feat: support 3D data from chromeleon ascii format, v0.7.2

Author: ethanbass

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: chromConverter
 Title: Chromatographic File Converter
-Version: 0.7.1
+Version: 0.7.2
 Authors@R: c(
     person(given = "Ethan", family = "Bass", email = "ethanbass@gmail.com",
                   role = c("aut", "cre"),

NEWS.md

@@ -1,3 +1,10 @@
+## chromConverter 0.7.2
+
+* Added preliminary support for extraction of peak tables from 'Shimadzu' `.lcd` files.
+* Added support for inference of retention times from 'Shimadzu' `.lcd` files lacking `Data Item` streams.
+* Added support for raw format File Properties stream in 'Shimadzu' `.lcd` files.
+* Added support for parsing 3D data field from 'Chromeleon' ascii files.
+
 ## chromConverter 0.7.1
 
 * Fixed automatic file detection for directories (e.g., Waters `.raw` and Agilent `.D`)
@@ -10,7 +17,7 @@
 ### Major features
 
 * Added preliminary support for 'Varian Worktation' (`.sms`) format through `read_varian_sms` function.
-* Added preliminary support for 'Shimadzu QGD' GCMS files through the `read_shimadzu_qgd` function.
+* Added preliminary support for 'Shimadzu QGD' GC-MS files through the `read_shimadzu_qgd` function.
 * Added preliminary support for 'Allotrope Simple Model' (ASM) 2D chromatography date files.
 * Added support for reading multiple files from 'Agilent' `.D` directories through `read_agilent_d` function.
 * Added internal parser for 'Agilent ChemStation' MS files through `read_agilent_ms`.

R/attach_metadata.R

@@ -288,6 +288,7 @@ attach_metadata <- function(x, meta, format_in, format_out, data_format,
                                    fs::path_ext_remove(basename(source_file)),
                                    meta[["SampleInfo.smpl_name"]]),
               sample_id = get_metadata_field(meta, "SampleInfo.smpl_id"),
+              vial = get_metadata_field(meta, 'SampleInfo.smpl_vial'),
               sample_type = get_metadata_field(meta, "SampleInfo.smpl_type"),
               sample_dilution = get_metadata_field(meta, "SampleInfo.dil_factor"),
               sample_injection_volume = get_metadata_field(meta, "SampleInfo.inj_vol"),
@@ -309,52 +310,73 @@ attach_metadata <- function(x, meta, format_in, format_out, data_format,
              parser = "chromconverter",
              format_out = format_out)
     }, "chromeleon" = {
-    datetime.idx <- unlist(sapply(c("Date$", "Time$"), function(str){
-        grep(str, names(meta))
-      })
-    )
-    datetime <- unlist(meta[datetime.idx])
-    if (length(datetime > 1)){
-      datetime <- paste(datetime, collapse = " ")
-    }
-    datetime <- as.POSIXct(datetime, format = c("%m/%d/%Y %H:%M:%S",
-                                                "%d.%m.%Y %H:%M:%S",
-                                                "%m/%d/%Y %H:%M:%S %p %z"),
-                           tz = "UTC")
-    datetime <- datetime[!is.na(datetime)]
+      if (is.null(meta$`Inject Time`)){
+        datetime.idx <- unlist(sapply(c("Date$", "Time$"), function(str){
+          grep(str, names(meta))
+        })
+        )
+        datetime <- unlist(meta[datetime.idx])
+        if (length(datetime > 1)){
+          datetime <- paste(datetime, collapse = " ")
+        }
+        datetime <- as.POSIXct(datetime, format = c("%m/%d/%Y %H:%M:%S",
+                                                    "%d.%m.%Y %H:%M:%S",
+                                                    "%m/%d/%Y %H:%M:%S %p %z"),
+                               tz = "UTC")
+        datetime <- datetime[!is.na(datetime)]
+      } else {
+        datetime <- sub("(\\+\\d{2}):(\\d{2})$", "\\1\\2", meta$`Inject Time`)
+        datetime <- as.POSIXct(strptime(datetime, format = "%d/%m/%Y %H:%M:%S %z"),
+                               tz="UTC")
+
+      }
     time_interval_unit <- tryCatch({
       get_time_unit(grep("Average Step", names(meta), value = TRUE)[1],
                     format_in = "chromeleon")}, error = function(err) NA)
     time_unit <- tryCatch({
       get_time_unit(grep("Time Min.", names(meta), value = TRUE)[1],
                     format_in = "chromeleon")}, error = function(err) NA)
+    if (is.null(meta$Name) && !is.null(meta$Injection)){
+      meta$Name <- meta$Injection
+    }
+    if (is.null(meta$`Signal Unit`)){
+      unit <- grep("Signal Min", names(meta), value = TRUE)
+      unit <- sub(".*(?:\\((.*)\\)).*|.*", "\\1", unit)
+      meta$`Signal Unit` <- unit
+    }
+
     structure(x, instrument = NA,
               detector = meta$Detector,
               software = meta$`Generating Data System`,
               method = meta$`Instrument Method`,
-              batch = NA,
+              batch = meta$Sequence,
               operator = meta$`Operator`,
               run_datetime = datetime,
-              # run_date = meta$`Injection Date`,
-              # run_time = meta$`Injection Time`,
-              sample_name = ifelse(is.null(meta$Injection),
+              sample_name = ifelse(is.null(meta$Name),
                                    fs::path_ext_remove(basename(source_file)),
-                                   meta$Injection),
+                                   meta$Name),
               sample_id = NA,
-              sample_injection_volume = meta$`Injection Volume`,
-              sample_amount =  meta$`Injection Volume`,
-              time_range = c(meta$`Time Min. (min)`, meta$`Time Max. (min)`),
-              # start_time = meta$`Time Min. (min)`,
-              # end_time = meta$`Time Max. (min)`,
-              time_interval = meta[[grep("Average Step", names(meta))]],
+              vial = meta$Position,
+              sample_injection_volume = meta[[which(grepl("Volume",names(meta)))]],
+              sample_amount = NA,
+              sample_dilution = meta$`Dilution Factor`,
+              sample_type = get_metadata_field(meta, "Type"),
+              time_range = c(get_metadata_field(meta, "Time Min. (min)"),
+                             get_metadata_field(meta, "Time Max. (min)")),
+              time_interval = tryCatch({
+                meta[[grep("Average Step", names(meta))]]
+                }, error = function(err) NA),
               time_interval_unit = time_interval_unit,
               time_unit = time_unit,
-              # uniform_sampling = meta$`Min. Step (s)` == meta$`Max. Step (s)`,
-              detector_range = NA,
+              detector_range = ifelse(meta$`Spectral Field` == "3DFIELD",
+                                      c(get_metadata_field(meta, "Scan Min. (nm)"),
+                                        get_metadata_field(meta, "Scan Max. (nm)")),
+                                      NA),
               detector_y_unit = meta$`Signal Unit`,
               source_file = source_file,
               source_file_format = source_file_format,
-              source_sha1 = digest::digest(source_file, algo="sha1", file=TRUE),
+              source_sha1 = digest::digest(source_file, algo = "sha1",
+                                           file = TRUE),
               format_out = format_out,
               data_format = data_format,
               parser = "chromconverter"
@@ -698,18 +720,6 @@ read_masshunter_metadata <- function(file){
   meta_sample
 }
 
