Skip to content

Commit

Permalink
Study table constructed from maes
Browse files Browse the repository at this point in the history
  • Loading branch information
@Syksy
Syksy committed Aug 4, 2023
1 parent 71c73c6 commit 90a37f3
Showing 1 changed file with 70 additions and 106 deletions.
176 changes: 70 additions & 106 deletions vignettes/overview.Rmd
View file
Original file line number Diff line number Diff line change
Expand Up @@ -54,49 +54,14 @@ Fetching all datasets available in `curatedPCaData`:
```{r message=FALSE}
library(curatedPCaData)
# Iterate over the available datasets and make them available in vignette space for the latest time stamp
mae_abida <- curatedPCaData::getPCa("abida")
mae_baca <- curatedPCaData::getPCa("baca")
mae_barbieri <- curatedPCaData::getPCa("barbieri")
mae_barwick <- curatedPCaData::getPCa("barwick")
mae_chandran <- curatedPCaData::getPCa("chandran")
mae_friedrich <- curatedPCaData::getPCa("friedrich")
mae_hieronymus <- curatedPCaData::getPCa("hieronymus")
mae_icgcca <- curatedPCaData::getPCa("icgcca")
mae_igc <- curatedPCaData::getPCa("igc")
mae_kim <- curatedPCaData::getPCa("kim")
mae_kunderfranco <- curatedPCaData::getPCa("kunderfranco")
mae_ren <- curatedPCaData::getPCa("ren")
mae_sun <- curatedPCaData::getPCa("sun")
mae_taylor <- curatedPCaData::getPCa("taylor")
mae_tcga <- curatedPCaData::getPCa("tcga")
mae_true <- curatedPCaData::getPCa("true")
mae_wallace <- curatedPCaData::getPCa("wallace")
mae_wang <- curatedPCaData::getPCa("wang")
mae_weiner <- curatedPCaData::getPCa("weiner")
# Create a list of the MAE objects for creating summary tables
maes <- list(
abida = mae_abida,
baca = mae_baca,
barbieri = mae_barbieri,
barwick = mae_barwick,
chandran = mae_chandran,
friedrich = mae_friedrich,
hieronymus = mae_hieronymus,
icgcca = mae_icgcca,
igc = mae_igc,
kim = mae_kim,
kunderfranco = mae_kunderfranco,
ren = mae_ren,
sun = mae_sun,
taylor = mae_taylor,
tcga = mae_tcga,
true = mae_true,
wallace = mae_wallace,
wang = mae_wang,
weiner = mae_weiner
)
# Use a function to extract all known study short identifiers
studies <- curatedPCaData::getPCaStudies()
studies
# List apply across studies to extract all MAE objects corresponding to the short identifiers
maes <- lapply(studies, FUN=\(id) { curatedPCaData::getPCa(id) })
names(maes) <- studies
```

