From e8cb851bb5f00d977b7edd2371e78557b87f3c92 Mon Sep 17 00:00:00 2001 From: EnesSefaAyar Date: Tue, 9 Apr 2024 14:53:46 +0200 Subject: [PATCH 1/6] petrosius_mouse: added script to make data --- inst/scripts/make-data_petrosius_mouse.R | 129 +++++++++++++++++++++++ 1 file changed, 129 insertions(+) create mode 100644 inst/scripts/make-data_petrosius_mouse.R diff --git a/inst/scripts/make-data_petrosius_mouse.R b/inst/scripts/make-data_petrosius_mouse.R new file mode 100644 index 0000000..bea2fd2 --- /dev/null +++ b/inst/scripts/make-data_petrosius_mouse.R @@ -0,0 +1,129 @@ + +####---- Petrosius et al, 2023 ---#### + + +## Petrosius, V., Aragon-Fernandez, P., Üresin, N. et al. Exploration of cell +## state heterogeneity using single-cell proteomics through sensitivity-tailored +## data-independent acquisition. Nat Commun 14, 5910 (2023). +## https://doi.org/10.1038/s41467-023-41602-1 + +library(SingleCellExperiment) +library(scp) +library(tidyverse) + +####---- Load PSM data ----#### +## The PSM data downloaded from the https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT +## and 'sample_facs.csv' from the https://zenodo.org/records/8146605 +## '20240205_111251_PEPQuant (Normal).tsv' = contains the PSM data. +## 'sample_facs.csv' = contains the cell annotations. + +root <- "~/localdata/SCP/petrosiusmESC/20240205_111248_mESC_SNEcombine_m15-m2i/" +ev <- read.delim(paste0(root, "20240205_111251_PEPQuant (Normal).tsv")) +design <- read.delim(paste0(root, "sample_facs.csv")) + +####---- Create sample annotation ----#### +design %>% + select(-X) %>% + distinct() %>% + add_column(Channel = "PEP.Quantity") %>% + rename(Set = File.Name, + SampleType = Plate) -> + meta + +## Clean quantitative data +ev %>% + rename(Set = R.FileName, + protein = PG.ProteinAccessions) %>% + ## Create a modified sequence + charge variable + mutate(peptide = paste0("_", PEP.StrippedSequence, "_.", FG.Charge)) %>% + filter(Set %in% meta$Set) -> + evproc + +## Create the QFeatures object +petrosius_mouse <- readSCP(evproc, + meta, + channelCol = "Channel", + batchCol = "Set", + removeEmptyCols = TRUE) + + +####---- Peptide data ----#### +## The peptide data downloaded from the https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT +## '20240205_111251_Peptide Quant (Normal).tsv' contains the peptide data. + +## Load the peptide level quantification data +pep_data <- read.delim(paste0(root, "20240205_111251_Peptide Quant (Normal).tsv")) + +## Clean quantitative data +pep_data %>% + pivot_wider(names_from = R.FileName, + values_from = PG.Quantity, + id_cols = c(EG.PrecursorId, PG.ProteinAccessions)) -> + peps + +## Create the SingleCellExperiment object +pep <- readSingleCellExperiment(peps, + ecol = 3:605) + +## Name rows with peptide sequence +rownames(pep) <- peps$EG.PrecursorId + +## Rename columns so they math with the PSM data +colnames(pep) %>% + paste0("PEP.Quantity") -> + colnames(pep) + +## Include the peptide data in the QFeatures object +petrosius_mouse <- addAssay(petrosius_mouse, pep, name = "peptides") + +## Link the PSMs and the peptides +petrosius_mouse <- addAssayLink(petrosius_mouse, + from = 1:603, + to = "peptides", + varFrom = rep("EG.PrecursorId", 603), + varTo = "EG.PrecursorId") + + +####---- Add the protein data ----#### +## The peptide data downloaded from the https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT +## '20240205_111251_PGQuant (Normal).tsv' contains the protein data. + +prot_data <- read.delim(paste0(root, "20240205_111251_PGQuant (Normal).tsv")) + +## Clean quantitative data +prot_data %>% + mutate(R.FileName = sub(".