@platforma-open/milaboratories.immune-assay-data.workflow 1.6.3 → 1.7.1

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@1.6.3 build /home/runner/work/immune-assay-data/immune-assay-data/workflow
+> @platforma-open/milaboratories.immune-assay-data.workflow@1.7.1 build /home/runner/work/immune-assay-data/immune-assay-data/workflow
 > rm -rf dist && pl-tengo check && pl-tengo build
 
 Processing "src/build-outputs.tpl.tengo"...

package/CHANGELOG.md

@@ -1,5 +1,24 @@
 # @platforma-open/milaboratories.immune-assay-data.workflow
 
+## 1.7.1
+
+### Patch Changes
+
+- cc7794e: Update mmseqs binary
+
+## 1.7.0
+
+### Minor Changes
+
+- c98d8b5: - Introduce fast mode for sequence match
+  - Support XLSX file as assay data input
+
+### Patch Changes
+
+- Updated dependencies [c98d8b5]
+  - @platforma-open/milaboratories.immune-assay-data.coverage-mode-calc@1.2.0
+  - @platforma-open/milaboratories.immune-assay-data.xlsx-to-csv@1.1.0
+
 ## 1.6.3
 
 ### Patch Changes

package/package.json

@@ -1,15 +1,16 @@
 {
   "name": "@platforma-open/milaboratories.immune-assay-data.workflow",
-  "version": "1.6.3",
+  "version": "1.7.1",
   "type": "module",
   "description": "Tengo-based template",
   "dependencies": {
     "@platforma-sdk/workflow-tengo": "5.9.0",
-    "@platforma-open/soedinglab.software-mmseqs2": "^1.17.2",
+    "@platforma-open/soedinglab.software-mmseqs2": "1.18.3",
     "@platforma-open/milaboratories.immune-assay-data.prepare-fasta": "1.1.3",
     "@platforma-open/milaboratories.immune-assay-data.add-header": "1.1.3",
-    "@platforma-open/milaboratories.immune-assay-data.fasta-to-tsv": "1.1.3",
-    "@platforma-open/milaboratories.immune-assay-data.coverage-mode-calc": "1.1.3"
+    "@platforma-open/milaboratories.immune-assay-data.xlsx-to-csv": "1.1.0",
+    "@platforma-open/milaboratories.immune-assay-data.coverage-mode-calc": "1.2.0",
+    "@platforma-open/milaboratories.immune-assay-data.fasta-to-tsv": "1.1.3"
   },
   "devDependencies": {
     "@platforma-sdk/tengo-builder": "2.4.25"

package/src/build-outputs.tpl.tengo

@@ -191,7 +191,7 @@ self.body(func(inputs) {
 	cloneImportResults := xsv.importFile(
 		inputs.clonesDataTsv, "tsv", {
 			axes: [{
-				column: "query",
+				column: "target",
 				spec: inputs.datasetSpec.axesSpec[1]
 			}],
 			columns: cloneColumns,
@@ -206,11 +206,11 @@ self.body(func(inputs) {
 		inputs.bestAlignmentTsv, "tsv", {
 			axes: [
 				{
-					column: "query",
+					column: "target",
 					spec: inputs.datasetSpec.axesSpec[1]
 				},
 				{
-					column: "target",
+					column: "query",
 					spec: {
 						name: "pl7.app/vdj/assay/sequenceId",
 						type: "String",

package/src/main.tpl.tengo

@@ -21,6 +21,7 @@ prepareFastaSw := assets.importSoftware("@platforma-open/milaboratories.immune-a
 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")
+xlsxToCsvSw := assets.importSoftware("@platforma-open/milaboratories.immune-assay-data.xlsx-to-csv:main")
 
 wf.prepare(func(args){
 	bundleBuilder := wf.createPBundleBuilder()
@@ -112,7 +113,7 @@ prepareClonesTsv := func(args) {
 runTsvToFasta := func(fileTsv) {
 	e := exec.builder().
 		software(prepareFastaSw).
-		mem("16GiB").
+		mem("8GiB").
 		cpu(1).
 		addFile("input.tsv", fileTsv).
 		arg("-i").arg("input.tsv").
@@ -132,7 +133,7 @@ runTsvToFasta := func(fileTsv) {
 runFastaToTsv := func(fileFasta) {
 	e := exec.builder().
 		software(fastaToTsvSw).
-		mem("16GiB").
+		mem("8GiB").
 		cpu(1).
 		addFile("input.fasta", fileFasta).
 		arg("-i").arg("input.fasta").
@@ -142,6 +143,24 @@ runFastaToTsv := func(fileFasta) {
 	return e.run()
 }
 
