@platforma-open/milaboratories.mixcr-clonotyping-2.workflow 2.4.1 → 2.5.0

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@2.4.1 build /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.5.0 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@2.4.1 test /home/runner/work/mixcr-clonotyping-2/mixcr-clonotyping-2/workflow
+> @platforma-open/milaboratories.mixcr-clonotyping-2.workflow@2.5.0 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) 53502ms
-   ✓ checking preset for 'milab-human-dna-xcr-7genes-multiplex' 13417ms
-   ✓ checking preset for '10x-sc-xcr-vdj' 8367ms
-   ✓ checking preset for 'cellecta-human-rna-xcr-umi-drivermap-…' 8046ms
-   ✓ checking preset for 'takara-human-rna-bcr-umi-smartseq' 8241ms
-   ✓ checking preset for 'rna-seq' 7618ms
-   ✓ checking preset for 'generic-single-cell-gex' 7812ms
+ ✓ 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
 
  Test Files  1 passed (1)
       Tests  6 passed (6)
-   Start at  17:05:40
-   Duration  54.41s (transform 56ms, setup 0ms, collect 641ms, tests 53.50s, environment 0ms, prepare 74ms)
+   Start at  09:32:55
+   Duration  53.99s (transform 41ms, setup 0ms, collect 564ms, tests 53.19s, environment 0ms, prepare 60ms)
 

package/CHANGELOG.md

@@ -1,5 +1,13 @@
 # @platforma-open/milaboratories.mixcr-clonotyping.workflow
 
+## 2.5.0
+
+### Minor Changes
+
+- 8643dbf: Output column signeture refactoring:
+  - chain and receptor information moved to clonotype key axis
+  - clonotypingRunId domain also moved to clonotype key axis
+
 ## 2.4.1
 
 ### Patch Changes

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

@@ -530,30 +530,6 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 
 
-
-
-	columnsSpecPerSample = addSpec(columnsSpecPerSample, { spec: { domain: {
-		"pl7.app/vdj/clonotypingRunId": blockId
-	} } })
-
-	columnsSpecPerSampleSc = addSpec(columnsSpecPerSampleSc, { spec: { domain: {
-		"pl7.app/vdj/clonotypingRunId": blockId
-	} } })
-
-
-
-
-
-
-	columnsSpecPerClonotype = addSpec(columnsSpecPerClonotype, { spec: {
-		domain: {
-			"pl7.app/vdj/clonotypingRunId": blockId
-		},
-		annotations: {
-			"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
-		}
-	} })
-
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotype
 
 
@@ -579,6 +555,11 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			keyStrincture += [ toCombinedDomainValue(columnSpec.spec) ]
 		}
 
+
+
+
+
+
 		axesByClonotypeKey = [ {
 			column: "clonotypeKey",
 			naRegex: "",
@@ -586,12 +567,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				name: "pl7.app/vdj/clonotypeKey",
 				type: "String",
 				domain: {
-					"pl7.app/vdj/clonotypeKey/structure": string(json.encode(keyStrincture))
+					"pl7.app/vdj/clonotypeKey/structure": string(json.encode(keyStrincture)),
+					"pl7.app/vdj/clonotypingRunId": blockId
 				},
 				annotations: {
 					"pl7.app/label": "Clonotype key",
 					"pl7.app/table/visibility": "optional",
-					"pl7.app/table/orderPriority": "110000"
+					"pl7.app/table/orderPriority": "110000",
+					"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
 				}
 			}
 		} ]
@@ -608,12 +591,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 					name: "pl7.app/vdj/scClonotypeKey",
 					type: "String",
 					domain: {
-						"pl7.app/vdj/scClonotypeKey/structure": string(json.encode(keyStrincture))
+						"pl7.app/vdj/scClonotypeKey/structure": string(json.encode(keyStrincture)),
+						"pl7.app/vdj/clonotypingRunId": blockId
 					},
 					annotations: {
 						"pl7.app/label": "SC Clonotype key",
 						"pl7.app/table/visibility": "optional",
-						"pl7.app/table/orderPriority": "110000"
+						"pl7.app/table/orderPriority": "110000",
+						"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
 					}
 				}
 			} ]

