Store barcodes as list to enforce uniqueness

bbimber · bbimber · commit d4ad7d4d3752 · 2021-01-29T15:26:20.000-08:00
diff --git a/singlecell/api-src/org/labkey/api/singlecell/CellHashingService.java b/singlecell/api-src/org/labkey/api/singlecell/CellHashingService.java
@@ -26,7 +26,9 @@
 import java.util.ArrayList;
 import java.util.Arrays;
 import java.util.Collections;
+import java.util.HashSet;
 import java.util.List;
+import java.util.Set;
 import java.util.stream.Collectors;
 
 abstract public class CellHashingService
@@ -71,14 +73,14 @@ static public void setInstance(CellHashingService instance)
 
     abstract public List<ToolParameterDescriptor> getDefaultHashingParams(boolean includeExcludeFailedcDNA);
 
-    abstract public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException;
+    abstract public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException;
 
     public static class CellHashingParameters
     {
         public BARCODE_TYPE type;
 
         private File htoOrCiteseqBarcodesFile;
-        public List<String> allowableHtoOrCiteseqBarcodes;
+        public Set<String> allowableHtoOrCiteseqBarcodes;
 
         public File cellBarcodeWhitelistFile;
 
@@ -227,18 +229,18 @@ public void validate(boolean allowMissingHtoReadset)
             }
         }
 
-        public List<String> getAllowableBarcodeNames() throws PipelineJobException
+        public Set<String> getAllowableBarcodeNames() throws PipelineJobException
         {
             if (allowableHtoOrCiteseqBarcodes != null)
             {
-                return Collections.unmodifiableList(allowableHtoOrCiteseqBarcodes);
+                return Collections.unmodifiableSet(allowableHtoOrCiteseqBarcodes);
             }
             if (htoOrCiteseqBarcodesFile == null)
             {
                 throw new IllegalArgumentException("Barcode file was null");
             }
 
-            List<String> allowableBarcodes = new ArrayList<>();
+            Set<String> allowableBarcodes = new HashSet<>();
             try (CSVReader reader = new CSVReader(Readers.getReader(htoOrCiteseqBarcodesFile), '\t'))
             {
                 String[] line;
diff --git a/singlecell/resources/chunks/NormalizeAndScale.R b/singlecell/resources/chunks/NormalizeAndScale.R
@@ -4,7 +4,7 @@ for (datasetId in names(seuratObjects)) {
     seuratObjects[[datasetId]] <- NULL
     gc()
 
-    seuratObj <- CellMembrane::NormalizeAndScale(seuratObj, variableFeatureSelectionMethod = variableFeatureSelectionMethod)
+    seuratObj <- CellMembrane::NormalizeAndScale(seuratObj, variableFeatureSelectionMethod = variableFeatureSelectionMethod, block.size = block.size)
 
     newSeuratObjects[[datasetId]] <- seuratObj
 
diff --git a/singlecell/resources/chunks/RemoveCellCycle.R b/singlecell/resources/chunks/RemoveCellCycle.R
@@ -1,7 +1,7 @@
 for (datasetId in names(seuratObjects)) {
     seuratObj <- seuratObjects[[datasetId]]
 
-    seuratObj <- CellMembrane::RemoveCellCycle(seuratObj)
+    seuratObj <- CellMembrane::RemoveCellCycle(seuratObj, block.size = block.size)
 
     newSeuratObjects[[datasetId]] <- seuratObj
 
diff --git a/singlecell/resources/chunks/SaveData.R b/singlecell/resources/chunks/SaveData.R
@@ -14,7 +14,8 @@ for (datasetId in names(newSeuratObjects)) {
 
     savedFiles <- rbind(savedFiles, data.frame(datasetId = datasetId, datasetName = datasetName, filename = fn, outputFileId = outputFileId))
 
-    CellMembrane::WriteCellBarcodes(seuratObj, file = barcodeFile)
+    # WriteCellBarcodes
+    write.table(data.frame(CellBarcode = colnames(seuratObj)), file = barcodeFile, quote = F, row.names = F, sep = ',', col.names = F)
 }
 
 write.table(savedFiles, file = 'savedSeuratObjects.txt', quote = FALSE, sep = '\t', row.names = FALSE, col.names = FALSE)
diff --git a/singlecell/src/org/labkey/singlecell/CellHashingServiceImpl.java b/singlecell/src/org/labkey/singlecell/CellHashingServiceImpl.java
@@ -1226,7 +1226,7 @@ private File generateCellHashingCalls(File citeSeqCountOutDir, File outputDir, S
                     cellbarcodeWhitelist = "'/work/" + cellBarcodeWhitelistFile.getName() + "'";
                 }
 
