This markdown file outputs the results of the HIPC ImmuneSignatures Project using the original parameters
developed by the collaborators. Interested users may re-run the full pipeline using the hipc_full_pipeline()
command with different parameters by following the prompts and seeing the different sections below for parameter
options. For example, during the raw data pre-processing step the user may select different gene annotation
methods that can affect the final results. Once the full pipeline has been run once through, you may also use
the hipc_meta_analysis()
command to re-run only the meta-analysis with different parameters.
library(ImmSigPkg) options(width = 999) knitr::opts_chunk$set(echo=FALSE, cache=FALSE, warning=FALSE, message=FALSE, tidy=TRUE, fig.height=7, fig.width=7, fig.align = "center")
# Setup initial directory structure and options for Preprocessing step studies <- c("SDY212", "SDY63", "SDY404", "SDY400", "SDY80", "SDY67") ImmSig_dir <- file.path(getwd(),"ImmSig_Analysis") dir.create(ImmSig_dir) pp_dir <- file.path(ImmSig_dir,"PreProc_Data") dir.create(path = pp_dir) hai_dir <- file.path(pp_dir,"HAI") dir.create(path = hai_dir) ge_dir <- file.path(pp_dir,"GE") dir.create(path = ge_dir) rawdata_dir <- file.path(pp_dir,"rawdata") dir.create(path = rawdata_dir) yale.anno <- "original" sdy80.anno <- "original" sdy80.norm <- FALSE
# 1. Extract and pre-process data from ImmuneSpace, ImmPort, or GEO databases for(sdy in studies){ makeGE(sdy, yale.anno = yale.anno, sdy80.anno = sdy80.anno, sdy80.norm = sdy80.norm, output_dir = ge_dir, rawdata_dir = rawdata_dir) makeHAI(sdy, output_dir = hai_dir) makeDemo(sdy, output_dir = ge_dir) }
r yale.anno
r sdy80.anno
r sdy80.norm
r ImmSig_dir
manifest = Uses the manifest available from the Illumina website which consists of all historic probeIDs. In the case of the Yale Studies, this generates complete mapping, whereas the original table has only partial mapping and the library even less.
SDY80 / CHI-nih normalization:
In the original code used to develop the manuscript, The study's rawdata from the GEO database has been log2 transformed, but is not normalized in the same was as the discovery studies (i.e. preprocessCore::normalize.quantiles). Therefore sdy80.norm is FALSE by default. However, the user may set it to TRUE and use the same normalization procedure as the other studies.
SDY212 GE data removal:
# Setup for Rds Generation (BioConductor eset) rds_dir <- file.path(ImmSig_dir, "Rds_data") dir.create(path = rds_dir)
combined_hai <- combine_hai_data(hai_dir, output_dir = rds_dir) for(sdy in studies){ make_rds(sdy, ge_dir, combined_hai, output_dir = rds_dir) }
# Setup for Meta Analyis script data("geneSetDB") FDR.cutoff <- 0.5 pvalue.cutoff <- 0.01 endPoint <- "fc_res_max_d30" adjusted <- FALSE baselineOnly <- TRUE indiv_rds <- FALSE output_dir <- "Placeholder"
yng_res_dfs <- meta_analysis(geneSetDB = geneSetDB, rds_data_dir = rds_dir, cohort = "young", FDR.cutoff = FDR.cutoff, pvalue.cutoff = pvalue.cutoff, endPoint = endPoint, adjusted = adjusted, baselineOnly = baselineOnly, indiv_rds = indiv_rds, markdown = T, output_dir = output_dir)
DT::datatable(yng_res_dfs$dsc)
DT::datatable(yng_res_dfs$val)
old_res_dfs <- meta_analysis(geneSetDB = geneSetDB, rds_data_dir = rds_dir, cohort = "old", FDR.cutoff = FDR.cutoff, pvalue.cutoff = pvalue.cutoff, endPoint = endPoint, adjusted = adjusted, baselineOnly = baselineOnly, indiv_rds = indiv_rds, markdown = T, output_dir = output_dir)
DT::datatable(old_res_dfs$dsc)
DT::datatable(old_res_dfs$val)
r FDR.cutoff
r pvalue.cutoff
r endPoint
r adjusted
r baselineOnly
r indiv_rds
Expected Input Data Types in [brackets]
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.