improve code redundancy

DESCRIPTION

@@ -69,6 +69,7 @@ Collate:
  'annotate_spectra.R'
  'clean_bio.R'
  'clean_chemo.R'
+ 'clean_collapse.R'
  'complement_metadata_structures.R'
  'create_adducts_neg.R'
  'create_adducts_pos.R'
@@ -86,6 +87,7 @@ Collate:
  'export_spectra.R'
  'export_spectra_2.R'
  'extract_spectra.R'
+ 'get_example_sirius.R'
  'get_file.R'
  'get_gnps_tables.R'
  'get_last_version_from_zenodo.R'

NAMESPACE

@@ -4,6 +4,7 @@ export(annotate_masses)
 export(annotate_spectra)
 export(clean_bio)
 export(clean_chemo)
+export(clean_collapse)
 export(complement_metadata_structures)
 export(create_adducts_neg)
 export(create_adducts_pos)
@@ -22,6 +23,7 @@ export(export_params)
 export(export_spectra)
 export(export_spectra_2)
 export(extract_spectra)
+export(get_example_sirius)
 export(get_file)
 export(get_gnps_tables)
 export(get_last_version_from_zenodo)

R/clean_collapse.R

@@ -0,0 +1,24 @@
+#' @title Clean collapse
+#'
+#' @description This function collapses a grouped dataframe and trims it
+#'
+#' @param grouped_df Grouped dataframe
+#'
+#' @return NULL
+#'
+#' @export
+#'
+#' @examples NULL
+clean_collapse <- function(grouped_df) {
+ clean_collapse_df <- grouped_df |>
+ dplyr::summarize(dplyr::across(
+ dplyr::everything(),
+ .fns = function(x) {
+ x <- list(paste(unique(x[!is.na(x)]), collapse = " $ "))
+ }
+ )) |>
+ dplyr::ungroup() |>
+ dplyr::mutate(dplyr::across(dplyr::everything(), trimws))
+
+ return(clean_collapse_df)
+}

R/get_example_sirius.R

@@ -0,0 +1,25 @@
+#' @title Get example sirius
+#'
+#' @description This function gets example SIRIUS annotations
+#'
+#' @param url URL where the example is accessible
+#' @param export Path where to save the example
+#'
+#' @return NULL
+#'
+#' @export
+#'
+#' @examples NULL
+get_example_sirius <-
+ function(url = paths$urls$examples$sirius,
+ export = paths$data$interim$annotations$example_sirius) {
+ get_file(
+ url = url,
+ export = export
+ )
+ message("Unzipping")
+ utils::unzip(
+ zipfile = export,
+ exdir = dirname(export)
+ )
+ }

R/split_tables_sop.R

@@ -124,11 +124,7 @@ split_tables_sop <- function(table) {
  structure_inchikey,
  structure_smiles
  ) |>
- dplyr::summarize(dplyr::across(dplyr::everything(), .fns = function(x) {
- x <- list(paste(unique(x[!is.na(x)]), collapse = " $ "))
- })) |>
- dplyr::ungroup() |>
- dplyr::mutate(dplyr::across(dplyr::everything(), trimws))
+ clean_collapse()
 
  table_structures_taxonomy_npc <- table |>
  dplyr::filter(!is.na(structure_smiles_2D)) |>
@@ -145,11 +141,7 @@ split_tables_sop <- function(table) {
  ) |>
  tidytable::distinct() |>
  dplyr::group_by(structure_smiles_2D) |>
- dplyr::summarize(dplyr::across(dplyr::everything(), .fns = function(x) {
- x <- list(paste(unique(x[!is.na(x)]), collapse = " $ "))
- })) |>
- dplyr::ungroup() |>
- dplyr::mutate(dplyr::across(dplyr::everything(), trimws)) |>
+ clean_collapse() |>
  dplyr::mutate(dplyr::across(
  dplyr::matches("taxonomy.*_0"),
  .fns = function(x) {

