@platforma-open/milaboratories.mixcr-clonotyping-2.workflow 2.5.0 → 2.6.0

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@2.5.0 build /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.6.0 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@2.5.0 test /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.6.0 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) 53188ms
-   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 12934ms
-   ✓ checking preset for '10x-sc-xcr-vdj' 8323ms
-   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8051ms
-   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8026ms
-   ✓ checking preset for 'rna-seq' 7829ms
-   ✓ checking preset for 'generic-single-cell-gex' 8023ms
+ ✓ src/test/columns.test.ts (6 tests) 53410ms
+   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 13379ms
+   ✓ checking preset for '10x-sc-xcr-vdj' 8349ms
+   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8047ms
+   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8039ms
+   ✓ checking preset for 'rna-seq' 7808ms
+   ✓ checking preset for 'generic-single-cell-gex' 7786ms
 
  Test Files  1 passed (1)
       Tests  6 passed (6)
-   Start at  09:32:55
-   Duration  53.99s (transform 41ms, setup 0ms, collect 564ms, tests 53.19s, environment 0ms, prepare 60ms)
+   Start at  10:16:02
+   Duration  54.29s (transform 57ms, setup 0ms, collect 610ms, tests 53.41s, environment 0ms, prepare 72ms)
 

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @platforma-open/milaboratories.mixcr-clonotyping.workflow
 
+## 2.6.0
+
+### Minor Changes
+
+- 4b789fc: Added CDR3 length; removed unnecessary columns; removed pf from outputs
+
+## 2.5.1
+
+### Patch Changes
+
+- fedc4ee: Added clonotype key label column for bulk data
+- Updated dependencies [fedc4ee]
+  - @platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts@1.1.1
+
 ## 2.5.0
 
 ### Minor Changes

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

@@ -285,9 +285,10 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				alphabet := isAminoAcid ? "aminoacid" : "nucleotide"
 				alphabetShort := isAminoAcid ? "aa" : "nt"
 				alphabetShortMixcr := isAminoAcid ? "aa" : "n"
+				columnName := alphabetShortMixcr + "Seq" + imputedU + featureU
 				visibility := isSingleCell ? (featureU == "CDR3") && isAminoAcid : (featureU == "CDR3") || (featureU == assemblingFeature)
 				columnsSpecPerClonotype += [ {
-						column: alphabetShortMixcr + "Seq" + imputedU + featureU,
+						column: columnName,
 						id: alphabetShortMixcr + "-seq-" + featureL + (isImputed ? "-imputed" : ""),
 						naRegex: "region_not_covered",
 						spec: {
@@ -303,28 +304,27 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 							})
 						}
 					} ]
-				exportArgs += [ [ "-" + alphabetShortMixcr + "Feature" + imputedU, featureU ] ]
-				if !isImputed && !isAminoAcid {
-					columnsSpecPerSample += [ {
-							column: "minQual" + featureU,
-							id: "min-qual-" + featureL,
-							naRegex: "region_not_covered",
-							spec: {
-								name: "pl7.app/vdj/sequenceQuality",
-								valueType: "Int",
-								domain: {
-									"pl7.app/vdj/quality": "minQuality",
-									"pl7.app/vdj/feature": featureU
-								},
-								annotations: a(orderP - 10, false, {
-									"pl7.app/min": "0",
-									"pl7.app/max": "60",
-									"pl7.app/label": "Min quality " + featureU
-								})
+
+
+				if isAminoAcid && !isSingleCell && featureU == "CDR3" {
+					columnsSpecPerClonotype += [ {
+						column: columnName,
+						id: "clonotype-label",
+						preProcess: [{
+							type: "regexpReplace",
+							pattern: "^region_not_covered$",
+							replacement: "Unlabelled"
+						}],
+						spec: {
+							name: "pl7.app/label",
+							valueType: "String",
+							annotations: {
+								"pl7.app/label": "Clone label"
 							}
-						} ]
-					exportArgs += [ [ "-minFeatureQuality", featureU ] ]
+						}
+					} ]
 				}
+				exportArgs += [ [ "-" + alphabetShortMixcr + "Feature" + imputedU, featureU ] ]
 				orderP -= 100
 			}
 		}
@@ -376,12 +376,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 	orderP = 10000
 
