@platforma-open/milaboratories.mixcr-amplicon-alignment.workflow 1.16.0 → 1.17.0

package/.turbo/turbo-build.log

@@ -1,6 +1,6 @@
  WARN  Issue while reading "/home/runner/work/mixcr-amplicon-alignment/mixcr-amplicon-alignment/.npmrc". Failed to replace env in config: ${NPMJS_TOKEN}
 
-> @platforma-open/milaboratories.mixcr-amplicon-alignment.workflow@1.16.0 build /home/runner/work/mixcr-amplicon-alignment/mixcr-amplicon-alignment/workflow
+> @platforma-open/milaboratories.mixcr-amplicon-alignment.workflow@1.17.0 build /home/runner/work/mixcr-amplicon-alignment/mixcr-amplicon-alignment/workflow
 > rm -rf dist && pl-tengo check && pl-tengo build
 
 Processing "src/aggregate-by-clonotype-key.tpl.tengo"...

package/CHANGELOG.md

@@ -1,5 +1,11 @@
 # @platforma-open/milaboratories.mixcr-amplicon-alignment.workflow
 
+## 1.17.0
+
+### Minor Changes
+
+- 34824d1: mutations columns added, removed unused columns, dependency updates and migrate block code to latest layout
+
 ## 1.16.0
 
 ### Minor Changes

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

@@ -91,13 +91,10 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			[ "-jGene" ]
 		]
 	}
-	if splitByC {
-		clonotypeKeyColumns += ["bestCGene"]
-		clonotypeKeyArgs += [ [ "-cGene" ] ]
-	}
 
 	columnsSpecPerSample := []
 	columnsSpecPerClonotypeNoAggregates := []
+	mutationColumns := []
 
 	clonotypeLabelColumn := {
 		column: "clonotypeLabel",
@@ -419,14 +416,15 @@ inFrameFeatures := {
 			argSuffix: "Gene",
 			visible: true
 		} ]
-	for vdjcU in ["V", "D", "J", "C"] {
+
+	for vdjcU in ["V", "J"] {
 		vdjcL := text.to_lower(vdjcU)
 		for variant in geneHitColumnVariants {
 			columnsSpecPerClonotypeNoAggregates += [ {
 					column: "best" + vdjcU + variant.columnNameSuffix,
 					id: "best-" + vdjcL + variant.idSuffix,
 					naRegex: "",
-					allowNA: vdjcU == "C" || vdjcU == "D",
+					allowNA: false,
 					spec: {
 						name: variant.name,
 						valueType: "String",
@@ -475,7 +473,7 @@ inFrameFeatures := {
 				}
 				
 				for variant in mutationColumnVariants {
-					columnsSpecPerClonotypeNoAggregates += [ {
+					mutationColumns += [ {
 							column: alphabetShortMixcr + variant.name + coreFeature,
 							id: alphabetShortMixcr + variant.idPart + geneL,
 							allowNA: true,
@@ -499,6 +497,212 @@ inFrameFeatures := {
 	}
 
