Merge discvr-22.11 to develop

root · root · commit 4914eb9cb1ee · 2023-01-13T20:30:26.000Z
diff --git a/SequenceAnalysis/pipeline_code/sequence_tools_install.sh b/SequenceAnalysis/pipeline_code/sequence_tools_install.sh
@@ -872,7 +872,8 @@ then
     else
       CUTADAPT_BRANCH=v4.0
       $PIP_EXE install --target ${LKTOOLS_DIR}/cutadapt_pip git+https://github.com/marcelm/cutadapt.git@${CUTADAPT_BRANCH}
-      ln -s ${LKTOOLS_DIR}/cutadapt_pip/bin/cutadapt ${LKTOOLS_DIR}/cutadapt
+      cd ${LKTOOLS_DIR}
+      ln -s ./cutadapt_pip/bin/cutadapt cutadapt
     fi
 else
     echo "Already installed"
diff --git a/SequenceAnalysis/src/org/labkey/sequenceanalysis/SequenceAnalysisMaintenanceTask.java b/SequenceAnalysis/src/org/labkey/sequenceanalysis/SequenceAnalysisMaintenanceTask.java
@@ -500,8 +500,9 @@ private void deleteFile(File f, Logger log) throws IOException
     private static FileType _bamFileType = new FileType("bam");
     private static FileType _cramFileType = new FileType("cram");
     private static FileType _vcfFileType = new FileType("vcf", FileType.gzSupportLevel.SUPPORT_GZ);
-    private static FileType _bedFileType = new FileType("bed");
+    private static FileType _bedFileType = new FileType("bed", FileType.gzSupportLevel.SUPPORT_GZ);
     private static FileType _fastaFileType = new FileType(Arrays.asList("fasta", "fa"), "fasta", FileType.gzSupportLevel.SUPPORT_GZ);
+    private static FileType _gxfFileType = new FileType(Arrays.asList("gtf", "gff", "gff3"), "gff", FileType.gzSupportLevel.SUPPORT_GZ);
 
     /**
      * This is intended to return any files associated with an input, which is primarily designed to pick up index files
@@ -532,9 +533,17 @@ else if (_vcfFileType.isType(f))
                 ret.add(f.getName() + ".gz.idx");
             }
         }
-        else if (_bedFileType.isType(f))
+        else if (_bedFileType.isType(f) || _gxfFileType.isType(f))
         {
             ret.add(f.getName() + ".idx");
+            ret.add(f.getName() + ".tbi");
+
+            if (includeGz)
+            {
+                ret.add(f.getName() + ".gz");
+                ret.add(f.getName() + ".gz.tbi");
+                ret.add(f.getName() + ".gz.idx");
+            }
         }
         else if (_fastaFileType.isType(f))
         {
diff --git a/SequenceAnalysis/src/org/labkey/sequenceanalysis/run/preprocessing/TagPcrSummaryStep.java b/SequenceAnalysis/src/org/labkey/sequenceanalysis/run/preprocessing/TagPcrSummaryStep.java
@@ -72,9 +72,9 @@ public Provider()
                         put("checked", true);
                     }}, true),
                     ToolParameterDescriptor.createCommandLineParam(CommandLineParam.create("--insert-name"), "insertType", "Insert Type", "The type of insert to detect.", "ldk-simplecombo", new JSONObject(){{
-                        put("storeValues", "PiggyBac;Lentivirus");
+                        put("storeValues", "PiggyBac;Lentivirus;PREDICT");
                         put("allowBlank", false);
-                    }}, "PiggyBac"),
+                    }}, null),
                     ToolParameterDescriptor.create(DESIGN_PRIMERS, "Design Primers", "If selected, Primer3 will be used to design primers to flank integration sites", "checkbox", new JSONObject(){{
                         put("checked", false);
                     }}, false),
diff --git a/singlecell/resources/chunks/RunCelltypist.R b/singlecell/resources/chunks/RunCelltypist.R
@@ -3,7 +3,7 @@ for (datasetId in names(seuratObjects)) {
     seuratObj <- readRDS(seuratObjects[[datasetId]])
 
