update vignette following example data update

Author: Carol-seven

.Rbuildignore

@@ -4,6 +4,7 @@
 ^\.Rproj\.user$
 ^\.github$
 ^_pkgdown\.yml$
+^data-raw$
 ^docs$
 ^pkgdown$
 ^vignettes/\.quarto$

.gitignore

@@ -2,10 +2,11 @@
 .Rhistory
 .Rproj.user
 .Ruserdata
+data-raw/
+inst/extdata/20260319_DIAPlasmaProteomics_SpectronautProteinReport.csv
 inst/extdata/Toy_Scaffold_Data_old.xls
 inst/extdata/Toy_Spectronaut_Data_old.csv
 man/figures/workflow.pptx
-R/gen_data.R
 vignettes/analyze_ma.csv
 vignettes/analyze_modt.csv
 vignettes/analyze_t.csv

vignettes/analysis.qmd

@@ -62,7 +62,7 @@ If you specify `ref = "A"`, then the result includes two comparisons: "B-A" and
 
 
 ```{r}
-anlys_t <- analyze.t(dataImput, ref = "50pmol", adjust.method = "none",
+anlys_t <- analyze.t(dataImput, ref = "50fmol", adjust.method = "none",
                      saveRes = TRUE)
 ```
 
@@ -75,21 +75,21 @@ with the same value in all samples. In this case, the p-value of t-test returns
 
 
 ```{r echo=FALSE}
-cat("$`100pmol-50pmol`\n")
+cat("$`100fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_t$`100pmol-50pmol`)
+knitr::kable(anlys_t$`100fmol-50fmol`)
 ```
 </div>
 
 
 ```{r echo=FALSE}
-cat("$`200pmol-50pmol`\n")
+cat("$`200fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_t$`200pmol-50pmol`)
+knitr::kable(anlys_t$`200fmol-50fmol`)
 ```
 </div>
 
@@ -154,7 +154,7 @@ The default value `"none"` indicates that no correction is applied.
 
 
 ```{r}
-anlys_modt <- analyze.mod_t(dataImput, ref = "50pmol", adjust.method = "none",
+anlys_modt <- analyze.mod_t(dataImput, ref = "50fmol", adjust.method = "none",
                             saveRes = TRUE)
 ```
 
@@ -175,21 +175,21 @@ it merely serves to alert users to its occurrence. </div>
 
 
 ```{r echo=FALSE}
-cat("$`100pmol-50pmol`\n")
+cat("$`100fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_modt$`100pmol-50pmol`)
+knitr::kable(anlys_modt$`100fmol-50fmol`)
 ```
 </div>
 
 
 ```{r echo=FALSE}
-cat("$`200pmol-50pmol`\n")
+cat("$`200fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_modt$`200pmol-50pmol`)
+knitr::kable(anlys_modt$`200fmol-50fmol`)
 ```
 </div>
 
@@ -212,7 +212,7 @@ in the current dataset to calculate variance.
 
 
 ```{r warning=FALSE}
-anlys_wilcox <- analyze.wilcox(dataImput, ref = "50pmol", adjust.method = "none",
+anlys_wilcox <- analyze.wilcox(dataImput, ref = "50fmol", adjust.method = "none",
                                saveRes = TRUE)
 ```
 
@@ -227,21 +227,21 @@ same value, the corresponding p-value returns NaN. </div>
 
 
 ```{r echo=FALSE}
-cat("$`100pmol-50pmol`\n")
+cat("$`100fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_wilcox$`100pmol-50pmol`)
+knitr::kable(anlys_wilcox$`100fmol-50fmol`)
 ```
 </div>
 
 
 ```{r echo=FALSE}
-cat("$`200pmol-50pmol`\n")
+cat("$`200fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_wilcox$`200pmol-50pmol`)
+knitr::kable(anlys_wilcox$`200fmol-50fmol`)
 ```
 </div>
 
@@ -265,26 +265,26 @@ the same.
 
 
 ```{r}
-anlys_ma <- analyze.ma(dataImput, ref = "50pmol", saveRes = TRUE)
+anlys_ma <- analyze.ma(dataImput, ref = "50fmol", saveRes = TRUE)
 ```
 
 
 ```{r echo=FALSE}
-cat("$`100pmol-50pmol`\n")
+cat("$`100fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_ma$`100pmol-50pmol`)
+knitr::kable(anlys_ma$`100fmol-50fmol`)
 ```
 </div>
 
