taxonomicallyinformedannotation · Adafede · Jul 23, 2024 · Jul 23, 2024 · Jul 23, 2024
diff --git a/R/annotate_masses.R b/R/annotate_masses.R
@@ -68,7 +68,7 @@
 #' @param neutral_losses_list List of neutral losses to be used
 #' @param ms_mode Ionization mode. Must be 'pos' or 'neg'
 #' @param tolerance_ppm Tolerance to perform annotation. Should be <= 10 ppm
-#' @param tolerance_rt Tolerance to group adducts. Should be <= 0.1min
+#' @param tolerance_rt Tolerance to group adducts. Should be <= 0.05 minutes
 #'
 #' @return A table containing MS1 annotations based on exact mass
 #'
@@ -76,23 +76,23 @@
 #'
 #' @examples NULL
 annotate_masses <-
  function(features = get_params(step = "annotate_masses")$files$features$prepared,
           output_annotations = get_params(step = "annotate_masses")$files$annotations$prepared$structural$ms1,
           output_edges = get_params(step = "annotate_masses")$files$networks$spectral$edges$raw,
           name_source = get_params(step = "annotate_masses")$names$source,
           name_target = get_params(step = "annotate_masses")$names$target,
           library = get_params(step = "annotate_masses")$files$libraries$sop$merged$keys,
           str_stereo = get_params(step = "annotate_masses")$files$libraries$sop$merged$structures$stereo,
           str_met = get_params(step = "annotate_masses")$files$libraries$sop$merged$structures$metadata,
           str_nam = get_params(step = "annotate_masses")$files$libraries$sop$merged$structures$names,
           str_tax_cla = get_params(step = "annotate_masses")$files$libraries$sop$merged$structures$taxonomies$cla,
           str_tax_npc = get_params(step = "annotate_masses")$files$libraries$sop$merged$structures$taxonomies$npc,
           adducts_list = get_params(step = "annotate_masses")$ms$adducts,
           clusters_list = get_params(step = "annotate_masses")$ms$clusters,
            neutral_losses_list = get_params(step = "annotate_masses")$ms$neutral_losses,
            ms_mode = get_params(step = "annotate_masses")$ms$polarity,
            tolerance_ppm = get_params(step = "annotate_masses")$ms$tolerances$mass$ppm$ms1,
-           tolerance_rt = get_params(step = "annotate_masses")$ms$tolerances$rt$minutes) {
+           tolerance_rt = get_params(step = "annotate_masses")$ms$tolerances$rt$adducts) {
     stopifnot("Your ppm tolerance must be <= 20" = tolerance_ppm <= 20)
     stopifnot("Your rt tolerance must be <= 0.05" = tolerance_rt <= 0.05)
 

diff --git a/R/filter_annotations.R b/R/filter_annotations.R
@@ -42,7 +42,7 @@ filter_annotations <-
            features = get_params(step = "filter_annotations")$files$features$prepared,
            rts = get_params(step = "filter_annotations")$files$libraries$temporal$prepared,
            output = get_params(step = "filter_annotations")$files$annotations$filtered,
-           tolerance_rt = get_params(step = "filter_annotations")$ms$tolerances$rt$minutes) {
+           tolerance_rt = get_params(step = "filter_annotations")$ms$tolerances$rt$library) {
     stopifnot("Annotations file(s) do(es) not exist" = all(lapply(X = annotations, FUN = file.exists) |> unlist()))
     stopifnot("Retention time file(s) do(es) not exist" = all(lapply(X = rts, FUN = file.exists) |> unlist()))
     stopifnot("Your features file does not exist." = file.exists(features))
@@ -83,7 +83,7 @@ filter_annotations <-
     if (!is.null(rts)) {
       log_debug(
         "Filtering annotations outside of",
-        tolerance_rt * 3,
+        tolerance_rt,
         "minutes tolerance"
       )
       features_annotated_table_2 <- features_annotated_table_1 |>
@@ -92,9 +92,8 @@ filter_annotations <-
           as.numeric(rt_target)) |>
         arrange(abs(candidate_structure_error_rt)) |>
         distinct(-candidate_structure_error_rt, -rt_target, .keep_all = TRUE) |>
-        ## ISSUE see #149 adapt for types and improve the * 3
         filter(
-          abs(candidate_structure_error_rt) <= abs(tolerance_rt * 3) |
+          abs(candidate_structure_error_rt) <= abs(tolerance_rt) |
             is.na(candidate_structure_error_rt)
         ) |>
         select(-rt_target, -type)

