UCLouvain-CBIO · lgatto · Apr 10, 2024 · Apr 10, 2024 · Apr 10, 2024 · Apr 10, 2024
diff --git a/R/data.R b/R/data.R
@@ -2711,7 +2711,7 @@
 ##'
 "petrosius2023_mES"
 
-####---- petrosius2023_AML ----####
+####---- petrosius2023_AstralAML ----####
 
 ##' Petrosius et al. 2023 (bioRxiv): AML hierarchy on Astral.
 ##'
@@ -2734,7 +2734,7 @@
 ##' - `proteins`: Protein data from the Spectronaut PGQuant file with
 ##'   LFQ quantities from the PG.Quantity column.
 ##'
-##' The `colData(petrosius2023_AML())` contains cell type annotation, batch
+##' The `colData(petrosius2023_AstralAML())` contains cell type annotation, batch
 ##' annotation and FACS data. The description of the `rowData` fields
 ##' can be found in the [`Spectronaut` user manual](https://biognosys.com/content/uploads/2023/03/Spectronaut-17_UserManual.pdf).
 ##'
@@ -2826,9 +2826,9 @@
 ##'
 ##' @examples
 ##' \donttest{
-##' petrosius2023_AML()
+##' petrosius2023_AstralAML()
 ##' }
 ##'
 ##' @keywords datasets
 ##'
-"petrosius2023_AML"
+"petrosius2023_AstralAML"
diff --git a/inst/extdata/metadata.csv b/inst/extdata/metadata.csv
@@ -24,4 +24,4 @@
 "khan2023","Single-cell proteomics data of 421 MCF-10A cells undergoing EMT triggered by TGFβ","3.19",NA,"TXT","https://drive.google.com/drive/folders/1zCsRKWNQuAz5msxx0DfjDrIe6pUjqQmj",NA,"Homo sapiens",9606,TRUE,"MassIVE","Enes Sefa Ayar <[email protected]>","QFeatures","Rda","scpdata/khan2023.Rda",2023-12-21,47,"MaxQuant","TMTPro 16plex",TRUE,TRUE,TRUE,TRUE,NA
 "guise2024","Single-cell proteomics data of 108 postmortem CTL or ALS spinal moto neurons","3.19",NA,"TXT","ftp://massive.ucsd.edu/v05/MSV000092119/",NA,"Homo sapiens",9606,TRUE,"MassIVE","Christophe Vanderaa <[email protected]>","QFeatures","Rda","scpdata/guise2024.rda",2024-01-05,47,"Proteome Discoverer","LFQ",TRUE,TRUE,TRUE,TRUE,NA
 "petrosius2023_mES","Mouse embryonic stem cells across ground-state (m2i) and differentiation-permissive (m15) culture conditions.","3.19",NA,"TXT","https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT",NA,"Homo sapiens",9606,TRUE,"Dataverse","Enes Sefa Ayar <[email protected]>","QFeatures","Rda","scpdata/petrosius2023_mES.Rda",2024-04-09,605,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA
-"petrosius2023_AML","Single-cell proteomics data of 4 cell types from the OCI-AML8227 model.","3.19",NA,"TXT","https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/4DSPJM",NA,"Homo sapiens",9606,TRUE,"Dataverse","Samuel Gregoire <[email protected]>","QFeatures","Rda","scpdata/petrosius2023.Rda",2023-06-08,217,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA
+"petrosius2023_AstralAML","Single-cell proteomics data of 4 cell types from the OCI-AML8227 model.","3.19",NA,"TXT","https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/4DSPJM",NA,"Homo sapiens",9606,TRUE,"Dataverse","Samuel Gregoire <[email protected]>","QFeatures","Rda","scpdata/petrosius2023_AstralAML.Rda",2023-06-08,217,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA
diff --git a/inst/scripts/make-data_petrosius2023_AML.R → ...ripts/make-data_petrosius2023_AstralAML.R b/inst/scripts/make-data_petrosius2023_AML.R → ...ripts/make-data_petrosius2023_AstralAML.R
@@ -4,13 +4,15 @@
 library(SingleCellExperiment)
 library(scp)
 library(tidyverse)
-dataDir <- "~/isilon/DataSets/SCPCBIO/SNEcomb_sc8227_ASTRAL/"
+dataDir <- "https://dataverse.uclouvain.be/api/access/datafile/"
 
 ####---- Create sample annotation ----####
 
 ## Retrieve annotation files
-facs <- read.csv(paste0(dataDir, "index_map.csv"))
-map <- read.csv(paste0(dataDir, "msRuns_overview.csv"), row.names = "X")
+## index_map.tab file
+facs <- read.delim(url(paste0(dataDir, "24337")))
+## msRuns_overview.csv file
+map <- read.csv(url(paste0(dataDir, "24339")), row.names = "X")
 
