@platforma-open/milaboratories.mixcr-clonotyping-2.workflow 2.8.2 → 2.10.0

package/.turbo/turbo-build.log

@@ -1,6 +1,6 @@
  WARN  Issue while reading "/home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/.npmrc". Failed to replace env in config: ${NPMJS_TOKEN}
 
-> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.8.2 build /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.10.0 build /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
 > rm -rf dist && pl-tengo check && pl-tengo build
 
   info: Skipping unknown file type: test/columns.test.ts

package/.turbo/turbo-test.log

@@ -1,21 +1,21 @@
  WARN  Issue while reading "/home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/.npmrc". Failed to replace env in config: ${NPMJS_TOKEN}
 
-> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.8.2 test /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.10.0 test /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
 > vitest
 
 
  RUN  v2.1.8 /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
 
- ✓ src/test/columns.test.ts (6 tests) 53957ms
-   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 12559ms
-   ✓ checking preset for '10x-sc-xcr-vdj' 8530ms
-   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8433ms
-   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8412ms
-   ✓ checking preset for 'rna-seq' 8008ms
-   ✓ checking preset for 'generic-single-cell-gex' 8014ms
+ ✓ src/test/columns.test.ts (6 tests) 54411ms
+   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 12674ms
+   ✓ checking preset for '10x-sc-xcr-vdj' 8775ms
+   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8518ms
+   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8439ms
+   ✓ checking preset for 'rna-seq' 8026ms
+   ✓ checking preset for 'generic-single-cell-gex' 7977ms
 
  Test Files  1 passed (1)
       Tests  6 passed (6)
-   Start at  16:34:49
-   Duration  54.77s (transform 44ms, setup 0ms, collect 587ms, tests 53.96s, environment 0ms, prepare 62ms)
+   Start at  14:49:37
+   Duration  55.34s (transform 57ms, setup 0ms, collect 660ms, tests 54.41s, environment 0ms, prepare 68ms)
 

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @platforma-open/milaboratories.mixcr-clonotyping.workflow
 
+## 2.10.0
+
+### Minor Changes
+
+- b334fd0: Aggregated column "Number Of Samples" added to per-clonotype output
+  Exported clonotypes are limited only to productive & full-receptor
+
+## 2.9.0
+
+### Minor Changes
+
+- 1de5b81: MiXCR upgrade to increase export process memory
+
 ## 2.8.2
 
 ### Patch Changes

package/dist/tengo/lib/calculate-export-specs.lib.tengo

@@ -121,6 +121,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 	columnsSpecPerSample := []
 	columnsSpecPerSampleSc := undefined
 	columnsSpecPerClonotype := []
+	columnsSpecPerClonotypeSc := undefined
 
 
 	exportArgs := []
@@ -211,6 +212,23 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		mainAbundanceColumn = "uniqueMoleculeFraction"
 	}
 
+	sampleCountColumn := {
+		column: "sampleCount",
+		id: "sample-count",
+		allowNA: false,
+		spec: {
+			name: "pl7.app/vdj/sampleCount",
+			valueType: "Int",
+			annotations: a(87110, true, {
+				"pl7.app/min": "1",
+				"pl7.app/isAbundance": "true",
+				"pl7.app/abundance/unit": "samples",
+				"pl7.app/abundance/normalized": "false",
+				"pl7.app/label": "Number of Samples"
+			})
+		}
+	}
+
 	if isSingleCell {
 
 		columnsSpecPerSample = addSpec(columnsSpecPerSample, {
@@ -247,6 +265,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				valueType: "Double",
 				annotations: a(20000, false, {
 					"pl7.app/min": "0",
+					"pl7.app/max": "1",
 					"pl7.app/isAbundance": "true",
 					"pl7.app/abundance/unit": "cells",
 					"pl7.app/abundance/normalized": "true",
@@ -255,6 +274,9 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				})
 			}
 		} ]
+		columnsSpecPerClonotypeSc = [ sampleCountColumn ]
+	} else {
+		columnsSpecPerClonotype += [ sampleCountColumn ]
 	}
 
 	orderP := 80000
@@ -478,6 +500,8 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 
 	]
+	mainProductiveColumn := flagColumnVariants[0].columnPrefix + productiveFeature
+	mainProductiveArgs := [ flagColumnVariants[0].arg, productiveFeature ]
 	for variant in flagColumnVariants {
 		columnsSpecPerClonotype += [ {
 				column: variant.columnPrefix + productiveFeature,
@@ -658,10 +682,13 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		columnsSpecPerSample: columnsSpecPerSample,
 		columnsSpecPerSampleSc: columnsSpecPerSampleSc,
 		columnsSpecPerClonotype: columnsSpecPerClonotype,
+		columnsSpecPerClonotypeSc: columnsSpecPerClonotypeSc,
 