 
 ```{r echo=FALSE}
-cat("$`200pmol-50pmol`\n")
+cat("$`200fmol-50fmol`\n")
 ```
 <div style="overflow-x: auto;">
 ```{r echo=FALSE}
-knitr::kable(anlys_ma$`200pmol-50pmol`)
+knitr::kable(anlys_ma$`200fmol-50fmol`)
 ```
 </div>
 

vignettes/cust_vis.qmd

@@ -48,8 +48,8 @@ dataFilt <- filterNA(dataNorm, minProp = 0.51, by = "cond", saveRm = TRUE)
 ## imputation
 dataImput <- impute.min_local(dataFilt)
 ## analysis
-anlys_modt <- analyze.mod_t(dataImput, ref = "50pmol")
-anlys_ma <- analyze.ma(dataImput, ref = "50pmol")
+anlys_modt <- analyze.mod_t(dataImput, ref = "50fmol")
+anlys_ma <- analyze.ma(dataImput, ref = "50fmol")
 ```
 
 
@@ -58,7 +58,7 @@ anlys_ma <- analyze.ma(dataImput, ref = "50pmol")
 
 ```{r}
 ## default volcano
-visualize.volcano(anlys_modt$`100pmol-50pmol`, P.thres = 0.05, F.thres = 1)
+visualize.volcano(anlys_modt$`100fmol-50fmol`, P.thres = 0.05, F.thres = 1)
 ```
 
 
@@ -70,7 +70,7 @@ the volcano plot with gene or protein names, using additional information.
 
 
 ```{r message=FALSE}
-volcano <- visualize.volcano(anlys_modt$`100pmol-50pmol`,
+volcano <- visualize.volcano(anlys_modt$`100fmol-50fmol`,
                              P.thres = 0.05, F.thres = 1)
 
 ## change labels of proteins
@@ -92,7 +92,7 @@ different significance levels in the output plot.
 
 
 ```{r}
-volcano <- visualize.volcano(anlys_modt$`100pmol-50pmol`,
+volcano <- visualize.volcano(anlys_modt$`100fmol-50fmol`,
                              P.thres = 0.05, F.thres = 1)
 
 library(ggplot2)
@@ -113,7 +113,7 @@ look of the plot, including the background, gridlines, and text.
 
 
 ```{r}
-volcano <- visualize.volcano(anlys_modt$`100pmol-50pmol`,
+volcano <- visualize.volcano(anlys_modt$`100fmol-50fmol`,
                              P.thres = 0.05, F.thres = 1)
 
 library(ggplot2)
@@ -127,7 +127,7 @@ volcano + theme_classic()
 
 ```{r}
 ## default MA
-visualize.ma(anlys_ma$`100pmol-50pmol`, M.thres = 0.5)
+visualize.ma(anlys_ma$`100fmol-50fmol`, M.thres = 0.5)
 ```
 
 
@@ -139,7 +139,7 @@ names, follow these steps:
 
 
 ```{r message=FALSE}
-ma <- visualize.ma(anlys_ma$`100pmol-50pmol`, M.thres = 0.5)
+ma <- visualize.ma(anlys_ma$`100fmol-50fmol`, M.thres = 0.5)
 
 ## change labels of proteins
 library(dplyr)
@@ -160,7 +160,7 @@ modify the colors in the plot:
 
 
 ```{r}
-ma <- visualize.ma(anlys_ma$`100pmol-50pmol`, M.thres = 0.5)
+ma <- visualize.ma(anlys_ma$`100fmol-50fmol`, M.thres = 0.5)
 
 library(ggplot2)
 new <- ggplot_build(ma)
@@ -179,7 +179,7 @@ ggplot2's theme functions.
 
 
 ```{r}
-ma <- visualize.ma(anlys_ma$`100pmol-50pmol`, M.thres = 0.5)
+ma <- visualize.ma(anlys_ma$`100fmol-50fmol`, M.thres = 0.5)
 
 library(ggplot2)
  ## use a minimal theme

vignettes/preprocessing.qmd

@@ -40,8 +40,8 @@ You still need to use the function `transform()`. </div>
 
 
 ```{r}
-## if the raw data is in an .Rdata file
-load("../inst/extdata/Toy_Spectronaut_Data.RData")
+## if the raw data is in an R data file
+data("Toy_Spectronaut_Data")
 dataSet <- preprocessing(dataSet = Toy_Spectronaut_Data,
                          filterNaN = TRUE, filterUnique = 2,
                          replaceBlank = TRUE, saveRm = TRUE)
@@ -74,9 +74,11 @@ The steps below describe the operations performed during preprocessing.
 specify the `fileName` to read the raw data file into R.
 
 
-+ If the raw data is stored as an `.RData` file
-[Toy_Spectronaut_Data.RData](https://github.com/uconn-scs/msDiaLogue/blob/main/inst/extdata/Toy_Spectronaut_Data.RData),
-first load the data file directly, then specify the `dataSet` in the function.
++ If the raw data is stored in an R data file (e.g.,
+[Toy_Spectronaut_Data.rda](https://github.com/uconn-scs/msDiaLogue/blob/main/data/Toy_Spectronaut_Data.rda)
+or a `.RData` file),
+first load the data file directly, then specify the loaded object as
+the `dataSet` argument.
 
