add Report.Derks2022.plexDIA.tsv

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: MsDataHub
 Title: Mass Spectrometry Data on ExperimentHub
-Version: 1.3.2
+Version: 1.3.3
 Authors@R:
     c(person(given = "Laurent",
              family = "Gatto",

NEWS.md

@@ -1,12 +1,17 @@
 # MsDataHub 1.3
 
+## MsDataHub 1.3.3
+
+- Add `Report.Derks2022.plexDIA.tsv`, plexDIA DIA-NN output from Derks
+  et al. (2022).
+
 ## MsDataHub 1.3.2
 
-- Fix path to benchmarkingDIA.tsv on zenodo.
+- Fix path to `benchmarkingDIA.tsv` on zenodo.
 
 ## MsDataHub 1.3.1
 
-- Add benchmarkingDIA data, contributed by Kristina Gomoryova.
+- Add `benchmarkingDIA.tsv` data, contributed by Kristina Gomoryova.
 
 # MsDataHub 1.0
 

R/benchmarkingDIA.R

@@ -6,7 +6,7 @@
 ##'
 ##' @description
 ##'
-##' This data were generated based on publicly available DIA
+##' These data were generated based on publicly available DIA
 ##' benchmarking dataset from Gotti et al. (2021). A subset of raw
 ##' data, containing "overlapped" in the File.Name were searched using
 ##' the DIA-NN software, and the resulting report.tsv (here labelled

R/derks2022plexDIA.R

@@ -0,0 +1,32 @@
+##' @title Derks 2022 plexDIA data
+##'
+##' @name Report.Derks2022.plexDIA.tsv
+##'
+##' @description
+##'
+##' Single cell proteomics data acquired by the Slavov Lab using the
+##' plexDIA protocol. It contains quantitative information from
+##' pancreatic ductal acinar cells (PDAC; HPAF-II), melanoma cells
+##' (WM989-A6-G3) and monocytes (U-937) at precursor and protein
+##' level. The each run acquired 3 samples thanks to mTRAQ
+##' multiplexing.
+##'
+##' The data were downloaded from the Slavov lab google drive:
+##' - https://drive.google.com/drive/folders/1pUC2zgXKtKYn22mlor0lmUDK0frgwL_-
+##' - DIANN_outputs
+##' - wJD1146_1193_1200_tsvLib
+##' - Report.tsv
+##'
+##' For more details about the data: https://plexdia.slavovlab.net/
+##'
+##' The file is reshare here allow its dissemination via the MsDataHub
+##' package.
+##'
+##' @references
+##'
+##' Derks, J., Leduc, A., Wallmann, G. et al. Increasing the
+##' throughput of sensitive proteomics by plexDIA. Nat Biotechnol
+##' (2022). 10.1038/s41587-022-01389-w.
+##'
+##' @author Laurent Gatto
+NULL

inst/extdata/metadata.csv

@@ -10,3 +10,4 @@
 "PestMix1_DDA.mzML","Triple TOF DDA raw data, in mzML format. See ?TripleTOF for details.","3.17","","mzML","https://bioconductor.org/packages/3.16/data/experiment/html/msdata.html","1.0","","","","","Laurent Gatto <[email protected]>","Spectra","FilePath","","MsDataHub/TripleTOF-SWATH/PestMix1_DDA.mzML",""
 "PestMix1_SWATH.mzML","Triple TOF SWATH raw data, in mzML format. See ?TripleTOF for details.","3.17","","mzML","https://bioconductor.org/packages/3.16/data/experiment/html/msdata.html","1.0","","","","","Laurent Gatto <[email protected]>","Spectra","FilePath","","MsDataHub/TripleTOF-SWATH/PestMix1_SWATH.mzML",""
 "benchmarkingDIA.tsv","Output of DIA-NN software (report.tsv)","3.17","","TSV","https://zenodo.org/records/8063173","1.0","Homo sapiens","9606","","","Laurent Gatto <[email protected]>","data.frame","FilePath","https://zenodo.org/","record/8063173/files/benchmarkingDIA.tsv",""
+"Report.Derks2022.plexDIA.tsv","Derk et al. (2022) single-cell proteomics plexDIA results (DIA-NN report.tsv).","3.19","","TSV","https://drive.google.com/drive/folders/1pUC2zgXKtKYn22mlor0lmUDK0frgwL_-","1.0","Homo sapiens","9606","","","Laurent Gatto <[email protected]>","data.frame","FilePath","https://zenodo.org/","records/10938597/files/Report-Derks2022-plexDIA.tsv",""

