisIT method testSNVPhylSuccess.
/**
* Tests out successfully executing the SNVPhyl pipeline.
*
* @throws Exception
*/
@Test
@WithMockUser(username = "aaron", roles = "ADMIN")
public void testSNVPhylSuccess() throws Exception {
SequenceFilePair sequenceFilePairA = databaseSetupGalaxyITService.setupSampleSequenceFileInDatabase(1L, sequenceFilePathsA1List, sequenceFilePathsA2List).get(0);
SequenceFilePair sequenceFilePairB = databaseSetupGalaxyITService.setupSampleSequenceFileInDatabase(2L, sequenceFilePathsB1List, sequenceFilePathsB2List).get(0);
SequenceFilePair sequenceFilePairC = databaseSetupGalaxyITService.setupSampleSequenceFileInDatabase(3L, sequenceFilePathsC1List, sequenceFilePathsC2List).get(0);
Map<String, String> parameters = ImmutableMap.of("snv-abundance-ratio", "0.75", "minimum-read-coverage", "2", "filter-density-threshold", "2", "filter-density-window-size", "3");
waitForFilesToSettle(sequenceFilePairA, sequenceFilePairB, sequenceFilePairC);
AnalysisSubmission submission = databaseSetupGalaxyITService.setupPairSubmissionInDatabase(Sets.newHashSet(sequenceFilePairA, sequenceFilePairB, sequenceFilePairC), referenceFilePath, parameters, snvPhylWorkflow.getWorkflowIdentifier());
completeSubmittedAnalyses(submission.getId());
submission = analysisSubmissionRepository.findOne(submission.getId());
assertEquals("analysis state should be completed.", AnalysisState.COMPLETED, submission.getAnalysisState());
Analysis analysisPhylogenomics = submission.getAnalysis();
assertEquals("Should have generated a phylogenomics pipeline analysis type.", AnalysisType.PHYLOGENOMICS, analysisPhylogenomics.getAnalysisType());
assertEquals("the phylogenomics pipeline should have 8 output files.", 8, analysisPhylogenomics.getAnalysisOutputFiles().size());
@SuppressWarnings("resource") String matrixContent = new Scanner(analysisPhylogenomics.getAnalysisOutputFile(MATRIX_KEY).getFile().toFile()).useDelimiter("\\Z").next();
assertTrue("snpMatrix should be the same but is \"" + matrixContent + "\"", com.google.common.io.Files.equal(outputSnvMatrix1.toFile(), analysisPhylogenomics.getAnalysisOutputFile(MATRIX_KEY).getFile().toFile()));
assertNotNull("file should have tool provenance attached.", analysisPhylogenomics.getAnalysisOutputFile(MATRIX_KEY).getCreatedByTool());
@SuppressWarnings("resource") String snpTableContent = new Scanner(analysisPhylogenomics.getAnalysisOutputFile(TABLE_KEY).getFile().toFile()).useDelimiter("\\Z").next();
assertTrue("snpTable should be the same but is \"" + snpTableContent + "\"", com.google.common.io.Files.equal(outputSnvTable1.toFile(), analysisPhylogenomics.getAnalysisOutputFile(TABLE_KEY).getFile().toFile()));
assertNotNull("file should have tool provenance attached.", analysisPhylogenomics.getAnalysisOutputFile(TABLE_KEY).getCreatedByTool());
@SuppressWarnings("resource") String vcf2coreContent = new Scanner(analysisPhylogenomics.getAnalysisOutputFile(CORE_KEY).getFile().toFile()).useDelimiter("\\Z").next();
assertTrue("vcf2core should be the same but is \"" + vcf2coreContent + "\"", com.google.common.io.Files.equal(vcf2core1.toFile(), analysisPhylogenomics.getAnalysisOutputFile(CORE_KEY).getFile().toFile()));
assertNotNull("file should have tool provenance attached.", analysisPhylogenomics.getAnalysisOutputFile(CORE_KEY).getCreatedByTool());
// only check size of mapping quality file due to samples output in random order
assertTrue("the mapping quality file should not be empty.", Files.size(analysisPhylogenomics.getAnalysisOutputFile(QUALITY_KEY).getFile()) > 0);
@SuppressWarnings("resource") String filterStatsContent = new Scanner(analysisPhylogenomics.getAnalysisOutputFile(STATS_KEY).getFile().toFile()).useDelimiter("\\Z").next();
assertTrue("filterStats should be the same but is \"" + filterStatsContent + "\"", com.google.common.io.Files.equal(filterStats1.toFile(), analysisPhylogenomics.getAnalysisOutputFile(STATS_KEY).getFile().toFile()));
assertNotNull("file should have tool provenance attached.", analysisPhylogenomics.getAnalysisOutputFile(STATS_KEY).getCreatedByTool());
@SuppressWarnings("resource") String snvAlignContent = new Scanner(analysisPhylogenomics.getAnalysisOutputFile(ALIGN_KEY).getFile().toFile()).useDelimiter("\\Z").next();
assertTrue("snvAlign should be the same but is \"" + snvAlignContent + "\"", com.google.common.io.Files.equal(snvAlign1.toFile(), analysisPhylogenomics.getAnalysisOutputFile(ALIGN_KEY).getFile().toFile()));
assertNotNull("file should have tool provenance attached.", analysisPhylogenomics.getAnalysisOutputFile(ALIGN_KEY).getCreatedByTool());
// only test to make sure the files have a valid size since PhyML uses a
// random seed to generate the tree (and so changes results)
assertTrue("the phylogenetic tree file should not be empty.", Files.size(analysisPhylogenomics.getAnalysisOutputFile(TREE_KEY).getFile()) > 0);
assertTrue("the phylogenetic tree stats file should not be empty.", Files.size(analysisPhylogenomics.getAnalysisOutputFile(TREE_KEY).getFile()) > 0);
// try to follow the phylogenomics provenance all the way back to the
// upload tools
final List<ToolExecution> toolsToVisit = Lists.newArrayList(analysisPhylogenomics.getAnalysisOutputFile(TREE_KEY).getCreatedByTool());
assertFalse("file should have tool provenance attached.", toolsToVisit.isEmpty());
boolean foundReadsInputTool = false;
boolean foundReferenceInputTool = false;
// one where you upload the reads.
while (!toolsToVisit.isEmpty()) {
final ToolExecution ex = toolsToVisit.remove(0);
toolsToVisit.addAll(ex.getPreviousSteps());
if (ex.isInputTool()) {
final Map<String, String> params = ex.getExecutionTimeParameters();
logger.debug("Input tool has " + params);
foundReferenceInputTool |= params.containsKey("files.NAME") && params.get("files.NAME").contains("reference") && params.get("file_type").contains("fasta");
foundReadsInputTool |= params.get("file_type").contains("fastq");
}
}
assertTrue("Should have found both reads and reference input tools.", foundReadsInputTool && foundReferenceInputTool);
}
Aggregations