 
 ### 2. Filters out identified proteins that exhibit `NaN` quantitative values

vignettes/scaffold.qmd

@@ -170,9 +170,11 @@ Scaffold data is called `preprocessing_scaffold()`, given in the code box below.
 [Toy_Scaffold_Data.xls](https://github.com/uconn-scs/msDiaLogue/blob/main/inst/extdata/Toy_Scaffold_Data.xls),
 specify the `fileName` to read the raw data file into R.
 
-+ If the raw data is stored as an `.RData` file
-[Toy_Scaffold_Data.RData](https://github.com/uconn-scs/msDiaLogue/blob/main/inst/extdata/Toy_Scaffold_Data.RData),
-first load the data file directly, then specify the `dataSet` in the function.
++ If the raw data is stored in an  R data file (e.g.,
+[Toy_Scaffold_Data.rda](https://github.com/uconn-scs/msDiaLogue/blob/main/data/Toy_Scaffold_Data.rda)
+or a `.RData` file),
+first load the data file directly, then specify the loaded object as
+the `dataSet` argument.
 
 
 <div class="note">
@@ -197,7 +199,7 @@ dataSet <- preprocessing_scaffold(fileName = "../inst/extdata/Toy_Scaffold_Data.
 
 ```{r}
 ## if the raw data is in an .Rdata file
-load("../inst/extdata/Toy_Scaffold_Data.RData")
+data("Toy_Scaffold_Data")
 dataSet <- preprocessing_scaffold(dataSet = Toy_Scaffold_Data,
                                   zeroNA = TRUE, oneNA = TRUE)
 ```

vignettes/visualization.qmd

@@ -53,9 +53,9 @@ dataImput <- impute.min_local(dataFilt)
 ## summarization
 dataSumm <- summarize(dataImput, saveSumm = TRUE)
 ## analysis: MA
-anlys_ma <- analyze.ma(dataImput, ref = "50pmol")
+anlys_ma <- analyze.ma(dataImput, ref = "50fmol")
 ## analysis: Empirical Bayes moderated t-test
-anlys_modt <- analyze.mod_t(dataImput, ref = "50pmol", adjust.method = "none")
+anlys_modt <- analyze.mod_t(dataImput, ref = "50fmol", adjust.method = "none")
 ## analysis: PCA
 anlys_pca <- analyze.pca(dataImput, center = TRUE, scale = TRUE)
 ## analysis: PLS-DA
@@ -170,7 +170,7 @@ visualize.heatmap(dataSet, pkg = "ggplot2",
 
 
 ```{r}
-visualize.ma(anlys_ma$`100pmol-50pmol`, M.thres = 1)
+visualize.ma(anlys_ma$`100fmol-50fmol`, M.thres = 1)
 ```
 
 
@@ -266,7 +266,7 @@ visualize.target(dataImput, type = "bar", facet = FALSE,
 
 
 ```{r}
-visualize.test(anlys_modt$`100pmol-50pmol`)
+visualize.test(anlys_modt$`100fmol-50fmol`)
 ```
 
 
@@ -304,8 +304,8 @@ visualize.upset(dataSet)
 ```
 
 
-This plot reveals that 42 proteins are shared by 50pmol, 100pmol, and 200pmol,
-while only 3 proteins are shared by 100 pmol and 200pmol, but not with 50pmol.
+This plot reveals that 42 proteins are shared by 50fmol, 100fmol, and 200fmol,
+while only 3 proteins are shared by 100fmol and 200fmol, but not with 50fmol.
 
 
 ## Venn plot
@@ -328,8 +328,8 @@ representing sets in Venn plot information will be saved as a `.csv` file named
 *venn_information.csv* in the current working directory.
 
 
-In the example above, 50pmol, 100pmol, and 200pmol groups share 42 proteins.
-Notably, 3 proteins are exclusively found in the 100pmol and 200pmol groups.
+In the example above, 50fmol, 100fmol, and 200fmol groups share 42 proteins.
+Notably, 3 proteins are exclusively found in the 100fmol and 200fmol groups.
 
 
 ## Volcano plot
@@ -339,7 +339,7 @@ Notably, 3 proteins are exclusively found in the 100pmol and 200pmol groups.
 
 
 ```{r}
-visualize.volcano(anlys_modt$`100pmol-50pmol`, P.thres = 0.05, F.thres = 1)
+visualize.volcano(anlys_modt$`100fmol-50fmol`, P.thres = 0.05, F.thres = 1)
 ```