     for (mn in modelNames) {
-        seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = paste0(mn, '.pkl'), convertAmbiguousToNA = convertAmbiguousToNA, columnPrefix = paste0('celltypist.', mn, '.'), pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
+        seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = paste0(mn, '.pkl'), columnPrefix = paste0('celltypist.', mn, '.'), pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
     }
 
     saveData(seuratObj, datasetId)
diff --git a/singlecell/resources/chunks/RunCelltypistCustomModel.R b/singlecell/resources/chunks/RunCelltypistCustomModel.R
@@ -2,7 +2,7 @@ for (datasetId in names(seuratObjects)) {
     printName(datasetId)
     seuratObj <- readRDS(seuratObjects[[datasetId]])
 
-    seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = modelFile, columnPrefix = columnPrefix, convertAmbiguousToNA = convertAmbiguousToNA, pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
+    seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = modelFile, columnPrefix = columnPrefix, pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
 
     saveData(seuratObj, datasetId)
 }
diff --git a/singlecell/resources/chunks/RunRiraClassification.R b/singlecell/resources/chunks/RunRiraClassification.R
@@ -2,8 +2,8 @@ for (datasetId in names(seuratObjects)) {
     printName(datasetId)
     seuratObj <- readRDS(seuratObjects[[datasetId]])
 
-    seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = 'RIRA_Immune_v1', maxBatchSize = maxBatchSize, columnPrefix = 'RIRA_Immune_v1.', retainProbabilityMatrix = retainProbabilityMatrix)
-    seuratObj <- RIRA::Classify_TNK(seuratObj, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix, columnPrefix = 'RIRA_TNK_v2.')
+    seuratObj <- RIRA::Classify_ImmuneCells(seuratObj, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
+    seuratObj <- RIRA::Classify_TNK(seuratObj, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)
 
     seuratObj$RIRA_TNK_v2.predicted_labels[seuratObj$RIRA_Immune_v1.majority_voting != 'T_NK'] <- 'Other'
 
diff --git a/singlecell/resources/chunks/SplitSeurat.R b/singlecell/resources/chunks/SplitSeurat.R
@@ -2,7 +2,7 @@ for (datasetId in names(seuratObjects)) {
     printName(datasetId)
     seuratObj <- readRDS(seuratObjects[[datasetId]])
 