diff --git a/R/parse_cli_params.R b/R/parse_cli_params.R
@@ -228,8 +228,11 @@ parse_cli_params <- function(arguments, parameters) {
       parameters$ms$tolerances$mass$dalton$ms2 <-
         as.numeric(arguments$ms_tol_mas_dal_ms2)
     }
-    if (!is.null(arguments$ms_tol_rt_min)) {
-      parameters$ms$tolerances$rt$minutes <- as.numeric(arguments$ms_tol_rt_min)
+    if (!is.null(arguments$ms_tol_rt_add)) {
+      parameters$ms$tolerances$rt$adducts <- as.numeric(arguments$ms_tol_rt_add)
+    }
+    if (!is.null(arguments$ms_tol_rt_lib)) {
+      parameters$ms$tolerances$rt$library <- as.numeric(arguments$ms_tol_rt_lib)
     }
     if (!is.null(arguments$names_adduct)) {
       parameters$names$adduct <- as.character(arguments$names_adduct)

diff --git a/R/prepare_params.R b/R/prepare_params.R
@@ -106,7 +106,8 @@ prepare_params <- function(params_small = get_params(step = "prepare_params"),
   ms_tol_mas_ppm_ms2 <- params_advanced$ms$tolerances$mass$ppm$ms2
   ms_tol_mas_dal_ms1 <- params_advanced$ms$tolerances$mass$dalton$ms1
   ms_tol_mas_dal_ms2 <- params_advanced$ms$tolerances$mass$dalton$ms2
-  ms_tol_rt_min <- params_advanced$ms$tolerances$rt$minutes
+  ms_tol_rt_add <- params_advanced$ms$tolerances$rt$adducts
+  ms_tol_rt_lib <- params_advanced$ms$tolerances$rt$library
   names_extension <- params_advanced$names$extension
   names_features <- params_advanced$names$features
   names_filename <- params_advanced$names$filename
@@ -233,8 +234,8 @@ prepare_params <- function(params_small = get_params(step = "prepare_params"),
         ms_tol_mas_ppm_ms1
       yamls_params$annotate_masses$ms$tolerances$mass$dalton$ms1 <-
         ms_tol_mas_dal_ms1
-      yamls_params$annotate_masses$ms$tolerances$rt$minutes <-
-        ms_tol_rt_min
+      yamls_params$annotate_masses$ms$tolerances$rt$adducts <-
+        ms_tol_rt_add
       yamls_params$annotate_masses$names$source <-
         names_source
       yamls_params$annotate_masses$names$target <-
@@ -301,8 +302,8 @@ prepare_params <- function(params_small = get_params(step = "prepare_params"),
         fil_fea_pre
       yamls_params$filter_annotations$files$libraries$temporal$prepared <-
         fil_lib_tem_pre
-      yamls_params$filter_annotations$ms$tolerances$rt$minutes <-
-        ms_tol_rt_min
+      yamls_params$filter_annotations$ms$tolerances$rt$library <-
+        ms_tol_rt_lib
     },
     prepare_annotations_gnps = {
       yamls_params$prepare_annotations_gnps$files$annotations$raw$spectral$gnps <-

diff --git a/codemeta.json b/codemeta.json
@@ -616,7 +616,7 @@
     "SystemRequirements": null
   },
   "keywords": ["metaboliteannotation", "chemotaxonomy", "scoringsystem", "naturalproducts", "computationalmetabolomics", "taxonomicdistance", "specializedmetabolome"],
-  "fileSize": "3167.296KB",
+  "fileSize": "3168.108KB",
   "citation": [
     {
       "@type": "ScholarlyArticle",

