gluco

Author: ofilangi

Readme.md

@@ -64,6 +64,10 @@ java -cp ./assembly/pack.jar MainDistributionMzIons
 java -cp ./assembly/pack.jar MainDistributionDiffMzIons -i 50000
 ```
 
+```bash
+java -cp ./assembly/pack.jar MainGlucosinolates src/test/resources/Orbitrap_Exploris_240_precision64.mzXML --output test.out --startRT 0   --endRT 2   --minIntensity 7500   --deltaMp0Mp2 1.9958   --carbonMin 3   --carbonMax 35   --sulfurMin 1.5   --sulfurMax 5   --precisionMz 0.0001
+```
+
 ## ammonite example
 
 ### Precursor Mz search

build.sbt

@@ -39,7 +39,7 @@ libraryDependencies ++= Seq(
   "co.fs2" %% "fs2-core" % "3.11.0",
   "co.fs2" %% "fs2-io" % "3.11.0",
   "co.fs2" %% "fs2-core" % "3.11.0",
-  "org.gnieh" %%"fs2-data-xml"%"1.11.2",
+  "org.gnieh" %%"fs2-data-xml"%"1.8.0",
   "com.github.marklister" %% "base64" % "0.3.0",
   "com.github.nscala-time" %% "nscala-time" %"3.0.0",
   "org.scala-lang.modules" %% "scala-parallel-collections" % "1.2.0",

src/main/scala/MainGlucosinolates.scala

@@ -29,34 +29,57 @@ object MainGlucosinolates extends IOApp {
 
   private val builder = OParser.builder[Config]
   private val parser1 = {
-    import builder._
-    OParser.sequence(
-      programName("MainGlucosinolates"),
-      head("MainGlucosinolates", "1.0"),
-      opt[String]('o', "output")
-        .required()
-        .action((x, c) => c.copy(outputFile = Some(x)))
-        .text("Output file"),
-      opt[Double]('s', "startRT")
-        .optional()
-        .action((x, c) => c.copy(startRT = Some(x)))
-        .text("start RT"),
-      opt[Double]('e', "endRT")
-        .optional()
-        .action((x, c) => c.copy(endRT = Some(x)))
-        .text("end RT"),
-      opt[Double]('i', "minIntensity")
-        .optional()
-        .action((x, c) => c.copy(minIntensity = x))
-        .text("Minimum intensity threshold selecting the ions of interest"),
-      arg[String]("<file>")
-        .required()
-        .action((x, c) => c.copy(mzFile = Some(x)))
-        .text("Input mzXML file"),
-      help("help").text("prints this usage text")
-    )
-  }
-
+  import builder._
+  OParser.sequence(
+    programName("MainGlucosinolates"),
+    head("MainGlucosinolates", "1.0"),
+    opt[String]('o', "output")
+      .required()
+      .action((x, c) => c.copy(outputFile = Some(x)))
+      .text("Output file"),
+    opt[Double]('s', "startRT")
+      .optional()
+      .action((x, c) => c.copy(startRT = Some(x)))
+      .text("Start retention time"),
+    opt[Double]('e', "endRT")
+      .optional()
+      .action((x, c) => c.copy(endRT = Some(x)))
+      .text("End retention time"),
+    opt[Double]('i', "minIntensity")
+      .optional()
+      .action((x, c) => c.copy(minIntensity = x))
+      .text("Minimum intensity threshold"),
+    opt[Double]("deltaMp0Mp2")
+      .optional()
+      .action((x, c) => c.copy(deltaMp0Mp2 = x))
+      .text("Delta between M0 and M2 peaks"),
+    opt[Int]("carbonMin")
+      .optional()
+      .action((x, c) => c.copy(numberCarbonMin = x))
+      .text("Minimum number of carbon atoms"),
+    opt[Int]("carbonMax")
+      .optional()
+      .action((x, c) => c.copy(numberCarbonMax = x))
+      .text("Maximum number of carbon atoms"),
+    opt[Double]("sulfurMin")
+      .optional()
+      .action((x, c) => c.copy(numberSulfurMin = x))
+      .text("Minimum number of sulfur atoms"),
+    opt[Double]("sulfurMax")
+      .optional()
+      .action((x, c) => c.copy(numberSulfurMax = x))
+      .text("Maximum number of sulfur atoms"),
+    opt[Double]("precisionMz")
+      .optional()
+      .action((x, c) => c.copy(precisionMz = x))
+      .text("Precision for m/z matching"),
+    arg[String]("<file>")
+      .required()
+      .action((x, c) => c.copy(mzFile = Some(x)))
+      .text("Input mzXML file"),
+    help("help").text("prints this usage text")
+  )
+}
   def run(args: List[String]): IO[ExitCode] = {
     OParser.parse(parser1, args, Config()) match {
       case Some(config) =>
@@ -70,6 +93,7 @@ private def processFile(config: Config): IO[Unit] = {
     mzXMLFile <- IO.fromOption(config.mzFile)(new IllegalArgumentException("Missing mzXML file"))
     startTime = config.startRT.getOrElse(0.0)
     endTime = config.endRT.getOrElse(Double.MaxValue)
+    
     processStart <- IO.realTime.map(rt => DateTime.now().plus(rt.toMillis))
     _ <- IO.println(s"Start analyze: $mzXMLFile")
 
@@ -87,7 +111,7 @@ private def processFile(config: Config): IO[Unit] = {
       .count
 
     _ <- totalSpectraRef.set(totalSpectra.toInt)
-
+    
     results <- SpectrumRequest(mzXMLFile)
       .msLevel(1)
       .filter(_.isDefined)
@@ -110,8 +134,22 @@ private def processFile(config: Config): IO[Unit] = {
 
     _ <- IO.println(s"Sorting completed. Number of results: ${sortedResults.size}")
 
-    _ <- Stream.emits(sortedResults)
-      .evalMap(result => IO.println(result.toString))
+    // CSV Header
+    csvHeader = "RetentionTime;M0_mz;M0_intensity;M1_mz;M1_intensity;M2_mz;M2_intensity"
+    
+    _ <- Stream.emits(Seq(csvHeader) ++ sortedResults)
+      .map { 
+        case header: String => header
+        case result: Product => 
+          result match {
+            case (rt: Double, ((mz0: Double, int0: Double), (mz1: Double, int1: Double), (mz2: Double, int2: Double))) =>
+              s"$rt;$mz0;$int0;$mz1;$int1;$mz2;$int2"
+            case _ => ""
+          }
+      }
+      .map(_ + "\n")
+      .through(text.utf8.encode)
+      .through(Files[IO].writeAll(Path(config.outputFile.getOrElse("output.csv"))))
       .compile
       .drain
 
@@ -122,7 +160,6 @@ private def processFile(config: Config): IO[Unit] = {
   } yield ()
 }
 
-
 private def processSpectrum(config: Config, spectrum: Spectrum): Seq[(Double, ((Double, Double), (Double, Double), (Double, Double)))] = {
     spectrum.peaks
       .filter { case (_, int0) => int0 > config.minIntensity }