 
+	if assemblingFeature == "VDJRegion" {
+		orderP = 9500
+		
+
+
+
+		for featureU in features {
+
+			if featureU == "CDR3" || featureU == "VDJRegion" || featureU == "FR4" {
+				continue
+			}
+			featureL := text.to_lower(formatId(featureU))
+			rateOrderP := orderP - 1
+			columnName := "nMutationsCount" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "n-mutations-count-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Int",
+					name: "pl7.app/vdj/sequence/nMutationsCount",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "Nt mutations count in " + featureU
+					})
+				}
+			} ]
+			columnName = "nMutationsRate" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "n-mutations-rate-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Double",
+					name: "pl7.app/vdj/sequence/nMutationsRate",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(rateOrderP, false, {
+						"pl7.app/label": "Nt mutations rate in " + featureU
+					})
+				}
+			} ]
+			exportArgs += [ [ "-nMutationRate", featureU ] ]
+			orderP -= 100
+		}
+
+
+		exportArgs += [ [ "-allNMutationsCount", "FR1Begin", "FR4End" ] ]
+		
+
+		orderP = 8500
+		
+
+
+
+		for featureU in features {
+
+			if featureU == "CDR3" || featureU == "VDJRegion" || featureU == "FR4" {
+				continue
+			}
+			featureL := text.to_lower(formatId(featureU))
+			rateOrderP := orderP - 1
+			columnName := "aaMutationsCount" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "aa-mutations-count-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Int",
+					name: "pl7.app/vdj/sequence/aaMutationsCount",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "AA mutations count in " + featureU
+					})
+				}
+			} ]
+			columnName = "aaMutationsRate" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "aa-mutations-rate-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Double",
+					name: "pl7.app/vdj/sequence/aaMutationsRate",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(rateOrderP, false, {
+						"pl7.app/label": "AA mutations rate in " + featureU
+					})
+				}
+			} ]
+			exportArgs += [ [ "-aaMutationRate", featureU ] ]
+			orderP -= 100
+		}
+
+
+		exportArgs += [ [ "-allAAMutationsCount", "FR1Begin", "FR4End" ] ]
+		
+	}
+	
+
+
+	germlineVFeature := "GermlineVCDR3Part"
+	germlineJFeature := "GermlineJCDR3Part"
+	exportArgs += [ [ "-nMutationsCount", germlineVFeature ] ]
+	exportArgs += [ [ "-nMutationsCount", germlineJFeature ] ]
+	exportArgs += [ [ "-aaMutationsCount", germlineVFeature ] ]
+	exportArgs += [ [ "-aaMutationsCount", germlineJFeature ] ]
+	
+
+
+	orderP = 9400
+	cdr3Feature := "CDR3"
+	cdr3FeatureL := text.to_lower(formatId(cdr3Feature))
+
+
+	columnName := "nMutationsCount" + cdr3Feature
+	cdr3DistanceColumnsSpec := [ {
+		column: columnName,
+		id: "n-mutations-count-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Int",
+			name: "pl7.app/vdj/sequence/nMutationsCount",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "Nt mutations count in " + cdr3Feature
+			})
+		}
+	} ]
+
+
+	orderP = 8400
+	columnName = "aaMutationsCount" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "aa-mutations-count-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Int",
+			name: "pl7.app/vdj/sequence/aaMutationsCount",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "AA mutations count in " + cdr3Feature
+			})
+		}
+	} )
+
+
+	orderP = 9300
+	columnName = "nMutationsRate" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "n-mutations-rate-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Double",
+			name: "pl7.app/vdj/sequence/nMutationsRate",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "Nt mutations rate in " + cdr3Feature
+			})
+		}
+	})
+
+
+	orderP = 8300
+	columnName = "aaMutationsRate" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "aa-mutations-rate-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Double",
+			name: "pl7.app/vdj/sequence/aaMutationsRate",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "AA mutations rate in " + cdr3Feature
+			})
+		}
+	})
+
+
+	orderP = 12000
 
 	flagColumnVariants := [ {
 			columnPrefix: "isProductive",
@@ -533,18 +737,6 @@ inFrameFeatures := {
 
 
 	columnsSpecPerClonotypeNoAggregates += [ {
-			column: "isotypePrimary",
-			id: "isotype",
-			naRegex: "",
-			spec: {
-				valueType: "String",
-				name: "pl7.app/vdj/isotype",
-				annotations: a(orderP, true, {
-					"pl7.app/label": "IG isotype",
-					"pl7.app/isDiscreteFilter": "true"
-				})
-			}
-		}, {
 			column: "topChains",
 			id: "top-chains",
 			naRegex: "",
@@ -560,12 +752,12 @@ inFrameFeatures := {
 			}
 		} ]
 	exportArgs += [
-		[ "-isotype", "primary" ],
 		[ "-topChains" ]
 	]
 