diff --git a/inst/app.R b/inst/app.R
@@ -398,18 +398,31 @@ ui <- shiny::fluidPage(
             content = c("Mass tolerance (in Da) used for MS2 annotation.")
           ),
         shiny::sliderInput(
-          inputId = "ms_tol_rt_min",
-          label = "Retention time tolerance in minutes",
-          min = 0.01,
-          max = 0.20,
-          value = 0.05,
+          inputId = "ms_tol_rt_add",
+          label = "Retention time tolerance for adducts annotation in minutes",
+          min = 0.005,
+          max = 0.1,
+          value = 0.02,
+          ticks = FALSE
+        ) |>
+          shinyhelper::helper(
+            type = "inline",
+            content = c(
+              "Retention time tolerance (minutes) used for adducts annotation."
+            )
+          ),
+        shiny::sliderInput(
+          inputId = "ms_tol_rt_lib",
+          label = "Retention time tolerance for library annotation in minutes",
+          min = 0.005,
+          max = 0.2,
+          value = 0.1,
           ticks = FALSE
         ) |>
           shinyhelper::helper(
             type = "inline",
             content = c(
-              "Retention time tolerance (minutes) used for adducts attribution",
-              "and annotation if an experimental library is provided.",
+              "Retention time tolerance (minutes) used for library annotation.",
               "If no experimental library is given, does not impact results."
             )
           ),
@@ -2018,8 +2031,10 @@ save_input <- function(input) {
     shiny::isolate(input$ms_tol_mas_dal_ms1)
   yaml_advanced$ms$tolerances$mass$dalton$ms2 <-
     shiny::isolate(input$ms_tol_mas_dal_ms2)
-  yaml_advanced$ms$tolerances$rt$minutes <-
-    shiny::isolate(input$ms_tol_rt_min)
+  yaml_advanced$ms$tolerances$rt$adducts <-
+    shiny::isolate(input$ms_tol_rt_add)
+  yaml_advanced$ms$tolerances$rt$library <-
+    shiny::isolate(input$ms_tol_rt_lib)
   yaml_advanced$names$adduct <-
     shiny::isolate(input$names_adduct)
   yaml_advanced$names$extension <-

diff --git a/inst/params/default/annotate_masses.yaml b/inst/params/default/annotate_masses.yaml
@@ -213,8 +213,8 @@ ms:
 
     #' For retention time.
     rt:
-      #' Retention time tolerance in minutes. FLOAT
-      minutes: 0.05
+      #' Retention time tolerance for adducts in minutes. FLOAT
+      adducts: 0.02
 
 #' Names of the different variables in the input files.
 names:

diff --git a/inst/params/default/filter_annotations.yaml b/inst/params/default/filter_annotations.yaml
@@ -39,5 +39,5 @@ ms:
   tolerances:
     #' For retention time.
     rt:
-      #' Retention time tolerance in minutes. FLOAT
-      minutes: 0.05
+      #' Retention time tolerance for library in minutes. FLOAT
+      library: 0.1
diff --git a/inst/params/prepare_params_advanced.yaml b/inst/params/prepare_params_advanced.yaml
@@ -452,8 +452,11 @@ ms:
 
     #' For retention time.
     rt:
-      #' Retention time tolerance in minutes. FLOAT
-      minutes: 0.05
+      #' Retention time tolerance for adducts in minutes. FLOAT
+      adducts: 0.02
+
+      #' Retention time tolerance for library in minutes. FLOAT
+      library: 0.1
 
 #' Names of the different variables in the input files.
 names:

