Abstract

Source Code

Setup

Load package

suppressPackageStartupMessages({
  library(GenomicSuperSignature)
})
## Warning: package 'GenomicSuperSignature' was built under R version 4.1.3

PCSSs

Ma et al. proposed a continuous scoring system (PCSS) based on the analysis of eight colorectal cancer microarray datasets comprising 1,867 samples, and found that PCSSs are more closely correlated to microsatellite instability (MSI), grade, stage, and tumor location.

avgLoading <- read.table("data/avg_loadings.csv", 
                         header = TRUE, sep = ",")
avgLoading <- tibble::column_to_rownames(avgLoading, var="X")
colnames(avgLoading) <- paste0("PCSS", 1:4)

head(avgLoading)
##              PCSS1        PCSS2        PCSS3         PCSS4
## A1CF  -0.018923764  0.015043200  0.016192833  0.0027314229
## A2M    0.022619204  0.016479342  0.008791011 -0.0007293910
## AAAS  -0.002700998 -0.005051213 -0.001248883  0.0037994266
## AACS  -0.002542282 -0.006858940  0.005834412  0.0058956790
## AADAC -0.003473766 -0.002360232 -0.003660762 -0.0047612188
## AAK1   0.001522205  0.005908014 -0.004708509 -0.0006853461

RAVmodel

RAVmodel <- getModel("C2", load=TRUE)
RAVmodel
## class: PCAGenomicSignatures 
## dim: 13934 4764 
## metadata(8): cluster size ... version geneSets
## assays(1): RAVindex
## rownames(13934): CASKIN1 DDX3Y ... CTC-457E21.9 AC007966.1
## rowData names(0):
## colnames(4764): RAV1 RAV2 ... RAV4763 RAV4764
## colData names(4): RAV studies silhouetteWidth gsea
## trainingData(2): PCAsummary MeSH
## trainingData names(536): DRP000987 SRP059172 ... SRP164913 SRP188526

version(RAVmodel)
## [1] "1.1.1"

RAVs vs. PCSSs

Most similar to PCSS1/2

We identified RAV1575 and RAV834 as the most similar RAVs to PCSS1 and PCSS2, respectively, based on Pearson correlation coefficient.

cg <- intersect(rownames(avgLoading), rownames(RAVmodel))
loading_cor <- abs(stats::cor(avgLoading[cg,], RAVindex(RAVmodel)[cg,], 
                              use="pairwise.complete.obs", method="pearson"))

max1 <- which.max(loading_cor[1,])  # max. correlation with PCSS1
max2 <- which.max(loading_cor[2,])  # max. correlation with PCSS2
loading_cor[1, max1, drop = FALSE]
##         RAV1575
## PCSS1 0.5894306
loading_cor[2, max2, drop = FALSE]
##          RAV834
## PCSS2 0.5624299

Session Info

sessionInfo()
## R version 4.1.2 (2021-11-01)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.3 LTS
## 
## Matrix products: default
## BLAS/LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.8.so
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats4    stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
##  [1] GenomicSuperSignature_1.3.6 SummarizedExperiment_1.24.0
##  [3] Biobase_2.54.0              GenomicRanges_1.46.1       
##  [5] GenomeInfoDb_1.30.1         IRanges_2.28.0             
##  [7] S4Vectors_0.32.3            BiocGenerics_0.40.0        
##  [9] MatrixGenerics_1.6.0        matrixStats_0.61.0         
## [11] BiocStyle_2.22.0           
## 
## loaded via a namespace (and not attached):
##  [1] bitops_1.0-7           fs_1.5.2               bit64_4.0.5           
##  [4] filelock_1.0.2         httr_1.4.2             doParallel_1.0.17     
##  [7] RColorBrewer_1.1-2     rprojroot_2.0.2        tools_4.1.2           
## [10] backports_1.4.1        bslib_0.3.1            utf8_1.2.2            
## [13] R6_2.5.1               DBI_1.1.2              colorspace_2.0-3      
## [16] GetoptLong_1.0.5       tidyselect_1.1.2       curl_4.3.2            
## [19] bit_4.0.4              compiler_4.1.2         textshaping_0.3.6     
## [22] cli_3.2.0              desc_1.4.1             DelayedArray_0.20.0   
## [25] bookdown_0.25          sass_0.4.0             scales_1.1.1          
## [28] rappdirs_0.3.3         pkgdown_2.0.2          systemfonts_1.0.4     
## [31] stringr_1.4.0          digest_0.6.29          rmarkdown_2.13        
## [34] XVector_0.34.0         pkgconfig_2.0.3        htmltools_0.5.2       
## [37] dbplyr_2.1.1           fastmap_1.1.0          rlang_1.0.2           
## [40] GlobalOptions_0.1.2    RSQLite_2.2.10         shape_1.4.6           
## [43] jquerylib_0.1.4        generics_0.1.2         jsonlite_1.8.0        
## [46] dplyr_1.0.8            car_3.0-12             RCurl_1.98-1.6        
## [49] magrittr_2.0.2         GenomeInfoDbData_1.2.7 Matrix_1.4-0          
## [52] Rcpp_1.0.8.3           munsell_0.5.0          fansi_1.0.2           
## [55] abind_1.4-5            lifecycle_1.0.1        stringi_1.7.6         
## [58] yaml_2.3.5             carData_3.0-5          zlibbioc_1.40.0       
## [61] BiocFileCache_2.2.1    blob_1.2.2             grid_4.1.2            
## [64] parallel_4.1.2         crayon_1.5.0           lattice_0.20-45       
## [67] circlize_0.4.14        knitr_1.37             ComplexHeatmap_2.10.0 
## [70] pillar_1.7.0           ggpubr_0.4.0           rjson_0.2.21          
## [73] ggsignif_0.6.3         codetools_0.2-18       glue_1.6.2            
## [76] evaluate_0.15          BiocManager_1.30.16    png_0.1-7             
## [79] vctrs_0.3.8            foreach_1.5.2          gtable_0.3.0          
## [82] purrr_0.3.4            tidyr_1.2.0            clue_0.3-60           
## [85] assertthat_0.2.1       cachem_1.0.6           ggplot2_3.3.5         
## [88] xfun_0.30              broom_0.7.12           rstatix_0.7.0         
## [91] ragg_1.2.2             tibble_3.1.6           iterators_1.0.14      
## [94] memoise_2.0.1          cluster_2.1.2          ellipsis_0.3.2