 
 
+	columnsSpecPerClonotypeNoAggregates += mutationColumns
 
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotypeNoAggregates + columnsSpecPerClonotypeAggregates
 
@@ -623,6 +815,7 @@ inFrameFeatures := {
 		columnsSpecPerSample: columnsSpecPerSample,
 		columnsSpecPerClonotypeNoAggregates: columnsSpecPerClonotypeNoAggregates,
 		columnsSpecPerClonotypeAggregates: columnsSpecPerClonotypeAggregates,
+		cdr3DistanceColumnsSpec: cdr3DistanceColumnsSpec,
 
 		columnsSpec: columnsSpec,
 

package/package.json

@@ -1,21 +1,20 @@
 {
   "name": "@platforma-open/milaboratories.mixcr-amplicon-alignment.workflow",
-  "version": "1.16.0",
+  "version": "1.17.0",
   "description": "MiXCR Amplicon Alignment Workflow",
   "type": "module",
   "dependencies": {
-    "@platforma-sdk/workflow-tengo": "^5.8.0",
-    "@platforma-open/milaboratories.software-mixcr": "4.7.0-254-develop",
-    "@platforma-open/milaboratories.software-repseqio": "^2.5.0-13-master"
+    "@platforma-sdk/workflow-tengo": "5.8.0",
+    "@platforma-open/milaboratories.software-mixcr": "4.7.0-279-develop",
+    "@platforma-open/milaboratories.software-repseqio": "^2.5.0-13-master",
+    "@platforma-open/milaboratories.mixcr-amplicon-alignment.software": "1.0.0"
   },
   "devDependencies": {
-    "@platforma-sdk/tengo-builder": "^2.4.11",
-    "@platforma-sdk/test": "^1.52.4",
-    "vitest": "^4.0.17"
+    "@platforma-sdk/tengo-builder": "2.4.11"
   },
   "scripts": {
     "build": "rm -rf dist && pl-tengo check && pl-tengo build",
-    "test": "vitest",
-    "format": "/usr/bin/env emacs --script ./format.el"
+    "format": "/usr/bin/env emacs --script ./format.el",
+    "do-pack": "rm -f *.tgz && pnpm pack && mv *.tgz package.tgz"
   }
 }

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

@@ -5,12 +5,16 @@ slices := import("@platforma-sdk/workflow-tengo:slices")
 maps := import("@platforma-sdk/workflow-tengo:maps")
 units := import("@platforma-sdk/workflow-tengo:units")
 pt := import("@platforma-sdk/workflow-tengo:pt")
+assets := import("@platforma-sdk/workflow-tengo:assets")
+exec := import("@platforma-sdk/workflow-tengo:exec")
 clonotypeLabel := import(":clonotype-label")
 
 math := import("math")
 json := import("json")
 
-self.defineOutputs("tsv")
+self.defineOutputs("tsv", "cdr3DistancesTsv")
+
+cdr3DistanceSw := assets.importSoftware("@platforma-open/milaboratories.mixcr-amplicon-alignment.software:cdr3-distance-calculation")
 
 self.body(func(inputs) {
 	inputData := inputs[pConstants.VALUE_FIELD_NAME]
@@ -88,13 +92,37 @@ self.body(func(inputs) {
 
 	aggregatedDf = clonotypeLabel.addClonotypeLabelColumnsPt(aggregatedDf, "clonotypeKey", "clonotypeLabel", pt)
 