diff --git a/inst/pipelines/_targets.R b/inst/pipelines/_targets.R
@@ -1498,7 +1498,7 @@ list(
               neutral_losses_list = par_ann_mas$ms$neutral_losses,
               ms_mode = par_ann_mas$ms$polarity,
               tolerance_ppm = par_ann_mas$ms$tolerances$mass$ppm$ms1,
-              tolerance_rt = par_ann_mas$ms$tolerances$rt$minutes
+              tolerance_rt = par_ann_mas$ms$tolerances$rt$adducts
             )
         }
       ),
@@ -1781,7 +1781,7 @@ list(
         features = fea_pre,
         rts = lib_rt_rts,
         output = par_fil_ann$files$annotations$filtered,
-        tolerance_rt = par_fil_ann$ms$tolerances$rt$minutes
+        tolerance_rt = par_fil_ann$ms$tolerances$rt$library
       )
     }
   ),
@@ -2215,7 +2215,7 @@ list(
             neutral_losses_list = par_ann_mas$ms$neutral_losses,
             ms_mode = "pos",
             tolerance_ppm = benchmark_def_ann_mas$ms$tolerances$mass$ppm$ms1,
-            tolerance_rt = benchmark_def_ann_mas$ms$tolerances$rt$minutes
+            tolerance_rt = benchmark_def_ann_mas$ms$tolerances$rt$adducts
           )
       }
     ),
@@ -2241,7 +2241,7 @@ list(
             neutral_losses_list = par_ann_mas$ms$neutral_losses,
             ms_mode = "neg",
             tolerance_ppm = benchmark_def_ann_mas$ms$tolerances$mass$ppm$ms1,
-            tolerance_rt = benchmark_def_ann_mas$ms$tolerances$rt$minutes
+            tolerance_rt = benchmark_def_ann_mas$ms$tolerances$rt$adducts
           )
       }
     ),
@@ -2533,7 +2533,7 @@ list(
           features = benchmark_pre_meta_neg,
           rts = list(),
           output = "data/interim/benchmark/benchmark_ann_spe_fil_neg.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),
@@ -2551,7 +2551,7 @@ list(
           rts = list(),
           output =
             "data/interim/benchmark/benchmark_ann_spe_ms1_fil_neg.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),
@@ -2567,7 +2567,7 @@ list(
           features = benchmark_pre_meta_neg,
           rts = list(),
           output = "data/interim/benchmark/benchmark_ann_ms1_fil_neg.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),
@@ -2583,7 +2583,7 @@ list(
           features = benchmark_pre_meta_pos,
           rts = list(),
           output = "data/interim/benchmark/benchmark_ann_spe_fil_pos.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),
@@ -2601,7 +2601,7 @@ list(
           rts = list(),
           output =
             "data/interim/benchmark/benchmark_ann_spe_ms1_fil_pos.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),
@@ -2617,7 +2617,7 @@ list(
           features = benchmark_pre_meta_pos,
           rts = list(),
           output = "data/interim/benchmark/benchmark_ann_ms1_fil_pos.tsv.gz",
-          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$minutes
+          tolerance_rt = benchmark_def_fil_ann$ms$tolerances$rt$library
         )
       }
     ),

diff --git a/inst/scripts/docopt/annotate_masses.txt b/inst/scripts/docopt/annotate_masses.txt
@@ -2,7 +2,7 @@ You can use this script with the following example:
   Rscript inst/scripts/annotate_masses.R
 
 Usage:
-  annotate_masses.R [--fil-ann-pre-str=<fil-ann-pre-str>] [--fil-lib-sop-mer=<fil-lib-sop-mer>] [--fil-lib-add-neg=<fil-lib-add-neg>] [--fil-lib-add-pos=<fil-lib-add-pos>] [--fil-lib-add-pro=<fil-lib-add-pro>] [--ms-add-neg=<ms-add-neg>] [--ms-add-pos=<ms-add-pos>] [--ms-clu-neg=<ms-clu-neg>] [--ms-clu-pos=<ms-clu-pos>] [--ms-neu=<ms-neu>] [--ms-pol=<ms-pol>] [--ms-tol-mas-ppm-ms1=<ms-tol-mas-ppm-ms1>] [--ms-tol-mas-dal-ms1=<ms-tol-mas-dal-ms1>] [--ms-tol-rt-min=<ms-tol-rt-min>] [--force=<force>] [--nit-rul=<nit-rul>]
+  annotate_masses.R [--fil-ann-pre-str=<fil-ann-pre-str>] [--fil-lib-sop-mer=<fil-lib-sop-mer>] [--fil-lib-add-neg=<fil-lib-add-neg>] [--fil-lib-add-pos=<fil-lib-add-pos>] [--fil-lib-add-pro=<fil-lib-add-pro>] [--ms-add-neg=<ms-add-neg>] [--ms-add-pos=<ms-add-pos>] [--ms-clu-neg=<ms-clu-neg>] [--ms-clu-pos=<ms-clu-pos>] [--ms-neu=<ms-neu>] [--ms-pol=<ms-pol>] [--ms-tol-mas-ppm-ms1=<ms-tol-mas-ppm-ms1>] [--ms-tol-mas-dal-ms1=<ms-tol-mas-dal-ms1>] [--ms-tol-rt-add=<ms-tol-rt-add>] [--force=<force>]
 
