Merge discvr-25.3 to develop

SequenceAnalysis/src/org/labkey/sequenceanalysis/run/util/LiftoverBcfToolsWrapper.java → SequenceAnalysis/api-src/org/labkey/api/sequenceanalysis/run/LiftoverBcfToolsWrapper.java

@@ -1,11 +1,10 @@
-package org.labkey.sequenceanalysis.run.util;
+package org.labkey.api.sequenceanalysis.run;
 
 import org.apache.logging.log4j.Logger;
 import org.jetbrains.annotations.Nullable;
 import org.labkey.api.pipeline.PipelineJobException;
 import org.labkey.api.sequenceanalysis.SequenceAnalysisService;
 import org.labkey.api.sequenceanalysis.pipeline.SequencePipelineService;
-import org.labkey.api.sequenceanalysis.run.PicardWrapper;
 
 import java.io.File;
 import java.io.IOException;

SequenceAnalysis/src/org/labkey/sequenceanalysis/analysis/AbstractCombineGeneCountsHandler.java

@@ -81,11 +81,16 @@ private static List<ToolParameterDescriptor> getParams(boolean allowInferStrande
 
         if (allowInferStranded)
         {
-            ret.add(ToolParameterDescriptor.create(STRANDED, "Strand 1", "Choose whether to treat these data as stranded, unstranded, or to have the script infer the strandedness", "ldk-simplecombo", new JSONObject()
+            ret.add(ToolParameterDescriptor.create(STRANDED, "Strandedness", "Choose whether to treat these data as stranded, unstranded, or to have the script infer the strandedness", "ldk-simplecombo", new JSONObject()
             {{
                 put("storeValues", STRAND1 + ";" + STRAND2 + ";" + UNSTRANDED + ";" + INFER);
                 put("value", INFER);
             }}, INFER));
+            ret.add(ToolParameterDescriptor.create("strandedThreshold", "Strandedness Threshold", "If infer is selected, Choose whether to treat these data as stranded, unstranded, or to have the script infer the strandedness", "ldk-simplecombo", new JSONObject(){{
+                put("minValue", 0);
+                put("maxValue", 1);
+                put("decimalPrecision", 2);
+            }}, 0.9));
         }
 
         return ret;
@@ -305,29 +310,20 @@ public void prepareFiles(JobContext ctx, List<SequenceOutputFile> inputFiles, St
                 header.add(hp.getHeader(ctx, outputFileMap.get(rowId)));
             }
 
-            writer.writeNext(header.toArray(new String[header.size()]));
+            writer.writeNext(header.toArray(new String[0]));
 
             Set<String> genesWithoutData = new TreeSet<>();
             for (String geneId : results.distinctGenes)
             {
                 List<String> row = new ArrayList<>(inputFiles.size() + 3);
                 if (translator.getGeneMap().containsKey(geneId))
                 {
-                    if (translator.getGeneMap().containsKey(geneId))
-                    {
-                        row.add(geneId);
-                        row.add(translator.getGeneMap().get(geneId).get("gene_name"));
-                        row.add(translator.getGeneMap().get(geneId).get("gene_description"));
-                    }
-                    else
-                    {
-                        row.add(geneId);
-                        row.add("");
-                        row.add("");
-                    }
+                    row.add(geneId);
+                    row.add(translator.getGeneMap().get(geneId).get("gene_name"));
+                    row.add(translator.getGeneMap().get(geneId).get("gene_description"));
 
                     List<String> toAdd = new ArrayList<>();
-                    Integer totalWithData = 0;
+                    int totalWithData = 0;
                     for (Integer rowId : outputFileMap.keySet())
                     {
                         Double count = results.counts.get(rowId).get(geneId);
@@ -341,9 +337,9 @@ public void prepareFiles(JobContext ctx, List<SequenceOutputFile> inputFiles, St
 
                     if (totalWithData > 0 || !doSkipGenesWithoutData)
                     {
-                        row.add(totalWithData.toString());
+                        row.add(String.valueOf(totalWithData));
                         row.addAll(toAdd);
-                        writer.writeNext(row.toArray(new String[row.size()]));
+                        writer.writeNext(row.toArray(new String[0]));
                     }
 
                     if (totalWithData == 0 && !OTHER_IDS.contains(geneId))