-	mutationColumnVariants := [ {
-		name: "Mutations",
-		valueType: "String",
-		labelPart: " mutations in ",
-		idPart: "-mutations-"
-	}, {
+	mutationColumnVariants := [ 
+
+
+
+
+
+
+	{
 		name: "MutationsCount",
 		valueType: "Int",
 		labelPart: " mutations count in ",
@@ -435,21 +437,23 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			label: "Productive",
 			id: "is-productive",
 			visibility: false
-		}, {
-			columnPrefix: "isOOF",
-			arg: "-isOOF",
-			specName: "pl7.app/vdj/sequence/containsOOF",
-			label: "Contains OOF",
-			id: "is-oof",
-			visibility: false
-		}, {
-			columnPrefix: "hasStopsIn",
-			arg: "-hasStops",
-			specName: "pl7.app/vdj/sequence/containsStopCodons",
-			label: "Contains stop codons",
-			id: "has-stops",
-			visibility: false
-		} ]
+		}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+	]
 	for variant in flagColumnVariants {
 		columnsSpecPerClonotype += [ {
 				column: variant.columnPrefix + productiveFeature,
@@ -470,29 +474,29 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 
 
-	geneRegions := ["VRegion", "DRegion", "JRegion"]
 
-	for region in geneRegions {
-		columnsSpecPerClonotype += [ {
-				column: "nSeq" + region + "OfGermline",
-				naRegex: "",
-				allowNA: true,
-				id: "n-seq-" + text.to_lower(region) + "-germline",
-				spec: {
-					name: "pl7.app/vdj/germlineSequence",
-					valueType: "String",
-					domain: {
-						"pl7.app/vdj/feature": region,
-						"pl7.app/alphabet": "nucleotide"
-					},
-					annotations: a(orderP, false, {
-						"pl7.app/label": region[0:1] + " germline"
-					})
-				}
-			} ]
-		exportArgs += [ [ "-nFeature", region, "germline" ] ]
-		orderP -= 100
-	}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
 
 
 
@@ -529,6 +533,38 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 	]
 
 
+	
+
+	lengthColumns := ["CDR3"] // assemblingFeatureInfo.nonImputed
+
+	for featureU in lengthColumns {
+		featureL := text.to_lower(featureU)
+		for isAminoAcid in [false, true] {
+			alphabet := isAminoAcid ? "aminoacid" : "nucleotide"
+			alphabetShort := isAminoAcid ? "aa" : "nt"
+			alphabetShortMixcr := isAminoAcid ? "aa" : "n"
+			columnsSpecPerClonotype += [ {
+				column: alphabetShortMixcr + "Length" + featureU,
+				id: alphabetShortMixcr + "-length-" + featureL,
+				naRegex: "region_not_covered",
+				spec: {
+					name: "pl7.app/vdj/sequenceLength",
+					valueType: "Int",
+					domain: {
+						"pl7.app/vdj/feature": featureU,
+						"pl7.app/alphabet": alphabet
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "Length of " + featureU + " " + alphabetShort
+					})
+				}
+			} ]
+			exportArgs += [ [ "-" + alphabetShortMixcr + "Length", featureU ] ]
+			orderP -= 100
+		}
+	}
+
+
 
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotype
 
@@ -595,7 +631,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 						"pl7.app/vdj/clonotypingRunId": blockId
 					},
 					annotations: {
-						"pl7.app/label": "SC Clonotype key",
+						"pl7.app/label": "Clone label",
 						"pl7.app/table/visibility": "optional",
 						"pl7.app/table/orderPriority": "110000",
 						"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))

package/package.json

@@ -1,10 +1,10 @@
 {
   "name": "@platforma-open/milaboratories.mixcr-clonotyping-2.workflow",
-  "version": "2.5.0",
+  "version": "2.6.0",
   "description": "Tengo-based template",
   "dependencies": {
     "@platforma-sdk/workflow-tengo": "^3.1.0",
-    "@platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts": "1.1.0"
+    "@platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts": "1.1.1"
   },
   "devDependencies": {
     "@platforma-sdk/tengo-builder": "^2.0.2",