-                List<String> allowableBarcodes = parameters.getAllowableBarcodeNames();
+                Set<String> allowableBarcodes = parameters.getAllowableBarcodeNames();
                 String allowableBarcodeParam = allowableBarcodes != null ? "c('" + StringUtils.join(allowableBarcodes, "','") + "')" : "NULL";
 
                 writer.println("cellhashR::CallAndGenerateReport(rawCountData = '/work/" + citeSeqCountOutDir.getName() + "', reportFile = '/work/" + htmlFile.getName() + "', callFile = '/work/" + callsFile.getName() + "', metricsFile = '/work/" + metricsFile.getName() + "', cellbarcodeWhitelist  = " + cellbarcodeWhitelist + ", barcodeWhitelist = " + allowableBarcodeParam + ", title = '" + parameters.getReportTitle() + "', methods = c('" + StringUtils.join(methodNames, "','") + "'))");
@@ -1466,12 +1466,12 @@ else if (line.startsWith("Percentage unmapped"))
     }
 
     @Override
-    public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException
+    public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException
     {
         return getHtosForParentReadset(parentReadsetId, webserverJobDir, support, true);
     }
 
-    public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support, boolean throwIfNotFound) throws PipelineJobException
+    public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support, boolean throwIfNotFound) throws PipelineJobException
     {
         Integer htoReadset = getCachedHashingReadsetMap(support).get(parentReadsetId);
         if (htoReadset == null)
@@ -1482,16 +1482,16 @@ public List<String> getHtosForParentReadset(Integer parentReadsetId, File webser
             }
             else
             {
-                return (Collections.emptyList());
+                return (Collections.emptySet());
             }
         }
 
         return getHtosForReadset(htoReadset, webserverJobDir);
     }
 
-    public List<String> getHtosForReadset(Integer hashingReadsetId, File webserverJobDir) throws PipelineJobException
+    public Set<String> getHtosForReadset(Integer hashingReadsetId, File webserverJobDir) throws PipelineJobException
     {
-        List<String> htosPerReadset = new ArrayList<>();
+        Set<String> htosPerReadset = new HashSet<>();
         try (CSVReader reader = new CSVReader(Readers.getReader(CellHashingServiceImpl.get().getCDNAInfoFile(webserverJobDir)), '\t'))
         {
             String[] line;
diff --git a/singlecell/src/org/labkey/singlecell/SingleCellController.java b/singlecell/src/org/labkey/singlecell/SingleCellController.java
@@ -429,10 +429,11 @@ public URLHelper getSuccessURL(Object form)
             return getContainer().getStartURL(getUser());
         }
 
+        @Override
         public ModelAndView getView(Object form, BindException errors) throws Exception
         {
             LinkedHashSet<ClientDependency> cds = new LinkedHashSet<>();
-            for (PipelineStepProvider fact : SequencePipelineService.get().getAllProviders())
+            for (PipelineStepProvider<?> fact : SequencePipelineService.get().getAllProviders())
             {
                 cds.addAll(fact.getClientDependencies());
             }
diff --git a/singlecell/src/org/labkey/singlecell/analysis/CellRangerSeuratHandler.java b/singlecell/src/org/labkey/singlecell/analysis/CellRangerSeuratHandler.java
@@ -671,7 +671,7 @@ else if (rs.getReadsetId() == null)
                     throw new PipelineJobException("Unable to find hashing readset for GEX readset: " + rs.getReadsetId());
                 }
 
-                List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(hashingReadsetId, ctx.getSourceDirectory());
+                Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(hashingReadsetId, ctx.getSourceDirectory());
                 if (htosPerReadset.size() > 1)
                 {
                     ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());
diff --git a/singlecell/src/org/labkey/singlecell/analysis/LoupeCellHashingHandler.java b/singlecell/src/org/labkey/singlecell/analysis/LoupeCellHashingHandler.java
@@ -24,6 +24,7 @@
 import java.util.LinkedHashSet;
 import java.util.List;
 import java.util.Map;
+import java.util.Set;
 
 public class LoupeCellHashingHandler extends AbstractParameterizedOutputHandler<SequenceOutputHandler.SequenceOutputProcessor>
 {
@@ -179,7 +180,7 @@ else if (rs.getReadsetId() == null)
                     throw new PipelineJobException("Unable to find Hashing/Cite-seq readset for GEX readset: " + rs.getReadsetId());
                 }
 
