if (!requireNamespace("BiocManager", quietly = TRUE))
install.packages("BiocManager")
# orthogene is only available on Bioconductor>=3.14
if(BiocManager::version()<"3.14")
BiocManager::install(update = TRUE, ask = FALSE)
BiocManager::install("orthogene")
library(orthogene)
data("exp_mouse")
# Setting to "homologene" for the purposes of quick demonstration.
# We generally recommend using method="gprofiler" (default).
method <- "homologene"
It’s not always clear whether a dataset is using the original species gene names, human gene names, or some other species’ gene names.
infer_species
takes a list/matrix/data.frame with genes and
infers the species that they best match to!
For the sake of speed, the genes extracted from gene_df
are tested against genomes from only the following 6 test_species
by default:
- human
- monkey
- rat
- mouse
- zebrafish
- fly
However, you can supply your own list of test_species
, which will
be automatically be mapped and standardised using map_species
.
matches <- orthogene::infer_species(gene_df = exp_mouse,
method = method)
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 15,259 genes extracted.
## Testing for gene overlap with: human
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: human
## Common name mapping found for human
## 1 organism identified from search: 9606
## Gene table with 19,129 rows retrieved.
## Returning all 19,129 genes from human.
## Testing for gene overlap with: monkey
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: monkey
## Common name mapping found for monkey
## 1 organism identified from search: 9544
## Gene table with 16,843 rows retrieved.
## Returning all 16,843 genes from monkey.
## Testing for gene overlap with: rat
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: rat
## Common name mapping found for rat
## 1 organism identified from search: 10116
## Gene table with 20,616 rows retrieved.
## Returning all 20,616 genes from rat.
## Testing for gene overlap with: mouse
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: mouse
## Common name mapping found for mouse
## 1 organism identified from search: 10090
## Gene table with 21,207 rows retrieved.
## Returning all 21,207 genes from mouse.
## Testing for gene overlap with: zebrafish
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: zebrafish
## Common name mapping found for zebrafish
## 1 organism identified from search: 7955
## Gene table with 20,897 rows retrieved.
## Returning all 20,897 genes from zebrafish.
## Testing for gene overlap with: fly
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: fly
## Common name mapping found for fly
## 1 organism identified from search: 7227
## Gene table with 8,438 rows retrieved.
## Returning all 8,438 genes from fly.
## Top match:
## - species: mouse
## - percent_match: 92%
To create an example dataset, turn the gene names into rat genes.
exp_rat <- orthogene::convert_orthologs(gene_df = exp_mouse,
input_species = "mouse",
output_species = "rat",
method = method)
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 15,259 genes extracted.
## Converting mouse ==> rat orthologs using: homologene
## Retrieving all organisms available in homologene.
## Mapping species name: mouse
## Common name mapping found for mouse
## 1 organism identified from search: 10090
## Retrieving all organisms available in homologene.
## Mapping species name: rat
## Common name mapping found for rat
## 1 organism identified from search: 10116
## Checking for genes without orthologs in rat.
## Extracting genes from input_gene.
## 13,812 genes extracted.
## Extracting genes from ortholog_gene.
## 13,812 genes extracted.
## Checking for genes without 1:1 orthologs.
## Dropping 486 genes that have multiple input_gene per ortholog_gene.
## Dropping 148 genes that have multiple ortholog_gene per input_gene.
## Filtering gene_df with gene_map
## Setting ortholog_gene to rownames.
##
## =========== REPORT SUMMARY ===========
## Total genes dropped after convert_orthologs :
## 2,322 / 15,259 (15%)
## Total genes remaining after convert_orthologs :
## 12,937 / 15,259 (85%)
matches <- orthogene::infer_species(gene_df = exp_rat,
method = method)
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 12,937 genes extracted.