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

@@ -285,9 +285,10 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				alphabet := isAminoAcid ? "aminoacid" : "nucleotide"
 				alphabetShort := isAminoAcid ? "aa" : "nt"
 				alphabetShortMixcr := isAminoAcid ? "aa" : "n"
+				columnName := alphabetShortMixcr + "Seq" + imputedU + featureU
 				visibility := isSingleCell ? (featureU == "CDR3") && isAminoAcid : (featureU == "CDR3") || (featureU == assemblingFeature)
 				columnsSpecPerClonotype += [ {
-						column: alphabetShortMixcr + "Seq" + imputedU + featureU,
+						column: columnName,
 						id: alphabetShortMixcr + "-seq-" + featureL + (isImputed ? "-imputed" : ""),
 						naRegex: "region_not_covered",
 						spec: {
@@ -303,28 +304,27 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 							})
 						}
 					} ]
-				exportArgs += [ [ "-" + alphabetShortMixcr + "Feature" + imputedU, featureU ] ]
-				if !isImputed && !isAminoAcid {
-					columnsSpecPerSample += [ {
-							column: "minQual" + featureU,
-							id: "min-qual-" + featureL,
-							naRegex: "region_not_covered",
-							spec: {
-								name: "pl7.app/vdj/sequenceQuality",
-								valueType: "Int",
-								domain: {
-									"pl7.app/vdj/quality": "minQuality",
-									"pl7.app/vdj/feature": featureU
-								},
-								annotations: a(orderP - 10, false, {
-									"pl7.app/min": "0",
-									"pl7.app/max": "60",
-									"pl7.app/label": "Min quality " + featureU
-								})
+
+				// label column
+				if isAminoAcid && !isSingleCell && featureU == "CDR3" {
+					columnsSpecPerClonotype += [ {
+						column: columnName,
+						id: "clonotype-label",
+						preProcess: [{
+							type: "regexpReplace",
+							pattern: "^region_not_covered$",
+							replacement: "Unlabelled"
+						}],
+						spec: {
+							name: "pl7.app/label",
+							valueType: "String",
+							annotations: {
+								"pl7.app/label": "Clone label"
 							}
-						} ]
-					exportArgs += [ [ "-minFeatureQuality", featureU ] ]
+						}
+					} ]
 				}
+				exportArgs += [ [ "-" + alphabetShortMixcr + "Feature" + imputedU, featureU ] ]
 				orderP -= 100
 			}
 		}
@@ -376,12 +376,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 	orderP = 10000
 
-	mutationColumnVariants := [ {
-		name: "Mutations",
-		valueType: "String",
-		labelPart: " mutations in ",
-		idPart: "-mutations-"
-	}, {
+	mutationColumnVariants := [ 
+	// {
+	// 	name: "Mutations",
+	// 	valueType: "String",
+	// 	labelPart: " mutations in ",
+	// 	idPart: "-mutations-"
+	// },
+	{
 		name: "MutationsCount",
 		valueType: "Int",
 		labelPart: " mutations count in ",
@@ -435,21 +437,23 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			label: "Productive",
 			id: "is-productive",
 			visibility: false
-		}, {
-			columnPrefix: "isOOF",
-			arg: "-isOOF",
-			specName: "pl7.app/vdj/sequence/containsOOF",
-			label: "Contains OOF",
-			id: "is-oof",
-			visibility: false
-		}, {
-			columnPrefix: "hasStopsIn",
-			arg: "-hasStops",
-			specName: "pl7.app/vdj/sequence/containsStopCodons",
-			label: "Contains stop codons",
-			id: "has-stops",
-			visibility: false
-		} ]
+		}
+		// {
+		// 	columnPrefix: "isOOF",
+		// 	arg: "-isOOF",
+		// 	specName: "pl7.app/vdj/sequence/containsOOF",
+		// 	label: "Contains OOF",
+		// 	id: "is-oof",
+		// 	visibility: false
+		// }, {
+		// 	columnPrefix: "hasStopsIn",
+		// 	arg: "-hasStops",
+		// 	specName: "pl7.app/vdj/sequence/containsStopCodons",
+		// 	label: "Contains stop codons",
+		// 	id: "has-stops",
+		// 	visibility: false
+		// }
+	]
 	for variant in flagColumnVariants {
 		columnsSpecPerClonotype += [ {
 				column: variant.columnPrefix + productiveFeature,
@@ -470,29 +474,29 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 	// Germline sequences
 