-#' @name read_chromeleon_metadata
-#' @return A list containing extracted metadata.
-#' @author Ethan Bass
-#' @noRd
-read_chromeleon_metadata <- function(x){
-  meta_fields <- grep("Information:", x)
-  meta <- do.call(rbind, strsplit(x[(meta_fields[1] + 1):(meta_fields[length(meta_fields)] - 1)], "\t"))
-  rownames(meta) <- meta[, 1]
-  meta <- as.list(meta[, -1])
-  meta
-}
-
 #' @name read_waters_metadata
 #' @param file file
 #' @return A list containing extracted metadata.

R/read_chromeleon.R

@@ -1,3 +1,4 @@
+
 #' Chromeleon ASCII reader
 #'
 #' Reads 'Thermo Fisher Chromeleon™ CDS' files into R.
@@ -15,7 +16,8 @@
 #' @author Ethan Bass
 #' @export
 
-read_chromeleon <- function(path, format_out = c("matrix", "data.frame", "data.table"),
+read_chromeleon <- function(path, format_out = c("matrix", "data.frame",
+                                                 "data.table"),
                             data_format = c("wide", "long"),
                             read_metadata = TRUE,
                             metadata_format = c("chromconverter", "raw")){
@@ -27,21 +29,29 @@ read_chromeleon <- function(path, format_out = c("matrix", "data.frame", "data.t
   xx <- readLines(path)
   xx <- remove_unicode_chars(xx)
   start <- tail(grep("Data:", xx), 1)
-  x <- read.csv(path, skip = start, sep = "\t", row.names = NULL)
-  x <- x[,-2, drop = FALSE]
-  x <- x[,colSums(is.na(x)) < nrow(x)]
-  if (any(grepl(",",as.data.frame(x)[-1, 2]))){
+  x <- read.csv(path, skip = start, sep = "\t", row.names = NULL,
+                check.names = FALSE)
+  x <- x[, -2, drop = FALSE]
+  x <- x[, colSums(is.na(x)) < nrow(x)]
+  if (any(grepl(",", as.data.frame(x)[-1, 2]))){
     decimal_separator <- ","
     x <- apply(x, 2, function(x) gsub("\\.", "", x))
     x <- apply(x, 2, function(x) gsub(",", ".", x))
   } else {
     decimal_separator <- "."
   }
   x <- apply(x, 2, as.numeric)
-  colnames(x) <- c("rt", "intensity")
+  if (ncol(x) == 2){
+    colnames(x) <- c("rt", "intensity")
+  }
   if (data_format == "wide"){
-    rownames(x) <- x[,1]
-    x <- x[, 2, drop = FALSE]
+    rownames(x) <- x[, 1]
+    x <- x[, -1, drop = FALSE]
+  }
+  if (data_format == "long" && ncol(x) > 2){
+    rownames(x) <- x[, 1]
+    x <- x[, -1, drop = FALSE]
+    x <- reshape_chrom(x, data_format = "long")
   }
   x <- convert_chrom_format(x, format_out = format_out)
   if (read_metadata){
@@ -57,3 +67,17 @@ read_chromeleon <- function(path, format_out = c("matrix", "data.frame", "data.t
   }
   x
 }
+
+#' @name read_chromeleon_metadata
+#' @return A list containing extracted metadata.
+#' @author Ethan Bass
+#' @noRd
+read_chromeleon_metadata <- function(x){
+  start <- tail(grep("Data:", x), 1)
+  meta <- strsplit(x[seq_len(start - 1)], split = '\t')
+  meta <- meta[which(sapply(meta,length) == 2)]
+  meta <- do.call(rbind, meta)
+  rownames(meta) <- meta[, 1]
+  meta <- as.list(meta[, -1])
+  meta
+}