## Testing for gene overlap with: human
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: human
## Common name mapping found for human
## 1 organism identified from search: 9606
## Gene table with 19,129 rows retrieved.
## Returning all 19,129 genes from human.
## Testing for gene overlap with: monkey
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: monkey
## Common name mapping found for monkey
## 1 organism identified from search: 9544
## Gene table with 16,843 rows retrieved.
## Returning all 16,843 genes from monkey.
## Testing for gene overlap with: rat
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: rat
## Common name mapping found for rat
## 1 organism identified from search: 10116
## Gene table with 20,616 rows retrieved.
## Returning all 20,616 genes from rat.
## Testing for gene overlap with: mouse
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: mouse
## Common name mapping found for mouse
## 1 organism identified from search: 10090
## Gene table with 21,207 rows retrieved.
## Returning all 21,207 genes from mouse.
## Testing for gene overlap with: zebrafish
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: zebrafish
## Common name mapping found for zebrafish
## 1 organism identified from search: 7955
## Gene table with 20,897 rows retrieved.
## Returning all 20,897 genes from zebrafish.
## Testing for gene overlap with: fly
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: fly
## Common name mapping found for fly
## 1 organism identified from search: 7227
## Gene table with 8,438 rows retrieved.
## Returning all 8,438 genes from fly.
## Top match:
## - species: rat
## - percent_match: 100%
To create an example dataset, turn the gene names into human genes.
exp_human <- orthogene::convert_orthologs(gene_df = exp_mouse,
input_species = "mouse",
output_species = "human",
method = method)
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 15,259 genes extracted.
## Converting mouse ==> human orthologs using: homologene
## Retrieving all organisms available in homologene.
## Mapping species name: mouse
## Common name mapping found for mouse
## 1 organism identified from search: 10090
## Retrieving all organisms available in homologene.
## Mapping species name: human
## Common name mapping found for human
## 1 organism identified from search: 9606
## Checking for genes without orthologs in human.
## Extracting genes from input_gene.
## 13,416 genes extracted.
## Extracting genes from ortholog_gene.
## 13,416 genes extracted.
## Checking for genes without 1:1 orthologs.
## Dropping 46 genes that have multiple input_gene per ortholog_gene.
## Dropping 56 genes that have multiple ortholog_gene per input_gene.
## Filtering gene_df with gene_map
## Setting ortholog_gene to rownames.
##
## =========== REPORT SUMMARY ===========
## Total genes dropped after convert_orthologs :
## 2,016 / 15,259 (13%)
## Total genes remaining after convert_orthologs :
## 13,243 / 15,259 (87%)
matches <- orthogene::infer_species(gene_df = exp_human,
method = method)
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 13,243 genes extracted.
## Testing for gene overlap with: human
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: human
## Common name mapping found for human
## 1 organism identified from search: 9606
## Gene table with 19,129 rows retrieved.
## Returning all 19,129 genes from human.
## Testing for gene overlap with: monkey
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: monkey
## Common name mapping found for monkey
## 1 organism identified from search: 9544
## Gene table with 16,843 rows retrieved.
## Returning all 16,843 genes from monkey.
## Testing for gene overlap with: rat
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: rat
## Common name mapping found for rat
## 1 organism identified from search: 10116
## Gene table with 20,616 rows retrieved.
## Returning all 20,616 genes from rat.
## Testing for gene overlap with: mouse
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: mouse
## Common name mapping found for mouse
## 1 organism identified from search: 10090
## Gene table with 21,207 rows retrieved.
## Returning all 21,207 genes from mouse.
## Testing for gene overlap with: zebrafish
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: zebrafish
## Common name mapping found for zebrafish
## 1 organism identified from search: 7955
## Gene table with 20,897 rows retrieved.
## Returning all 20,897 genes from zebrafish.
## Testing for gene overlap with: fly
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: fly
## Common name mapping found for fly
## 1 organism identified from search: 7227
## Gene table with 8,438 rows retrieved.
## Returning all 8,438 genes from fly.
## Top match:
## - species: human
## - percent_match: 100%
test_species
You can even supply test_species
with the name of one of the R packages that
orthogene
gets orthologs from. This will test against all species available
in that particular R package.