## Dataset criteria
Expand All @@ -114,92 +79,91 @@ The datasets were manually selected based on various criteria, such as:
The function `getPCa` utilizes the studies' short name for identifying which data to extract. An overview into the main datasets is as follows:

```{r studies, results = 'asis', echo=FALSE}
studies <- matrix("", nrow = length(maes), ncol = 7)
colnames(studies) <- c("MAE-object", "Study short name(s)", "Sample types", "GEX/CNA/MUT platform(s)", "Notes", "Data source", "Reference(s)")
studies[, "MAE-object"] <- grep("mae_", ls(), value = TRUE)
studies[, 2] <- gsub("mae_", "", studies[, "MAE-object"])
studies <- matrix("", nrow = length(maes), ncol = 6)
colnames(studies) <- c("Study short id", "Sample types", "GEX/CNA/MUT platform(s)", "Notes", "Data source", "Reference(s)")
studies[, 1] <- curatedPCaData::getPCaStudies()
# Reformat names with special cases for abbreviations vs. names
studies[, 2] <- ifelse(studies[, 2] %in% c("tcga", "icgcca", "igc"), base::toupper(studies[, 2]), stringr::str_to_title(studies[, 2]))
for (mae in studies[, "MAE-object"]) {
w <- which(mae == studies[, "MAE-object"])
eval(parse(text = paste0("maeobj <- ", mae)))
studies[, 1] <- ifelse(studies[, 1] %in% c("tcga", "icgcca", "igc"), base::toupper(studies[, 1]), stringr::str_to_title(studies[, 1]))
for (index in 1:length(maes)) {
mae <- names(maes)[index]
maeobj <- maes[[index]]
samptypes <- table(colData(maeobj)$sample_type)
sampnames <- names(samptypes)
studies[w, "Sample types"] <- paste(paste(sampnames, samptypes, sep = ": "), collapse = ", ")
studies[index, "Sample types"] <- paste(paste(sampnames, samptypes, sep = ": "), collapse = ", ")
# Annotate additional useful information and append to correct positions
if (mae == "mae_abida") {
studies[w, "Data source"] <- "cBioPortal"
studies[w, "Reference(s)"] <- "Abida et al."
studies[index, "Data source"] <- "cBioPortal"
studies[index, "Reference(s)"] <- "Abida et al."
} else if (mae == "mae_baca") {
studies[w, "Data source"] <- "cBioPortal"
studies[w, "Reference(s)"] <- "Baca et al."
studies[index, "Data source"] <- "cBioPortal"
studies[index, "Reference(s)"] <- "Baca et al."
} else if (mae == "mae_barbieri") {
studies[w, "Data source"] <- "cBioPortal"
studies[w, "Reference(s)"] <- "Barbieri et al."
studies[index, "Data source"] <- "cBioPortal"
studies[index, "Reference(s)"] <- "Barbieri et al."
} else if (mae == "mae_barwick") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "Custom DASL"
studies[w, "Reference(s)"] <- "Barwick et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "Custom DASL"
studies[index, "Reference(s)"] <- "Barwick et al."
} else if (mae == "mae_chandran") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL8300 [HG_U95Av2]"
studies[w, "Reference(s)"] <- "Chandran et al., Yu et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL8300 [HG_U95Av2]"
studies[index, "Reference(s)"] <- "Chandran et al., Yu et al."
} else if (mae == "mae_friedrich") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "Custom Agilent array"
studies[w, "Reference(s)"] <- "Friedrich et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "Custom Agilent array"
studies[index, "Reference(s)"] <- "Friedrich et al."
} else if (mae == "mae_hieronymus") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL8737 Agilent-021529 Human CGH"
studies[w, "Notes"] <- "CNA only"
studies[w, "Reference(s)"] <- "Hieronymus et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL8737 Agilent-021529 Human CGH"
studies[index, "Notes"] <- "CNA only"
studies[index, "Reference(s)"] <- "Hieronymus et al."
} else if (mae == "mae_icgcca") {
studies[w, "Data source"] <- "ICGC Data Portal (PRAD-CA)"
studies[w, "Notes"] <- "Canadian data from International Cancer Genome Collaboratory"
studies[w, "Reference(s)"] <- "PRAD-CA in Zhang et al."
studies[index, "Data source"] <- "ICGC Data Portal (PRAD-CA)"
studies[index, "Notes"] <- "Canadian data from International Cancer Genome Collaboratory"
studies[index, "Reference(s)"] <- "PRAD-CA in Zhang et al."
} else if (mae == "mae_igc") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL570 [HG-U133_Plus_2]"
studies[w, "Reference(s)"] <- "GEO accession code GSE2109"
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL570 [HG-U133_Plus_2]"
studies[index, "Reference(s)"] <- "GEO accession code GSE2109"
} else if (mae == "mae_kim") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL5188 [HuEx-1_0-st]"
studies[w, "Reference(s)"] <- "Kim et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL5188 [HuEx-1_0-st]"
studies[index, "Reference(s)"] <- "Kim et al."
} else if (mae == "mae_kunderfranco") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL887 Agilent-012097 Human 1A Microarray (V2)"
studies[w, "Reference(s)"] <- "Kunderfranco et al., Peraldo-Neia et al., Longoni et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL887 Agilent-012097 Human 1A Microarray (V2)"
studies[index, "Reference(s)"] <- "Kunderfranco et al., Peraldo-Neia et al., Longoni et al."
} else if (mae == "mae_ren") {
studies[w, "Data source"] <- "cBioPortal"
studies[w, "Reference(s)"] <- "Ren et al."
studies[index, "Data source"] <- "cBioPortal"
studies[index, "Reference(s)"] <- "Ren et al."
} else if (mae == "mae_sun") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL96 [HG-U133A]"
studies[w, "Reference(s)"] <- "Sun et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL96 [HG-U133A]"
studies[index, "Reference(s)"] <- "Sun et al."
} else if (mae == "mae_taylor") {
studies[w, "Data source"] <- "GEO"
studies[w, "Notes"] <- "Also known as MSKCC"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GEX: GPL5188 [HuEx-1_0-st], CNA: GPL4091 Agilent CGH"
studies[w, "Reference(s)"] <- "Taylor et al."
studies[index, "Data source"] <- "GEO"
studies[index, "Notes"] <- "Also known as MSKCC"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GEX: GPL5188 [HuEx-1_0-st], CNA: GPL4091 Agilent CGH"
studies[index, "Reference(s)"] <- "Taylor et al."
} else if (mae == "mae_tcga") {
studies[w, "Data source"] <- "Xenabrowser"
studies[w, "Reference(s)"] <- "Cancer Genome Atlas Research Network, Goldman et al."
studies[index, "Data source"] <- "Xenabrowser"
studies[index, "Reference(s)"] <- "Cancer Genome Atlas Research Network, Goldman et al."
} else if (mae == "mae_true") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL3834 FHCRC Human Prostate PEDB cDNA v3 / v4"
studies[w, "Reference(s)"] <- "True et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL3834 FHCRC Human Prostate PEDB cDNA v3 / v4"
studies[index, "Reference(s)"] <- "True et al."
} else if (mae == "mae_wallace") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL571 [HG-U133A_2]"
studies[w, "Reference(s)"] <- "Wallace et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL571 [HG-U133A_2]"
studies[index, "Reference(s)"] <- "Wallace et al."
} else if (mae == "mae_wang") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL96 [HG-U133A]"
studies[w, "Reference(s)"] <- "Wang et al., Jia et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL96 [HG-U133A]"
studies[index, "Reference(s)"] <- "Wang et al., Jia et al."
} else if (mae == "mae_weiner") {
studies[w, "Data source"] <- "GEO"
studies[w, "GEX/CNA/MUT platform(s)"] <- "GPL5175 [HuEx-1_0-st]"
studies[w, "Reference(s)"] <- "Weiner et al."
studies[index, "Data source"] <- "GEO"
studies[index, "GEX/CNA/MUT platform(s)"] <- "GPL5175 [HuEx-1_0-st]"
studies[index, "Reference(s)"] <- "Weiner et al."
}
}
knitr::kable(studies, caption = "Key study characteristics")
Expand Down

0 comments on commit 90a37f3

Please sign in to comment.