*rawfiles/", "", R.Raw.File.Name)) %>% + mutate(R.FileName = sub(".raw", "", R.FileName)) %>% + pivot_wider(names_from = R.FileName, + values_from = PG.Quantity, + id_cols = PG.ProteinAccessions) -> + prots + +## Create the SingleCellExperiment object +pro <- readSingleCellExperiment(prots, + ecol = 2:604) + +## Name rows with peptide sequence +rownames(pro) <- prots$PG.ProteinAccessions + +## Rename columns so they math with the PSM data +colnames(pro) %>% + paste0("PEP.Quantity") -> + colnames(pro) + +## Include the peptide data in the QFeatures object +petrosius_mouse <- addAssay(petrosius_mouse, pro, name = "proteins") + +## Link the PSMs and the peptides +petrosius_mouse <- addAssayLink(petrosius_mouse, + from = "peptides", + to = "proteins", + varFrom = "PG.ProteinAccessions", + varTo = "PG.ProteinAccessions") + +## Save data +save(petrosius_mouse, + file = file.path(paste0(root, "petrosius_mouse.Rda")), + compress = "xz", + compression_level = 9) + From 3981b6fb297cb4794714fe672af5b88f0e34cf0e Mon Sep 17 00:00:00 2001 From: EnesSefaAyar Date: Tue, 9 Apr 2024 14:54:42 +0200 Subject: [PATCH 2/6] petrosius_mouse: added documentation --- R/data.R | 129 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 129 insertions(+) diff --git a/R/data.R b/R/data.R index 5d92fa5..0320b78 100644 --- a/R/data.R +++ b/R/data.R @@ -2592,3 +2592,132 @@ ##' @keywords datasets ##' "guise2024" + +####---- petrosius_mouse ----#### + +##' Petrosius et al, 2023 (Nat. Comm.): Mouse embryonic stem cell (mESC) in +##' different culture conditions +##' +##' @description +##' Profiling mouse embryonic stem cells across ground-state (m2i) and +##' differentiation-permissive (m15) culture conditions. The data were +##' acquired using orbitrap-based data-independent acquisition (DIA). +##' The objective was to demonstrate the capability of their approach +##' by profiling mouse embryonic stem cell culture conditions, showcasing +##' heterogeneity in global proteomes, and highlighting differences in +##' the expression of key metabolic enzymes in distinct cell subclusters. +##' +##' @format A [QFeatures] object with 605 assays, each assay being a +##' [SingleCellExperiment] object: +##' +##' - Assay 1-603: PSM data acquired with a orbitrap-based data-independent +##' acquisition (DIA) protocol, hence those assays contain single column +##' that contains the quantitative information. +##' - `peptides`: peptide data containing quantitative data for 9884 +##' peptides and 603 single-cells. +##' - `proteins`: protein data containing quantitative data for 4270 +##' proteins and 603 single-cells. +##' +##' Sample annotation is stored in `colData(petrosius_mouse())`. +##' +##' @section Acquisition protocol: +##' +##' The data were acquired using the following setup. More information +##' can be found in the source article (see `References`). +##' +##' - **Sample isolation**: Cell sorting was done on a Sony MA900 cell sorter +##' using a 130 μm sorting chip. Cells were sorted at single-cell resolution, +##' into a 384-well Eppendorf LoBind PCR plate (Eppendorf AG) containing 1 μL +##' of lysis buffer. +##' - **Sample preparation**: Single-cell protein lysates were digested with +##' 2 ng of Trypsin (Sigma cat. Nr. T6567) supplied in 1 μL of digestion +##' buffer (100mM TEAB pH 8.5, 1:5000 (v/v) benzonase (Sigma cat. Nr. E1014)). +##' The digestion was carried out overnight at 37 °C, and subsequently +##' acidified by the addition of 1 μL 1% (v/v) trifluoroacetic acid (TFA). +##' All liquid dispensing was done using an I-DOT One instrument (Dispendix). +##' - **Liquid chromatography**: The Evosep one liquid chromatography system was +##' used for DIA isolation window survey and HRMS1-DIA experiments.The standard +##' 31 min or 58min pre-defined Whisper gradients were used, where peptide +##' elution is carried out with 100 nl/min flow rate. A 15 cm × 75 μm +##' ID column (PepSep) with 1.9 μm C18 beads (Dr. Maisch, Germany) and a 10 +##' μm ID silica electrospray emitter (PepSep) was used. Both LC systems were +##' coupled online to an orbitrap Eclipse TribridMass Spectrometer +##' (ThermoFisher Scientific) via an EasySpray ion source connected to a +##' FAIMSPro device. +##' - **Mass spectrometry**: The mass spectrometer was operated in positive +##' mode with the FAIMSPro interface compensation voltage set to −45 V. +##' MS1 scans were carried out at 120,000 resolution with an automatic gain +##' control (AGC) of 300% and maximum injection time set to auto. For the DIA +##' isolation window survey a scan range of 500–900 was used and 400–1000 +##' rest of the experiments. Higher energy collisional dissociation (HCD) was +##' used for precursor fragmentation with a normalized collision energy (NCE) +##' of 33% and MS2 scan AGC target was set to 1000%. +##' - **Raw data processing**: Spectronaut 16 and 17 versions were used to +##' process raw data files. DirectDIA analysis was run on pipeline mode using +##' modified BGS factory settings. Specifically, the imputation strategy was +##' set to “None” and Quantity MS level was changed to MS1. Trypsin and Lys-C +##' were selected as digestion enzymes and N-terminal protein acetylation and +##' methionine oxidation were set as variable modifications. +##' Carbamidomethylation of cysteines was set as fixed modification for +##' experiments that used diluted Hela peptides and removed when single-cell +##' runs were searched. The single-cell GPF library runs were added to +##' direct-DIA to supplement the single-cell dataset search. SILAC +##' experiments were processed in Spectronaut 16, with the Pulsar search +##' engine setting altered to accommodate multiplexed samples. Two label +##' channels were enabled and fixed Arg10 and Lys8 modifications were added +##' to the second channel. The in-Silico Generate Missing channel setting was +##' used with the workflow set to “label. +##' +##' @section Data collection: +##' +##' The data were provided by the Author and is accessible at the Dataverse +##' (https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT) +##' The folder ('20240205_111248_mESC_SNEcombine_m15-m2i/') contains the +##' following files of interest: +##' +##' - `20240205_111251_PEPQuant (Normal).tsv`: the PSM level data +##' - `20240205_111251_Peptide Quant (Normal).tsv`: the peptide level data +##' - `20240205_111251_PGQuant (Normal).tsv`: the protein level data +##' +##' The metadata downloaded from the https://zenodo.org/records/8146605. +##' +##' - `sample_facs.csv`: the metadata +##' +##' We formatted the quantification table so that columns match with the +##' metadata. Then, both tables are then combined in a single +##' [QFeatures] object using the [scp::readSCP] function. +##' +##' The peptide data were formated to a [SingleCellExperiment] object and the +##' sample metadata were matched to the column names and stored in the `colData`. +##' The object is then added to the [QFeatures] object and the rows of the PSM +##' data are linked to the rows of the peptide data based on the peptide sequence +##' information through an `AssayLink` object. +##' +##' The protein data were formated to a [SingleCellExperiment] object and +##' the sample metadata were matched to the column names and stored in the +##' `colData`. The object is then added to the [QFeatures] object and the rows +##' of the peptide data are linked to the rows of the protein data based on the +##' protein sequence information through an `AssayLink` object. +##' +##' @source +##' The peptide and protein data can be downloaded from the Dataverse +##' https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT +##' The raw data and the quantification data can also be found in the +##' MassIVE repository `MSV000092429`: +##' ftp://MSV000092429@massive.ucsd.edu/. +##' +##' @references +##' **Source article**: Petrosius, V., Aragon-Fernandez, P., Üresin, N. et al. +##' "Exploration of cell state heterogeneity using single-cell proteomics +##' through sensitivity-tailored data-independent acquisition." +##' Nat Commun 14, 5910 (2023). +##' ([link to article](https://doi.org/10.1038/s41467-023-41602-1)). +##' +##' @examples +##' \donttest{ +##' petrosius_mouse() +##' } +##' +##' @keywords datasets +##' +"petrosius_mouse" From b735cd8a0b5d1e6d699ed06ae3f74392b89a106b Mon Sep 17 00:00:00 2001 From: EnesSefaAyar Date: Tue, 9 Apr 2024 14:55:20 +0200 Subject: [PATCH 3/6] petrosius_mouse: updated metadata --- inst/extdata/metadata.csv | 1 + inst/scripts/make-metadata.R | 27 +++++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/inst/extdata/metadata.csv b/inst/extdata/metadata.csv index 7b44f60..a1274cb 100644 --- a/inst/extdata/metadata.csv +++ b/inst/extdata/metadata.csv @@ -23,3 +23,4 @@ "22","gregoire2023_mixCTRL","Single-cell proteomics data from two monocyte cell lines","3.19",NA,"TXT","https://www.ebi.ac.uk/pride/archive/projects/PXD046211",NA,"Homo sapiens",9606,TRUE,"PRIDE","Samuel Gregoire ","QFeatures","Rda","scpdata/gregoire2023_mixCTRL.Rda",2024-01-22,119,"Sage","TMT-16",TRUE,TRUE,TRUE,TRUE,NA "23","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 ","QFeatures","Rda","scpdata/khan2023.Rda",2023-12-21,47,"MaxQuant","TMTPro 16plex",TRUE,TRUE,TRUE,TRUE,NA "24","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 ","QFeatures","Rda","scpdata/guise2024.rda",2024-01-05,47,"Proteome Discoverer","LFQ",TRUE,TRUE,TRUE,TRUE,NA +"25","petrosius_mouse","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 ","QFeatures","Rda","scpdata/petrosius_mouse.Rda",2024-04-09,605,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA diff --git a/inst/scripts/make-metadata.R b/inst/scripts/make-metadata.R index 4b8d483..3ee49b0 100644 --- a/inst/scripts/make-metadata.R +++ b/inst/scripts/make-metadata.R @@ -656,6 +656,33 @@ meta <- list( ProteinsAvailable = TRUE, ContainsSingleCells = TRUE, Notes = NA_character_ + ), + data.frame( + Title = "petrosius_mouse", + Description = paste0("Mouse embryonic stem cells across ground-state (m2i) ", + "and differentiation-permissive (m15) culture conditions."), + BiocVersion = "3.19", + Genome = NA_character_, + SourceType = "TXT", + SourceUrl = "https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT", + SourceVersion = NA_character_, + Species = "Homo sapiens", + TaxonomyId = 9606, + Coordinate_1_based = TRUE, + DataProvider = "Dataverse", + Maintainer = "Enes Sefa Ayar ", + RDataClass = "QFeatures", + DispatchClass = "Rda", + RDataPath = "scpdata/petrosius_mouse.Rda", + PublicationDate = as.Date("2024/04/09"), + NumberAssays = 605, + PreprocessingSoftware = "Spectronaut", + LabelingProtocol = "LFQ", + PsmsAvailable = TRUE, + PeptidesAvailable = TRUE, + ProteinsAvailable = TRUE, + ContainsSingleCells = TRUE, + Notes = NA_character_ ) ) meta <- do.call(rbind, meta) From 8b95356e9edc95e09d163f5e47c1d58cfd21d2a6 Mon Sep 17 00:00:00 2001 From: EnesSefaAyar Date: Tue, 9 Apr 2024 15:42:00 +0200 Subject: [PATCH 4/6] review updates --- R/data.R | 37 +++++++------------ inst/extdata/metadata.csv | 2 +- ..._mouse.R => make-data_petrosius2023_mES.R} | 14 +++---- inst/scripts/make-metadata.R | 4 +- 4 files changed, 23 insertions(+), 34 deletions(-) rename inst/scripts/{make-data_petrosius_mouse.R => make-data_petrosius2023_mES.R} (91%) diff --git a/R/data.R b/R/data.R index 0320b78..6280bf7 100644 --- a/R/data.R +++ b/R/data.R @@ -2593,7 +2593,7 @@ ##' "guise2024" -####---- petrosius_mouse ----#### +####---- petrosius2023_mES ----#### ##' Petrosius et al, 2023 (Nat. Comm.): Mouse embryonic stem cell (mESC) in ##' different culture conditions @@ -2618,7 +2618,7 @@ ##' - `proteins`: protein data containing quantitative data for 4270 ##' proteins and 603 single-cells. ##' -##' Sample annotation is stored in `colData(petrosius_mouse())`. +##' Sample annotation is stored in `colData(petrosius2023_mES())`. ##' ##' @section Acquisition protocol: ##' @@ -2652,25 +2652,13 @@ ##' rest of the experiments. Higher energy collisional dissociation (HCD) was ##' used for precursor fragmentation with a normalized collision energy (NCE) ##' of 33% and MS2 scan AGC target was set to 1000%. -##' - **Raw data processing**: Spectronaut 16 and 17 versions were used to -##' process raw data files. DirectDIA analysis was run on pipeline mode using -##' modified BGS factory settings. Specifically, the imputation strategy was -##' set to “None” and Quantity MS level was changed to MS1. Trypsin and Lys-C -##' were selected as digestion enzymes and N-terminal protein acetylation