RECETOX · hechth · Dec 6, 2022 · Dec 5, 2022 · Dec 5, 2022 · Dec 5, 2022
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -24,11 +24,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - exported functions in NAMESPACE [#154](https://github.com/RECETOX/recetox-aplcms/pull/154)
 - docstrings and documentation files for refactored functions [#160](https://github.com/RECETOX/recetox-aplcms/pull/160)
 - refactored parameter names to keep them more harmonized [#167](https://github.com/RECETOX/recetox-aplcms/pull/167)
-- moved some utility functions to a more suitable locations [#164](https://github.com/RECETOX/recetox-aplcms/pull/160)
+- moved some utility functions to a more suitable locations [#164](https://github.com/RECETOX/recetox-aplcms/pull/164)
 ### Removed
 - `extract_features` and `feature.align` [#154](https://github.com/RECETOX/recetox-aplcms/pull/154)
 - improper usage of `@examples` [#160](https://github.com/RECETOX/recetox-aplcms/pull/160)
-- several obsolete utility functions [#164](https://github.com/RECETOX/recetox-aplcms/pull/160)
+- several obsolete utility functions [#164](https://github.com/RECETOX/recetox-aplcms/pull/164)
+- several outdated `.Rd` files [#168](https://github.com/RECETOX/recetox-aplcms/pull/168)
+- default argument values from low-level functions [#168](https://github.com/RECETOX/recetox-aplcms/pull/168)
 
 ## [0.9.4] - 2022-05-10
 

diff --git a/R/adaptive.bin.R b/R/adaptive.bin.R
@@ -75,7 +75,7 @@ adaptive.bin <- function(features,
                          min_pres,
                          mz_tol,
                          baseline_correct,
-                         intensity_weighted = FALSE) {
+                         intensity_weighted) {
   # order inputs after mz values
   features <- features |> dplyr::arrange_at("mz")
 

diff --git a/R/compute_clusters.R b/R/compute_clusters.R
@@ -25,7 +25,7 @@ compute_clusters <- function(feature_tables,
                              mz_tol_absolute,
                              mz_max_diff,
                              rt_tol_relative,
-                             do.plot = FALSE,
+                             do.plot,
                              sample_names = NA) {
   number_of_samples <- length(feature_tables)
   all <- concatenate_feature_tables(feature_tables, sample_names)
@@ -34,6 +34,9 @@ compute_clusters <- function(feature_tables,
     mz_tol_relative <- find.tol(
       all$mz,
       mz_max_diff = mz_max_diff,
+      aver.bin.size = 4000,
+      min.bins = 50,
+      max.bins = 200,
       do.plot = do.plot
     )
     if (length(mz_tol_relative) == 0) {
@@ -60,7 +63,11 @@ compute_clusters <- function(feature_tables,
     number_of_samples = number_of_samples,
     mz_tol_relative = mz_tol_relative,
     rt_tol_relative = rt_tol_relative,
+    aver.bin.size = 200,
+    min.bins = 50,
+    max.bins = 100,
     mz_tol_absolute = mz_tol_absolute,
+    max.num.segments = 10000,
     do.plot = do.plot
   )
 

diff --git a/R/find.match.R b/R/find.match.R
@@ -5,7 +5,7 @@
 #' @param a A matrix of distances.
 #' @param unacceptable A distance larger than which cannot be accepted as pairs.
 #' @return A matrix the same dimension as the input matrix, with matched position taking value 1, and all other positions taking value 0.
-find.match <- function(a, unacceptable=4) {
+find.match <- function(a, unacceptable) {
     find.min.pos<-function(d)
     {
         pos<-which(d==min(d))[1]

diff --git a/R/find.tol.R b/R/find.tol.R
@@ -15,11 +15,11 @@ NULL
 #' @return The tolerance level is returned.
 #' @export
 find.tol <- function(mz,
-                     mz_max_diff = 1e-4,
-                     aver.bin.size = 4000,
-                     min.bins = 50,
-                     max.bins = 200,
-                     do.plot = TRUE) {
+                     mz_max_diff,
+                     aver.bin.size,
+                     min.bins,
+                     max.bins,
+                     do.plot) {
     mz <- mz[order(mz)]
     l <- length(mz)
     # pairwise m/z difference divided by their average, filtered outside of tolerance limit