+	cdr3Df := aggregatedDf.select(
+		pt.col("clonotypeKey"),
+		pt.col("nSeqCDR3").alias("nSeqCDR3"),
+		pt.col("aaSeqCDR3").alias("aaSeqCDR3")
+	)
+
 	aggregatedDf.save("output.tsv")
+	cdr3Df.save("cdr3-sequences.tsv")
 
 	ptablerResult := wf.run()
 
 	processedTsv := ptablerResult.getFile("output.tsv")
+	cdr3Tsv := ptablerResult.getFile("cdr3-sequences.tsv")
+	cdr3DistancesTsv := undefined
+
+	if !is_undefined(params.cdr3Sequences) {
+		cdr3DistanceCmd := exec.builder().
+			software(cdr3DistanceSw).
+			mem("8GB").
+			cpu(1).
+			writeFile("cdr3-sequences.fasta", params.cdr3Sequences).saveFile("cdr3-sequences.fasta").
+			arg("--tsv").arg("cdr3-sequences.tsv").addFile("cdr3-sequences.tsv", cdr3Tsv).
+			arg("--ref-fasta").arg("cdr3-sequences.fasta").
+			arg("--out").arg("cdr3-distances.tsv").saveFile("cdr3-distances.tsv")
+
+		cdr3DistanceResult := cdr3DistanceCmd.run()
+		cdr3DistancesTsv = cdr3DistanceResult.getFile("cdr3-distances.tsv")
+	}
 
 	return {
-		tsv: processedTsv
+		tsv: processedTsv,
+		cdr3DistancesTsv: cdr3DistancesTsv
 	}
 }) 

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

@@ -91,13 +91,10 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			[ "-jGene" ]
 		]
 	}
-	if splitByC {
-		clonotypeKeyColumns += ["bestCGene"]
-		clonotypeKeyArgs += [ [ "-cGene" ] ]
-	}
 
 	columnsSpecPerSample := []
 	columnsSpecPerClonotypeNoAggregates := []
+	mutationColumns := []
 
 	clonotypeLabelColumn := {
 		column: "clonotypeLabel",
@@ -419,14 +416,15 @@ inFrameFeatures := {
 			argSuffix: "Gene",
 			visible: true
 		} ]
-	for vdjcU in ["V", "D", "J", "C"] {
+	// Only export V and J genes (D and C are excluded)
+	for vdjcU in ["V", "J"] {
 		vdjcL := text.to_lower(vdjcU)
 		for variant in geneHitColumnVariants {
 			columnsSpecPerClonotypeNoAggregates += [ {
 					column: "best" + vdjcU + variant.columnNameSuffix,
 					id: "best-" + vdjcL + variant.idSuffix,
 					naRegex: "",
-					allowNA: vdjcU == "C" || vdjcU == "D",
+					allowNA: false,
 					spec: {
 						name: variant.name,
 						valueType: "String",
@@ -475,7 +473,7 @@ inFrameFeatures := {
 				}
 				
 				for variant in mutationColumnVariants {
-					columnsSpecPerClonotypeNoAggregates += [ {
+					mutationColumns += [ {
 							column: alphabetShortMixcr + variant.name + coreFeature,
 							id: alphabetShortMixcr + variant.idPart + geneL,
 							allowNA: true,
@@ -498,7 +496,213 @@ inFrameFeatures := {
 		}
 	}
 
