Calculate Test Data PCs from Training-Data Estimated Loadings

Given a list of loading vectors from a training data set, calculate the PCs of the test data set.

LoadOntoPCs(design_df, loadings_ls, sampleID = c("firstCol", "rowNames"))

Arguments

design_df	A test data frame with rows as samples and named features as columns
loadings_ls	A list of \(p \times d\) loading vectors or matrices as returned by either the SuperPCA_pVals, AESPCA_pVals, or ExtractAESPCs functions. These lists of loadings will have feature names as their row names. Such feature names must match a subset of the column names of design_df exactly, as pathway-specific test-data subsetting is performed by column name.
sampleID	Are the sample IDs in the first column of design_df or in accessible by rownames(design_df)? Defaults to the first column. If your data does not have sample IDs for some reason, set this to rowNames.

Value

A data frame with the PCs from each pathway concatenated by column. If you have the tidyverse loaded, this object will display as a tibble.

Details

This function takes in a list of loadings and a training-centered test data set, applies over the list of loadings, subsets the columns of the test data by the row names of the loading vectors, right-multiplies the test-data subset matrix by the loading vector / matrix, and returns a data frame of the test-data PCs for each loading vector.

Examples

  ###  Load the Data  ###
  data("colonSurv_df")
  data("colon_pathwayCollection")

  ###  Create -Omics Container  ###
  colon_Omics <- CreateOmics(
    assayData_df = colonSurv_df[, -(2:3)],
    pathwayCollection_ls = colon_pathwayCollection,
    response = colonSurv_df[, 1:3],
    respType = "survival"
  )
#> 
#>   ======  Creating object of class OmicsSurv  =======
#> The input pathway database included 676 unique features.
#> The input assay dataset included 656 features.
#> Only pathways with at least 3 or more features included in the assay dataset are
#>   tested (specified by minPathSize parameter). There are 15 pathways which meet
#>   this criterion.
#> Because pathwayPCA is a self-contained test (PMID: 17303618), only features in
#>   both assay data and pathway database are considered for analysis. There are 615
#>   such features shared by the input assay and pathway database.

  ###  Extract AESPCs  ###
  colonSurv_aespc <- AESPCA_pVals(
    object = colon_Omics,
    numReps = 0,
    parallel = TRUE,
    numCores = 2,
    adjustpValues = TRUE,
    adjustment = c("Hoch", "SidakSD")
  )
#> Part 1: Calculate Pathway AES-PCs
#> Initializing Computing Cluster: 
#> DONE
#> Extracting Pathway PCs in Parallel: 
#> DONE
#> 
#> Part 2: Calculate Pathway p-Values
#> Initializing Computing Cluster: 
#> DONE
#> Extracting Pathway p-Values in Parallel: 
#> DONE
#> 
#> Part 3: Adjusting p-Values and Sorting Pathway p-Value Data Frame
#> DONE

  ###  Project Data onto Pathway First PCs  ###
  LoadOntoPCs(
    design_df = colonSurv_df,
    loadings_ls = colonSurv_aespc$loadings_ls
  )
#> # A tibble: 250 x 16
#>    SampleID pathway757 pathway491 pathway781 pathway1211 pathway536 pathway60
#>    <chr>         <dbl>      <dbl>      <dbl>       <dbl>      <dbl>     <dbl>
#>  1 subj1          3.82      -21.0       15.3       1.86        15.6      26.9
#>  2 subj2          3.00      -20.8       15.8       0.814       16.0      27.8
#>  3 subj3          2.84      -21.7       17.5       0.896       17.1      25.4
#>  4 subj4          4.68      -19.2       12.1       2.77        14.4      28.0
#>  5 subj5          4.12      -21.4       15.6       2.24        16.9      27.6
#>  6 subj6          3.92      -20.0       14.6       1.85        16.1      26.1
#>  7 subj7          4.50      -19.7       13.9       2.47        14.3      26.8
#>  8 subj8          3.65      -21.2       16.2       1.83        16.1      26.0
#>  9 subj9          3.35      -20.8       15.3       1.39        15.3      25.6
#> 10 subj10         4.58      -20.0       15.4       2.64        15.2      26.2
#> # … with 240 more rows, and 9 more variables: pathway87 <dbl>, pathway3 <dbl>,
#> #   pathway187 <dbl>, pathway120 <dbl>, pathway413 <dbl>, pathway390 <dbl>,
#> #   pathway266 <dbl>, pathway176 <dbl>, pathway177 <dbl>