diff --git a/R/find.tol.time.R b/R/find.tol.time.R
@@ -151,14 +151,14 @@ compute_rt_tol_relative <- function(breaks,
 #'  spectrum label, and peak group label. The rows are ordered by the median m/z of each peak group, and with each peak group the rows are ordered
 find.tol.time <- function(features,
                           number_of_samples,
-                          mz_tol_relative = 2e-5,
-                          rt_tol_relative = NA,
-                          aver.bin.size = 200,
-                          min.bins = 50,
-                          max.bins = 100,
-                          mz_tol_absolute = 0.01,
-                          max.num.segments = 10000,
-                          do.plot = TRUE) {
+                          mz_tol_relative,
+                          rt_tol_relative,
+                          aver.bin.size,
+                          min.bins,
+                          max.bins,
+                          mz_tol_absolute,
+                          max.num.segments,
+                          do.plot) {
     features <- dplyr::arrange_at(features, "mz")
 
     min_mz_tol <- compute_min_mz_tolerance(

diff --git a/R/hybrid.R b/R/hybrid.R
@@ -295,6 +295,7 @@ augment_known_table <- function(
 #' @param use_observed_range If the value is TRUE, the actual range of the observed locations of the feature in all the spectra will be used.
 #' @param recover_min_count Minimum number of raw data points to support a recovery.
 #' @param intensity_weighted Whether to use intensity to weight mass density estimation.
+#' @param do.plot Indicates whether plot should be drawn.
 #' @param cluster The number of CPU cores to be used
 #' @export
 hybrid <- function(
@@ -326,6 +327,7 @@ hybrid <- function(
   use_observed_range = TRUE,
   recover_min_count = 3,
   intensity_weighted = FALSE,
+  do_plot = FALSE,
   cluster = 4
 ) {
   if (!is(cluster, 'cluster')) {
@@ -351,7 +353,7 @@ hybrid <- function(
           baseline_correct = baseline_correct,
           baseline_correct_noise_percentile = baseline_correct_noise_percentile,
           intensity_weighted = intensity_weighted,
-          do.plot = FALSE,
+          do.plot = do_plot,
           cache = FALSE
       )
   })
@@ -369,7 +371,7 @@ hybrid <- function(
           component_eliminate = component_eliminate,
           moment_power = moment_power,
           BIC_factor = BIC_factor,
-          do.plot = FALSE
+          do.plot = do_plot
       )
   })
 
@@ -380,6 +382,7 @@ hybrid <- function(
     mz_tol_absolute = mz_tol_absolute,
     mz_max_diff = 10 * mz_tol,
     rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot,
     sample_names = sample_names
   )
 
@@ -401,7 +404,8 @@ hybrid <- function(
     mz_tol_relative = extracted_clusters$mz_tol_relative,
     mz_tol_absolute = extracted_clusters$rt_tol_relative,
     mz_max_diff = 10 * mz_tol,
-    rt_tol_relative = rt_tol_relative
+    rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot
   )
 
   message("**** feature alignment ****")
@@ -455,7 +459,8 @@ hybrid <- function(
     mz_tol_relative = mz_tol_relative,
     mz_tol_absolute = mz_tol_absolute,
     mz_max_diff = 10 * mz_tol,
-    rt_tol_relative = rt_tol_relative
+    rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot
   )
 
   message("**** computing template ****")
@@ -476,7 +481,8 @@ hybrid <- function(
     mz_tol_relative = recovered_clusters$mz_tol_relative,
     mz_tol_absolute = recovered_clusters$rt_tol_relative,
     mz_max_diff = 10 * mz_tol,
-    rt_tol_relative = rt_tol_relative
+    rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot
   )
 
   message("**** second feature alignment ****")

diff --git a/R/proc.cdf.R b/R/proc.cdf.R
@@ -65,14 +65,14 @@ load_data <- function(filename,
 #' @return A matrix with four columns: m/z value, retention time, intensity, and group number.
 #' @export
 proc.cdf <- function(filename,
-                     min_pres = 0.5,
-                     min_run = 12,
-                     mz_tol = 1e-05,
-                     baseline_correct = 0.0,
-                     baseline_correct_noise_percentile = 0.05,
-                     intensity_weighted = FALSE,
-                     do.plot = FALSE,
-                     cache = FALSE) {
+                     min_pres,
+                     min_run,
+                     mz_tol,
+                     baseline_correct,
+                     baseline_correct_noise_percentile,
+                     intensity_weighted,
+                     do.plot,
+                     cache) {
   raw.prof <- load_data(
     filename,
     cache,