inst/scripts/make-metadata.R

@@ -18,7 +18,8 @@ metadata <-
             "20171016_POOL_POS_3_105-134.mzML",
             "PestMix1_DDA.mzML",
             "PestMix1_SWATH.mzML",
-            "benchmarkingDIA.tsv"
+            "benchmarkingDIA.tsv",
+            "Report-Derks2022-plexDIA.tsv"
         ),
         Description = c(
             "Raw metabolomics MS file in netCDF format. See ?ko15.CDF for details.",
@@ -31,9 +32,10 @@ metadata <-
             "AB Sciex LC-MS data file (injection index 19), in mzML format. See ?sciex for details.",
             "Triple TOF DDA raw data, in mzML format. See ?TripleTOF for details.",
             "Triple TOF SWATH raw data, in mzML format. See ?TripleTOF for details.",
-            "Output of DIA-NN software (report.tsv)"
+            "Output of DIA-NN software (report.tsv)",
+            "Derk et al. (2022) single-cell proteomics plexDIA results (DIA-NN report.tsv)."
             ),
-        BiocVersion = rep("3.17", 11),
+        BiocVersion = c(rep("3.17", 11), "3.19"),
         Genome = "",
         SourceType = c(
             "CDF",
@@ -46,6 +48,7 @@ metadata <-
             "mzML",
             "mzML",
             "mzML",
+            "TSV",
             "TSV"
         ),
         SourceUrl = c(
@@ -59,9 +62,10 @@ metadata <-
             "https://bioconductor.org/packages/3.16/data/experiment/html/msdata.html",
             "https://bioconductor.org/packages/3.16/data/experiment/html/msdata.html",
             "https://bioconductor.org/packages/3.16/data/experiment/html/msdata.html",
-            "https://zenodo.org/records/8063173"
+            "https://zenodo.org/records/8063173",
+            "https://drive.google.com/drive/folders/1pUC2zgXKtKYn22mlor0lmUDK0frgwL_-"
             ),
-        SourceVersion = rep("1.0", 11),
+        SourceVersion = rep("1.0", 12),
         Species = c(
             "Mus musculus",
             "Saccharomyces cerevisiae",
@@ -73,6 +77,7 @@ metadata <-
             "Homo sapiens",
             "",
             "",
+            "Homo sapiens",
             "Homo sapiens"
         ),
         TaxonomyId = c(
@@ -86,6 +91,7 @@ metadata <-
             "9606",
             "",
             "",
+            "9606",
             "9606"
         ),
         Coordinate_1_based = "",
@@ -102,6 +108,7 @@ metadata <-
             "Spectra",
             "Spectra",
             "Spectra",
+            "data.frame",
             "data.frame"
         ),
         DispatchClass = c(
@@ -115,13 +122,15 @@ metadata <-
             "FilePath",
             "FilePath",
             "FilePath",
+            "FilePath",
             "FilePath"
         ),
         ## NB: locally, the data are stored in the package's data
         ## directory, by in the Azure cloud, they are located in the
         ## package's root directory.
         Location_Prefix = c(
           rep("", times = 10),
+          "https://zenodo.org/",
           "https://zenodo.org/"
         ),
          RDataPath = c(
@@ -135,7 +144,8 @@ metadata <-
             "MsDataHub/sciex/20171016_POOL_POS_3_105-134.mzML",
             "MsDataHub/TripleTOF-SWATH/PestMix1_DDA.mzML",
             "MsDataHub/TripleTOF-SWATH/PestMix1_SWATH.mzML",
-            "record/8063173/files/benchmarkingDIA.tsv"
+            "record/8063173/files/benchmarkingDIA.tsv",
+            "records/10938597/files/Report-Derks2022-plexDIA.tsv"
         ),
         Tags = ""
     )
@@ -152,12 +162,13 @@ if (!grepl("MsDataHub/inst/scripts", getwd()))
     stop("Run from MsDataHub/inst/scripts")
 
 library(here)
-write.csv(metadata, file = here("inst", "extdata", "metadata.csv"), row.names = FALSE)
+write.csv(metadata, file = here("inst", "extdata", "metadata.csv"),
+          row.names = FALSE)
 
 # pkg_source <- file.path(ifelse(file.exists("~/wrk"), "~/wrk", "~/dev"),
 #                         "MsDataHub")
 
-pkg_source <- file.path(ifelse(file.exists("~/wrk"), "~/wrk", "~/dev"),
+pkg_source <- file.path(ifelse(file.exists("~/dev"), "~/dev", "~/wrk"),
                         "MsDataHub")
 
 stopifnot(file.exists(pkg_source))

vignettes/MsDataHub.Rmd

@@ -146,6 +146,11 @@ f <- ko15.CDF()
 Spectra(f)
 ```
 
+## DIA-NN software outputs
+
+- Label-free DIA: `benchmarkingDIA.tsv`
+- mTRAQ plexDIA: `Report.Derks2022.plexDIA.tsv`
+
 # Adding data to `MsDataHub`
 
 1. If you would like additional dataset to `MsDataHub`, start by