 		columnsSpec: columnsSpec,
 
 		mainAbundanceColumn: mainAbundanceColumn,
+		mainProductiveColumn: mainProductiveColumn,
+		mainProductiveArgs: mainProductiveArgs,
 
 		exportArgs: exportArgs
 	}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@platforma-open/milaboratories.mixcr-clonotyping-2.workflow",
-  "version": "2.8.2",
+  "version": "2.10.0",
   "description": "Tengo-based template",
   "dependencies": {
     "@platforma-sdk/workflow-tengo": "^4.0.8",
@@ -8,7 +8,7 @@
   },
   "devDependencies": {
     "@platforma-sdk/tengo-builder": "^2.0.3",
-    "@platforma-open/milaboratories.software-mixcr": "4.7.0-149-develop",
+    "@platforma-open/milaboratories.software-mixcr": "4.7.0-150-develop",
     "@platforma-open/milaboratories.software-ptransform": "^1.3.1",
     "@platforma-sdk/test": "^1.29.3",
     "vitest": "^2.1.8",

package/src/aggregate-by-clonotype-key.tpl.tengo

@@ -4,6 +4,7 @@ pConstants := import("@platforma-sdk/workflow-tengo:pframes.constants")
 slices := import("@platforma-sdk/workflow-tengo:slices")
 assets := import("@platforma-sdk/workflow-tengo:assets")
 exec := import("@platforma-sdk/workflow-tengo:exec")
+maps := import("@platforma-sdk/workflow-tengo:maps")
 
 json := import("json")
 
@@ -21,6 +22,14 @@ self.body(func(inputs) {
 	mainAbundanceColumn := params.mainAbundanceColumn
 	clonotypeColumns := params.clonotypeColumns
 
+	pickCols := []
+	for col in clonotypeColumns {
+		if col == "sampleCount" {
+			continue
+		}
+		pickCols = append(pickCols, [col, col])
+	}
+
 	// Adding clonotypeKey column
 	pWorkflow := {
 		steps: [ {
@@ -29,9 +38,11 @@ self.body(func(inputs) {
 			aggregations: [ {
 				type: "max_by",
 				rankingCol: mainAbundanceColumn,
-				pickCols: slices.map(clonotypeColumns, func(col) {
-					return [col, col]
-				})
+				pickCols: pickCols
+			}, {
+				type: "count",
+				src: mainAbundanceColumn,
+				dst: "sampleCount"
 			} ]
 		} ]
 	}
@@ -42,7 +53,9 @@ self.body(func(inputs) {
 		arg("--workflow").arg("wf.json").
 		writeFile("wf.json", json.encode(pWorkflow))
 
-	for sKey, inputFile in inputData.inputs() {
+	inputMap := inputData.inputs()
+	for sKey in maps.getKeys(inputMap) {
+		inputFile := inputMap[sKey]
 		key := json.decode(sKey)
 		if len(key) != 1 {
 			ll.panic("malformed key: %v", sKey)

package/src/calculate-export-specs.lib.tengo

@@ -121,6 +121,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 	columnsSpecPerSample := []
 	columnsSpecPerSampleSc := undefined
 	columnsSpecPerClonotype := []
+	columnsSpecPerClonotypeSc := undefined
 
 	// array of array of arg groups
 	exportArgs := []
@@ -211,6 +212,23 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		mainAbundanceColumn = "uniqueMoleculeFraction"
 	}
 
+	sampleCountColumn := {
+		column: "sampleCount",
+		id: "sample-count",
+		allowNA: false,
+		spec: {
+			name: "pl7.app/vdj/sampleCount",
+			valueType: "Int",
+			annotations: a(87110, true, {
+				"pl7.app/min": "1",
+				"pl7.app/isAbundance": "true",
+				"pl7.app/abundance/unit": "samples",
+				"pl7.app/abundance/normalized": "false",
+				"pl7.app/label": "Number of Samples"
+			})
+		}
+	}
+
 	if isSingleCell {
 		// copying reads and umi counts and fraction removing isPrimary and isAnchor
 		columnsSpecPerSample = addSpec(columnsSpecPerSample, {
@@ -247,6 +265,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				valueType: "Double",
 				annotations: a(20000, false, {
 					"pl7.app/min": "0",
+					"pl7.app/max": "1",
 					"pl7.app/isAbundance": "true",
 					"pl7.app/abundance/unit": "cells",
 					"pl7.app/abundance/normalized": "true",
@@ -255,6 +274,9 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				})
 			}
 		} ]
+		columnsSpecPerClonotypeSc = [ sampleCountColumn ]
+	} else {
+		columnsSpecPerClonotype += [ sampleCountColumn ]
 	}
 