SequenceAnalysis/src/org/labkey/sequenceanalysis/analysis/CombineStarGeneCountsHandler.java

@@ -31,7 +31,6 @@ public CombineStarGeneCountsHandler()
     @Override
     protected void processOutputFiles(CountResults results, List<SequenceOutputFile> inputFiles, JSONObject params, GeneToNameTranslator translator, PipelineJob job, RecordedAction action) throws PipelineJobException
     {
-
         String strandedSelection = params.optString(STRANDED, INFER);
 
         //next iterate all read count TSVs to guess strandedness
@@ -69,12 +68,12 @@ protected void processOutputFiles(CountResults results, List<SequenceOutputFile>
                         continue;
                     }
 
-                    Long unstranded = Long.parseLong(cells[1]);
-                    Long strand1 = Long.parseLong(cells[2]);
+                    long unstranded = Long.parseLong(cells[1]);
+                    long strand1 = Long.parseLong(cells[2]);
                     totalStrand1 += strand1;
-                    Long strand2 = Long.parseLong(cells[3]);
+                    long strand2 = Long.parseLong(cells[3]);
                     totalStrand2 += strand2;
-                    Long strandMax = Math.max(strand1, strand2);
+                    long strandMax = Math.max(strand1, strand2);
 
                     results.distinctGenes.add(geneId);
 
@@ -103,9 +102,9 @@ protected void processOutputFiles(CountResults results, List<SequenceOutputFile>
                         strand2Map = new HashMap<>(Math.max(results.distinctGenes.size() + 500, 5000));
                     }
 
-                    unstrandedMap.put(geneId, unstranded.doubleValue());
-                    strand1Map.put(geneId, strand1.doubleValue());
-                    strand2Map.put(geneId, strand2.doubleValue());
+                    unstrandedMap.put(geneId, (double)unstranded);
+                    strand1Map.put(geneId, (double)strand1);
+                    strand2Map.put(geneId, (double)strand2);
 
                     unstrandedCounts.put(so.getRowid(), unstrandedMap);
                     strand1Counts.put(so.getRowid(), strand1Map);
@@ -125,8 +124,9 @@ protected void processOutputFiles(CountResults results, List<SequenceOutputFile>
 
         //finally build output
         double avgStrandRatio = sumStrandRatio / countStrandRatio;
+        double threshold = params.optDouble("strandedThreshold", 0.9);
         job.getLogger().info("the average stranded/unstranded ratio for all samples was: " + avgStrandRatio);
-        double threshold = 0.9;
+
         String inferredStrandedness;
         job.getLogger().info("Attempting to infer strandedness");
         if (avgStrandRatio > threshold)

SequenceAnalysis/src/org/labkey/sequenceanalysis/analysis/LiftoverHandler.java

@@ -37,7 +37,7 @@
 import org.labkey.api.writer.PrintWriters;
 import org.labkey.sequenceanalysis.SequenceAnalysisModule;
 import org.labkey.sequenceanalysis.pipeline.ProcessVariantsHandler;
-import org.labkey.sequenceanalysis.run.util.LiftoverBcfToolsWrapper;
+import org.labkey.api.sequenceanalysis.run.LiftoverBcfToolsWrapper;
 import org.labkey.sequenceanalysis.run.util.LiftoverVcfWrapper;
 import org.labkey.sequenceanalysis.util.SequenceUtil;
 

SequenceAnalysis/src/org/labkey/sequenceanalysis/run/variant/VariantAnnotatorStep.java

