Define species

Repeat tests across various common model organisms.

species <- c(human="H sapiens",
             chimp="P troglodytes",
             baboon="P anubis", 
             macaque = "M mulatta",
             marmoset = "C jacchus",
             mouse = "M musculus",
             rat = "R norvegicus",
             hamster = "M auratus",
             dog = "C lupus familiaris",
             cat = "F catus",
             cow = "B taurus",
             chicken = "G gallus",
             zebrafish = "D rerio",
             fly = "D melanogaster",
             worm = "C elegans",
             rice = "O sativa"
             )
species_mapped <- map_species(species = species) %>% `names<-`(names(species))

## Using stored `gprofiler_orgs`.

## Mapping species name: H sapiens

## 1 organism identified from search: hsapiens

## Mapping species name: P troglodytes

## 1 organism identified from search: ptroglodytes

## Mapping species name: P anubis

## 1 organism identified from search: panubis

## Mapping species name: M mulatta

## 1 organism identified from search: mmulatta

## Mapping species name: C jacchus

## 1 organism identified from search: cjacchus

## Mapping species name: M musculus

## 1 organism identified from search: mmusculus

## Mapping species name: R norvegicus

## 1 organism identified from search: rnorvegicus

## Mapping species name: M auratus

## 1 organism identified from search: mauratus

## Mapping species name: C lupus familiaris

## 1 organism identified from search: clfamiliaris

## Mapping species name: F catus

## 1 organism identified from search: fcatus

## Mapping species name: B taurus

## 1 organism identified from search: btaurus

## Mapping species name: G gallus

## 1 organism identified from search: ggallus

## Mapping species name: D rerio

## 1 organism identified from search: drerio

## Mapping species name: D melanogaster

## 1 organism identified from search: dmelanogaster

## Mapping species name: C elegans

## 1 organism identified from search: celegans

## Mapping species name: O sativa

## 1 organism identified from search: osativa

Benchmark

Note the orthogene:::function notation is needed to use these benchmarking functions, as they are internal.

Run benchmark

run_benchmark() will run the full benchmarking pipeline.

You can set mc.cores to speed this up with multi-core parallelisation.

WARNING: This step can take a long time. For the purposes of this example, we’ll not run the full benchmark and instead provide some pre-computed results.

bench_res <- orthogene:::run_benchmark(species_mapped = species_mapped[c("human","mouse","fly")], 
                                       run_convert_orthologs = TRUE, 
                                       mc.cores = 10) 
# write.csv(bench_res, here::here("inst/benchmark/bench_res_example.csv"), row.names = FALSE)

Print results

Load stored benchmark results.

if(!exists("bench_res")) {
  bench_res <- read.csv(system.file(package = "orthogene","benchmark/bench_res_example.csv"))
}
knitr::kable(bench_res)

species	method	test	time	genes
hsapiens	homologene	all_genes()	0.4597051	19129
hsapiens	homologene	convert_orthologs()	0.7699881	18713
hsapiens	gprofiler	all_genes()	8.6186595	39357
hsapiens	gprofiler	convert_orthologs()	134.0899084	1
mmusculus	homologene	all_genes()	0.4631681	21207
mmusculus	homologene	convert_orthologs()	0.8222713	16482
mmusculus	gprofiler	all_genes()	10.9749143	53725
mmusculus	gprofiler	convert_orthologs()	146.1204503	16189
dmelanogaster	homologene	all_genes()	0.4492853	8437
dmelanogaster	homologene	convert_orthologs()	0.7071683	4059
dmelanogaster	gprofiler	all_genes()	6.1289411	4493
dmelanogaster	gprofiler	convert_orthologs()	5.2325366	638

Plot results

Bar plot

For each method, plot the run time (a) and the number of genes returned (b).

bench_barplot <- orthogene:::plot_benchmark_bar(bench_res = bench_res)

# ggsave(here::here("inst/benchmark/bench_barplot.pdf"),bench_barplot, height = 8)

Scatter plot

For each method, plot the relationship between number of genes returned and run time.