-                List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());
+                Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());
                 if (htosPerReadset.size() > 1)
                 {
                     ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());
diff --git a/singlecell/src/org/labkey/singlecell/analysis/SeuratCellHashingHandler.java b/singlecell/src/org/labkey/singlecell/analysis/SeuratCellHashingHandler.java
@@ -20,6 +20,7 @@
 import java.util.ArrayList;
 import java.util.List;
 import java.util.Map;
+import java.util.Set;
 
 public class SeuratCellHashingHandler extends AbstractParameterizedOutputHandler<SequenceOutputHandler.SequenceOutputProcessor>
 {
@@ -135,7 +136,7 @@ else if (rs.getReadsetId() == null)
                     throw new PipelineJobException("Unable to find Hashing/Cite-seq readset for GEX readset: " + rs.getReadsetId());
                 }
 
-                List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());
+                Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());
                 if (htosPerReadset.size() > 1)
                 {
                     ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/DoubletFinder.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/DoubletFinder.java
@@ -20,7 +20,7 @@ public static class Provider extends AbstractPipelineStepProvider<SingleCellStep
         public Provider()
         {
             super("DoubletFinder", "DoubletFinder", "DoubletFinder", "This will run DoubletFinder to identify putative doublets.", Arrays.asList(
-                    SeuratToolParameter.create("dropDoublets", "Drop Doublets", "This will run DoubletFinder on the seurat object(s)", "checkbox", new JSONObject(){{
+                    SeuratToolParameter.create("dropDoublets", "Drop Doublets", "If true, any cells flagged as doublets will be dropped from the seurat object", "checkbox", new JSONObject(){{
 
                     }}, false)
             ), null, null);
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/NormalizeAndScale.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/NormalizeAndScale.java
@@ -24,12 +24,12 @@ public Provider()
                         put("storeValues", "vst");
                         put("initialValues", "vst");
                         put("allowBlank", false);
-                    }}, "vst")
-//                    SeuratToolParameter.create("toRegress", "Variables to Regress", "These will be passed to Seurat::ScaleData. Enter comma-separated or one field name per line", "sequenceanalysis-trimmingtextarea", new JSONObject(){{
-//                        put("allowBlank", false);
-//                        put("height", 150);
-//                        put("delimiter", ",");
-//                    }}, "nCount_RNA,p.mito")
+                    }}, "vst"),
+                    SeuratToolParameter.create("blockSize", "Block Size", "This will be passed to block.size in Seurat::ScaleData, which determines the number of features processed as a time. Increasing might increase speed at a memory cost, and descreasing on large datasets might reduce memory at a cost of overall speed.", "ldk-integerfield", new JSONObject(){{
+                        put("allowBlank", false);
+                        put("height", 150);
+                        put("delimiter", ",");
+                    }}, 1000, "block.size", true)
             ), Arrays.asList("/sequenceanalysis/field/TrimmingTextArea.js"), null);
         }
 
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RemoveCellCycle.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RemoveCellCycle.java
@@ -1,7 +1,9 @@
 package org.labkey.singlecell.pipeline.singlecell;
 
+import org.json.JSONObject;
 import org.labkey.api.sequenceanalysis.pipeline.AbstractPipelineStepProvider;
 import org.labkey.api.sequenceanalysis.pipeline.PipelineContext;
+import org.labkey.api.singlecell.pipeline.SeuratToolParameter;
 import org.labkey.api.singlecell.pipeline.SingleCellStep;
 
 import java.util.Arrays;
@@ -18,11 +20,14 @@ public static class Provider extends AbstractPipelineStepProvider<SingleCellStep
         public Provider()
         {
             super("RemoveCellCycle", "Remove Cell Cycle", "OOSAP", "This will score cells by cell cycle phase and regress out cell cycle.", Arrays.asList(
-
+                    SeuratToolParameter.create("blockSize", "Block Size", "This will be passed to block.size in Seurat::ScaleData, which determines the number of features processed as a time. Increasing might increase speed at a memory cost, and descreasing on large datasets might reduce memory at a cost of overall speed.", "ldk-integerfield", new JSONObject(){{
+                        put("allowBlank", false);
+                        put("height", 150);
+                        put("delimiter", ",");
+                    }}, 1000, "block.size", true)
             ), null, null);
         }
 