and -##' methionine oxidation were set as variable modifications. -##' Carbamidomethylation of cysteines was set as fixed modification for -##' experiments that used diluted Hela peptides and removed when single-cell -##' runs were searched. The single-cell GPF library runs were added to -##' direct-DIA to supplement the single-cell dataset search. SILAC -##' experiments were processed in Spectronaut 16, with the Pulsar search -##' engine setting altered to accommodate multiplexed samples. Two label -##' channels were enabled and fixed Arg10 and Lys8 modifications were added -##' to the second channel. The in-Silico Generate Missing channel setting was -##' used with the workflow set to “label. +##' - **Raw data processing**: The mESC raw data files were processed with +##' Spectronaut 17 and protein abundance tables exported and analyzed further +##' with python. ##' ##' @section Data collection: ##' -##' The data were provided by the Author and is accessible at the Dataverse +##' The data were provided by the Author and is accessible at the [Dataverse] ##' (https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT) ##' The folder ('20240205_111248_mESC_SNEcombine_m15-m2i/') contains the ##' following files of interest: @@ -2679,13 +2667,14 @@ ##' - `20240205_111251_Peptide Quant (Normal).tsv`: the peptide level data ##' - `20240205_111251_PGQuant (Normal).tsv`: the protein level data ##' -##' The metadata downloaded from the https://zenodo.org/records/8146605. +##' The metadata downloaded from the [Zenodo +##' repository] (https://zenodo.org/records/8146605). ##' ##' - `sample_facs.csv`: the metadata ##' ##' We formatted the quantification table so that columns match with the ##' metadata. Then, both tables are then combined in a single -##' [QFeatures] object using the [scp::readSCP] function. +##' [QFeatures] object using the [scp::readSCP()] function. ##' ##' The peptide data were formated to a [SingleCellExperiment] object and the ##' sample metadata were matched to the column names and stored in the `colData`. @@ -2700,8 +2689,8 @@ ##' protein sequence information through an `AssayLink` object. ##' ##' @source -##' The peptide and protein data can be downloaded from the Dataverse -##' https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT +##' The peptide and protein data can be downloaded from the [Dataverse] +##' (https://dataverse.uclouvain.be/dataset.xhtml?persistentId=doi:10.14428/DVN/EMAVLT) ##' The raw data and the quantification data can also be found in the ##' MassIVE repository `MSV000092429`: ##' ftp://MSV000092429@massive.ucsd.edu/. @@ -2715,9 +2704,9 @@ ##' ##' @examples ##' \donttest{ -##' petrosius_mouse() +##' petrosius2023_mES() ##' } ##' ##' @keywords datasets ##' -"petrosius_mouse" +"petrosius2023_mES" diff --git a/inst/extdata/metadata.csv b/inst/extdata/metadata.csv index a1274cb..1687869 100644 --- a/inst/extdata/metadata.csv +++ b/inst/extdata/metadata.csv @@ -23,4 +23,4 @@ "22","gregoire2023_mixCTRL","Single-cell proteomics data from two monocyte cell lines","3.19",NA,"TXT","https://www.ebi.ac.uk/pride/archive/projects/PXD046211",NA,"Homo sapiens",9606,TRUE,"PRIDE","Samuel Gregoire ","QFeatures","Rda","scpdata/gregoire2023_mixCTRL.Rda",2024-01-22,119,"Sage","TMT-16",TRUE,TRUE,TRUE,TRUE,NA "23","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 ","QFeatures","Rda","scpdata/khan2023.Rda",2023-12-21,47,"MaxQuant","TMTPro 16plex",TRUE,TRUE,TRUE,TRUE,NA "24","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 ","QFeatures","Rda","scpdata/guise2024.rda",2024-01-05,47,"Proteome Discoverer","LFQ",TRUE,TRUE,TRUE,TRUE,NA -"25","petrosius_mouse","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 ","QFeatures","Rda","scpdata/petrosius_mouse.Rda",2024-04-09,605,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA +"25","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 ","QFeatures","Rda","scpdata/petrosius2023_mES.Rda",2024-04-09,605,"Spectronaut","LFQ",TRUE,TRUE,TRUE,TRUE,NA diff --git