 ## Map FACS data with MS runs
 facs_mapped <- inner_join(map, facs, by = "Well")
@@ -33,15 +35,16 @@ colnames(meta) <- gsub("_$" , "", gsub("\\.+", "_", colnames(meta)))
 ## spectronaut
 
 ## Retrieve ID/quant file
+## '20240201_130747_PEPQuant (Normal).tsv' file
 psm <-
-  read.delim(paste0(dataDir, "20240201_130747_PEPQuant (Normal).tsv"))
+  read.delim(paste0(dataDir, "24335"))
 
 psm$fileID <- sub(".*sc8227_" , "", psm$R.FileName)
 
 colnames(psm)[colnames(psm) == "FG.MS1Quantity"] <- "quant"
 
 ## QFeatures object
-petrosius2023_AML <-
+petrosius2023_AstralAML <-
   readSCP(featureData = psm,
           colData = meta,
           batchCol = "fileID",
@@ -52,29 +55,29 @@ petrosius2023_AML <-
 
 ## Peptide data is generated by aggregation of the psm data
 
-petrosius2023_AML <-
-  aggregateFeatures(petrosius2023_AML,
-                    i = 1:length(petrosius2023_AML),
+petrosius2023_AstralAML <-
+  aggregateFeatures(petrosius2023_AstralAML,
+                    i = 1:length(petrosius2023_AstralAML),
                     fcol = "PEP.StrippedSequence",
                     fun = colMedians,
-                    name = paste0("peptide_", names(petrosius2023_AML)))
+                    name = paste0("peptide_", names(petrosius2023_AstralAML)))
 
-petrosius2023_AML <-
-  joinAssays(petrosius2023_AML,
-             i = grep("peptide", names(petrosius2023_AML)),
+petrosius2023_AstralAML <-
+  joinAssays(petrosius2023_AstralAML,
+             i = grep("peptide", names(petrosius2023_AstralAML)),
              name = "peptides")
 
-petrosius2023_AML <-
-  petrosius2023_AML[, , !grepl("peptide_", names(petrosius2023_AML))]
+petrosius2023_AstralAML <-
+  petrosius2023_AstralAML[, , !grepl("peptide_", names(petrosius2023_AstralAML))]
 
 
 ####---- Retrieve protein data ----####
 
 ## Protein data has been shared by the authors in a PGQuant file from
 ## spectronaut
-
+## 20240201_130747_PGQuant (Normal).tsv file
 prot <-
-  read.delim(paste0(dataDir, "20240201_130747_PGQuant (Normal).tsv"))
+  read.delim(paste0(dataDir, "24334"))
 
 prot$R.FileName <- sub(".*Bremen/" , "", prot$R.Raw.File.Name)
 prot$R.FileName <- sub(".raw" , "", prot$R.FileName)
@@ -97,21 +100,21 @@ prot_assay <-
                                                       colnames(prot))],
                            fnames = "PG.ProteinAccessions")
 
-## Add assay to petrosius2023_AML object
-petrosius2023_AML <-
-  addAssay(petrosius2023_AML,
+## Add assay to petrosius2023_AstralAML object
+petrosius2023_AstralAML <-
+  addAssay(petrosius2023_AstralAML,
            prot_assay,
            name = "proteins")
 
 ## Add link from peptide data to protein data
-petrosius2023_AML <- addAssayLink(petrosius2023_AML,
+petrosius2023_AstralAML <- addAssayLink(petrosius2023_AstralAML,
                               from = "peptides",
                               to = "proteins",
                               varFrom = "PG.ProteinAccessions",
                               varTo = "PG.ProteinAccessions")
 
 # Save data as Rda file
-save(petrosius2023_AML,
-     file = "~/2022-phd-samuel-gregoire/petrosius2023_AML.Rda",
+save(petrosius2023_AstralAML,
+     file = "~/2022-phd-samuel-gregoire/petrosius2023_AstralAML.Rda",
      compress = "xz",
      compression_level = 9)
diff --git a/inst/scripts/make-metadata.R b/inst/scripts/make-metadata.R
@@ -685,7 +685,7 @@ meta <- list(
         Notes = NA_character_
     ),
     data.frame(
-        Title = "petrosius2023_AML",
+        Title = "petrosius2023_AstralAML",
         Description = paste0("Single-cell proteomics data ",
                              "of 4 cell types from the OCI-AML8227 ",
                              "model."),
@@ -701,7 +701,7 @@ meta <- list(
         Maintainer = "Samuel Gregoire <[email protected]>",
         RDataClass = "QFeatures",
         DispatchClass = "Rda",
-        RDataPath = "scpdata/petrosius2023.Rda",
+        RDataPath = "scpdata/petrosius2023_AstralAML.Rda",
         PublicationDate = as.Date("2023/06/08"),
         NumberAssays = 217,
         PreprocessingSoftware = "Spectronaut",