Nothobranchius furzeri

Installation

To begin, install the {biomaRt} package.

if (!require("BiocManager", quietly = TRUE))
    install.packages("BiocManager")

BiocManager::install("biomaRt")

Package

Load package.

packageVersion("biomaRt")

[1] '2.62.1'

suppressPackageStartupMessages(library(biomaRt))

Getting started

Use mirro.

ensembl <- useEnsembl(biomart = "ensembl", mirror = "asia")

Ensembl site unresponsive, trying useast mirror

ensembl

Object of class 'Mart':
  Using the ENSEMBL_MART_ENSEMBL BioMart database
  No dataset selected.

Connect to the selected BioMart database by using useMart().

avail_datasets <- listDatasets(ensembl)
head(avail_datasets)

                       dataset                           description
1 abrachyrhynchus_gene_ensembl Pink-footed goose genes (ASM259213v1)
2     acalliptera_gene_ensembl      Eastern happy genes (fAstCal1.3)
3   acarolinensis_gene_ensembl       Green anole genes (AnoCar2.0v2)
4    acchrysaetos_gene_ensembl       Golden eagle genes (bAquChr1.2)
5    acitrinellus_gene_ensembl        Midas cichlid genes (Midas_v5)
6    amelanoleuca_gene_ensembl       Giant panda genes (ASM200744v2)
      version
1 ASM259213v1
2  fAstCal1.3
3 AnoCar2.0v2
4  bAquChr1.2
5    Midas_v5
6 ASM200744v2

Look for human datasets by searching the description column.

idx <- grep(pattern = "furzeri", avail_datasets$dataset, ignore.case = TRUE)
avail_datasets[idx, ]

                  dataset                              description      version
117 nfurzeri_gene_ensembl Turquoise killifish genes (Nfu_20140520) Nfu_20140520

Connect to the selected BioMart database and turquoise killifish dataset.

ensembl <- useEnsembl(biomart = "ensembl", mirror = "asia", dataset=avail_datasets[idx, 'dataset'])

Ensembl site unresponsive, trying www mirror

Ensembl site unresponsive, trying useast mirror

ensembl

Object of class 'Mart':
  Using the ENSEMBL_MART_ENSEMBL BioMart database
  Using the nfurzeri_gene_ensembl dataset

Building a query, requires three things:

1. filters
2. attributes
3. values

Use listFilters() to show available filters.

avail_filters <- listFilters(ensembl)
head(avail_filters)

                        name                            description
1            chromosome_name               Chromosome/scaffold name
2                      start                                  Start
3                        end                                    End
4                     strand                                 Strand
5         chromosomal_region e.g. 1:100:10000:-1, 1:100000:200000:1
6 with_entrezgene_trans_name  With EntrezGene transcript name ID(s)

Use listAttributes() to show available attributes.

avail_attributes <- listAttributes(ensembl)
avail_attributes |>
  head()

                           name                  description         page
1               ensembl_gene_id               Gene stable ID feature_page
2       ensembl_gene_id_version       Gene stable ID version feature_page
3         ensembl_transcript_id         Transcript stable ID feature_page
4 ensembl_transcript_id_version Transcript stable ID version feature_page
5            ensembl_peptide_id            Protein stable ID feature_page
6    ensembl_peptide_id_version    Protein stable ID version feature_page

The getBM() function is the main query function in {biomaRt}; use it once you have identified your attributes of interest and filters to use.

gene_ids <- c("ENSNFUG00015000040", "ENSNFUG00015000042", "ENSNFUG00015000043", "ENSNFUG00015000127")

getBM(
  attributes=c('ensembl_gene_id', 'external_gene_name', 'description'),
  filters = 'ensembl_gene_id',
  values = gene_ids,
  mart = ensembl
) -> res

res

     ensembl_gene_id external_gene_name
1 ENSNFUG00015000040                   
2 ENSNFUG00015000042              irf2b
3 ENSNFUG00015000043              CASP3
4 ENSNFUG00015000127            slc38a2
                                                               description
1                                                                         
2     interferon regulatory factor 2b [Source:ZFIN;Acc:ZDB-GENE-041212-38]
3                             caspase 3 [Source:HGNC Symbol;Acc:HGNC:1504]
4 solute carrier family 38 member 2 [Source:ZFIN;Acc:ZDB-GENE-030131-9659]

All gene IDs.

gtf_file <- "https://ftp.ensembl.org/pub/release-113/gtf/nothobranchius_furzeri/Nothobranchius_furzeri.Nfu_20140520.113.gtf.gz"
if(file.exists(basename(gtf_file)) == FALSE){
  download.file(url = gtf_file, destfile = basename(gtf_file))
}

gtf_cols <- c(
  "seqname",
  "source",
  "feature",
  "start",
  "end",
  "score",
  "strand",
  "frame",
  "attribute"
)

gtf <- readr::read_tsv(file = gtf_file, comment = "#", col_names = gtf_cols, show_col_types = FALSE)
gtf |>
  dplyr::filter(feature == "gene") |>
  dplyr::select(attribute) |>
  tidyr::separate_rows(attribute, sep = ";\\s*") |>
  dplyr::filter(grepl("gene_id", attribute)) |>
  tidyr::separate(attribute, c('key', 'value'), sep = "\\s") |>
  dplyr::pull(value) |>
  gsub(pattern ='"', replacement = "") -> all_gene_ids

length(all_gene_ids) == length(unique(all_gene_ids))