 	orderP := 80000
@@ -478,6 +500,8 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		// 	visibility: false
 		// }
 	]
+	mainProductiveColumn := flagColumnVariants[0].columnPrefix + productiveFeature
+	mainProductiveArgs := [ flagColumnVariants[0].arg, productiveFeature ]
 	for variant in flagColumnVariants {
 		columnsSpecPerClonotype += [ {
 				column: variant.columnPrefix + productiveFeature,
@@ -658,10 +682,13 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		columnsSpecPerSample: columnsSpecPerSample,
 		columnsSpecPerSampleSc: columnsSpecPerSampleSc,
 		columnsSpecPerClonotype: columnsSpecPerClonotype,
+		columnsSpecPerClonotypeSc: columnsSpecPerClonotypeSc,
 
 		columnsSpec: columnsSpec,
 
 		mainAbundanceColumn: mainAbundanceColumn,
+		mainProductiveColumn: mainProductiveColumn,
+		mainProductiveArgs: mainProductiveArgs,
 
 		exportArgs: exportArgs
 	}

package/src/mixcr-analyze.tpl.tengo

@@ -8,6 +8,7 @@ exec := import("@platforma-sdk/workflow-tengo:exec")
 assets := import("@platforma-sdk/workflow-tengo:assets")
 pcolumn := import("@platforma-sdk/workflow-tengo:pframes.pcolumn")
 times := import("times")
+maps := import("@platforma-sdk/workflow-tengo:maps")
 
 json := import("json")
 
@@ -92,16 +93,19 @@ self.body(func(inputs) {
 			arg(preset.name)
 	}
 
+	inputMap := inputData.inputs()
 	if inputDataMeta.keyLength == 0 {
 		ll.assert(aggregationAxesNames == [], "unexpected aggregation axes names")
-		inputFile := inputData.inputs()["[]"]
+		// Assuming only one key "[]" exists here, no need for sorted iteration
+		inputFile := inputMap["[]"]
 		ll.assert(!is_undefined(inputFile), "unexpected agg group structure")
 		inputFileName := "input." + fileExtension
 		mixcrCmdBuilder.addFile(inputFileName, inputFile)
 		mixcrCmdBuilder.arg(inputFileName)
 	} else if inputDataMeta.keyLength == 1 {
 		ll.assert(aggregationAxesNames == ["pl7.app/sequencing/readIndex"], "unexpected aggregation axes names")
-		for sKey, inputFile in inputData.inputs() {
+		for sKey in maps.getKeys(inputMap) {
+			inputFile := inputMap[sKey]
 			key := json.decode(sKey)
 			if len(key) != 1 {
 				ll.panic("malformed key: %v", sKey)
@@ -115,7 +119,8 @@ self.body(func(inputs) {
 		mixcrCmdBuilder.arg("input_{{R}}." + fileExtension)
 	} else if inputDataMeta.keyLength == 2 {
 		ll.assert(aggregationAxesNames == ["pl7.app/sequencing/lane", "pl7.app/sequencing/readIndex"], "unexpected aggregation axes names")
-		for sKey, inputFile in inputData.inputs() {
+		for sKey in maps.getKeys(inputMap) {
+			inputFile := inputMap[sKey]
 			key := json.decode(sKey)
 			if len(key) != 2 {
 				ll.panic("malformed key: %v", sKey)

package/src/mixcr-export.tpl.tengo

@@ -37,6 +37,7 @@ self.body(func(inputs) {
 			arg("--dont-split-files").
 			arg("--drop-default-fields").
 			arg("--reset-export-clone-table-splitting").
+			arg("--export-productive-clones-only").
 			arg("--chains").arg(chains)
 
 		if library {

package/src/process-single-cell.tpl.tengo

@@ -3,10 +3,11 @@ self := import("@platforma-sdk/workflow-tengo:tpl.light")
 pConstants := import("@platforma-sdk/workflow-tengo:pframes.constants")
 assets := import("@platforma-sdk/workflow-tengo:assets")
 exec := import("@platforma-sdk/workflow-tengo:exec")
+maps := import("@platforma-sdk/workflow-tengo:maps")
 
 json := import("json")
 