-    newList <- CellMembrane::SplitSeurat(seuratObj, splitField = splitField, minCellsToKeep = minCellsToKeep)
+    newList <- CellMembrane::SplitSeurat(seuratObj, splitField = splitField, minCellsToKeep = minCellsToKeep, excludedClasses = excludedClasses)
     for (name in names(newList)) {
         saveData(newList[[name]], paste0(datasetId, '-', name))
     }
diff --git a/singlecell/resources/views/singleCellDataManagement.html b/singlecell/resources/views/singleCellDataManagement.html
@@ -61,10 +61,27 @@
                         })
                     },{
                         name: 'Readsets Not Archived to SRA',
-                        url: LABKEY.ActionURL.buildURL('query', 'executeQuery.view', null, {schemaName: 'sequenceanalysis', queryName: 'sequence_readsets', 'query.totalForwardReads~isnonblank': null, 'query.isArchived~eq': 0})
-                    },{
+                        url: LABKEY.ActionURL.buildURL('query', 'executeQuery.view', null, {
+                            schemaName: 'sequenceanalysis',
+                            queryName: 'sequence_readsets',
+                            'query.totalForwardReads~isnonblank': null,
+                            'query.isArchived~eq': 0}
+                        )
+                    }, {
                         name: 'Analyses Using Old Readsets',
-                        url: LABKEY.ActionURL.buildURL('query', 'executeQuery.view', null, {schemaName: 'sequenceanalysis', queryName: 'sequence_analyses', 'query.readset/status~isnonblank': null})
+                        url: LABKEY.ActionURL.buildURL('query', 'executeQuery.view', null, {
+                            schemaName: 'sequenceanalysis',
+                            queryName: 'sequence_analyses',
+                            'query.readset/status~isnonblank': null
+                        })
+                    },{
+                        name: 'Orphan 10x Run Summaries',
+                        url: LABKEY.ActionURL.buildURL('query', 'executeQuery.view', null, {
+                            schemaName: 'sequenceanalysis',
+                            queryName: 'outputfiles',
+                            'query.category~eq': '10x Run Summary',
+                            'query.readset/totalOutputs~eq': 1
+                        })
                     }]
                 }]
             }]
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCelltypist.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCelltypist.java
@@ -27,10 +27,6 @@ public Provider()
                         put("delimiter", ";");
                         put("joinReturnValue", true);
                     }}, "Immune_All_Low.pkl", null, true, true).delimiter(";"),
-                    SeuratToolParameter.create("convertAmbiguousToNA", "Convert Ambiguous To NA", "If true, any values for majority_voting with commas (indicating they are ambiguous) will be converted to NA", "checkbox", new JSONObject()
-                    {{
-                        put("checked", false);
-                    }}, false),
                     SeuratToolParameter.create("maxAllowableClasses", "Max Allowable Classes", "Celltypist can assign a cell to many classes, creating extremely long labels. Any cell with more than this number of labels will be set to NA", "ldk-integerfield", new JSONObject()
                     {{
                         put("minValue", 0);
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCelltypistCustomModel.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/RunCelltypistCustomModel.java
@@ -34,10 +34,6 @@ public Provider()
                         put("performGenomeFilter", false);
                     }}, null),
                     SeuratToolParameter.create("columnPrefix", "Column Prefix", "This string will be pre-pended to the normal output columns (i.e. majority_voting and predicted_labels)", "textfield", null, null),
-                    SeuratToolParameter.create("convertAmbiguousToNA", "Convert Ambiguous To NA", "If true, any values for majority_voting with commas (indicating they are ambiguous) will be converted to NA", "checkbox", new JSONObject()
-                    {{
-                        put("checked", false);
-                    }}, false),
                     SeuratToolParameter.create("maxAllowableClasses", "Max Allowable Classes", "Celltypist can assign a cell to many classes, creating extremely long labels. Any cell with more than this number of labels will be set to NA", "ldk-integerfield", new JSONObject()
                     {{
                         put("minValue", 0);
diff --git a/singlecell/src/org/labkey/singlecell/pipeline/singlecell/SplitSeurat.java b/singlecell/src/org/labkey/singlecell/pipeline/singlecell/SplitSeurat.java
@@ -26,7 +26,12 @@ public Provider()
                     SeuratToolParameter.create("minCellsToKeep", "Min Cells To Keep", "If provided, any subset with fewer than this many cells will be discarded. Use zero to keep all. Note: if the value is less than 1 it will be interpreted as a fraction of the total input cells", "ldk-numberfield", new JSONObject(){{
                         put("allowBlank", false);
                         put("decimalPrecision", 3);
-                    }}, 0.05)
+                    }}, 0.05),
+                    SeuratToolParameter.create("excludedClasses", "Excluded Classes", "A list, one per line, of any classes to be excluded from the split. Cells with these values we will placed into the Other subset", "sequenceanalysis-trimmingtextarea", new JSONObject(){{
+                        put("height", 150);
+                        put("delimiter", ",");
+                        put("stripCharsRe", "/(^['\"]+)|(['\"]+$)/g");
+                    }}, null, null, true).delimiter(",")
             ), null, null);
         }
 