@@ -55,6 +55,9 @@ public Provider()
                     ToolParameterDescriptor.create("excessHet", "ExcessHet", "If selected, the ExcessHet annotation will run.", "checkbox", new JSONObject(){{
                         put("checked", false);
                     }}, null),
+                    ToolParameterDescriptor.create("svtype", "SVType", "If selected, the SVType annotation will run.", "checkbox", new JSONObject(){{
+                        put("checked", false);
+                    }}, null),
                     new PedigreeToolParameterDescriptor()
             ), PageFlowUtil.set(PedigreeToolParameterDescriptor.getClientDependencyPath()), "");
         }
@@ -119,6 +122,12 @@ public Output processVariants(File inputVCF, File outputDirectory, ReferenceGeno
             options.add("ExcessHet");
         }
 
+        if (getProvider().getParameterByName("svtype").extractValue(getPipelineCtx().getJob(), getProvider(), getStepIdx(), Boolean.class, false))
+        {
+            options.add("-A");
+            options.add("SVType");
+        }
+
         if (intervals != null)
         {
             intervals.forEach(interval -> {

singlecell/resources/web/singlecell/panel/PoolImportPanel.js

@@ -182,6 +182,13 @@ Ext4.define('SingleCell.panel.PoolImportPanel', {
                 val = val.replace(/ PBMC/, '');
             }
 
+            if (val.indexOf('=') > -1) {
+                const split = val.split('=')
+                if (split.length === 2) {
+                    val = split[1]
+                }
+            }
+
             return val;
         },
 

singlecell/src/org/labkey/singlecell/pipeline/singlecell/CalculateGeneComponentScores.java

@@ -25,7 +25,7 @@ public Provider()
             super("CalculateGeneComponentScores", "Calculate Gene Module Scores", "RIRA", "This will generate UCell scores for a set of pre-defined gene modules", Collections.singletonList(
                     SeuratToolParameter.create("savedComponent", "Saved Component(s)", "This is the name of the saved component (from RIRA) to apply", "ldk-simplecombo", new JSONObject()
                     {{
-                        put("storeValues", "Tcell_NaiveToEffector;Tcell_EffectorDifferentiation");
+                        put("storeValues", "Tcell_EffectorDifferentiation;TCR_EarlyStimulationComponent;TCR_StimulationComponent1");
                         put("multiSelect", true);
                         put("allowBlank", false);
                         put("joinReturnValue", true);

singlecell/src/org/labkey/singlecell/pipeline/singlecell/UpdateSeuratPrototype.java

@@ -140,7 +140,8 @@ public Output execute(SequenceOutputHandler.JobContext ctx, List<SeuratObjectWra
                 toReplace.delete();
             }
 
-            FileUtils.moveFile(wrapper.getFile(), toReplace);
+            FileUtils.copyFile(wrapper.getFile(), toReplace);
+            ctx.getFileManager().addIntermediateFile(wrapper.getFile());
 
             // Also metadata:
             File meta = CellHashingServiceImpl.get().getMetaTableFromSeurat(wrapper.getFile());
@@ -149,7 +150,8 @@ public Output execute(SequenceOutputHandler.JobContext ctx, List<SeuratObjectWra
             {
                 metaOrig.delete();
             }
-            FileUtils.moveFile(meta, metaOrig);
+            FileUtils.copyFile(meta, metaOrig);
+            ctx.getFileManager().addIntermediateFile(meta);
 
             // Also cellbarcodes:
             File cellbarcodes = CellHashingServiceImpl.get().getCellBarcodesFromSeurat(wrapper.getFile());
@@ -158,7 +160,8 @@ public Output execute(SequenceOutputHandler.JobContext ctx, List<SeuratObjectWra
             {
                 cellbarcodesOrig.delete();
             }
-            FileUtils.moveFile(cellbarcodes, cellbarcodesOrig);
+            FileUtils.copyFile(cellbarcodes, cellbarcodesOrig);
+            ctx.getFileManager().addIntermediateFile(cellbarcodes);
         }
         catch (IOException e)
         {

singlecell/src/org/labkey/singlecell/run/NimbleAlignmentStep.java

@@ -87,6 +87,8 @@ public AlignmentOutput performAlignment(Readset rs, List<File> inputFastqs1, @Nu
             }
         }
 
