Closed sdgamboa closed 2 years ago
Some numbers:
suppressMessages({
library(bugphyzz)
library(dplyr)
library(purrr)
phys <- physiologies()
phys[['fatty acid compositions']] <- fattyAcidComposition()
})
phys$`genome size` <- NULL
phys$`coding genes` <- NULL
phys <- discard(phys, is.null)
map(phys, ~ {
count(.x, Evidence, Confidence_interval)
}) %>%
bind_rows(.id = 'dataset')
#> dataset Evidence Confidence_interval n
#> 1 acetate producing EXP Unknown 24
#> 2 aerophilicity EXP always 1229
#> 3 aerophilicity EXP sometimes 24
#> 4 aerophilicity Unknown always 6788
#> 5 animal pathogen <NA> Unknown 1420
#> 6 antimicrobial resistance ASR Always 10321
#> 7 antimicrobial sensitivity EXP Usually 832
#> 8 arrangement Unknown 1071
#> 9 arrangement EXP always 142
#> 10 arrangement EXP sometimes 610
#> 11 biofilm forming EXP Unknown 426
#> 12 butyrate producing EXP Usually 24
#> 13 COGEM pathogenicity rating <NA> Usually 1043
#> 14 disease association EXP Usually 445
#> 15 extreme environment <NA> Always 1875
#> 16 gram stain EXP always 1337
#> 17 gram stain EXP sometimes 16
#> 18 gram stain unknown always 1
#> 19 gram stain Unknown always 2335
#> 20 gram stain Unknown unknown 1278
#> 21 growth medium EXP Always 304
#> 22 growth temperature EXP Unknown 2524
#> 23 habitat EXP Sometimes 9
#> 24 habitat EXP Unknown 5222
#> 25 habitat EXP Usually 12999
#> 26 health associated COM Usually 30
#> 27 hydrogen gas producing EXP Usually 24
#> 28 isolation site EXP always 5579
#> 29 lactate producing EXP Usually 24
#> 30 length EXP always 43
#> 31 length EXP sometimes 624
#> 32 length EXP Unknown 196
#> 33 mutation rate per site per generation EXP Sometimes 26
#> 34 mutation rates per site per year EXP Sometimes 81
#> 35 optimal ph EXP Usually 886
#> 36 plant pathogenicity <NA> Usually 1493
#> 37 shape unknown 1279
#> 38 shape EXP always 876
#> 39 shape EXP sometimes 974
#> 40 spore shape EXP always 50
#> 41 spore shape EXP sometimes 97
#> 42 spore shape EXP Usually 1388
#> 43 width always 1
#> 44 width EXP always 116
#> 45 width EXP sometimes 734
#> 46 width EXP <NA> 12
#> 47 fatty acid compositions EXP Unknown 138496
sessionInfo()
#> R version 4.2.0 (2022-04-22)
#> Platform: x86_64-pc-linux-gnu (64-bit)
#> Running under: Pop!_OS 22.04 LTS
#>
#> Matrix products: default
#> BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.10.0
#> LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.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
#>
#> attached base packages:
#> [1] stats graphics grDevices utils datasets methods base
#>
#> other attached packages:
#> [1] purrr_0.3.4 dplyr_1.0.9 bugphyzz_0.0.1.3
#>
#> loaded via a namespace (and not attached):
#> [1] Rcpp_1.0.8.3 ape_5.6-2 lattice_0.20-45 tidyr_1.2.0
#> [5] zoo_1.8-10 assertthat_0.2.1 digest_0.6.29 foreach_1.5.2
#> [9] utf8_1.2.2 R6_2.5.1 plyr_1.8.7 reprex_2.0.1
#> [13] RSQLite_2.2.14 evaluate_0.15 highr_0.9 pillar_1.7.0
#> [17] rlang_1.0.2 curl_4.3.2 uuid_1.1-0 rstudioapi_0.13
#> [21] data.table_1.14.2 taxize_0.9.100 blob_1.2.3 rmarkdown_2.14
#> [25] stringr_1.4.0 bit_4.0.4 compiler_4.2.0 xfun_0.30
#> [29] pkgconfig_2.0.3 conditionz_0.1.0 htmltools_0.5.2 tidyselect_1.1.2
#> [33] tibble_3.1.7 httpcode_0.3.0 mgsub_1.7.3 codetools_0.2-18
#> [37] reshape_0.8.9 fansi_1.0.3 crayon_1.5.1 hoardr_0.5.2
#> [41] dbplyr_2.1.1 withr_2.5.0 rappdirs_0.3.3 crul_1.2.0
#> [45] grid_4.2.0 nlme_3.1-157 jsonlite_1.8.0 lifecycle_1.0.1
#> [49] DBI_1.1.2 magrittr_2.0.3 taxizedb_0.3.0 cli_3.3.0
#> [53] stringi_1.7.6 cachem_1.0.6 fs_1.5.2 xml2_1.3.3
#> [57] ellipsis_0.3.2 generics_0.1.2 vctrs_0.4.1 iterators_1.0.14
#> [61] tools_4.2.0 bold_1.2.0 bit64_4.0.5 glue_1.6.2
#> [65] parallel_4.2.0 fastmap_1.1.0 yaml_2.3.5 memoise_2.0.1
#> [69] knitr_1.39
Created on 2022-05-11 by the reprex package (v2.0.1)
I think this is complete.
Some values for converting confidence interval character values to numeric values (and vice-versa).
From numeric to character
From character to numeric