johrpan/geposan
1
0
Fork 0
mirror of https://github.com/johrpan/geposan.git synced 2025-10-26 10:47:25 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions

preset: Filter species in addition to genes

Browse source
This commit is contained in:
Elias Projahn 2022-05-30 13:49:52 +02:00
parent 9e96c54f23
commit 3217c9bd29
4 changed files with 49 additions and 48 deletions
Download patch file Download diff file Expand all files Collapse all files

44
R/preset.R
View file

@ -3,16 +3,19 @@
#' A preset is used to specify which methods and inputs should be used for an
#' analysis. Note that the genes to process should normally include the
#' reference genes to be able to assess the results later. The genes will be
#' filtered based on how many species have data for them. Genes which only have
#' orthologs for less than 25% of the input species will be excluded from the
#' preset and the analyis. See the different method functions for the available
#' methods: [clustering()], [correlation()], [neural()], [adjacency()] and
#' [species_adjacency()].
#' filtered based on how many species have data for them. Afterwards, species
#' that still have many missing genes will also be excluded. See the different
#' method functions for the available methods: [clustering()], [correlation()],
#' [neural()], [adjacency()] and [species_adjacency()].
#'
#' @param reference_gene_ids IDs of reference genes to compare to.
#' @param methods List of methods to apply.
#' @param species_ids IDs of species to include.
#' @param gene_ids IDs of genes to screen.
#' @param species_requirement The proportion of species a gene has to have
#' orthologs in in order for the gene to qualify.
#' @param gene_requirement The proportion of genes that a species has to have
#' in order for the species to be included in the analysis.
#'
#' @return The preset to use with [analyze()].
#'
@ -20,21 +23,32 @@
preset <- function(reference_gene_ids,
methods = all_methods(),
species_ids = geposan::species$id,
gene_ids = geposan::genes$id) {
# Count included species per gene.
genes_n_species <- geposan::distances[
species %chin% species_ids,
.(n_species = .N),
by = "gene"
gene_ids = geposan::genes$id,
species_requirement = 0.25,
gene_requirement = 0.5) {
# Prefilter distances.
distances <- geposan::distances[
species %chin% species_ids & gene %chin% gene_ids
]
# Filter out genes with less than 25% existing orthologs.
# Count included species per gene.
genes_n_species <- distances[, .(n_species = .N), by = "gene"]
# Filter out genes with less too few existing orthologs.
gene_ids_filtered <- genes_n_species[
gene %chin% gene_ids &
n_species >= 0.25 * length(species_ids),
n_species >= species_requirement * length(species_ids),
gene
]
# Count included genes per species.
species_n_genes <- geposan::distances[, .(n_genes = .N), by = "species"]
# Filter out species that have too few of the genes.
species_ids_filtered <- species_n_genes[
n_genes >= gene_requirement * length(gene_ids_filtered),
species
]
reference_gene_ids_excluded <- reference_gene_ids[
!reference_gene_ids %chin% gene_ids_filtered
]
@ -65,7 +79,7 @@ preset <- function(reference_gene_ids,
list(
reference_gene_ids = sort(reference_gene_ids_included),
methods = methods,
species_ids = sort(species_ids),
species_ids = sort(species_ids_filtered),
gene_ids = sort(gene_ids_filtered)
),
class = "geposan_preset"