@platforma-open/milaboratories.mixcr-clonotyping-2.workflow 2.5.1 → 2.6.1

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@2.5.1 build /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.6.1 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@2.5.1 test /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.6.1 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) 55335ms
-   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 13611ms
-   ✓ checking preset for '10x-sc-xcr-vdj' 8802ms
-   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8358ms
-   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8466ms
-   ✓ checking preset for 'rna-seq' 8068ms
-   ✓ checking preset for 'generic-single-cell-gex' 8028ms
+ ✓ src/test/columns.test.ts (6 tests) 55868ms
+   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 14243ms
+   ✓ checking preset for '10x-sc-xcr-vdj' 8794ms
+   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8380ms
+   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8294ms
+   ✓ checking preset for 'rna-seq' 7887ms
+   ✓ checking preset for 'generic-single-cell-gex' 8268ms
 
  Test Files  1 passed (1)
       Tests  6 passed (6)
-   Start at  16:04:59
-   Duration  56.24s (transform 54ms, setup 0ms, collect 634ms, tests 55.34s, environment 0ms, prepare 77ms)
+   Start at  16:45:12
+   Duration  56.68s (transform 41ms, setup 0ms, collect 572ms, tests 55.87s, environment 0ms, prepare 60ms)
 

package/CHANGELOG.md

@@ -1,5 +1,17 @@
 # @platforma-open/milaboratories.mixcr-clonotyping.workflow
 
+## 2.6.1
+
+### Patch Changes
+
+- 24b689b: Fixes spec for mutation columns (adds pl7.app/vdj/gene domain to make column ids for V and J genes distinguishable)
+
+## 2.6.0
+
+### Minor Changes
+
+- 4b789fc: Added CDR3 length; removed unnecessary columns; removed pf from outputs
+
 ## 2.5.1
 
 ### Patch Changes

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

@@ -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 ",
@@ -415,6 +417,9 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 						spec: {
 							valueType: variant.valueType,
 							name: "pl7.app/vdj/sequence/" + alphabetShortMixcr + variant.name,
+							domain: {
+								"pl7.app/vdj/gene": geneU
+							},
 							annotations: a(orderP, false, {
 								"pl7.app/label": alphabetShort + variant.labelPart + geneU + " gene"
 							})
@@ -435,21 +440,23 @@ 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 +477,29 @@ 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 +536,38 @@ 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
 

package/package.json

@@ -1,16 +1,16 @@
 {
   "name": "@platforma-open/milaboratories.mixcr-clonotyping-2.workflow",
-  "version": "2.5.1",
+  "version": "2.6.1",
   "description": "Tengo-based template",
   "dependencies": {
-    "@platforma-sdk/workflow-tengo": "^3.1.0",
+    "@platforma-sdk/workflow-tengo": "^4.0.3",
     "@platforma-open/milaboratories.mixcr-clonotyping-2.single-cell-scripts": "1.1.1"
   },
   "devDependencies": {
-    "@platforma-sdk/tengo-builder": "^2.0.2",
+    "@platforma-sdk/tengo-builder": "^2.0.3",
     "@platforma-open/milaboratories.software-mixcr": "4.7.0-149-develop",
     "@platforma-open/milaboratories.software-ptransform": "^1.3.1",
-    "@platforma-sdk/test": "^1.25.0",
+    "@platforma-sdk/test": "^1.28.2",
     "vitest": "^2.1.8",
     "typescript": "~5.5.4"
   },

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

@@ -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 ",
@@ -415,6 +417,9 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 						spec: {
 							valueType: variant.valueType,
 							name: "pl7.app/vdj/sequence/" + alphabetShortMixcr + variant.name,
+							domain: {
+								"pl7.app/vdj/gene": geneU
+							},
 							annotations: a(orderP, false, {
 								"pl7.app/label": alphabetShort + variant.labelPart + geneU + " gene"
 							})
@@ -435,21 +440,23 @@ 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 +477,29 @@ 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 +535,38 @@ 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

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
 		}))