R/weight_annotations.R

@@ -204,81 +204,23 @@ weight_annotations <-
 
  log_debug(x = "performing taxonomically informed scoring")
  annotation_table_weighted_bio <-
- weight_bio(
- annotationTable = annotation_table_taxed,
- structureOrganismPairsTable = structure_organism_pairs_table,
- weightSpectral = weight_spectral,
- weightBiological = weight_biological,
- scoreBiologicalDomain = score_biological_domain,
- scoreBiologicalKingdom = score_biological_kingdom,
- scoreBiologicalPhylum = score_biological_phylum,
- scoreBiologicalClass = score_biological_class,
- scoreBiologicalOrder = score_biological_order,
- scoreBiologicalFamily = score_biological_family,
- scoreBiologicalTribe = score_biological_tribe,
- scoreBiologicalGenus = score_biological_genus,
- scoreBiologicalSpecies = score_biological_species,
- scoreBiologicalVariety = score_biological_variety
- )
+ weight_bio()
 
  annotation_table_weighted_bio |>
- decorate_bio(
- sc_kin = score_biological_kingdom,
- sc_phy = score_biological_phylum,
- sc_cla = score_biological_class,
- sc_ord = score_biological_order,
- sc_fam = score_biological_family,
- sc_gen = score_biological_genus,
- sc_spe = score_biological_species,
- sc_var = score_biological_variety
- )
+ decorate_bio()
 
  log_debug(x = "cleaning taxonomically informed results and preparing for chemically informed scoring")
- annotation_table_weighted_bio_cleaned <- clean_bio(
- annotationTableWeightedBio = annotation_table_weighted_bio,
- edgesTable = edges_table,
- candidatesInitial = candidates_initial,
- minimalMs1Bio = minimal_ms1_bio
- )
+ annotation_table_weighted_bio_cleaned <- clean_bio()
 
  log_debug(x = "performing chemically informed scoring")
  annotation_table_weighted_chemo <-
- weight_chemo(
- annotationTableWeightedBioCleaned = annotation_table_weighted_bio_cleaned,
- weightSpectral = weight_spectral,
- weightBiological = weight_biological,
- weightChemical = weight_chemical,
- scoreChemicalClaKingdom = score_chemical_cla_kingdom,
- scoreChemicalClaSuperclass = score_chemical_cla_superclass,
- scoreChemicalClaClass = score_chemical_cla_class,
- scoreChemicalClaParent = score_chemical_cla_parent,
- scoreChemicalNpcPathway = score_chemical_npc_pathway,
- scoreChemicalNpcSuperclass = score_chemical_npc_superclass,
- scoreChemicalNpcClass = score_chemical_npc_class
- )
+ weight_chemo()
 
  annotation_table_weighted_chemo |>
- decorate_chemo(
- sc_cla_kin = score_chemical_cla_kingdom,
- sc_cla_sup = score_chemical_cla_superclass,
- sc_cla_cla = score_chemical_cla_class,
- sc_cla_par = score_chemical_cla_parent,
- sc_npc_pat = score_chemical_npc_pathway,
- sc_npc_sup = score_chemical_npc_superclass,
- sc_npc_cla = score_chemical_npc_class
- )
+ decorate_chemo()
 
  log_debug(x = "cleaning for export")
- results <- clean_chemo(
- annotationTableWeightedChemo = annotation_table_weighted_chemo,
- componentsTable = components_table,
- featuresTable = features_table,
- structureOrganismPairsTable = structure_organism_pairs_table,
- candidatesFinal = candidates_final,
- minimalMs1Bio = minimal_ms1_bio,
- minimalMs1Chemo = minimal_ms1_chemo,
- summarize = summarise
- )
+ results <- clean_chemo()
 
  log_debug(x = "Exporting ...")
  time <- format(Sys.time(), "%y%m%d_%H%M%OS")

inst/scripts/get_example_sirius.R

@@ -14,15 +14,7 @@ log_debug(
 log_debug("Authors: ", crayon::green("AR"), "\n")
 log_debug("Contributors: ...")
 
-get_file(
- url = paths$urls$examples$sirius,
- export = paths$data$interim$annotations$example_sirius
-)
-message("Unzipping")
-utils::unzip(
- zipfile = paths$data$interim$annotations$example_sirius,
- exdir = dirname(paths$data$interim$annotations$example_sirius)
-)
+get_example_sirius()
 
 end <- Sys.time()
 

tests/testthat/test_functions.R

@@ -90,17 +90,7 @@ testthat::test_that("Whole process", {
 
  #### SIRIUS
  ## mini version for tests
- sirius_mini <- paths$data$interim$annotations$example_sirius |>
- gsub(pattern = ".zip", replacement = "_mini.zip")
- get_file(
- url = paths$urls$examples$sirius,
- export = paths$data$interim$annotations$example_sirius
- )
- message("Unzipping")
- utils::unzip(
- zipfile = paths$data$interim$annotations$example_sirius,
- exdir = dirname(paths$data$interim$annotations$example_sirius)
- )
+ get_example_sirius()
 
  ### Libraries
  #### ECMDB