diff --git a/R/prof.to.features.R b/R/prof.to.features.R
@@ -826,17 +826,17 @@ normix.bic <- function(x, y, moment_power = 2, do.plot = FALSE, bw = c(15, 30, 6
 #'  curve), and estimated total signal strength (total area of the estimated normal curve).
 #' @export
 prof.to.features <- function(profile,
-                             bandwidth = 0.5,
-                             min_bandwidth = NA,
-                             max_bandwidth = NA,
-                             sd_cut = c(0.01, 500),
-                             sigma_ratio_lim = c(0.01, 100),
-                             shape_model = "bi-Gaussian",
-                             peak_estim_method = "moment",
-                             moment_power = 1,
-                             component_eliminate = 0.01,
-                             BIC_factor = 2,
-                             do.plot = TRUE) {
+                             bandwidth,
+                             min_bandwidth,
+                             max_bandwidth,
+                             sd_cut,
+                             sigma_ratio_lim,
+                             shape_model,
+                             peak_estim_method,
+                             moment_power,
+                             component_eliminate,
+                             BIC_factor,
+                             do.plot) {
   validate_inputs(shape_model, peak_estim_method)
 
   profile <- preprocess_profile(profile)

diff --git a/R/recover.weaker.R b/R/recover.weaker.R
@@ -659,15 +659,15 @@ recover.weaker <- function(filename,
                            rt_tol_relative,
                            extracted_features,
                            adjusted_features,
-                           recover_mz_range = NA,
-                           recover_rt_range = NA,
-                           use_observed_range = TRUE,
-                           mz_tol = 1e-5,
-                           min_bandwidth = NA,
-                           max_bandwidth = NA,
-                           bandwidth = .5,
-                           recover_min_count = 3,
-                           intensity_weighted = FALSE) {
+                           recover_mz_range,
+                           recover_rt_range,
+                           use_observed_range,
+                           mz_tol,
+                           min_bandwidth,
+                           max_bandwidth,
+                           bandwidth,
+                           recover_min_count,
+                           intensity_weighted) {
   # load raw data
   data_table <- load_file(filename) |> dplyr::arrange_at("mz")
   times <- sort(unique(data_table$rt))

diff --git a/R/run_filter.R b/R/run_filter.R
@@ -5,7 +5,7 @@
 #' @param profile The matrix containing m/z, retention time, intensity, and EIC label as columns.
 #' @return unique_grp. 
 #' @export
-compute_uniq_grp <- function(profile, min_count_run, min_pres = 0.6) {
+compute_uniq_grp <- function(profile, min_count_run, min_pres) {
   grps <- profile  
   ttt <- table(grps)
   ttt <- ttt[ttt >= max(min_count_run * min_pres, 2)]
@@ -18,7 +18,7 @@ compute_uniq_grp <- function(profile, min_count_run, min_pres = 0.6) {
 #' @param times. Retention times vector.
 #' @return predicted rt.
 #' @export
-predict_smoothed_rt <- function(min_run = 5, times) {
+predict_smoothed_rt <- function(min_run, times) {
   # ksmooth(x, y, kernel, bandwidth, range, n.points, x.points)
   smooth <- ksmooth(
     seq(-min_run + 1, length(times) + min_run), 
@@ -78,8 +78,8 @@ label_val_to_keep <- function(min_run, timeline, min_pres, this_times, times) {
 #' @return A list is returned. new_rec - The matrix containing m/z, retention time, intensity, and EIC label as columns after applying the run filter.
 #' @export
 run_filter <- function(newprof,
-                       min_pres = 0.6,
-                       min_run = 5) {
+                       min_pres,
+                       min_run) {
 
   newprof <- tibble::tibble(mz = newprof[,1], rt = newprof[,2], intensi = newprof[,3], grps = newprof[,4])
 

diff --git a/R/semi.sup.R b/R/semi.sup.R
@@ -144,7 +144,7 @@ semi.sup <- function(
                 that.name<-paste(strsplit(tolower(files[j]),"\\.")[[1]][1],suf.prof,".profile",sep="_")
 