-	geneRegions := ["VRegion", "DRegion", "JRegion"]
-
-	for region in geneRegions {
-		columnsSpecPerClonotype += [ {
-				column: "nSeq" + region + "OfGermline",
-				naRegex: "",
-				allowNA: true,
-				id: "n-seq-" + text.to_lower(region) + "-germline",
-				spec: {
-					name: "pl7.app/vdj/germlineSequence",
-					valueType: "String",
-					domain: {
-						"pl7.app/vdj/feature": region,
-						"pl7.app/alphabet": "nucleotide"
-					},
-					annotations: a(orderP, false, {
-						"pl7.app/label": region[0:1] + " germline"
-					})
-				}
-			} ]
-		exportArgs += [ [ "-nFeature", region, "germline" ] ]
-		orderP -= 100
-	}
+	// geneRegions := ["VRegion", "DRegion", "JRegion"]
+
+	// for region in geneRegions {
+	// 	columnsSpecPerClonotype += [ {
+	// 			column: "nSeq" + region + "OfGermline",
+	// 			naRegex: "",
+	// 			allowNA: true,
+	// 			id: "n-seq-" + text.to_lower(region) + "-germline",
+	// 			spec: {
+	// 				name: "pl7.app/vdj/germlineSequence",
+	// 				valueType: "String",
+	// 				domain: {
+	// 					"pl7.app/vdj/feature": region,
+	// 					"pl7.app/alphabet": "nucleotide"
+	// 				},
+	// 				annotations: a(orderP, false, {
+	// 					"pl7.app/label": region[0:1] + " germline"
+	// 				})
+	// 			}
+	// 		} ]
+	// 	exportArgs += [ [ "-nFeature", region, "germline" ] ]
+	// 	orderP -= 100
+	// }
 
 	// Isotype and chain
 
@@ -528,6 +532,38 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 		[ "-topChains" ]
 	]
 
+	//Sequence length
+	
+	// for now use only CDR3 length to avoid generating too many columns
+	lengthColumns := ["CDR3"] // assemblingFeatureInfo.nonImputed
+
+	for featureU in lengthColumns {
+		featureL := text.to_lower(featureU)
+		for isAminoAcid in [false, true] {
+			alphabet := isAminoAcid ? "aminoacid" : "nucleotide"
+			alphabetShort := isAminoAcid ? "aa" : "nt"
+			alphabetShortMixcr := isAminoAcid ? "aa" : "n"
+			columnsSpecPerClonotype += [ {
+				column: alphabetShortMixcr + "Length" + featureU,
+				id: alphabetShortMixcr + "-length-" + featureL,
+				naRegex: "region_not_covered",
+				spec: {
+					name: "pl7.app/vdj/sequenceLength",
+					valueType: "Int",
+					domain: {
+						"pl7.app/vdj/feature": featureU,
+						"pl7.app/alphabet": alphabet
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "Length of " + featureU + " " + alphabetShort
+					})
+				}
+			} ]
+			exportArgs += [ [ "-" + alphabetShortMixcr + "Length", featureU ] ]
+			orderP -= 100
+		}
+	}
+
 	// All columns are added
 
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotype
@@ -595,7 +631,7 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 						"pl7.app/vdj/clonotypingRunId": blockId
 					},
 					annotations: {
-						"pl7.app/label": "SC Clonotype key",
+						"pl7.app/label": "Clone label",
 						"pl7.app/table/visibility": "optional",
 						"pl7.app/table/orderPriority": "110000",
 						"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))

package/src/main.tpl.tengo

@@ -135,8 +135,8 @@ wf.body(func(args) {
 		qc: pframes.exportColumnData(runMixcr.output("qc.data")),
 		reports: pframes.exportColumnData(runMixcr.output("reports.data")),
 		logs: runMixcr.output("logs.data"),
-		clonotypes: pframes.exportFrame(runMixcr.output("clonotypes")),
 		clns: runMixcr.output("clns.data"),
+		clonotypes: pframes.exportFrame(runMixcr.output("clonotypes")),
 		fileImports: smart.createMapResource(maps.mapValues(fileImports, func(im) {
 			return im.handle
 		}))