@platforma-open/milaboratories.immune-assay-data.workflow 1.2.0 → 1.4.0

package/.turbo/turbo-build.log

@@ -1,6 +1,6 @@
  WARN  Issue while reading "/home/runner/work/immune-assay-data/immune-assay-data/.npmrc". Failed to replace env in config: ${NPMJS_TOKEN}
 
-> @platforma-open/milaboratories.immune-assay-data.workflow@1.2.0 build /home/runner/work/immune-assay-data/immune-assay-data/workflow
+> @platforma-open/milaboratories.immune-assay-data.workflow@1.4.0 build /home/runner/work/immune-assay-data/immune-assay-data/workflow
 > rm -rf dist && pl-tengo check && pl-tengo build
 
 Processing "src/main.tpl.tengo"...

package/CHANGELOG.md

@@ -1,5 +1,25 @@
 # @platforma-open/milaboratories.immune-assay-data.workflow
 
+## 1.4.0
+
+### Minor Changes
+
+- 8e515a8: Support fasta file as assay data
+
+### Patch Changes
+
+- Updated dependencies [8e515a8]
+  - @platforma-open/milaboratories.immune-assay-data.coverage-mode-calc@1.1.0
+  - @platforma-open/milaboratories.immune-assay-data.prepare-fasta@1.1.0
+  - @platforma-open/milaboratories.immune-assay-data.fasta-to-tsv@1.1.0
+  - @platforma-open/milaboratories.immune-assay-data.add-header@1.1.0
+
+## 1.3.0
+
+### Minor Changes
+
+- b18f925: Update trace label and importance
+
 ## 1.2.0
 
 ### Minor Changes

package/package.json

@@ -1,18 +1,19 @@
 {
   "name": "@platforma-open/milaboratories.immune-assay-data.workflow",
-  "version": "1.2.0",
+  "version": "1.4.0",
   "type": "module",
   "description": "Block Workflow",
   "dependencies": {
-    "@platforma-sdk/workflow-tengo": "^4.9.0",
+    "@platforma-sdk/workflow-tengo": "4.8.0",
     "@platforma-open/soedinglab.software-mmseqs2": "^1.0.0",
-    "@platforma-open/milaboratories.immune-assay-data.prepare-fasta": "1.0.3",
-    "@platforma-open/milaboratories.immune-assay-data.add-header": "1.0.2",
-    "@platforma-open/milaboratories.immune-assay-data.coverage-mode-calc": "1.0.0"
+    "@platforma-open/milaboratories.immune-assay-data.prepare-fasta": "1.1.0",
+    "@platforma-open/milaboratories.immune-assay-data.add-header": "1.1.0",
+    "@platforma-open/milaboratories.immune-assay-data.coverage-mode-calc": "1.1.0",
+    "@platforma-open/milaboratories.immune-assay-data.fasta-to-tsv": "1.1.0"
   },
   "devDependencies": {
     "@platforma-sdk/tengo-builder": "^2.1.11",
-    "@platforma-sdk/test": "^1.37.8",
+    "@platforma-sdk/test": "^1.37.9",
     "vitest": "^2.1.8"
   },
   "scripts": {

package/src/main.tpl.tengo

@@ -16,6 +16,7 @@ strings := import("@platforma-sdk/workflow-tengo:strings")
 runAlignmentTpl := assets.importTemplate(":run-alignment")
 
 prepareFastaSw := assets.importSoftware("@platforma-open/milaboratories.immune-assay-data.prepare-fasta:main")
+fastaToTsvSw := assets.importSoftware("@platforma-open/milaboratories.immune-assay-data.fasta-to-tsv:main")
 addHeaderSw := assets.importSoftware("@platforma-open/milaboratories.immune-assay-data.add-header:main")
 covModeCalcSw := assets.importSoftware("@platforma-open/milaboratories.immune-assay-data.coverage-mode-calc:main")
 
