knitr::opts_chunk$set(echo = TRUE,warning = F,message = F)
devtools::install_github("AndrewC160/ROMOPomics",force=T) #for installation reference and not run
ROMOPOmics standardizes metadata of high throughput assays with associated patient clinical data. Our package ROMOPOmics provides a framework to standardize these datasets and a pipeline to convert this information into a SQL-friendly database that is easily accessed by users. After installation of our R package from the github repository, users specify a data directory and a mask file describing how to map their data's fields into a common data model. The resulting standardized data tables are then formatted into a SQLite database for easily interoperating and sharing the dataset.
knitr::include_graphics("man/figures/romopomics_code_flow.png")
See our vignette ROMOPOmics
library(ROMOPOmics)
dm_file <- system.file("extdata","OMOP_CDM_v6_0_custom.csv",package="ROMOPOmics",mustWork = TRUE) dm <- loadDataModel(master_table_file = dm_file) tcga_files <- list( "brca_clinical" = system.file("extdata","brca_clinical.csv",package="ROMOPOmics",mustWork = TRUE), "brca_mutation" = system.file("extdata","brca_mutation.csv",package="ROMOPOmics",mustWork = TRUE) ) msks <- list(brca_clinical=loadModelMasks(system.file("extdata","brca_clinical_mask.csv",package="ROMOPOmics",mustWork = TRUE)), brca_mutation=loadModelMasks(system.file("extdata","brca_mutation_mask.csv",package="ROMOPOmics",mustWork = TRUE))) omop_inputs <- list(brca_clinical=readInputFile(input_file = tcga_files$brca_clinical, data_model = dm, mask_table = msks$brca_clinical), brca_mutation=readInputFile(input_file = tcga_files$brca_mutation, data_model = dm, mask_table = msks$brca_mutation)) db_inputs <- combineInputTables(input_table_list = omop_inputs) omop_db <- buildSQLDBR(omop_tables = db_inputs,file.path(tempdir(),"TCGA.sqlite")) DBI::dbListTables(omop_db)
dm_file <- system.file("extdata","OMOP_CDM_v6_0_custom.csv",package="ROMOPOmics",mustWork = TRUE) dm <- loadDataModel(master_table_file = dm_file) msk_file <- system.file("extdata","GSE60682_standard_mask.csv",package="ROMOPOmics",mustWork = TRUE) msks <- loadModelMasks(msk_file) in_file <- system.file("extdata","GSE60682_standard.csv",package="ROMOPOmics",mustWork = TRUE) omop_inputs <- readInputFile(input_file=in_file,data_model=dm,mask_table=msks,transpose_input_table = TRUE) db_inputs <- combineInputTables(input_table_list = omop_inputs) omop_db <- buildSQLDBR(omop_tables = db_inputs, sql_db_file=file.path(tempdir(),"GSE60682_sqlDB.sqlite")) DBI::dbListTables(omop_db)
library(Biobase) gse_ids <- c("GSE9006", "GSE26440", "GSE11504", "TABM666", "GSE6011", "GSE37721", "GSE20307", "GSE20436") stevens_gse_lst <- fetch_geo_series(gse_ids,data_dir = tempdir()) stevens_gse_lst$merged_metadata
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.