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@platforma-open/milaboratories.mixcr-clonotyping-2.workflow",
-  "version": "2.4.1",
+  "version": "2.5.0",
   "description": "Tengo-based template",
   "dependencies": {
     "@platforma-sdk/workflow-tengo": "^3.1.0",

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

@@ -530,30 +530,6 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 
 	// All columns are added
 
-	// Adding block and segment annotations
-
-	columnsSpecPerSample = addSpec(columnsSpecPerSample, { spec: { domain: {
-		"pl7.app/vdj/clonotypingRunId": blockId
-	} } })
-
-	columnsSpecPerSampleSc = addSpec(columnsSpecPerSampleSc, { spec: { domain: {
-		"pl7.app/vdj/clonotypingRunId": blockId
-	} } })
-
-	//   "pl7.app/segmentedBy" annotation indicates columns that can be meaningfully merged across
-	//   different runs (given they have the same name and axes signature).
-	//   Its absence indicates that merging would be semantically meaningless (e.g., abundance
-	//   measurements specific to each analysis)
-
-	columnsSpecPerClonotype = addSpec(columnsSpecPerClonotype, { spec: {
-		domain: {
-			"pl7.app/vdj/clonotypingRunId": blockId
-		},
-		annotations: {
-			"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
-		}
-	} })
-
 	columnsSpec := columnsSpecPerSample + columnsSpecPerClonotype
 
 	// Creating a column map for fast search
@@ -579,6 +555,11 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 			keyStrincture += [ toCombinedDomainValue(columnSpec.spec) ]
 		}
 
+		//   "pl7.app/segmentedBy" annotation indicates columns that can be meaningfully merged across
+		//   different runs (given they have the same name and axes signature).
+		//   Its absence indicates that merging would be semantically meaningless (e.g., abundance
+		//   measurements specific to each analysis)
+
 		axesByClonotypeKey = [ {
 			column: "clonotypeKey",
 			naRegex: "",
@@ -586,12 +567,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 				name: "pl7.app/vdj/clonotypeKey",
 				type: "String",
 				domain: {
-					"pl7.app/vdj/clonotypeKey/structure": string(json.encode(keyStrincture))
+					"pl7.app/vdj/clonotypeKey/structure": string(json.encode(keyStrincture)),
+					"pl7.app/vdj/clonotypingRunId": blockId
 				},
 				annotations: {
 					"pl7.app/label": "Clonotype key",
 					"pl7.app/table/visibility": "optional",
-					"pl7.app/table/orderPriority": "110000"
+					"pl7.app/table/orderPriority": "110000",
+					"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
 				}
 			}
 		} ]
@@ -608,12 +591,14 @@ calculateExportSpecs := func(presetSpecForBack, blockId) {
 					name: "pl7.app/vdj/scClonotypeKey",
 					type: "String",
 					domain: {
-						"pl7.app/vdj/scClonotypeKey/structure": string(json.encode(keyStrincture))
+						"pl7.app/vdj/scClonotypeKey/structure": string(json.encode(keyStrincture)),
+						"pl7.app/vdj/clonotypingRunId": blockId
 					},
 					annotations: {
 						"pl7.app/label": "SC Clonotype key",
 						"pl7.app/table/visibility": "optional",
-						"pl7.app/table/orderPriority": "110000"
+						"pl7.app/table/orderPriority": "110000",
+						"pl7.app/segmentedBy": string(json.encode(["pl7.app/vdj/clonotypingRunId"]))
 					}
 				}
 			} ]

package/src/process.tpl.tengo

@@ -211,6 +211,14 @@ self.body(func(inputs) {
 
 	mainAbundanceColumn := exportSpecs.mainAbundanceColumn
 
+	if is_undefined(axesByClonotypeKey) {
+		ll.panic("Absent clonotype key not supported")
+	}
+
+	if len(axesByClonotypeKey) != 1 || (!is_undefined(axesByScClonotypeKey) && len(axesByScClonotypeKey) != 1) {
+		ll.panic("Assertion error: expected exactly one clonotype key axis")
+	}
+
 	mixcrResults := pframes.processColumn(
 		{ spec: inputSpec, data: inputs.inputData },
 		mixcrAnalyzeTpl,
@@ -274,6 +282,10 @@ self.body(func(inputs) {
 		chainInfo := chainInfos[chain]
 		ll.assert(!is_undefined(chainInfo), "chainInfo not found for chain %v", chain)
 