+/**
+ * Convert xlsx file to csv file
+ * @param fileXlsx - xlsx file
+ * @return csv file run result
+ */
+runXlsxToCsv := func(fileXlsx) {
+	e := exec.builder().
+		software(xlsxToCsvSw).
+		mem("16GiB").
+		cpu(1).
+		addFile("input.xlsx", fileXlsx).
+		arg("-i").arg("input.xlsx").
+		arg("-o").arg("output.csv").
+		saveFile("output.csv")
+
+	return e.run()
+}
+
 wf.body(func(args) {
 	importFile := file.importFile(args.fileHandle)
 	datasetSpec := args.columns.getSpec(args.datasetRef)
@@ -187,6 +206,18 @@ wf.body(func(args) {
 		xsvType = fileNameParts[len(fileNameParts)-1]
 	}
 
+	// Use detected delimiter from UI if available (file extension may not match actual delimiter)
+	if args.detectedXsvType != undefined {
+		xsvType = args.detectedXsvType
+	}
+
+	// Handle XLSX files by converting to CSV first
+	if xsvType == "xlsx" {
+		xlsxToCsvRun := runXlsxToCsv(importFile.file)
+		importFile.file = xlsxToCsvRun.getFile("output.csv")
+		xsvType = "csv"
+	}
+
 	// Handle FASTA files by converting to TSV first
 	if xsvType == "fasta" || xsvType == "fa" {
 		fastaToTsvRun := runFastaToTsv(importFile.file)
@@ -240,7 +271,10 @@ wf.body(func(args) {
 		identityThreshold: args.settings.identity,
 		similarityType: args.settings.similarityType,
 		clonesFasta: clonesFasta,
-		assayFasta: assayFasta
+		assayFasta: assayFasta,
+		lessSensitive: args.lessSensitive,
+		mem: args.mem,
+		cpu: args.cpu
 	})
 
 	mmseqsOutput := runMmseqs.output("mmseqsOutput")
@@ -287,7 +321,7 @@ wf.body(func(args) {
 		)
 
 		cols := []
-		for _, col in ["bits", "evalue", "target", "pident", "alnlen", "mismatch", "gapopen", "qstart", "qend", "tstart", "tend"] {
+		for _, col in ["bits", "evalue", "query", "pident", "alnlen", "mismatch", "gapopen", "qstart", "qend", "tstart", "tend"] {
 			cols = append(cols,
 						pt.col(col).maxBy(
 								pt.col("evalue").multiply(-1),
@@ -296,7 +330,7 @@ wf.body(func(args) {
 						)
 		}
 		
-		df = df.groupBy("query").agg(cols...)
+		df = df.groupBy("target").agg(cols...)
 		
 		// Add link column for linker pFrame (assayLinkerPframe)
 		df = df.withColumns(
@@ -312,13 +346,13 @@ wf.body(func(args) {
 		})
 		// import how many matches per assay sequence found
 		assayDf = assayDf.join(
-			df.groupBy("target").agg(
-				pt.col("query").count().alias("queryCount")
+			df.groupBy("query").agg(
+				pt.col("target").count().alias("queryCount")
 			),
 			{
 				how: "left",
 				leftOn: "seqId",
-				rightOn: "target"
+				rightOn: "query"
 			}
 		)
 		assayDf.save("assayData.tsv")
@@ -327,7 +361,7 @@ wf.body(func(args) {
 		clonesDf := df.join(assayDf,
 			{
 				how: "left",
-				leftOn: "target",
+				leftOn: "query",
 				rightOn: "seqId"
 			}
 		)

package/src/run-alignment.tpl.tengo

@@ -16,15 +16,26 @@ self.body(func(args) {
     clonesFasta := args.clonesFasta
     assayFasta := args.assayFasta
 
+	mem := "8GiB"
+	cpu := 1
+	if !is_undefined(args.mem) {
+		mem = string(args.mem) + "GiB"
+	}
+	if !is_undefined(args.cpu) {
+		cpu = args.cpu
+	}
+
 	mmseqs := exec.builder().
 		software(mmseqsSw).
-		mem("32GiB").
-		cpu(1).
+		mem(mem).
+		cpu(cpu).
 		arg("easy-search").
-		arg("clones.fasta").
 		arg("assay.fasta").
+		arg("clones.fasta").
 		arg("results.tsv").
 		arg("tmp").
+		arg("--threads").arg(string(cpu)).
+		arg("--max-seqs").arg("10000").
 		arg("--search-type").arg(mmseqsSearchType).
 		arg("--cov-mode").arg(string(covMode)).
 		arg("-c").arg(string(coverageThreshold)).
@@ -34,6 +45,15 @@ self.body(func(args) {
 		mmseqs = mmseqs.arg("--alignment-mode").arg("3")
 	}
 
+	lessSensitive := is_undefined(args.lessSensitive) ? false : args.lessSensitive
+	if lessSensitive {
+		mmseqs = mmseqs.
+			arg("--comp-bias-corr").arg("0").
+			arg("--mask").arg("0").
+			arg("--exact-kmer-matching").arg("1").
+			arg("-k").arg("7")
+	}
+
 	mmseqs = mmseqs.
 		addFile("clones.fasta", clonesFasta).
 		addFile("assay.fasta", assayFasta).