 Arguments:
   fil-ann-pre-str            List of prepared structural annotations. STRING
@@ -20,7 +20,7 @@ Arguments:
   ms-pol                     Polarity used. Must be "pos" or "neg". STRING
   ms-tol-mas-ppm-ms1         Relative mass tolerance for MS1 in ppm. FLOAT
   ms-tol-mas-dal-ms1         Absolute mass tolerance for MS1 in Dalton. FLOAT
-  ms-tol-rt-min              Retention time tolerance in minutes. FLOAT
+  ms-tol-rt-add              Retention time tolerance for adducts in minutes. FLOAT
 
   force                      Do not use it. BOOLEAN
 

diff --git a/inst/scripts/docopt/filter_annotations.txt b/inst/scripts/docopt/filter_annotations.txt
@@ -2,15 +2,15 @@ You can use this script with the following example:
   Rscript inst/scripts/filter_annotations.R
 
 Usage:
-  filter_annotations.R [--fil-ann-fil=<fil-ann-fil>] [--fil-ann-pre-str=<fil-ann-pre-str>] [--fil-fea-pre=<fil-fea-prer>] [--fil-lib-tem-pre=<fil-lib-tem-pre>] [--ms-tol-rt-min=<ms-tol-rt-min>] [--nit-rul=<nit-rul>]
+  filter_annotations.R [--fil-ann-fil=<fil-ann-fil>] [--fil-ann-pre-str=<fil-ann-pre-str>] [--fil-fea-pre=<fil-fea-prer>] [--fil-lib-tem-pre=<fil-lib-tem-pre>] [--ms-tol-rt-lib=<ms-tol-rt-lib>]
 
-Arguments:  
+Arguments:
   fil-ann-fil                Filtered annotation file. STRING
   fil-ann-pre-str            List of prepared structural annotations. STRING
   fil-fea-pre                Prepared features file. STRING
   fil-lib-tem-pre            List of prepared temporal libraries. STRING
-  
-  ms-tol-rt-min              Retention time tolerance in minutes. FLOAT
+
+  ms-tol-rt-lib              Retention time tolerance for library in minutes. FLOAT
 
 Options:
   -h --help                  Shows this screen.

diff --git a/man/annotate_masses.Rd b/man/annotate_masses.Rd
diff --git a/man/filter_annotations.Rd b/man/filter_annotations.Rd
diff --git a/tests/testthat/_snaps/shinytest2/001.json b/tests/testthat/_snaps/shinytest2/001.json
@@ -108,7 +108,8 @@
     "ms_tol_mas_dal_ms2": 0.01,
     "ms_tol_mas_ppm_ms1": 10,
     "ms_tol_mas_ppm_ms2": 10,
-    "ms_tol_rt_min": 0.05,
+    "ms_tol_rt_add": 0.02,
+    "ms_tol_rt_lib": 0.1,
     "names_adduct": "best ion",
     "names_extension": true,
     "names_features": "row ID",

diff --git a/tests/testthat/test-functions.R b/tests/testthat/test-functions.R
@@ -593,7 +593,8 @@ test_that(desc = "Test functions", code = {
   arguments$ms_tol_mas_ppm_ms2 <- "x"
   arguments$ms_tol_mas_dal_ms1 <- "x"
   arguments$ms_tol_mas_dal_ms2 <- "x"
-  arguments$ms_tol_rt_min <- "x"
+  arguments$ms_tol_rt_add <- "x"
+  arguments$ms_tol_rt_lib <- "x"
   arguments$names_adduct <- "x"
   arguments$names_extension <- "x"
   arguments$names_features <- "x"