-
         @Override
         public RemoveCellCycle create(PipelineContext ctx)
         {
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCellHashing.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCellHashing.java
@@ -19,6 +19,7 @@
 import java.util.HashMap;
 import java.util.List;
 import java.util.Map;
+import java.util.Set;
 
 public class RunCellHashing extends AbstractCellHashingCiteseqStep
 {
@@ -78,7 +79,7 @@ protected Map<Integer, File> prepareCountData(SingleCellOutput output, SequenceO
                 throw new PipelineJobException("Unable to find readset for outputfile: " + wrapper.getSequenceOutputFileId());
             }
 
-            List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForParentReadset(parentReadset.getReadsetId(), ctx.getSourceDirectory(), ctx.getSequenceSupport(), false);
+            Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForParentReadset(parentReadset.getReadsetId(), ctx.getSourceDirectory(), ctx.getSequenceSupport(), false);
             if (htosPerReadset.size() > 1)
             {
                 ctx.getLogger().info("Total barcodes for readset: " + htosPerReadset.size());

Original file line number	Diff line number	Diff line change
`@@ -26,7 +26,9 @@`
`26`	`26`	`import java.util.ArrayList;`
`27`	`27`	`import java.util.Arrays;`
`28`	`28`	`import java.util.Collections;`
	`29`	`+import java.util.HashSet;`
`29`	`30`	`import java.util.List;`
	`31`	`+import java.util.Set;`
`30`	`32`	`import java.util.stream.Collectors;`
`31`	`33`
`32`	`34`	`abstract public class CellHashingService`
`@@ -71,14 +73,14 @@ static public void setInstance(CellHashingService instance)`
`71`	`73`
`72`	`74`	`abstract public List<ToolParameterDescriptor> getDefaultHashingParams(boolean includeExcludeFailedcDNA);`
`73`	`75`
`74`		`- abstract public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException;`
	`76`	`+ abstract public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException;`
`75`	`77`
`76`	`78`	`public static class CellHashingParameters`
`77`	`79`	`{`
`78`	`80`	`public BARCODE_TYPE type;`
`79`	`81`
`80`	`82`	`private File htoOrCiteseqBarcodesFile;`
`81`		`- public List<String> allowableHtoOrCiteseqBarcodes;`
	`83`	`+ public Set<String> allowableHtoOrCiteseqBarcodes;`
`82`	`84`
`83`	`85`	`public File cellBarcodeWhitelistFile;`
`84`	`86`
`@@ -227,18 +229,18 @@ public void validate(boolean allowMissingHtoReadset)`
`227`	`229`	`}`
`228`	`230`	`}`
`229`	`231`
`230`		`- public List<String> getAllowableBarcodeNames() throws PipelineJobException`
	`232`	`+ public Set<String> getAllowableBarcodeNames() throws PipelineJobException`
`231`	`233`	`{`
`232`	`234`	`if (allowableHtoOrCiteseqBarcodes != null)`
`233`	`235`	`{`
`234`		`- return Collections.unmodifiableList(allowableHtoOrCiteseqBarcodes);`
	`236`	`+ return Collections.unmodifiableSet(allowableHtoOrCiteseqBarcodes);`
`235`	`237`	`}`
`236`	`238`	`if (htoOrCiteseqBarcodesFile == null)`
`237`	`239`	`{`
`238`	`240`	`throw new IllegalArgumentException("Barcode file was null");`
`239`	`241`	`}`
`240`	`242`
`241`		`- List<String> allowableBarcodes = new ArrayList<>();`
	`243`	`+ Set<String> allowableBarcodes = new HashSet<>();`
`242`	`244`	`try (CSVReader reader = new CSVReader(Readers.getReader(htoOrCiteseqBarcodesFile), '\t'))`
`243`	`245`	`{`
`244`	`246`	`String[] line;`
Original file line number	Diff line number	Diff line change
`@@ -14,7 +14,8 @@ for (datasetId in names(newSeuratObjects)) {`
`14`	`14`
`15`	`15`	`savedFiles <- rbind(savedFiles, data.frame(datasetId = datasetId, datasetName = datasetName, filename = fn, outputFileId = outputFileId))`
`16`	`16`
