library(amap)
library(RJSONIO)
library("MetaboAnalystR")
packageVersion("MetaboAnalystR")

## [1] '3.0.3'

STEP 1: Creating the mSet Object, specifying that the data to be uploaded is a compound concentration table (“conc”) and that statistical analysis will be performed (“stat”)

mSet<-InitDataObjects("conc", "stat", FALSE)

## Starting Rserve...
##  "C:\Users\julc\DOCUME~1\R\WIN-LI~1\4.0\Rserve\libs\x64\Rserve.exe" --no-save 
## [1] "MetaboAnalyst R objects initialized ..."

STEP 2: Reading in the concentration table, please set the path right first

mSet<-Read.TextData(mSet, "C:/ME-CFS/ME-CFS_MeTaQuaC_exported_data.csv", "rowu", "disc")

STEP 3: Performing data processing using MetaboAnalystR (filtering/normalization)

3.1: Performing data processing - Data checking

mSet<-SanityCheckData(mSet)

##  [1] "Successfully passed sanity check!"                                                                                
##  [2] "Samples are not paired."                                                                                          
##  [3] "2 groups were detected in samples."                                                                               
##  [4] "Only English letters, numbers, underscore, hyphen and forward slash (/) are allowed."                             
##  [5] "<font color=\"orange\">Other special characters or punctuations (if any) will be stripped off.</font>"            
##  [6] "All data values are numeric."                                                                                     
##  [7] "A total of 19 (1.2%) missing values were detected."                                                               
##  [8] "<u>By default, missing values will be replaced by 1/5 of min positive values of their corresponding variables</u>"
##  [9] "Click the <b>Skip</b> button if you accept the default practice;"                                                 
## [10] "Or click the <b>Missing value imputation</b> to use other methods."

3.2: Performing data processing - Minimum Value Replacing

Missing values will be replaced by 1/5 of min positive values of their corresponding variables

mSet<-ReplaceMin(mSet)

3.3: Performing data processing - Transformation and Scaling

“Normalization” in MetaboAnalyst implies “row-wise” normalization, which is sample-based: we don’t apply any.

Then transformation (generalized log).

Then column-wise scaling (feature-based) including Pareto.

Pareto scaling is mean-centered and divided by the square root of the SD

mSet<-PreparePrenormData(mSet)
mSet<-Normalization(mSet, "NULL", "LogNorm", "ParetoNorm", ratio=FALSE, ratioNum=20)

Visualizing (saving the figures in your work directory)

mSet<-PlotNormSummary(mSet, "norm_0_", "png", 300, width=NA)
mSet<-PlotSampleNormSummary(mSet, "snorm_0_", "png", 300, width=NA)

Saving your tables in your working directory

mSet<-SaveTransformedData(mSet)

STEP 4: Performing fold-change analysis

mSet<-FC.Anal.unpaired(mSet, 1.3, 0)
mSet<-PlotFC(mSet, "fc_0_", "png", 300, width=NA)

STEP 5: Performing t-test analysis (with FDR correction)

mSet <- Ttests.Anal(mSet, FALSE, 0.1, FALSE, TRUE, TRUE)

## [1] "A total of 0 significant features were found."

mSet <- PlotTT(mSet, "tt_0_", "png", 300, width=NA)

STEP 6: Creating a volcano plot combining the fold-change analysis to p-values WITHOUT FDR correction here.

mSet<-Volcano.Anal(mSet, FALSE, 1.3, 0, 0.75,F, 0.05, TRUE, "raw")
mSet<-PlotVolcano(mSet, "volcano_0_",1, "png", 300, width=NA)

STEP 7: Performing Principal Component Analysis (PCA)

mSet<-PCA.Anal(mSet)
mSet<-PlotPCAPairSummary(mSet, "pca_pair_0_", "png", 300, width=NA, 5)
mSet<-PlotPCAScree(mSet, "pca_scree_0_", "png", 300, width=NA, 5)
mSet<-PlotPCA2DScore(mSet, "pca_score2d_0_", "png", 300, width=NA, 1,2,0.95,0,0)
mSet<-PlotPCALoading(mSet, "pca_loading_0_", "png", 300, width=NA, 1,2);
mSet<-PlotPCABiplot(mSet, "pca_biplot_0_", "png", 300, width=NA, 1,2)
mSet<-PlotPCA3DLoading(mSet, "pca_loading3d_0_", "json", 1,2,3)

STEP 8: Visualizing data in Hierarchical Clustering Heatmaps.