a/inst/scripts/make-data_petrosius_mouse.R b/inst/scripts/make-data_petrosius2023_mES.R similarity index 91% rename from inst/scripts/make-data_petrosius_mouse.R rename to inst/scripts/make-data_petrosius2023_mES.R index bea2fd2..6c89fb2 100644 --- a/inst/scripts/make-data_petrosius_mouse.R +++ b/inst/scripts/make-data_petrosius2023_mES.R @@ -40,7 +40,7 @@ ev %>% evproc ## Create the QFeatures object -petrosius_mouse <- readSCP(evproc, +petrosius2023_mES <- readSCP(evproc, meta, channelCol = "Channel", batchCol = "Set", @@ -74,10 +74,10 @@ colnames(pep) %>% colnames(pep) ## Include the peptide data in the QFeatures object -petrosius_mouse <- addAssay(petrosius_mouse, pep, name = "peptides") +petrosius2023_mES <- addAssay(petrosius2023_mES, pep, name = "peptides") ## Link the PSMs and the peptides -petrosius_mouse <- addAssayLink(petrosius_mouse, +petrosius2023_mES <- addAssayLink(petrosius2023_mES, from = 1:603, to = "peptides", varFrom = rep("EG.PrecursorId", 603), @@ -112,18 +112,18 @@ colnames(pro) %>% colnames(pro) ## Include the peptide data in the QFeatures object -petrosius_mouse <- addAssay(petrosius_mouse, pro, name = "proteins") +petrosius2023_mES <- addAssay(petrosius2023_mES, pro, name = "proteins") ## Link the PSMs and the peptides -petrosius_mouse <- addAssayLink(petrosius_mouse, +petrosius2023_mES <- addAssayLink(petrosius2023_mES, from = "peptides", to = "proteins", varFrom = "PG.ProteinAccessions", varTo = "PG.ProteinAccessions") ## Save data -save(petrosius_mouse, - file = file.path(paste0(root, "petrosius_mouse.Rda")), +save(petrosius2023_mES, + file = file.path(paste0(root, "petrosius2023_mES.Rda")), compress = "xz", compression_level = 9) diff --git a/inst/scripts/make-metadata.R b/inst/scripts/make-metadata.R index 3ee49b0..3f74b96 100644 --- a/inst/scripts/make-metadata.R +++ b/inst/scripts/make-metadata.R @@ -658,7 +658,7 @@ meta <- list( Notes = NA_character_ ), data.frame( - Title = "petrosius_mouse", + Title = "petrosius2023_mES", Description = paste0("Mouse embryonic stem cells across ground-state (m2i) ", "and differentiation-permissive (m15) culture conditions."), BiocVersion = "3.19", @@ -673,7 +673,7 @@ meta <- list( Maintainer = "Enes Sefa Ayar ", RDataClass = "QFeatures", DispatchClass = "Rda", - RDataPath = "scpdata/petrosius_mouse.Rda", + RDataPath = "scpdata/petrosius2023_mES.Rda", PublicationDate = as.Date("2024/04/09"), NumberAssays = 605, PreprocessingSoftware = "Spectronaut", From 01314fdee8bebfdc4a20006ff2f051eb3669e2f4 Mon Sep 17 00:00:00 2001 From: Enes Sefa Ayar <92874184+EnesSefaAyar@users.noreply.github.com> Date: Tue, 9 Apr 2024 21:16:21 +0200 Subject: [PATCH 5/6] Update R/data.R Co-authored-by: samgregoire <79509477+samgregoire@users.noreply.github.com> --- R/data.R | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/R/data.R b/R/data.R index 6280bf7..31a2a93 100644 --- a/R/data.R +++ b/R/data.R @@ -2610,7 +2610,7 @@ ##' @format A [QFeatures] object with 605 assays, each assay being a ##' [SingleCellExperiment] object: ##' -##' - Assay 1-603: PSM data acquired with a orbitrap-based data-independent +##' - Assay 1-603: PSM data acquired with an orbitrap-based data-independent ##' acquisition (DIA) protocol, hence those assays contain single column ##' that contains the quantitative information. ##' - `peptides`: peptide data containing quantitative data for 9884 From e6eb099989e2bf88f2f0c0c145b6ee7a7b2a06a5 Mon Sep 17 00:00:00 2001 From: EnesSefaAyar Date: Wed, 10 Apr 2024 11:14:29 +0200 Subject: [PATCH 6/6] minor change --- R/data.R | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/R/data.R b/R/data.R index 6280bf7..9cb8a45 100644 --- a/R/data.R +++ b/R/data.R @@ -2667,7 +2667,7 @@ ##' - `20240205_111251_Peptide Quant (Normal).tsv`: the peptide level data ##' - `20240205_111251_PGQuant (Normal).tsv`: the protein level data ##' -##' The metadata downloaded from the [Zenodo +##' The metadata were downloaded from the [Zenodo ##' repository] (https://zenodo.org/records/8146605). ##' ##' - `sample_facs.csv`: the metadata