+		axesByClonotypeKeyWithChain := [ maps.deepTransform(axesByClonotypeKey[0], {
+			spec: { domain: { "pl7.app/vdj/chain": chain } }
+		}) ]
+
 		//
 		// Exporting CLNS -> TSV
 		//
@@ -292,16 +304,14 @@ self.body(func(inputs) {
 			path: ["tsv"]
 		} ]
 
-		if !is_undefined(axesByClonotypeKey) && !isSingleCell {
+		if !isSingleCell {
 			// only adding data outputs if we are in bulk mode
 			exportOutputs += [ {
 				type: "Xsv",
 				xsvType: "tsv",
 				settings: {
-					axes: axesByClonotypeKey,
-					columns: transformSpecs(columnsSpecPerSample, {
-						spec: { domain: { "pl7.app/vdj/chain": chain } }
-					}),
+					axes: axesByClonotypeKeyWithChain,
+					columns: columnsSpecPerSample,
 					storageFormat: "Binary",
 					partitionKeyLength: 0
 				},
@@ -317,7 +327,8 @@ self.body(func(inputs) {
 					kind: "PColumn",
 					name: "mixcr.com/clonotypeTableForSingleCell",
 					domain: {
-						"pl7.app/vdj/clonotypingRunId": blockId
+						"pl7.app/vdj/clonotypingRunId": blockId,
+						"pl7.app/vdj/chain": chain
 					},
 					valueType: "File"
 				},
@@ -372,10 +383,8 @@ self.body(func(inputs) {
 				type: "Xsv",
 				xsvType: "tsv",
 				settings: {
-					axes: axesByClonotypeKey,
-					columns: transformSpecs(columnsSpecPerClonotype, {
-						spec: { domain: { "pl7.app/vdj/chain": chain } }
-					}),
+					axes: axesByClonotypeKeyWithChain,
+					columns: columnsSpecPerClonotype,
 					storageFormat: "Binary",
 					partitionKeyLength: 0
 				},
@@ -418,6 +427,10 @@ self.body(func(inputs) {
 		for receptor in receptors {
 			receptorInfo := receptorInfos[receptor]
 
+			axesByScClonotypeKeyWithReceptor := [ maps.deepTransform(axesByScClonotypeKey[0], {
+				spec: { domain: { "pl7.app/vdj/receptor": receptor } }
+			}) ]
+
 			singleCellOutputs := [ {
 				type: "Resource",
 				spec: {
@@ -437,10 +450,8 @@ self.body(func(inputs) {
 					axes: [ {
 						column: "sampleId",
 						spec: inputSpec.axesSpec[0]
-					} ] + axesByScClonotypeKey,
-					columns: transformSpecs(columnsSpecPerSampleSc, {
-						spec: { domain: { "pl7.app/vdj/receptor": receptor } }
-					}),
+					} ] + axesByScClonotypeKeyWithReceptor,
+					columns: columnsSpecPerSampleSc,
 					storageFormat: "Binary",
 					partitionKeyLength: 1
 				},
@@ -492,11 +503,10 @@ self.body(func(inputs) {
 						type: "Xsv",
 						xsvType: "tsv",
 						settings: {
-							axes: axesByScClonotypeKey,
+							axes: axesByScClonotypeKeyWithReceptor,
 							columns: transformSpecs(columnsSpecPerClonotype, {
 								spec: {
 									domain: {
-										"pl7.app/vdj/receptor": receptor,
 										"pl7.app/vdj/scClonotypeChain": chainLetterU,
 										"pl7.app/vdj/scClonotypeChain/index": pPrefixL
 									},