8.1: full list of compounds

mSet<-PlotHeatMap(mSet, "heatmap_0_", "png", 300, width=NA, "norm", "row", "euclidean", "complete","bwm", "overview", T, T, NULL, T, F)

8.2: displaying only the 10 compounds with lowest p-values without FDR correction in the t-tests, i.e. here <0.15.

mSet<-PlotSubHeatMap(mSet, "heatmap_10comp_", "png", 300, width=NA, "norm", "row", "euclidean", "complete","bwm", "tanova", 10, "overview", T, T, T, F)

STEP 9: Creating individual boxplots for visualization of selected compounds and export as pdf

pdf(file="PC364_PC-O344_boxplots.pdf", width=10, height=5)

p1 <- ggplot2::ggplot(ft, ggplot2::aes(x = Type, y = ft[,109], color = Type)) +
    ggplot2::geom_boxplot(outlier.shape = NA) +
    ggplot2::geom_jitter(shape = 16, position = position_jitter(0.2)) +
    ggplot2::labs(y = "Concentrations in ng/mL") +
    ggplot2::labs(title = "PC(36:4)") +
    ggplot2::scale_x_discrete(labels = c(Controls = "Controls", Patients = "Patients")) +
    ggplot2::scale_colour_manual(values = c(rgb(96, 108, 158, maxColorValue = 255),
                                            rgb(193, 88, 88, maxColorValue = 255))) +
    ggplot2::theme_bw() +
    ggplot2::theme(panel.border = element_blank(), 
                   panel.grid.major = element_blank(),
                   panel.grid.minor = element_blank(), 
                   axis.line = element_line(colour = "black", size = 0.75),
                   axis.title.x = element_blank(),
                   axis.title.y = element_text(size = 20, 
                                               margin = margin(t = 0, r = 20, b = 0, l = 0)),
                   axis.text = element_text(colour = "black", size = 18),
                   plot.title = element_text(hjust = 0.5, size = 20),
                   legend.position = "none")

p2 <- ggplot2::ggplot(ft, ggplot2::aes(x = Type, y = ft[,76], color = Type)) +
    ggplot2::geom_boxplot(outlier.shape = NA) +
    ggplot2::geom_jitter(shape = 16, position = position_jitter(0.2)) +
    ggplot2::labs(y = "Concentrations in ng/mL") +
    ggplot2::labs(title = "PC-O(34:4)") +
    ggplot2::scale_x_discrete(labels = c(Controls = "Controls", Patients = "Patients")) +
    ggplot2::scale_colour_manual(values = c(rgb(96, 108, 158, maxColorValue = 255),
                                            rgb(193, 88, 88, maxColorValue = 255))) +
    ggplot2::theme_bw() +
    ggplot2::theme(panel.border = element_blank(), 
                   panel.grid.major = element_blank(),
                   panel.grid.minor = element_blank(), 
                   axis.line = element_line(colour = "black", size = 0.75),
                   axis.title.x = element_blank(),
                   axis.title.y = element_text(size = 20, 
                                               margin = margin(t = 0, r = 20, b = 0, l = 0)),
                   axis.text = element_text(colour = "black", size = 18),
                   plot.title = element_text(hjust = 0.5, size = 20),
                   legend.position = "none")

grid.arrange(p1, p2, nrow = 1)

dev.off()

## png 
##   2