`17`		`- CellMembrane::WriteCellBarcodes(seuratObj, file = barcodeFile)`
	`17`	`+ # WriteCellBarcodes`
	`18`	`+ write.table(data.frame(CellBarcode = colnames(seuratObj)), file = barcodeFile, quote = F, row.names = F, sep = ',', col.names = F)`
`18`	`19`	`}`
`19`	`20`
`20`	`21`	`write.table(savedFiles, file = 'savedSeuratObjects.txt', quote = FALSE, sep = '\t', row.names = FALSE, col.names = FALSE)`
Original file line number	Diff line number	Diff line change
`@@ -1226,7 +1226,7 @@ private File generateCellHashingCalls(File citeSeqCountOutDir, File outputDir, S`
`1226`	`1226`	`cellbarcodeWhitelist = "'/work/" + cellBarcodeWhitelistFile.getName() + "'";`
`1227`	`1227`	`}`
`1228`	`1228`
`1229`		`- List<String> allowableBarcodes = parameters.getAllowableBarcodeNames();`
	`1229`	`+ Set<String> allowableBarcodes = parameters.getAllowableBarcodeNames();`
`1230`	`1230`	`String allowableBarcodeParam = allowableBarcodes != null ? "c('" + StringUtils.join(allowableBarcodes, "','") + "')" : "NULL";`
`1231`	`1231`
`1232`	`1232`	`writer.println("cellhashR::CallAndGenerateReport(rawCountData = '/work/" + citeSeqCountOutDir.getName() + "', reportFile = '/work/" + htmlFile.getName() + "', callFile = '/work/" + callsFile.getName() + "', metricsFile = '/work/" + metricsFile.getName() + "', cellbarcodeWhitelist = " + cellbarcodeWhitelist + ", barcodeWhitelist = " + allowableBarcodeParam + ", title = '" + parameters.getReportTitle() + "', methods = c('" + StringUtils.join(methodNames, "','") + "'))");`
`@@ -1466,12 +1466,12 @@ else if (line.startsWith("Percentage unmapped"))`
`1466`	`1466`	`}`
`1467`	`1467`
`1468`	`1468`	`@Override`
`1469`		`- public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException`
	`1469`	`+ public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support) throws PipelineJobException`
`1470`	`1470`	`{`
`1471`	`1471`	`return getHtosForParentReadset(parentReadsetId, webserverJobDir, support, true);`
`1472`	`1472`	`}`
`1473`	`1473`
`1474`		`- public List<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support, boolean throwIfNotFound) throws PipelineJobException`
	`1474`	`+ public Set<String> getHtosForParentReadset(Integer parentReadsetId, File webserverJobDir, SequenceAnalysisJobSupport support, boolean throwIfNotFound) throws PipelineJobException`
`1475`	`1475`	`{`
`1476`	`1476`	`Integer htoReadset = getCachedHashingReadsetMap(support).get(parentReadsetId);`
`1477`	`1477`	`if (htoReadset == null)`
`@@ -1482,16 +1482,16 @@ public List<String> getHtosForParentReadset(Integer parentReadsetId, File webser`
`1482`	`1482`	`}`
`1483`	`1483`	`else`
`1484`	`1484`	`{`
`1485`		`- return (Collections.emptyList());`
	`1485`	`+ return (Collections.emptySet());`
`1486`	`1486`	`}`
`1487`	`1487`	`}`
`1488`	`1488`
`1489`	`1489`	`return getHtosForReadset(htoReadset, webserverJobDir);`
`1490`	`1490`	`}`
`1491`	`1491`
`1492`		`- public List<String> getHtosForReadset(Integer hashingReadsetId, File webserverJobDir) throws PipelineJobException`
	`1492`	`+ public Set<String> getHtosForReadset(Integer hashingReadsetId, File webserverJobDir) throws PipelineJobException`
`1493`	`1493`	`{`
`1494`		`- List<String> htosPerReadset = new ArrayList<>();`
	`1494`	`+ Set<String> htosPerReadset = new HashSet<>();`
`1495`	`1495`	`try (CSVReader reader = new CSVReader(Readers.getReader(CellHashingServiceImpl.get().getCDNAInfoFile(webserverJobDir)), '\t'))`
`1496`	`1496`	`{`
`1497`	`1497`	`String[] line;`
Original file line number	Diff line number	Diff line change
`@@ -429,10 +429,11 @@ public URLHelper getSuccessURL(Object form)`
`429`	`429`	`return getContainer().getStartURL(getUser());`
`430`	`430`	`}`
`431`	`431`
	`432`	`+ @Override`