                 processable<-"goodgood"
-                processable<-try(this.prof<-proc.cdf(files[j], min.pres=min.pres, min.run=min.run, tol=mz.tol, baseline.correct=baseline.correct, baseline.correct.noise.percentile=baseline.correct.noise.percentile, do.plot=FALSE, intensity.weighted=intensity.weighted))
+                processable<-try(this.prof<-proc.cdf(files[j], min_pres=min.pres, min_run=min.run, mz_tol=mz.tol, baseline_correct=baseline.correct, baseline_correct_noise_percentile=baseline.correct.noise.percentile, do.plot=FALSE, intensity_weighted=intensity.weighted, cache=FALSE))
                 if(substr(processable,1,5)=="Error")
                 {
                     file.copy(from=files[j], to="error_files")
@@ -156,7 +156,7 @@ semi.sup <- function(
                 if(substr(processable,1,5)!="Error")
                 {
                     processable.2<-"goodgood"
-                    processable.2<-try(this.feature<-prof.to.features(this.prof, min.bw=min.bw, max.bw=max.bw, sd.cut=sd.cut, shape.model=shape.model, estim.method=peak.estim.method, do.plot=FALSE, component.eliminate=component.eliminate, power=moment.power, BIC.factor=BIC.factor))
+                    processable.2<-try(this.feature<-prof.to.features(profile, bandwidth = 0.5, min_bandwidth=min.bw, max_bandwidth=max.bw, sd_cut=sd.cut, sigma_ratio_lim = c(0.01, 100), shape_model=shape.model, peak_estim_method=peak.estim.method, do.plot=FALSE, component_eliminate=component.eliminate, moment_power=moment.power, BIC_factor=BIC.factor))
 
                     if(substr(processable.2,1,5)=="Error")
                     {

diff --git a/R/unsupervised.R b/R/unsupervised.R
@@ -88,6 +88,7 @@ get_sample_name <- function(filename) {
 #'  the spectra will be used.
 #' @param recover_min_count Minimum number of raw data points to support a recovery.
 #' @param intensity_weighted Whether to use intensity to weight mass density estimation.
+#' @param do.plot Indicates whether plot should be drawn.
 #' @param cluster The number of CPU cores to be used
 #' @export
 unsupervised <- function(
@@ -116,6 +117,7 @@ unsupervised <- function(
   use_observed_range = TRUE,
   recover_min_count = 3,
   intensity_weighted = FALSE,
+  do_plot = FALSE,
   cluster = 4
 ) {
   if (!is(cluster, 'cluster')) {
@@ -141,7 +143,7 @@ unsupervised <- function(
           baseline_correct = baseline_correct,
           baseline_correct_noise_percentile = baseline_correct_noise_percentile,
           intensity_weighted = intensity_weighted,
-          do.plot = FALSE,
+          do.plot = do_plot,
           cache = FALSE
       )
   })
@@ -159,7 +161,7 @@ unsupervised <- function(
           component_eliminate = component_eliminate,
           moment_power = moment_power,
           BIC_factor = BIC_factor,
-          do.plot = FALSE
+          do.plot = do_plot
       )
   })
 
@@ -170,6 +172,7 @@ unsupervised <- function(
     mz_tol_absolute = mz_tol_absolute,
     mz_max_diff = 10 * mz_tol,
     rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot,
     sample_names = sample_names
   )
 
@@ -191,7 +194,8 @@ unsupervised <- function(
     mz_tol_relative = extracted_clusters$mz_tol_relative,
     mz_tol_absolute = extracted_clusters$rt_tol_relative,
     mz_max_diff = 10 * mz_tol,
-    rt_tol_relative = rt_tol_relative
+    rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot
   )
 
   message("**** feature alignment ****")
@@ -235,7 +239,8 @@ unsupervised <- function(
     mz_tol_relative = adjusted_clusters$mz_tol_relative,
     mz_tol_absolute = adjusted_clusters$rt_tol_relative,
     mz_max_diff = 10 * mz_tol,
-    rt_tol_relative = rt_tol_relative
+    rt_tol_relative = rt_tol_relative,
+    do.plot = do_plot
   )
 
   message("**** feature alignment ****")

diff --git a/man/adaptive.bin.Rd b/man/adaptive.bin.Rd
diff --git a/man/aligned.Rd b/man/aligned.Rd