For example, by setting test_species="homologene"
we automatically test for
% gene matches in each of the 20+ species available in homologene
.
matches <- orthogene::infer_species(gene_df = exp_human,
test_species = method,
method = method)
## Retrieving all organisms available in homologene.
## Preparing gene_df.
## sparseMatrix format detected.
## Extracting genes from rownames.
## 13,243 genes extracted.
## Testing for gene overlap with: Mus musculus
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Mus musculus
## 1 organism identified from search: 10090
## Gene table with 21,207 rows retrieved.
## Returning all 21,207 genes from Mus musculus.
## Testing for gene overlap with: Rattus norvegicus
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Rattus norvegicus
## 1 organism identified from search: 10116
## Gene table with 20,616 rows retrieved.
## Returning all 20,616 genes from Rattus norvegicus.
## Testing for gene overlap with: Kluyveromyces lactis
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Kluyveromyces lactis
## 1 organism identified from search: 28985
## Gene table with 4,283 rows retrieved.
## Returning all 4,283 genes from Kluyveromyces lactis.
## Testing for gene overlap with: Magnaporthe oryzae
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Magnaporthe oryzae
## 1 organism identified from search: 318829
## Gene table with 6,598 rows retrieved.
## Returning all 6,598 genes from Magnaporthe oryzae.
## Testing for gene overlap with: Eremothecium gossypii
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Eremothecium gossypii
## 1 organism identified from search: 33169
## Gene table with 3,874 rows retrieved.
## Returning all 3,874 genes from Eremothecium gossypii.
## Testing for gene overlap with: Arabidopsis thaliana
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Arabidopsis thaliana
## 1 organism identified from search: 3702
## Gene table with 19,143 rows retrieved.
## Returning all 19,143 genes from Arabidopsis thaliana.
## Testing for gene overlap with: Oryza sativa
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Oryza sativa
## 1 organism identified from search: 4530
## Gene table with 16,112 rows retrieved.
## Returning all 16,112 genes from Oryza sativa.
## Testing for gene overlap with: Schizosaccharomyces pombe
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Schizosaccharomyces pombe
## 1 organism identified from search: 4896
## Gene table with 3,018 rows retrieved.
## Returning all 3,018 genes from Schizosaccharomyces pombe.
## Testing for gene overlap with: Saccharomyces cerevisiae
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Saccharomyces cerevisiae
## 1 organism identified from search: 4932
## Gene table with 4,579 rows retrieved.
## Returning all 4,579 genes from Saccharomyces cerevisiae.
## Testing for gene overlap with: Neurospora crassa
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Neurospora crassa
## 1 organism identified from search: 5141
## Gene table with 5,807 rows retrieved.
## Returning all 5,807 genes from Neurospora crassa.
## Testing for gene overlap with: Caenorhabditis elegans
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Caenorhabditis elegans
## 1 organism identified from search: 6239
## Gene table with 7,575 rows retrieved.
## Returning all 7,575 genes from Caenorhabditis elegans.
## Testing for gene overlap with: Anopheles gambiae
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Anopheles gambiae
## 1 organism identified from search: 7165
## Gene table with 8,428 rows retrieved.
## Returning all 8,428 genes from Anopheles gambiae.
## Testing for gene overlap with: Drosophila melanogaster
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Drosophila melanogaster
## 1 organism identified from search: 7227
## Gene table with 8,438 rows retrieved.
## Returning all 8,438 genes from Drosophila melanogaster.
## Testing for gene overlap with: Danio rerio
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Danio rerio
## 1 organism identified from search: 7955
## Gene table with 20,897 rows retrieved.
## Returning all 20,897 genes from Danio rerio.
## Testing for gene overlap with: Xenopus (Silurana) tropicalis
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Xenopus (Silurana) tropicalis