-self.defineOutputs("abundanceTsv", "propertiesAPrimaryTsv", "propertiesASecondaryTsv", "propertiesBPrimaryTsv", "propertiesBSecondaryTsv")
+self.defineOutputs("abundanceTsv", "clonotypeTsv", "propertiesAPrimaryTsv", "propertiesASecondaryTsv", "propertiesBPrimaryTsv", "propertiesBSecondaryTsv")
 
 scGroupBuilderSw := assets.importSoftware("@platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts:sc-group-builder")
 scPreprocessingSw := assets.importSoftware("@platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts:preprocessing")
@@ -23,13 +24,17 @@ self.body(func(inputs) {
 
 	// Creating files map
 	filesMap := {}
-	for k, v in byCellTagA.inputs() {
+	inputMapA := byCellTagA.inputs()
+	for k in maps.getKeys(inputMapA) {
+		v := inputMapA[k]
 		key := json.decode(k)
 		fileName := "by_cell_a_" + key[0] + ".tsv"
 		filesMap[fileName] = v
 	}
 
-	for k, v in byCellTagB.inputs() {
+	inputMapB := byCellTagB.inputs()
+	for k in maps.getKeys(inputMapB) {
+		v := inputMapB[k]
 		key := json.decode(k)
 		fileName := "by_cell_b_" + key[0] + ".tsv"
 		filesMap[fileName] = v
@@ -37,11 +42,10 @@ self.body(func(inputs) {
 
 	scPreprocessingCmd := exec.builder().
 		printErrStreamToStdout().
-		software(scPreprocessingSw).
-		addFiles(filesMap)
+		software(scPreprocessingSw)
 
-	for name, f in filesMap {
-		scPreprocessingCmd = scPreprocessingCmd.arg(name)
+	for name in maps.getKeys(filesMap) {
+		scPreprocessingCmd.addFile(name, filesMap[name]).arg(name)
 	}
 
 	// Data preprocessing
@@ -60,6 +64,7 @@ self.body(func(inputs) {
 		software(scGroupBuilderSw).
 		addFile("chain_a_output.tsv", chainAoutput).
 		addFile("chain_b_output.tsv", chainBoutput).
+		arg("--only_full_clonotypes").
 		arg("--chainA").arg("chain_a_output.tsv").
 		arg("--chainB").arg("chain_b_output.tsv").
 		arg("--output_clonotype").arg("clonotype.tsv").
@@ -97,6 +102,8 @@ self.body(func(inputs) {
 	return {
 		// must have sampleId and scClonotypeKey columns
 		abundanceTsv: abundanceTsv,
+		// used for aggregates (i.e. sampleCount)
+		clonotypeTsv: clonotypeTsv,
 
 		// must have scClonotypeKey columns
 		propertiesAPrimaryTsv: scOutputCmd.getFile("properties_a_primary.tsv"),

package/src/process.tpl.tengo

@@ -197,7 +197,8 @@ self.body(func(inputs) {
 	columnsSpecPerSample := exportSpecs.columnsSpecPerSample
 	columnsSpecPerSampleSc := exportSpecs.columnsSpecPerSampleSc
 	columnsSpecPerClonotype := exportSpecs.columnsSpecPerClonotype
-	columnsSpec := exportSpecs.columnsSpec
+	columnsSpecPerClonotypeSc := exportSpecs.columnsSpecPerClonotypeSc
+	// columnsSpec := exportSpecs.columnsSpec
 
 	clonotypeKeyColumns := exportSpecs.clonotypeKeyColumns
 	clonotypeKeyArgs := exportSpecs.clonotypeKeyArgs
@@ -459,6 +460,16 @@ self.body(func(inputs) {
 				},
 				name: "abundanceTable",
 				path: ["abundanceTsv"]
+			}, {
+				type: "Xsv",
+				xsvType: "tsv",
+				settings: {
+					axes: axesByScClonotypeKeyWithReceptor,
+					columns: columnsSpecPerClonotypeSc,
+					storageFormat: "Binary"
+				},
+				name: "aggregates",
+				path: ["clonotypeTsv"]
 			} ]
 
 			for chainIdx in [0, 1] {
@@ -545,6 +556,7 @@ self.body(func(inputs) {
 			)
 
 			singleCellResult.addXsvOutputToBuilder(clonotypes, "abundanceTable", "clonotypeProperties/abundance/" + receptor + "/")
+			singleCellResult.addXsvOutputToBuilder(clonotypes, "aggregates", "clonotypeProperties/aggregates/" + receptor + "/")
 
 			singleCellResult.addXsvOutputToBuilder(clonotypes, "propertiesAPrimary", "clonotypeProperties/" + receptor + "/aPrimary/")
 			singleCellResult.addXsvOutputToBuilder(clonotypes, "propertiesASecondary", "clonotypeProperties/" + receptor + "/aSecondary/")