@@ -37,9 +38,26 @@ prepareAssayFile := func(args, file, xsvType) {
 	})
 
 	//////// calculate sequence id ////////
+	// Create unique seqId for each row by combining sequence with row index
+	// First add row index using ordinal rank
+	df = df.withColumns(
+		pt.rank(pt.col(args.sequenceColumnHeader)).
+			over(pt.col(args.sequenceColumnHeader)).
+			alias("rowIndex")
+	)
+	// Concatenate sequence with row index and then hash
+	df = df.withColumns(
+		pt.when(pt.col("rowIndex").gt(pt.lit(1))).
+			then(pt.concatStr([pt.col(args.sequenceColumnHeader), pt.col("rowIndex").cast("String")], {delimiter: "_"})).
+			otherwise(pt.col(args.sequenceColumnHeader)).
+			alias("uniqueKey")
+	)
+	// Create hash from the unique key
 	df = df.addColumns(
-		pt.col(args.sequenceColumnHeader).hash("sha256", "base64_alphanumeric", 120).alias("seqId")
+		pt.col("uniqueKey").hash("sha256", "base64_alphanumeric", 120).alias("seqId")
 	)
+	// Remove the temporary columns
+	//df = df.withoutColumns("uniqueKey", "rowIndex")
 	//////// add label to ids ////////
 	df = df.withColumns(
         pt.col("seqId").
@@ -104,6 +122,24 @@ runTsvToFasta := func(fileTsv) {
 	return e.run()
 }
 
+/**
+ * Convert fasta file to tsv file
+ * @param fileFasta - fasta file
+ * @return tsv file run result
+ */
+runFastaToTsv := func(fileFasta) {
+	e := exec.builder().
+		software(fastaToTsvSw).
+		mem("16GiB").
+		cpu(1).
+		addFile("input.fasta", fileFasta).
+		arg("-i").arg("input.fasta").
+		arg("-o").arg("output.tsv").
+		saveFile("output.tsv")
+
+	return e.run()
+}
+
 assayColumnName := func(header) {
 	return "pl7.app/vdj/assay-data/" + strings.substituteSpecialCharacters(header)
 }
@@ -147,12 +183,19 @@ wf.body(func(args) {
 		ll.panic("Could not determine filename from file handle: ", args.fileHandle)
 	}
 
-	fileNameParts := path.split(fileName, ".")
+	fileNameParts := path.split(text.to_lower(fileName), ".")
 	xsvType := "tsv"
 	if len(fileNameParts) > 1 {
 		xsvType = fileNameParts[len(fileNameParts)-1]
 	}
 
+	// Handle FASTA files by converting to TSV first
+	if xsvType == "fasta" || xsvType == "fa" {
+		fastaToTsvRun := runFastaToTsv(importFile.file)
+		importFile.file = fastaToTsvRun.getFile("output.tsv")
+		xsvType = "tsv"
+	}
+
 	assayTsv := prepareAssayFile(args, importFile.file, xsvType)
 	clonesTsv := prepareClonesTsv(args)
 
@@ -463,11 +506,18 @@ wf.body(func(args) {
 			{ splitDataAndSpec: true, cpu: 1, mem: "16GiB" }
 		)
 
+		// Create informative label with relevant matching parameters
+		identityStr := string(args.settings.identity)
+		coverageStr := string(args.settings.coverageThreshold)
+		similarityTypeStr := args.settings.similarityType == "sequence-identity" ? "Exact Match" : "BLOSUM"
+		
+		traceLabel := "Assay Data (sim:" + similarityTypeStr + ", ident:" + identityStr + ", cov:" + coverageStr + ")"
+		
 		trace := pSpec.makeTrace(datasetSpec,
 			{
 				type: "milaboratories.immune-assay-data",
-				importance: 30,
-				label: "Assay Data"
+				importance: 40,
+				label: traceLabel
 			})
 
 		epfB := pframes.pFrameBuilder()