Bugfix LoFreq variant import

Author: bbimber

SequenceAnalysis/src/org/labkey/sequenceanalysis/run/analysis/LofreqAnalysis.java

@@ -42,7 +42,6 @@
 import org.labkey.api.query.FieldKey;
 import org.labkey.api.reader.Readers;
 import org.labkey.api.sequenceanalysis.SequenceAnalysisService;
-import org.labkey.api.sequenceanalysis.SequenceOutputFile;
 import org.labkey.api.sequenceanalysis.model.AnalysisModel;
 import org.labkey.api.sequenceanalysis.model.Readset;
 import org.labkey.api.sequenceanalysis.pipeline.AbstractAnalysisStepProvider;
@@ -422,7 +421,7 @@ public Output performAnalysisPerSampleRemote(Readset rs, File inputBam, Referenc
         int totalIndelGTThreshold = 0;
         int totalConsensusInPBS= 0;
 
-        File loFreqConsensusVcf = new File(outputDir, FileUtil.getBaseName(inputBam) + ".lofreq.consensus.vcf.gz");
+        File loFreqConsensusVcf = getConsensusVcf(outputDir, inputBam);
         File loFreqAllVcf = getAllVcf(outputDir, inputBam);
         Double strandBiasRecoveryAF = getProvider().getParameterByName("strandBiasRecoveryAF").extractValue(getPipelineCtx().getJob(), getProvider(), getStepIdx(), Double.class, 1.0);
         SAMSequenceDictionary dict = SAMSequenceDictionaryExtractor.extractDictionary(referenceGenome.getSequenceDictionary().toPath());
@@ -707,9 +706,19 @@ private Set<String> runBcftools(File inputBam, ReferenceGenome referenceGenome,
         return variantsBcftools;
     }
 
+    private File getConsensusVcf(File outputDir, File inputBam)
+    {
+        return new File(outputDir, FileUtil.getBaseName(inputBam) + ".lofreq.consensus.vcf.gz");
+    }
+
+    private File getConsensusFasta(File loFreqConsensusVcf)
+    {
+        return new File(loFreqConsensusVcf.getParentFile(), SequenceAnalysisService.get().getUnzippedBaseName(loFreqConsensusVcf.getName()) + ".fasta");
+    }
+
     private File generateConsensus(File loFreqConsensusVcf, File fasta, File maskBed) throws PipelineJobException
     {
-        File ret = new File(loFreqConsensusVcf.getParentFile(), SequenceAnalysisService.get().getUnzippedBaseName(loFreqConsensusVcf.getName()) + ".fasta");
+        File ret = getConsensusFasta(loFreqConsensusVcf);
         List<String> args = new ArrayList<>();
 
         args.add(SequencePipelineService.get().getExeForPackage("BCFTOOLS", "bcftools").getPath());
@@ -868,24 +877,19 @@ public Output performAnalysisPerSampleLocal(AnalysisModel model, File inputBam,
         if (runPangolinAndNextClade)
         {
             //Find the NextClade json:
-            SimpleFilter filter = new SimpleFilter(FieldKey.fromString("analysis_id"), model.getRowId());
-            filter.addCondition(FieldKey.fromString("category"), NextCladeHandler.NEXTCLADE_JSON);
-            SequenceOutputFile jsonFileRecord = new TableSelector(SequenceAnalysisSchema.getTable(SequenceAnalysisSchema.TABLE_OUTPUTFILES), filter, null).getObject(SequenceOutputFile.class);
-            if (jsonFileRecord == null)
+            File jsonFile = NextCladeHandler.getJsonFile(outDir, getConsensusFasta(getConsensusVcf(outDir, inputBam)));
+            if (!jsonFile.exists())
             {
-                throw new PipelineJobException("Unable to find NextClade JSON record");
+                throw new PipelineJobException("Unable to find NextClade JSON record: " + jsonFile.getPath());
             }
 
-            //Find the NextClade json:
-            SimpleFilter filter2 = new SimpleFilter(FieldKey.fromString("analysis_id"), model.getRowId());
-            filter2.addCondition(FieldKey.fromString("category"), CATEGORY);
-            SequenceOutputFile vcfFileRecord = new TableSelector(SequenceAnalysisSchema.getTable(SequenceAnalysisSchema.TABLE_OUTPUTFILES), filter2, null).getObject(SequenceOutputFile.class);
-            if (vcfFileRecord == null)
+            File vcf = getAllVcf(outDir, inputBam);
+            if (!vcf.exists())
             {
-                throw new PipelineJobException("Unable to find LoFreq VCF record");
+                throw new PipelineJobException("Unable to find LoFreq VCF: " + vcf.getPath());
             }
 
