In grunwaldlab/metacoder: Tools for Parsing, Manipulating, and Graphing Taxonomic Abundance Data

flow chart code

file_path <- system.file("extdata", "unite_general_release.fasta", package = "metacoder")
sequences <- ape::read.FASTA(file_path)
data <- extract_taxonomy(sequences,
                         regex = "^(.*)\\|(.*)\\|(.*)\\|.*\\|(.*)$",
                         key = c(seq_name = "item_info", sequence_id = "item_info",
                                 other_id = "item_info", "class"),
                         class_regex = "^(.*)__(.*)$",
                         class_key = c(unite_rank = "taxon_info", "name"),
                         class_sep = ";")

set.seed(1)
data %>%
  filter_taxa(name %in% c("Russula"), subtaxa = TRUE, supertaxa = TRUE, taxonless = FALSE, reassign_items = FALSE) %>%
  filter_taxa(taxon_ranks <= 6, taxonless = FALSE) %>%
  filter_taxa(! grepl("[_0-9]+", name), taxonless = FALSE, reassign_items = FALSE) %>%
  arrange_taxa(c(p = 1, c = 2, o = 3, f = 4, g = 5, s = 6)[unite_rank]) %>%
plot(vertex_size = item_counts,
     vertex_color = item_counts,
     vertex_label = name,
     layout = "ka",
     make_legend = FALSE, 
     output_file = "figure_plot.svg")

------------------ taxon_data ------------------- taxon_ids parent_ids unite_rank name 1 3 NA p Basidiomycota 2 305 3 c Agaricomycetes 3 323 305 o Russulales 4 553 323 f Russulaceae 5 557 553 g Russula 6 575 557 s chloroides 7 576 557 s cyanoxantha ... ... ... ... ...

------------------ obs_data -------------------- item_taxon_ids seq_name sequence_id 1 576 Russula_cyanoxantha AB451977 2 578 Russula_sp DQ424937 3 578 Russula_sp HQ445312 4 578 Russula_sp DQ061867 ... ... ... ... ...

mutate_taxa, mutate_obs transmute_taxa, transmute_obs select_taxa, select_obs filter_taxa, filter_obs arrange_taxa, arrange_obs sample_n_taxa, sample_n_obs

... fRussulaceae;gRussula;sRussula_cyanoxantha ... fRussulaceae;gRussula;sRussula_chloroides ... fRussulaceae;gRussula;s__Russula_delica ...

grunwaldlab/metacoder documentation built on Feb. 22, 2024, 3:47 a.m.