In czang97/mpred: Predict unmeasured metabolites

knitr::opts_chunk$set(echo = TRUE)
library(readr)
library(stringr)
library(tidyverse)
library(dplyr)
library(broom)
library(tibble)
library(glmnet)
library(ggformula)
library(promises)
library(mosaic)
library(ggplot2)
library(modelr)
library(tibble)
library(manipulate)
library(rlist)
library(readxl)

#install.packages("devtools")
library(devtools)
devtools::install_github("czang97/mpred")
library(roxygen2)
library(mpred)

Host dataset

#RC 12
RC12_name <- "PreprocessedData/RC12_preprocessed_20190507_142544.xlsx"  
RC12 <- read_excel(df1_name)
RC12_sheet_all <- read_excel_allsheets(df1_name)
RC12_sampleinfo <- df1_sheet_all[[2]]
#save dataframes in data folder
devtools::use_data(RC12, pkg = ".")
devtools::use_data(RC12_sampleinfo, pkg = ".")

#RC18
name <- "PreprocessedData/RC18_preprocessed_20190507_142639.xlsx"
RC18 <- read_excel(name)
sheet_all <- read_excel_allsheets(name)
RC18_sampleinfo <- sheet_all[[2]]
#save dataframes in data folder
devtools::use_data(RC18, pkg = ".")
devtools::use_data(RC18_sampleinfo, pkg = ".")

#BC tang
name <- "PreprocessedData/BCa_tang_preprocessed_20190507_142324.xlsx"
BC_tang <- read_excel(name)
sheet_all <- read_excel_allsheets(name)
BC_tang_sampleinfo <- sheet_all[[2]]
#save dataframes in data folder
devtools::use_data(BC_tang , pkg = ".")
devtools::use_data(BC_tang_sampleinfo, pkg = ".")

#BC terunuma
name <- "PreprocessedData/BCa_terunuma_preprocessed_20190507_142112.xlsx"
BC_terunuma <- read_excel(name)
sheet_all <- read_excel_allsheets(name)
BC_terunuma_sampleinfo <- sheet_all[[2]]
colnames(BC_terunuma_sampleinfo)[1]<- "SAMPLE_NAME"
#save dataframes in data folder
devtools::use_data(BC_terunuma , pkg = ".")
devtools::use_data(BC_terunuma_sampleinfo, pkg = ".")


#HCC
name <- "PreprocessedData/HCC_preprocessed_20190507_142435.xlsx"
HCC <- read_excel(name)
sheet_all <- read_excel_allsheets(name)
HCC_sampleinfo <- sheet_all[[2]]
#save dataframes in data folder
devtools::use_data(HCC , pkg = ".")
devtools::use_data(HCC_sampleinfo, pkg = ".")



#HCC
name <- "PreprocessedData/PaCa_preprocessed_20190507_142906.xlsx"
PaCa <- read_excel(name)
sheet_all <- read_excel_allsheets(name)
PaCa_sampleinfo <- sheet_all[[2]]
#save dataframes in data folder
devtools::use_data(PaCa , pkg = ".")
devtools::use_data(PaCa_sampleinfo, pkg = ".")

RC12 <- RC12
RC18 <- RC18
RC12_sampleinfo <- RC12_sampleinfo
RC18_sampleinfo <- RC18_sampleinfo


RC12_tumor <- prepare_data(df = RC12, df_sampleinfo = RC12_sampleinfo, df_sample_name = "SAMPLE_NAME", type = "tumor")

#subst data
 list <- subset_data(df1 = RC12, df1_sampleinfo = RC12_sampleinfo, df2 = RC18, df2_sampleinfo = RC18_sampleinfo, df1_sample_name = "SAMPLE_NAME",  df2_sample_name = "SAMPLE_NAME")
 RC12_tumor_match <- list[[1]]

 #tidy data
 RC18_tumor_match <- list[[2]]
 t_RC12_tumor <- df_tidy( RC12_tumor_match, standardize = "z")
 t_RC18_tumor <- df_tidy( RC18_tumor_match, standardize = "z")