+	// All nucleotide mutations count for each feature (only for VDJRegion assembling feature)
+	if assemblingFeature == "VDJRegion" {
+		orderP = 9500
+		
+		// MixCR -allNMutationsCount exports columns for all features between specified boundaries.
+		// We add column specs for each feature and call -allNMutationsCount once with boundaries
+		// FR1Begin FR4End to cover all features. This exports all mutation types in one column.
+		for featureU in features {
+			// Skip CDR3 and VDJRegion features
+			if featureU == "CDR3" || featureU == "VDJRegion" || featureU == "FR4" {
+				continue
+			}
+			featureL := text.to_lower(formatId(featureU))
+			rateOrderP := orderP - 1
+			columnName := "nMutationsCount" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "n-mutations-count-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Int",
+					name: "pl7.app/vdj/sequence/nMutationsCount",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "Nt mutations count in " + featureU
+					})
+				}
+			} ]
+			columnName = "nMutationsRate" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "n-mutations-rate-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Double",
+					name: "pl7.app/vdj/sequence/nMutationsRate",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(rateOrderP, false, {
+						"pl7.app/label": "Nt mutations rate in " + featureU
+					})
+				}
+			} ]
+			exportArgs += [ [ "-nMutationRate", featureU ] ]
+			orderP -= 100
+		}
+		// Call -allNMutationsCount with boundaries FR1Begin FR4End (no mutation type parameter)
+		// This will export columns for all features between FR1Begin and FR4End with all mutation types
+		exportArgs += [ [ "-allNMutationsCount", "FR1Begin", "FR4End" ] ]
+		
+		// All amino acid mutations count for each feature (only for VDJRegion assembling feature)
+		orderP = 8500
+		
+		// MixCR -allAAMutationsCount exports columns for all features between specified boundaries.
+		// We add column specs for each feature and call -allAAMutationsCount once with boundaries
+		// FR1Begin FR4End to cover all features. This exports all mutation types in one column.
+		for featureU in features {
+			// Skip CDR3 and VDJRegion features
+			if featureU == "CDR3" || featureU == "VDJRegion" || featureU == "FR4" {
+				continue
+			}
+			featureL := text.to_lower(formatId(featureU))
+			rateOrderP := orderP - 1
+			columnName := "aaMutationsCount" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "aa-mutations-count-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Int",
+					name: "pl7.app/vdj/sequence/aaMutationsCount",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(orderP, false, {
+						"pl7.app/label": "AA mutations count in " + featureU
+					})
+				}
+			} ]
+			columnName = "aaMutationsRate" + featureU
+			mutationColumns += [ {
+				column: columnName,
+				id: "aa-mutations-rate-" + featureL,
+				allowNA: true,
+				naRegex: "region_not_covered",
+				spec: {
+					valueType: "Double",
+					name: "pl7.app/vdj/sequence/aaMutationsRate",
+					domain: {
+						"pl7.app/vdj/feature": featureU
+					},
+					annotations: a(rateOrderP, false, {
+						"pl7.app/label": "AA mutations rate in " + featureU
+					})
+				}
+			} ]
+			exportArgs += [ [ "-aaMutationRate", featureU ] ]
+			orderP -= 100
+		}
+		// Call -allAAMutationsCount with boundaries FR1Begin FR4End (no mutation type parameter)
+		// This will export columns for all features between FR1Begin and FR4End with all mutation types
+		exportArgs += [ [ "-allAAMutationsCount", "FR1Begin", "FR4End" ] ]
+		
+	}
+	
+	// Export germline CDR3 part mutations for both VDJRegion and CDR3 assembling features
+	// These will be summed to create the CDR3 mutations count columns
+	germlineVFeature := "GermlineVCDR3Part"
+	germlineJFeature := "GermlineJCDR3Part"
+	exportArgs += [ [ "-nMutationsCount", germlineVFeature ] ]
+	exportArgs += [ [ "-nMutationsCount", germlineJFeature ] ]
+	exportArgs += [ [ "-aaMutationsCount", germlineVFeature ] ]
+	exportArgs += [ [ "-aaMutationsCount", germlineJFeature ] ]
+	
+	// Add CDR3 mutations count columns (sum of V and J germline CDR3 part mutations)
+	// These work for both VDJRegion and CDR3 assembling features
+	orderP = 9400
+	cdr3Feature := "CDR3"
+	cdr3FeatureL := text.to_lower(formatId(cdr3Feature))
+
+	// Nucleotide mutations count
+	columnName := "nMutationsCount" + cdr3Feature
+	cdr3DistanceColumnsSpec := [ {
+		column: columnName,
+		id: "n-mutations-count-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Int",
+			name: "pl7.app/vdj/sequence/nMutationsCount",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "Nt mutations count in " + cdr3Feature
+			})
+		}
+	} ]
+
+	// Amino acid mutations count
+	orderP = 8400
+	columnName = "aaMutationsCount" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "aa-mutations-count-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Int",
+			name: "pl7.app/vdj/sequence/aaMutationsCount",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "AA mutations count in " + cdr3Feature
+			})
+		}
+	} )
+
+	// Nucleotide mutations rate
+	orderP = 9300
+	columnName = "nMutationsRate" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "n-mutations-rate-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Double",
+			name: "pl7.app/vdj/sequence/nMutationsRate",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "Nt mutations rate in " + cdr3Feature
+			})
+		}
+	})
+
+	// Amino acid mutations rate
+	orderP = 8300
+	columnName = "aaMutationsRate" + cdr3Feature
+	cdr3DistanceColumnsSpec = append(cdr3DistanceColumnsSpec, {
+		column: columnName,
+		id: "aa-mutations-rate-" + cdr3FeatureL,
+		allowNA: true,
+		naRegex: "region_not_covered",
+		spec: {
+			valueType: "Double",
+			name: "pl7.app/vdj/sequence/aaMutationsRate",
+			domain: {
+				"pl7.app/vdj/feature": cdr3Feature
+			},
+			annotations: a(orderP, false, {
+				"pl7.app/label": "AA mutations rate in " + cdr3Feature
+			})
+		}
+	})
+
 	// Flags: productive, oof, stop codons
+	orderP = 12000
 