README.md

@@ -17,17 +17,17 @@ chromConverter aims to facilitate the conversion of chromatography data from var
 
 ### Formats
 
-##### ChromConverter
+##### ChromConverter (internal parsers)
 - 'Agilent ChemStation' & 'OpenLab' `.uv` files (versions 131, 31)
 - 'Agilent ChemStation' & 'OpenLab' `.ch` files (versions 30, 130, 8, 81, 179, 181)
 - Allotrope® Simple Model (ASM) 2D chromatograms (`.asm`)
-- ÅNDI (Analytical Data Interchange) Chromatography & MS formats (`.cdf`)
+- ANDI (Analytical Data Interchange) Chromatography & MS formats (`.cdf`)
 - 'Allotrope Simple Model' (ASM) 2D chromatograms.
-- mzML (`.mzml`) & mzXML (.`mzxml`) (via RaMS).
+- mzML (`.mzml`) & mzXML (.`mzxml`) (via *RaMS*).
 - 'Shimadzu LabSolutions' ascii (`.txt`)
 - 'Shimadzu GCsolution' data files (`.gcd`)
 - 'Shimadzu GCMSsolution' data files (`.qgd`) 
-- 'Shimadzu LabSolutions'`.lcd` (*provisional support* for PDA and chromatogram streams)
+- 'Shimadzu LabSolutions'`.lcd` (*provisional support* for PDA, chromatogram, and peak table streams)
 - 'Thermo Scientific Chromeleon' ascii (`.txt`)
 - 'Varian Workstation' (`.SMS`)
 - 'Waters Empower' ascii (`.arw`)
@@ -149,15 +149,15 @@ Thermo RAW files can be converted by calling the [ThermoRawFileParser](https://g
 
 ### Further analysis
 
-For downstream analyses of chromatographic data, you can also check out my package [chromatographR](https://ethanbass.github.io/chromatographR/). For interactive visualization of chromatograms, you can check out my new package [ShinyChromViewer](https://github.com/ethanbass/ShinyChromViewer) (alpha release). There is also a vignette providing an introduction to some basic syntax for [plotting mass spectrometry data](https://ethanbass.github.io/chromConverter/articles/plot_ms.html) returned by chromConverter in various R dialects.
+For downstream analyses of chromatographic data, you can also check out my package [chromatographR](https://ethanbass.github.io/chromatographR/). For interactive visualization of chromatograms, you can check out my new package [ShinyChromViewer](https://github.com/ethanbass/ShinyChromViewer) (alpha release). There is also a vignette providing an introduction to some basic syntax for [plotting mass spectrometry data](https://ethanbass.github.io/chromConverter/articles/plot_ms.html) returned by chromConverter in various R dialects (e.g., base R, tidyverse, and data.table).
 
 ### Contributing
 
 Contributions of source code, ideas, or documentation are always welcome. Please get in touch (preferable by opening a GitHub [issue](https://github.com/ethanbass/chromatographR/issues)) to discuss any suggestions or to file a bug report. Some good reasons to file an issue:
 
 - You've found an actual bug.  
 - You're getting a cryptic error message that you don't understand.  
-- You have a file format you'd like to read that isn't currently supported by chromConverter.  (Please make sure to attach example files or a link to the files.)  
+- You have a file format you'd like to read that isn't currently supported by chromConverter.  (Please make sure to attach example files or a link to the files).  
 - There's another new feature you'd like to see implemented.  
 
 **Note: Before filing a bug report, please make sure to install the latest development version of chromConverter from GitHub**, in case your bug has already been patched. After installing the latest version, you may also need to refresh your R session to remove the older version from the cache.

inst/CITATION

@@ -5,7 +5,7 @@ bibentry(
   title    = "chromConverter: Chromatographic File Converter",
   author   = "Ethan Bass",
   year     = "2024",
-  version  = "version 0.7.1",
+  version  = "version 0.7.2",
   doi      = "10.5281/zenodo.6792521",
   url      = "https://ethanbass.github.io/chromConverter/",
   textVersion = paste("Bass, E. (2024).",