bench_scatterplot <- orthogene:::plot_benchmark_scatter(bench_res = bench_res)

## `geom_smooth()` using formula 'y ~ x'

# ggsave(here::here("inst/benchmark/bench_scatterplot.pdf"),bench_scatterplot)

Session Info

utils::sessionInfo()

## R version 4.1.0 (2021-05-18)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.2 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=C              
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=C             
##  [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] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
## [1] patchwork_1.1.1 ggplot2_3.3.5   dplyr_1.0.7     orthogene_0.1.0
## 
## loaded via a namespace (and not attached):
##  [1] nlme_3.1-152              fs_1.5.0                 
##  [3] usethis_2.0.1             devtools_2.4.2           
##  [5] httr_1.4.2                rprojroot_2.0.2          
##  [7] tools_4.1.0               backports_1.2.1          
##  [9] bslib_0.2.5.1             utf8_1.2.2               
## [11] R6_2.5.0                  mgcv_1.8-36              
## [13] DBI_1.1.1                 lazyeval_0.2.2           
## [15] colorspace_2.0-2          withr_2.4.2              
## [17] tidyselect_1.1.1          prettyunits_1.1.1        
## [19] processx_3.5.2            curl_4.3.2               
## [21] compiler_4.1.0            cli_3.0.1                
## [23] xml2_1.3.2                desc_1.3.0               
## [25] plotly_4.9.4.9000         labeling_0.4.2           
## [27] sass_0.4.0                scales_1.1.1             
## [29] callr_3.7.0               stringr_1.4.0            
## [31] digest_0.6.27             foreign_0.8-81           
## [33] rmarkdown_2.9             rio_0.5.27               
## [35] pkgconfig_2.0.3           htmltools_0.5.1.1        
## [37] sessioninfo_1.1.1         highr_0.9                
## [39] fastmap_1.1.0             htmlwidgets_1.5.3        
## [41] rlang_0.4.11              readxl_1.3.1             
## [43] rstudioapi_0.13           farver_2.1.0             
## [45] jquerylib_0.1.4           generics_0.1.0           
## [47] jsonlite_1.7.2            zip_2.2.0                
## [49] car_3.0-11                homologene_1.4.68.19.3.27
## [51] magrittr_2.0.1            Matrix_1.3-4             
## [53] Rcpp_1.0.7                munsell_0.5.0            
## [55] fansi_0.5.0               abind_1.4-5              
## [57] lifecycle_1.0.0           stringi_1.7.3            
## [59] yaml_2.2.1                carData_3.0-4            
## [61] pkgbuild_1.2.0            grid_4.1.0               
## [63] parallel_4.1.0            forcats_0.5.1            
## [65] crayon_1.4.1              lattice_0.20-44          
## [67] splines_4.1.0             haven_2.4.1              
## [69] hms_1.1.0                 knitr_1.33               
## [71] ps_1.6.0                  pillar_1.6.1             
## [73] ggpubr_0.4.0              ggsignif_0.6.2           
## [75] pkgload_1.2.1             glue_1.4.2               
## [77] gprofiler2_0.2.0          evaluate_0.14            
## [79] data.table_1.14.0         remotes_2.4.0            
## [81] vctrs_0.3.8               testthat_3.0.4           
## [83] cellranger_1.1.0          gtable_0.3.0             
## [85] purrr_0.3.4               tidyr_1.1.3              
## [87] assertthat_0.2.1          cachem_1.0.5             
## [89] xfun_0.24                 openxlsx_4.2.4           
## [91] broom_0.7.8               roxygen2_7.1.1           
## [93] rstatix_0.7.0             viridisLite_0.4.0        
## [95] tibble_3.1.3              memoise_2.0.0            
## [97] ellipsis_0.3.2            here_1.0.1

benchmarks

Author: Brian M. Schilder

Most recent update: Aug-01-2021