-            NextCladeHandler.processAndImportNextCladeAa(getPipelineCtx().getJob(), jsonFileRecord, model.getRowId(), vcfFileRecord.getFile(), dbImport);
+            NextCladeHandler.processAndImportNextCladeAa(getPipelineCtx().getJob(), jsonFile, model.getRowId(), model.getLibraryId(), model.getAlignmentFile(), model.getReadset(), vcf, dbImport);
         }
         else
         {

SequenceAnalysis/src/org/labkey/sequenceanalysis/run/analysis/NextCladeHandler.java

@@ -117,7 +117,7 @@ public void complete(PipelineJob job, List<SequenceOutputFile> inputFiles, List<
                     throw new PipelineJobException("Unable to find parent for output: " + so.getRowid());
                 }
 
-                processAndImportNextCladeAa(job, so, parent.getAnalysis_id(), parent.getFile(), true);
+                processAndImportNextCladeAa(job, so.getFile(), parent.getAnalysis_id(), so.getLibrary_id(), so.getDataId(), so.getReadset(), parent.getFile(), true);
             }
         }
 
@@ -134,6 +134,11 @@ public void processFilesRemote(List<SequenceOutputFile> inputFiles, JobContext c
         }
     }
 
+    public static File getJsonFile(File outputDir, File consensusFasta)
+    {
+        return new File(outputDir, FileUtil.getBaseName(consensusFasta) + ".json");
+    }
+
     public static File runNextClade(File consensusFasta, Logger log, PipelineOutputTracker tracker, File outputDir) throws PipelineJobException
     {
         if (!consensusFasta.getParentFile().equals(outputDir))
@@ -151,7 +156,7 @@ public static File runNextClade(File consensusFasta, Logger log, PipelineOutputT
             }
         }
 
-        File jsonFile = new File(outputDir, FileUtil.getBaseName(consensusFasta) + ".json");
+        File jsonFile = getJsonFile(outputDir, consensusFasta);
 
         File localBashScript = new File(outputDir, "dockerWrapper.sh");
         try (PrintWriter writer = PrintWriters.getPrintWriter(localBashScript))
@@ -224,17 +229,18 @@ private static JSONObject parseNextClade(File jsonFile) throws PipelineJobExcept
         }
     }
 
-    public static void processAndImportNextCladeAa(PipelineJob job, SequenceOutputFile so, int analysisId, File consensusVCF, boolean dbImport) throws PipelineJobException
+    public static void processAndImportNextCladeAa(PipelineJob job, File jsonFile, int analysisId, int libraryId, int alignmentId, int readsetId, File consensusVCF, boolean dbImport) throws PipelineJobException
     {
-        JSONObject sample = parseNextClade(so.getFile());
+        JSONObject sample = parseNextClade(jsonFile);
 
-        ReferenceGenome genome = SequenceAnalysisService.get().getReferenceGenome(so.getLibrary_id(), job.getUser());
+        ReferenceGenome genome = SequenceAnalysisService.get().getReferenceGenome(libraryId, job.getUser());
         String clade = sample.getString("clade");
-        saveClade(so, clade, analysisId, job);
+        saveClade(clade, analysisId, alignmentId, readsetId, job);
 
         if (!dbImport)
         {
             job.getLogger().info("DB Import not selected, will not import AA SNPs");
+            return;
         }
 
         JSONArray aaSubstitutions = sample.getJSONArray("aaSubstitutions");
@@ -334,17 +340,17 @@ public static void processAndImportNextCladeAa(PipelineJob job, SequenceOutputFi
         }
     }
 
-    private static void saveClade(SequenceOutputFile so, String clade, int analysisId, PipelineJob job) throws PipelineJobException
+    private static void saveClade(String clade, int analysisId, int alignmentId, int readsetId, PipelineJob job) throws PipelineJobException
     {
         List<Map<String, Object>> toInsert = new ArrayList<>();
         Map<String, Object> row1 = new CaseInsensitiveHashMap<>();
-        row1.put("dataid", so.getDataId());
-        row1.put("readset", so.getReadset());
+        row1.put("dataid", alignmentId);
+        row1.put("readset", readsetId);
         row1.put("analysis_id", analysisId);
         row1.put("category", "NextClade");
         row1.put("metricName", "NextCladeClade");
         row1.put("qualvalue", clade);
-        row1.put("container", so.getContainer());
+        row1.put("container", job.getContainer().getId());
         toInsert.add(row1);
 
         Container targetContainer = job.getContainer().isWorkbook() ? job.getContainer().getParent() : job.getContainer();