 	flagColumnVariants := [ {
 			columnPrefix: "isProductive",
@@ -530,21 +734,9 @@ inFrameFeatures := {
 		orderP -= 100
 	}
 
-	// Isotype and chain
+	// Chain (isotype removed)
 
 	columnsSpecPerClonotypeNoAggregates += [ {
-			column: "isotypePrimary",
-			id: "isotype",
-			naRegex: "",
-			spec: {
-				valueType: "String",
-				name: "pl7.app/vdj/isotype",
-				annotations: a(orderP, true, {
-					"pl7.app/label": "IG isotype",
-					"pl7.app/isDiscreteFilter": "true"
-				})
-			}
-		}, {
 			column: "topChains",
 			id: "top-chains",
 			naRegex: "",
@@ -560,12 +752,12 @@ inFrameFeatures := {
 			}
 		} ]
 	exportArgs += [
-		[ "-isotype", "primary" ],
 		[ "-topChains" ]
 	]
 
 
 	// All columns are added
+	columnsSpecPerClonotypeNoAggregates += mutationColumns
 
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotypeNoAggregates + columnsSpecPerClonotypeAggregates
 
@@ -623,6 +815,7 @@ inFrameFeatures := {
 		columnsSpecPerSample: columnsSpecPerSample,
 		columnsSpecPerClonotypeNoAggregates: columnsSpecPerClonotypeNoAggregates,
 		columnsSpecPerClonotypeAggregates: columnsSpecPerClonotypeAggregates,
+		cdr3DistanceColumnsSpec: cdr3DistanceColumnsSpec,
 
 		columnsSpec: columnsSpec,
 

package/src/main.tpl.tengo

@@ -58,6 +58,7 @@ wf.body(func(args) {
 		inputData: input.getFutureInputField("data"),
 		referenceLibrary: referenceLibrary,
 		limitInput: limitInput,
+		cdr3Sequences: args.cdr3Sequences,
 
 		params: smart.createJsonResource({
 			blockId: blockId,

package/src/process.tpl.tengo

@@ -22,6 +22,7 @@ self.awaitState("InputsLocked")
 self.awaitState("params", "ResourceReady")
 self.awaitState("inputSpec", "ResourceReady")
 self.awaitState("referenceLibrary", "ResourceReady")
+self.awaitState("cdr3Sequences", "ResourceReady")
 