## 1 organism identified from search: 8364
## Gene table with 18,446 rows retrieved.
## Returning all 18,446 genes from Xenopus (Silurana) tropicalis.
## Testing for gene overlap with: Gallus gallus
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Gallus gallus
## 1 organism identified from search: 9031
## Gene table with 14,600 rows retrieved.
## Returning all 14,600 genes from Gallus gallus.
## Testing for gene overlap with: Macaca mulatta
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Macaca mulatta
## 1 organism identified from search: 9544
## Gene table with 16,843 rows retrieved.
## Returning all 16,843 genes from Macaca mulatta.
## Testing for gene overlap with: Pan troglodytes
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Pan troglodytes
## 1 organism identified from search: 9598
## Gene table with 18,730 rows retrieved.
## Returning all 18,730 genes from Pan troglodytes.
## Testing for gene overlap with: Homo sapiens
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Homo sapiens
## 1 organism identified from search: 9606
## Gene table with 19,129 rows retrieved.
## Returning all 19,129 genes from Homo sapiens.
## Testing for gene overlap with: Canis lupus familiaris
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Canis lupus familiaris
## 1 organism identified from search: 9615
## Gene table with 18,117 rows retrieved.
## Returning all 18,117 genes from Canis lupus familiaris.
## Testing for gene overlap with: Bos taurus
## Retrieving all genes using: homologene.
## Retrieving all organisms available in homologene.
## Mapping species name: Bos taurus
## 1 organism identified from search: 9913
## Gene table with 18,797 rows retrieved.
## Returning all 18,797 genes from Bos taurus.
## Top match:
## - species: Homo sapiens
## - percent_match: 100%
utils::sessionInfo()
## R version 4.2.1 (2022-06-23)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 20.04.5 LTS
##
## Matrix products: default
## BLAS: /home/biocbuild/bbs-3.15-bioc/R/lib/libRblas.so
## LAPACK: /home/biocbuild/bbs-3.15-bioc/R/lib/libRlapack.so
##
## locale:
## [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C
## [3] LC_TIME=en_GB LC_COLLATE=C
## [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] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] orthogene_1.2.1 BiocStyle_2.24.0
##
## loaded via a namespace (and not attached):
## [1] Rcpp_1.0.9 ape_5.6-2
## [3] lattice_0.20-45 tidyr_1.2.1
## [5] assertthat_0.2.1 digest_0.6.29
## [7] utf8_1.2.2 R6_2.5.1
## [9] backports_1.4.1 evaluate_0.16
## [11] highr_0.9 httr_1.4.4
## [13] ggplot2_3.3.6 pillar_1.8.1
## [15] ggfun_0.0.7 yulab.utils_0.0.5
## [17] rlang_1.0.6 lazyeval_0.2.2
## [19] data.table_1.14.2 car_3.1-0
## [21] jquerylib_0.1.4 magick_2.7.3
## [23] Matrix_1.5-1 rmarkdown_2.16
## [25] labeling_0.4.2 stringr_1.4.1
## [27] htmlwidgets_1.5.4 munsell_0.5.0
## [29] broom_1.0.1 gprofiler2_0.2.1
## [31] compiler_4.2.1 xfun_0.33
## [33] pkgconfig_2.0.3 gridGraphics_0.5-1
## [35] htmltools_0.5.3 tidyselect_1.1.2
## [37] tibble_3.1.8 bookdown_0.29
## [39] viridisLite_0.4.1 fansi_1.0.3
## [41] dplyr_1.0.10 ggpubr_0.4.0
## [43] grid_4.2.1 nlme_3.1-159
## [45] jsonlite_1.8.2 gtable_0.3.1
## [47] lifecycle_1.0.2 DBI_1.1.3
## [49] magrittr_2.0.3 scales_1.2.1
## [51] tidytree_0.4.1 cli_3.4.1
## [53] stringi_1.7.8 cachem_1.0.6
## [55] carData_3.0-5 farver_2.1.1
## [57] ggsignif_0.6.3 ggtree_3.4.4
## [59] bslib_0.4.0 ellipsis_0.3.2
## [61] generics_0.1.3 vctrs_0.4.2
## [63] treeio_1.20.2 tools_4.2.1
## [65] homologene_1.4.68.19.3.27 ggplotify_0.1.0
## [67] glue_1.6.2 purrr_0.3.4
## [69] abind_1.4-5 parallel_4.2.1
## [71] fastmap_1.1.0 yaml_2.3.5
## [73] babelgene_22.9 colorspace_2.0-3
## [75] BiocManager_1.30.18 rstatix_0.7.0
## [77] aplot_0.1.7 plotly_4.10.0
## [79] knitr_1.40 patchwork_1.1.2
## [81] sass_0.4.2