Original file line number	Diff line number	Diff line change
`@@ -500,8 +500,9 @@ private void deleteFile(File f, Logger log) throws IOException`
`500`	`500`	`private static FileType _bamFileType = new FileType("bam");`
`501`	`501`	`private static FileType _cramFileType = new FileType("cram");`
`502`	`502`	`private static FileType _vcfFileType = new FileType("vcf", FileType.gzSupportLevel.SUPPORT_GZ);`
`503`		`- private static FileType _bedFileType = new FileType("bed");`
	`503`	`+ private static FileType _bedFileType = new FileType("bed", FileType.gzSupportLevel.SUPPORT_GZ);`
`504`	`504`	`private static FileType _fastaFileType = new FileType(Arrays.asList("fasta", "fa"), "fasta", FileType.gzSupportLevel.SUPPORT_GZ);`
	`505`	`+ private static FileType _gxfFileType = new FileType(Arrays.asList("gtf", "gff", "gff3"), "gff", FileType.gzSupportLevel.SUPPORT_GZ);`
`505`	`506`
`506`	`507`	`/**`
`507`	`508`	`* This is intended to return any files associated with an input, which is primarily designed to pick up index files`
`@@ -532,9 +533,17 @@ else if (_vcfFileType.isType(f))`
`532`	`533`	`ret.add(f.getName() + ".gz.idx");`
`533`	`534`	`}`
`534`	`535`	`}`
`535`		`- else if (_bedFileType.isType(f))`
	`536`	`+ else if (_bedFileType.isType(f) \|\| _gxfFileType.isType(f))`
`536`	`537`	`{`
`537`	`538`	`ret.add(f.getName() + ".idx");`
	`539`	`+ ret.add(f.getName() + ".tbi");`
	`540`	`+`
	`541`	`+ if (includeGz)`
	`542`	`+ {`
	`543`	`+ ret.add(f.getName() + ".gz");`
	`544`	`+ ret.add(f.getName() + ".gz.tbi");`
	`545`	`+ ret.add(f.getName() + ".gz.idx");`
	`546`	`+ }`
`538`	`547`	`}`
`539`	`548`	`else if (_fastaFileType.isType(f))`
`540`	`549`	`{`
Original file line number	Diff line number	Diff line change
`@@ -3,7 +3,7 @@ for (datasetId in names(seuratObjects)) {`
`3`	`3`	`seuratObj <- readRDS(seuratObjects[[datasetId]])`
`4`	`4`
`5`	`5`	`for (mn in modelNames) {`
`6`		`- seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = paste0(mn, '.pkl'), convertAmbiguousToNA = convertAmbiguousToNA, columnPrefix = paste0('celltypist.', mn, '.'), pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)`
	`6`	`+ seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = paste0(mn, '.pkl'), columnPrefix = paste0('celltypist.', mn, '.'), pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)`
`7`	`7`	`}`
`8`	`8`
`9`	`9`	`saveData(seuratObj, datasetId)`
Original file line number	Diff line number	Diff line change
`@@ -2,7 +2,7 @@ for (datasetId in names(seuratObjects)) {`
`2`	`2`	`printName(datasetId)`
`3`	`3`	`seuratObj <- readRDS(seuratObjects[[datasetId]])`
`4`	`4`
`5`		`- seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = modelFile, columnPrefix = columnPrefix, convertAmbiguousToNA = convertAmbiguousToNA, pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)`
	`5`	`+ seuratObj <- RIRA::RunCellTypist(seuratObj, modelName = modelFile, columnPrefix = columnPrefix, pThreshold = pThreshold, minProp = minProp, maxAllowableClasses = maxAllowableClasses, minFractionToInclude = minFractionToInclude, useMajorityVoting = useMajorityVoting, mode = mode, maxBatchSize = maxBatchSize, retainProbabilityMatrix = retainProbabilityMatrix)`
`6`	`6`
`7`	`7`	`saveData(seuratObj, datasetId)`
`8`	`8`	`}`