 self.body(func(inputs) {
 
@@ -86,6 +87,7 @@ self.body(func(inputs) {
 	columnsSpecPerSample := exportSpecs.columnsSpecPerSample
 	columnsSpecPerClonotypeNoAggregates := exportSpecs.columnsSpecPerClonotypeNoAggregates
 	columnsSpecPerClonotypeAggregates := exportSpecs.columnsSpecPerClonotypeAggregates
+	cdr3DistanceColumnsSpec := exportSpecs.cdr3DistanceColumnsSpec
 	clonotypeKeyColumns := exportSpecs.clonotypeKeyColumns
 	clonotypeKeyArgs := exportSpecs.clonotypeKeyArgs
 	exportArgs := exportSpecs.exportArgs
@@ -294,6 +296,18 @@ self.body(func(inputs) {
 		cpu: 2,
 		name: "aggregates",
 		path: ["tsv"]
+	}, {
+		type: "Xsv",
+		xsvType: "tsv",
+		settings: {
+			axes: axesByClonotypeKeyWithChain,
+			columns: cdr3DistanceColumnsSpec,
+			storageFormat: "Parquet"
+		},
+		mem: "8GB",
+		cpu: 1,
+		name: "cdr3Distances",
+		path: ["cdr3DistancesTsv"]
 	} ]
 
 	aggregationResults := pframes.processColumn(
@@ -310,7 +324,9 @@ self.body(func(inputs) {
 					mainAbundanceColumnUnnormalized: mainAbundanceColumnUnnormalized,
 					schemaPerClonotypeNoAggregates: columnsToSchema(columnsSpecPerClonotypeNoAggregates),
 					schemaPerClonotypeAggregates: columnsToSchema(columnsSpecPerClonotypeAggregates),
-					schemaPerSample: columnsToSchema(columnsSpecPerSample)
+					schemaPerSample: columnsToSchema(columnsSpecPerSample),
+					cdr3Sequences: inputs.cdr3Sequences,
+					cdr3DistanceColumnsSpec: cdr3DistanceColumnsSpec
 				}
 			}
 		}
@@ -320,6 +336,7 @@ self.body(func(inputs) {
 	clones := pframes.pFrameBuilder()
 	exportResults.addXsvOutputToBuilder(clones, "byCloneKeyBySample", "clonotypeProperties/bySample/" + chains + "/")
 	aggregationResults.addXsvOutputToBuilder(clones, "aggregates", "clonotypeProperties/aggregates/" + chains + "/")
+	aggregationResults.addXsvOutputToBuilder(clones, "cdr3Distances", "clonotypeProperties/cdr3Distances/" + chains + "/")
 
 	qcReportTable := render.create(exportReportTpl, {
 		clnsData: mixcrResults.outputData("clns"),

package/index.d.ts

@@ -1,4 +0,0 @@
-declare type TemplateFromFile = { readonly type: "from-file"; readonly path: string; };
-declare type TplName = "main";
-declare const Templates: Record<TplName, TemplateFromFile>;
-export { Templates };

package/index.js

@@ -1,3 +0,0 @@
-module.exports = { Templates: {
-  'main': { type: 'from-file', path: require.resolve('./dist/tengo/tpl/main.plj.gz') }
-}}

package/tsconfig.json

@@ -1,16 +0,0 @@
-{
-  "compilerOptions": {
-    "target": "es2022",
-    "module": "commonjs",
-    "moduleResolution": "node",
-    "esModuleInterop": true,
-    "strict": true,
-    "outDir": "./dist",
-    "rootDir": "./src",
-    "sourceMap": true,
-    "declaration": true
-  },
-  "types": [],
-  "include": ["src/**/*"],
-  "exclude": ["node_modules", "dist"]
-}

package/vitest.config.mts

@@ -1,9 +0,0 @@
-import { defineConfig } from 'vitest/config';
-
-export default defineConfig({
-  test: {
-    watch: false,
-    maxConcurrency: 3,
-    testTimeout: 5000
-  }
-});