[1] TRUE

Get gene names and descriptions.

getBM(
  attributes=c('ensembl_gene_id', 'external_gene_name', 'description'),
  filters = 'ensembl_gene_id',
  values = all_gene_ids,
  mart = ensembl
) -> all_gene_info

head(all_gene_info)

     ensembl_gene_id external_gene_name
1 ENSNFUG00015000040                   
2 ENSNFUG00015000041                   
3 ENSNFUG00015000042              irf2b
4 ENSNFUG00015000043              CASP3
5 ENSNFUG00015000044                   
6 ENSNFUG00015000045            st3gal5
                                                                             description
1                                                                                       
2                                                                                       
3                   interferon regulatory factor 2b [Source:ZFIN;Acc:ZDB-GENE-041212-38]
4                                           caspase 3 [Source:HGNC Symbol;Acc:HGNC:1504]
5            centromere protein U [Source:NCBI gene (formerly Entrezgene);Acc:107390684]
6 ST3 beta-galactoside alpha-2,3-sialyltransferase 5 [Source:ZFIN;Acc:ZDB-GENE-060322-1]

Save lookup table.

readr::write_csv(x = all_gene_info, file = "data/nfurzeri_gene_info.csv.gz")

Gene Ontology terms

Find GO attribute names.

grep("^go", avail_attributes$name, ignore.case=TRUE, value=TRUE)

[1] "go_id"                  "go_linkage_type"        "goslim_goa_accession"  
[4] "goslim_goa_description"

Query.

getBM(
  attributes=c("ensembl_gene_id", "go_id"),
  filters="ensembl_gene_id",
  values = all_gene_ids,
  mart = ensembl
) -> all_gene_go_ids

head(all_gene_go_ids)

     ensembl_gene_id      go_id
1 ENSNFUG00015000040           
2 ENSNFUG00015000041 GO:0007156
3 ENSNFUG00015000041 GO:0005886
4 ENSNFUG00015000041 GO:0005737
5 ENSNFUG00015000041 GO:0050808
6 ENSNFUG00015000041 GO:0007411

Save GO table.

readr::write_csv(x = all_gene_go_ids, file = "data/nfurzeri_gene_id_to_go_id.csv.gz")

Session information

sessionInfo()

R version 4.4.1 (2024-06-14)
Platform: x86_64-pc-linux-gnu
Running under: Ubuntu 22.04.5 LTS

Matrix products: default
BLAS:   /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3 
LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.20.so;  LAPACK version 3.10.0

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       

time zone: Etc/UTC
tzcode source: system (glibc)

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] biomaRt_2.62.1  workflowr_1.7.1

loaded via a namespace (and not attached):
 [1] KEGGREST_1.46.0         xfun_0.48               bslib_0.8.0            
 [4] httr2_1.0.5             processx_3.8.4          Biobase_2.66.0         
 [7] tzdb_0.4.0              callr_3.7.6             generics_0.1.3         
[10] vctrs_0.6.5             tools_4.4.1             ps_1.8.1               
[13] parallel_4.4.1          curl_5.2.3              stats4_4.4.1           
[16] tibble_3.2.1            fansi_1.0.6             AnnotationDbi_1.68.0   
[19] RSQLite_2.3.7           blob_1.2.4              pkgconfig_2.0.3        
[22] dbplyr_2.5.0            S4Vectors_0.44.0        lifecycle_1.0.4        
[25] GenomeInfoDbData_1.2.13 compiler_4.4.1          stringr_1.5.1          
[28] git2r_0.35.0            Biostrings_2.74.1       progress_1.2.3         
[31] getPass_0.2-4           httpuv_1.6.15           GenomeInfoDb_1.42.3    
[34] htmltools_0.5.8.1       sass_0.4.9              yaml_2.3.10            
[37] tidyr_1.3.1             later_1.3.2             pillar_1.9.0           
[40] crayon_1.5.3            jquerylib_0.1.4         whisker_0.4.1          
[43] cachem_1.1.0            tidyselect_1.2.1        digest_0.6.37          
[46] stringi_1.8.4           purrr_1.0.2             dplyr_1.1.4            
[49] rprojroot_2.0.4         fastmap_1.2.0           cli_3.6.3              
[52] magrittr_2.0.3          utf8_1.2.4              readr_2.1.5            
[55] withr_3.0.2             filelock_1.0.3          prettyunits_1.2.0      
[58] UCSC.utils_1.2.0        promises_1.3.0          rappdirs_0.3.3         
[61] bit64_4.5.2             rmarkdown_2.28          XVector_0.46.0         
[64] httr_1.4.7              bit_4.5.0               png_0.1-8              
[67] hms_1.1.3               memoise_2.0.1           evaluate_1.0.1         
[70] knitr_1.48              IRanges_2.40.1          BiocFileCache_2.14.0   
[73] rlang_1.1.4             Rcpp_1.0.13             glue_1.8.0             
[76] DBI_1.2.3               xml2_1.3.6              BiocGenerics_0.52.0    
[79] vroom_1.6.5             rstudioapi_0.17.1       jsonlite_1.8.9         
[82] R6_2.5.1                fs_1.6.4                zlibbioc_1.52.0