J. Taroni 2018

Apply the MultiPLIER (recount2) model to the two datasets prepped in 34-DIPG_data_cleaning.

Set up

`%>%` <- dplyr::`%>%`
source(file.path("util", "plier_util.R"))

Directories for this notebook

# plot and result directory setup for this notebook
plot.dir <- file.path("plots", "35")
dir.create(plot.dir, recursive = TRUE, showWarnings = FALSE)
results.dir <- file.path("results", "35")
dir.create(results.dir, recursive = TRUE, showWarnings = FALSE)

Read in data

recount2 PLIER model

recount.file <- file.path("data", "recount2_PLIER_data", 
                          "recount_PLIER_model.RDS")
recount.plier <- readRDS(recount.file)

DIPG Expression data

# we want this is matrix form, with the gene symbols as rownames
gse50021 <- readr::read_tsv(file.path("data", "expression_data", 
                                      "GSE50021_mean_agg.pcl")) %>%
  as.data.frame() %>%
  tibble::column_to_rownames("Gene") %>%
  as.matrix()
Parsed with column specification:
cols(
  .default = col_double(),
  Gene = col_character()
)
See spec(...) for full column specifications.
e.geod.file <- 
  file.path("data", "expression_data", 
            "DIPG_E-GEOD-26576_hgu133plus2_SCANfast_with_GeneSymbol.pcl")
gse26576 <- readr::read_tsv(e.geod.file) %>%
  dplyr::select(-EntrezID) %>%
  as.data.frame() %>%
  tibble::column_to_rownames("GeneSymbol") %>%
  as.matrix()
Parsed with column specification:
cols(
  .default = col_double(),
  EntrezID = col_integer(),
  GeneSymbol = col_character()
)
See spec(...) for full column specifications.

|=======================                                                                                                 |  19%    2 MB
|========================                                                                                                |  20%    2 MB
|==========================                                                                                              |  21%    2 MB
|===========================                                                                                             |  22%    2 MB
|=============================                                                                                           |  24%    2 MB
|==============================                                                                                          |  25%    3 MB
|================================                                                                                        |  26%    3 MB
|=================================                                                                                       |  28%    3 MB
|===================================                                                                                     |  29%    3 MB
|=====================================                                                                                   |  30%    3 MB
|======================================                                                                                  |  31%    3 MB
|========================================                                                                                |  33%    3 MB
|=========================================                                                                               |  34%    4 MB
|===========================================                                                                             |  35%    4 MB
|============================================                                                                            |  36%    4 MB
|==============================================                                                                          |  38%    4 MB
|===============================================                                                                         |  39%    4 MB
|=================================================                                                                       |  40%    4 MB
|==================================================                                                                      |  41%    5 MB
|====================================================                                                                    |  43%    5 MB
|=====================================================                                                                   |  44%    5 MB
|=======================================================                                                                 |  45%    5 MB
|========================================================                                                                |  46%    5 MB
|==========================================================                                                              |  48%    5 MB
|===========================================================                                                             |  49%    5 MB
|=============================================================                                                           |  50%    6 MB
|==============================================================                                                          |  52%    6 MB
|================================================================                                                        |  53%    6 MB
|==================================================================                                                      |  54%    6 MB
|===================================================================                                                     |  55%    6 MB
|=====================================================================                                                   |  57%    6 MB
|======================================================================                                                  |  58%    7 MB
|========================================================================                                                |  59%    7 MB
|=========================================================================                                               |  60%    7 MB
|===========================================================================                                             |  62%    7 MB
|============================================================================                                            |  63%    7 MB
|==============================================================================                                          |  64%    7 MB
|===============================================================================                                         |  65%    7 MB
|=================================================================================                                       |  67%    8 MB
|==================================================================================                                      |  68%    8 MB
|====================================================================================                                    |  69%    8 MB
|=====================================================================================                                   |  70%    8 MB
|=======================================================================================                                 |  72%    8 MB
|========================================================================================                                |  73%    8 MB
|==========================================================================================                              |  74%    8 MB
|===========================================================================================                             |  75%    9 MB
|=============================================================================================                           |  77%    9 MB
|==============================================================================================                          |  78%    9 MB
|================================================================================================                        |  79%    9 MB
|=================================================================================================                       |  80%    9 MB
|===================================================================================================                     |  82%    9 MB
|====================================================================================================                    |  83%   10 MB
|======================================================================================================                  |  84%   10 MB
|=======================================================================================================                 |  85%   10 MB
|=========================================================================================================               |  87%   10 MB
|==========================================================================================================              |  88%   10 MB
|============================================================================================================            |  89%   10 MB
|=============================================================================================================           |  90%   10 MB
|===============================================================================================================         |  92%   11 MB
|================================================================================================================        |  93%   11 MB
|==================================================================================================================      |  94%   11 MB
|====================================================================================================================    |  95%   11 MB
|=====================================================================================================================   |  97%   11 MB
|======================================================================================================================= |  98%   11 MB
|========================================================================================================================|  99%   12 MB
|=========================================================================================================================| 100%   12 MB

Apply the model

GSE50021

gse50021.b <- GetNewDataB(exprs.mat = gse50021,
                          plier.model = recount.plier)
Loading required package: PLIER
Loading required package: RColorBrewer
Loading required package: gplots

Attaching package: ‘gplots’

The following object is masked from ‘package:stats’:

    lowess

Loading required package: pheatmap
Loading required package: glmnet
Loading required package: Matrix
Loading required package: foreach
Loaded glmnet 2.0-13

Loading required package: knitr
Loading required package: rsvd
Loading required package: qvalue

Save the B matrix to file

saveRDS(gse50021.b, file = file.path(results.dir, "GSE50021_recount2_B.RDS"))

E-GEOD-26576

Now the next expression dataset

gse26576.b <- GetNewDataB(exprs.mat = gse26576,
                          plier.model = recount.plier)

Save to file

saveRDS(gse26576.b, file = file.path(results.dir, 
                                     "E-GEOD-26576_recount2_B.RDS"))
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