+        NimbleHelper.write10xBarcodes(localBam, getWrapper().getLogger(), rs, referenceGenome, output);
+
         // Now run nimble itself:
         NimbleHelper helper = new NimbleHelper(getPipelineCtx(), getProvider(), getStepIdx());
         helper.doNimbleAlign(localBam, output, rs, basename);

singlecell/src/org/labkey/singlecell/run/NimbleAnalysis.java

@@ -58,6 +58,8 @@ public Output performAnalysisPerSampleRemote(Readset rs, File inputBam, Referenc
         NimbleHelper helper = new NimbleHelper(getPipelineCtx(), getProvider(), getStepIdx());
         helper.doNimbleAlign(inputBam, output, rs, FileUtil.getBaseName(inputBam));
 
+        NimbleHelper.write10xBarcodes(inputBam, getPipelineCtx().getLogger(), rs, referenceGenome, output);
+
         return output;
     }
 

singlecell/src/org/labkey/singlecell/run/NimbleHelper.java

@@ -5,6 +5,7 @@
 import org.apache.commons.io.IOUtils;
 import org.apache.commons.io.output.StringBuilderWriter;
 import org.apache.commons.lang3.StringUtils;
+import org.apache.logging.log4j.Logger;
 import org.jetbrains.annotations.Nullable;
 import org.json.JSONArray;
 import org.json.JSONObject;
@@ -27,6 +28,7 @@
 import org.labkey.api.sequenceanalysis.pipeline.PipelineStepProvider;
 import org.labkey.api.sequenceanalysis.pipeline.ReferenceGenome;
 import org.labkey.api.sequenceanalysis.pipeline.SequencePipelineService;
+import org.labkey.api.sequenceanalysis.run.DISCVRSeqRunner;
 import org.labkey.api.sequenceanalysis.run.DockerWrapper;
 import org.labkey.api.util.PageFlowUtil;
 import org.labkey.api.writer.PrintWriters;
@@ -494,6 +496,28 @@ private Map<NimbleGenome, File> doAlignment(List<NimbleGenome> genomes, List<Fil
         return resultMap;
     }
 
+    public static void write10xBarcodes(File bam, Logger log, Readset rs, ReferenceGenome referenceGenome, PipelineStepOutput output) throws PipelineJobException
+    {
+        // Write barcodes:
+        DISCVRSeqRunner runner = new DISCVRSeqRunner(log);
+        List<String> barcodeArgs = new ArrayList<>(runner.getBaseArgs("Save10xBarcodes"));
+        barcodeArgs.add("-I");
+        barcodeArgs.add(bam.getPath());
+
+        File cbOutput = new File(bam.getParentFile(), SequenceAnalysisService.get().getUnzippedBaseName(bam.getName()) + "cb.txt.gz");
+        barcodeArgs.add("--cbOutput");
+        barcodeArgs.add(cbOutput.getPath());
+
+        File umiOutput = new File(bam.getParentFile(), SequenceAnalysisService.get().getUnzippedBaseName(bam.getName()) + "umi.txt.gz");
+        barcodeArgs.add("--umiOutput");
+        barcodeArgs.add(umiOutput.getPath());
+
+        runner.execute(barcodeArgs);
+
+        output.addSequenceOutput(cbOutput, "10x CellBarcode Map: " + rs.getName(), "10x CellBarcode Map", rs.getReadsetId(), null, referenceGenome.getGenomeId(), null);
+        output.addSequenceOutput(umiOutput, "10x UMI Map: " + rs.getName(), "10x UMI Map", rs.getReadsetId(), null, referenceGenome.getGenomeId(), null);
+    }
+
     public static File runNimbleReport(File alignResultsGz, int genomeId, PipelineStepOutput output, PipelineContext ctx) throws PipelineJobException
     {
         List<String> reportArgs = new ArrayList<>();