`432`	`433`	`public ModelAndView getView(Object form, BindException errors) throws Exception`
`433`	`434`	`{`
`434`	`435`	`LinkedHashSet<ClientDependency> cds = new LinkedHashSet<>();`
`435`		`- for (PipelineStepProvider fact : SequencePipelineService.get().getAllProviders())`
	`436`	`+ for (PipelineStepProvider<?> fact : SequencePipelineService.get().getAllProviders())`
`436`	`437`	`{`
`437`	`438`	`cds.addAll(fact.getClientDependencies());`
`438`	`439`	`}`
Original file line number	Diff line number	Diff line change
`@@ -671,7 +671,7 @@ else if (rs.getReadsetId() == null)`
`671`	`671`	`throw new PipelineJobException("Unable to find hashing readset for GEX readset: " + rs.getReadsetId());`
`672`	`672`	`}`
`673`	`673`
`674`		`- List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(hashingReadsetId, ctx.getSourceDirectory());`
	`674`	`+ Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(hashingReadsetId, ctx.getSourceDirectory());`
`675`	`675`	`if (htosPerReadset.size() > 1)`
`676`	`676`	`{`
`677`	`677`	`ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());`
Original file line number	Diff line number	Diff line change
`@@ -24,6 +24,7 @@`
`24`	`24`	`import java.util.LinkedHashSet;`
`25`	`25`	`import java.util.List;`
`26`	`26`	`import java.util.Map;`
	`27`	`+import java.util.Set;`
`27`	`28`
`28`	`29`	`public class LoupeCellHashingHandler extends AbstractParameterizedOutputHandler<SequenceOutputHandler.SequenceOutputProcessor>`
`29`	`30`	`{`
`@@ -179,7 +180,7 @@ else if (rs.getReadsetId() == null)`
`179`	`180`	`throw new PipelineJobException("Unable to find Hashing/Cite-seq readset for GEX readset: " + rs.getReadsetId());`
`180`	`181`	`}`
`181`	`182`
`182`		`- List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());`
	`183`	`+ Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());`
`183`	`184`	`if (htosPerReadset.size() > 1)`
`184`	`185`	`{`
`185`	`186`	`ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());`
Original file line number	Diff line number	Diff line change
`@@ -20,6 +20,7 @@`
`20`	`20`	`import java.util.ArrayList;`
`21`	`21`	`import java.util.List;`
`22`	`22`	`import java.util.Map;`
	`23`	`+import java.util.Set;`
`23`	`24`
`24`	`25`	`public class SeuratCellHashingHandler extends AbstractParameterizedOutputHandler<SequenceOutputHandler.SequenceOutputProcessor>`
`25`	`26`	`{`
`@@ -135,7 +136,7 @@ else if (rs.getReadsetId() == null)`
`135`	`136`	`throw new PipelineJobException("Unable to find Hashing/Cite-seq readset for GEX readset: " + rs.getReadsetId());`
`136`	`137`	`}`
`137`	`138`
`138`		`- List<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());`
	`139`	`+ Set<String> htosPerReadset = CellHashingServiceImpl.get().getHtosForReadset(htoReadset.getReadsetId(), ctx.getSourceDirectory());`
`139`	`140`	`if (htosPerReadset.size() > 1)`
`140`	`141`	`{`
`141`	`142`	`ctx.getLogger().info("Total HTOs for readset: " + htosPerReadset.size());`
Original file line number	Diff line number	Diff line change
`@@ -20,7 +20,7 @@ public static class Provider extends AbstractPipelineStepProvider<SingleCellStep`
`20`	`20`	`public Provider()`
`21`	`21`	`{`
`22`	`22`	`super("DoubletFinder", "DoubletFinder", "DoubletFinder", "This will run DoubletFinder to identify putative doublets.", Arrays.asList(`
`23`		`- SeuratToolParameter.create("dropDoublets", "Drop Doublets", "This will run DoubletFinder on the seurat object(s)", "checkbox", new JSONObject(){{`
	`23`	`+ SeuratToolParameter.create("dropDoublets", "Drop Doublets", "If true, any cells flagged as doublets will be dropped from the seurat object", "checkbox", new JSONObject(){{`
`24`	`24`
`25`	`25`	`}}, false)`
`26`	`26`	`), null, null);`