install.packages("lilikoi")

# Or for the latest dev version:
devtools::install_github("lanagarmire/lilikoi2")

# library(lilikoi)

dt <- lilikoi.Loaddata(file=system.file("extdata", "plasma_breast_cancer.csv", package = "lilikoi"))
Metadata <- dt$Metadata
dataSet <- dt$dataSet

# Transform the metabolite names to the HMDB ids using Lilikoi MetaTOpathway function
convertResults=lilikoi.MetaTOpathway('name')
Metabolite_pathway_table = convertResults$table
head(Metabolite_pathway_table)

# Transform metabolites into pathway using pathtracer algorithm
PDSmatrix=lilikoi.PDSfun(Metabolite_pathway_table)

# Select the most signficant pathway related to phenotype.
selected_Pathways_Weka= lilikoi.featuresSelection(PDSmatrix,threshold= 0.50,method="gain")

# Machine learning
lilikoi.machine_learning(MLmatrix = Metadata, measurementLabels = Metadata$Label,
                              significantPathways = 0,
                              trainportion = 0.8, cvnum = 10, dlround=50,nrun=10, Rpart=TRUE,
                              LDA=TRUE,SVM=TRUE,RF=TRUE,GBM=TRUE,PAM=FALSE,LOG=TRUE,DL=TRUE)
                              
# Prognosis model
lilikoi.prognosis(event, time, exprdata, percent=percent, alpha=0, nfold=5, method="quantile",
          cvlambda=cvlambda,python.path=NULL,coxnnet=FALSE,coxnnet_method="gradient")
          
# Metabolites-pathway regression
lilikoi.meta_path(PDSmatrix = PDSmatrix, selected_Pathways_Weka = selected_Pathways_Weka, Metabolite_pathway_table = Metabolite_pathway_table, pathway = "Pyruvate Metabolism")

# KEGG plot
lilikoi.KEGGplot(metamat = metamat, sampleinfo = sampleinfo, grouporder = grouporder,
                 pathid = '00250', specie = 'hsa',
                 filesuffix = 'GSE16873', 
                 Metabolite_pathway_table = Metabolite_pathway_table)