LMSstat

Automation of statistical test with an identical data input aiming to reduce arduous work searching for packages and changing data input.

The package includes

• Simple Statistics :u-test, t-test, post hocs of Anova and Kruskal Wallis with FDR adjusted values

• Bar, Box, Dot plots with significance (u-test, t-test, post hocs of Anova and Kruskal Wallis)

• Scaling & Transformation

• Normality check (Shapiro Wilk test)

• Heatmap

• PERMANOVA

• NMDS

• PCA

Instructions

Installation

install.packages("devtools")

devtools::install_github("CHKim5/LMSstat")

library(LMSstat)

Basic structure of the Data

Used in

• Simple statistics
• Barplot, Boxplot, Dotplot
• PERMANOVA
• NMDS
• PCA
• Scaling & Transformation
• Normality check (Shapiro Wilk test)
• Heatmap

#Sample Data provided within the package

data("Data")

# Uploading your own Data

setwd("C:/Users/82102/Desktop")

Data<-read.csv("statT.csv",header = F)

The column "Multilevel" is mandatory for the code to run flawlessly.

If Multilevel is not used, fill the column with random characters

statT.csv

Used in

• PERMANOVA

#Sample Data provided within the package
data("Classification")

# Uploading your own Data
Classification<-read.csv("statT_G.csv",header = F)

statT_G.csv

Univariate statistics

Statfile<-Allstats(Data,Adjust_p_value = T, Adjust_method = "BH")

Adjustable parameters

• Adjust_p_value = T # Set True if adjustment is needed
• Adjust_method = F # Adjustment methods frequently used. c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY","fdr", "none")

head(Statfile[["Result"]]) # includes all statistical results

write.csv(Statfile[["Result"]],"p_value_result.csv")  # Write csv with all the p-value included

Plots

# Makes a subdirectory and saves boxplots for all the variables
AS_boxplot(Statfile,asterisk = "u_test") 

# Makes a subdirectory and saves dotplots for all the variables
AS_dotplot(Statfile,asterisk = "t_test") 

# Makes a subdirectory and saves barplots for all the variables
AS_barplot(Statfile,asterisk = "Scheffe") 

     AS_boxplot(Statfile)      AS_dotplot(Statfile)       AS_barplot(Statfile)

Adjustable parameters

• asterisk = "t_test" #c("Dunn","Scheffe","u_test","t_test")
• significant_variable_only = F # If set to TRUE, insignificant results will not be plotted
• color = c("#FF3300", "#FF6600", "#FFCC00", "#99CC00", "#0066CC", "#660099") # Colors for the plots
• legend_position = "none" # "none","left","right","bottom","top"
• order = NULL # Order of the groups c("LAC","LUE","WEI","SDF","HGH","ASH")
• tip_length = 0.01 # significance tip length
• label_size = 2.88 # significance label size
• step_increase = 0.05 #significance step increase
• width = 0.3 # box width ; size = 3 # dot size
• fig_width = NA #figure size
• fig_height = NA #figure size

Scaling & Transformation

scaled_data<-D_tran(Data,param = "Pareto")

Adjustable parameters

• param = "None" # "None","Auto","log10","Pareto"
• save = F #Set true if datafile is to be saved

Normality check

Result<-Norm_test(Data)

write.csv(Result,"Normality_test_Result.csv")

Heatmap

scaled_data<-D_tran(Data,param = "Auto")

AS_heatmap(scaled_data) #data inheriting from D_tran

dev.off() # Saved as PDF

Adjustable parameters

• col =c("green", "white", "red") # colors for heatmap
• col_lim = c(-3, 0, 3) # color boundaries
• reverse = T # T,F Reverse column and rows
• distance = "pearson" # Distance matrix for HCA "pearson", "manhattan","euclidean","spearman","kendall" ,
• rownames = T # T,F
• colnames = T # T,F
• Hsize = (3,6) # Width & Height c(a,b)
• g_legend = "Group" # Annotation legend title
• h_legend = "Color Key" # Heatmap legend title
• Title ="Title" # Title
• T_size = 10 # Title text size
• R_size = 3 # row text size
• C_size = 3 # column text size
• Gcol =c("ASD" = "black","HGH"="red","LAC"="blue","LUE" ="grey","SDF" = "yellow","WEI"="green") # Color for top_annotation bar
• dend_h = 0.5 #dendrite height
• a_h = 0.2 # top annotation hegiht

Multivariate statistics

PERMANOVA

data("Data")

data("Classification") 

Single factor

PERMANOVA done with the Group column

Indiv_Perm(Data) # The group information is treated as a factor

Multiple Factors

Loops PERMANOVA over different classes provided by Classification

Result<-Multi_Perm(Data,Classification) # The group information is treated as factors

Adjustable parameters

• method = Dissimilarity index c("manhattan", "euclidean", "canberra", "clark", "bray", "kulczynski", "jaccard", "gower", "altGower", "morisita", "horn", "mountford", "raup", "binomial", "chao", "cao", "mahalanobis", "chisq",chord")

NMDS

NMDS(Data,methods = c("manhattan","bray","euclidean"))

NMDS plot with bray distance and p-value from PERMANOVA

Adjustable parameters

• methods = Dissimilarity index c("manhattan", "euclidean", "canberra", "clark", "bray", "kulczynski", "jaccard", "gower", "altGower", "morisita", "horn", "mountford", "raup", "binomial", "chao", "cao", "mahalanobis", "chisq",chord")

• color = c("#FF3300", "#FF6600", "#FFCC00", "#99CC00", "#0066CC", "#660099") # Colors for the plots

• legend_position = "none" # "none","left","right","bottom","top"

• fig_width = NA #figure size

• fig_height = NA #figure size

• names = F # used to indicate sample names

• dotsize = 3 # dotsize

• labsize = 3 # label size

PCA

PCA(Data,components = c(1,2),legend_position = "none")

PCA plot with selected components

Adjustable parameters

• color = c("#FF3300", "#FF6600", "#FFCC00", "#99CC00", "#0066CC", "#660099") # Colors for the plots
• legend_position = "none" # "none","left","right","bottom","top"
• fig_width = NA #figure size
• fig_height = NA #figure size
• components = c(1,2) # selected components
• names = F # used to indicate sample names
• dotsize = 3 # dotsize
• labsize = 3 # label size