Rename proc.cdf to remove_noise

CHANGELOG.md

@@ -51,7 +51,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - refactored `adjust.time.R` [#64](https://github.com/RECETOX/recetox-aplcms/pull/64)[#102](https://github.com/RECETOX/recetox-aplcms/pull/102)
 - refactored `find.tol.time.R` [#91](https://github.com/RECETOX/recetox-aplcms/pull/91)
 - refactored `find.turn.point.R` [#91](https://github.com/RECETOX/recetox-aplcms/pull/91)
-- refactored `proc.cdf.R` and `adaptive.bin.R` [#137](https://github.com/RECETOX/recetox-aplcms/pull/137)
+- refactored `remove_noise.R` and `adaptive.bin.R` [#137](https://github.com/RECETOX/recetox-aplcms/pull/137)
 - refactored `cont.index.R` and renamed as `run_filter.R` [#156](https://github.com/RECETOX/recetox-aplcms/pull/156)
 - use proper sample IDs inside feature tables [#153](https://github.com/RECETOX/recetox-aplcms/pull/153)
 - exported functions in NAMESPACE [#154](https://github.com/RECETOX/recetox-aplcms/pull/154)

NAMESPACE

@@ -71,9 +71,9 @@ export(predict_smoothed_rt)
 export(prep.uv)
 export(preprocess_bandwidth)
 export(preprocess_profile)
-export(proc.cdf)
 export(prof.to.features)
 export(recover.weaker)
+export(remove_noise)
 export(rev_cum_sum)
 export(rm.ridge)
 export(run_filter)

R/hybrid.R

@@ -256,7 +256,7 @@ augment_known_table <- function(
 #' @param filenames The CDF file names.
 #' @param known_table Table of known chemicals.
 #' @param min_occurrence A feature has to show up in at least this number of profiles to be included in the final result.
-#' @param min_pres This is a parameter of the run filter, to be passed to the function proc.cdf().
+#' @param min_pres This is a parameter of the run filter, to be passed to the function remove_noise().
 #' @param min_run Run filter parameter. The minimum length of elution time for a series of signals grouped by m/z to be considered a peak.
 #' @param mz_tol m/z tolerance level for the grouping of data points. This value is expressed as the fraction of the m/z value. 
 #'  This value, multiplied by the m/z value, becomes the cutoff level. The recommended value is the machine's nominal accuracy level. 
@@ -345,7 +345,7 @@ hybrid <- function(
 
   message("**** feature extraction ****")
   profiles <- snow::parLapply(cluster, filenames, function(filename) {
-      proc.cdf(
+      remove_noise(
           filename = filename,
           min_pres = min_pres,
           min_run = min_run,

R/prof.to.features.R

@@ -869,10 +869,10 @@ normix.bic <- function(x, y, do.plot = FALSE, bw = c(15, 30, 60), eliminate = .0
 
 #' Generate feature table from noise-removed LC/MS profile.
 #' @description
-#' Each LC/MS profile is first processed by the function proc.cdf() to remove noise and reduce data size. A matrix containing m/z
-#' value, retention time, intensity, and group number is output from proc.cdf(). This matrix is then fed to the function
+#' Each LC/MS profile is first processed by the function remove_noise() to remove noise and reduce data size. A matrix containing m/z
+#' value, retention time, intensity, and group number is output from remove_noise(). This matrix is then fed to the function
 #' prof.to.features() to generate a feature list. Every detected feature is summarized into a single row in the output matrix from this function.
-#' @param profile The matrix output from proc.cdf(). It contains columns of m/z value, retention time, intensity and group number.
+#' @param profile The matrix output from remove_noise(). It contains columns of m/z value, retention time, intensity and group number.
 #' @param bandwidth A value between zero and one. Multiplying this value to the length of the signal along the time axis helps
 #'  determine the bandwidth in the kernel smoother used for peak identification.
 #' @param min_bandwidth The minimum bandwidth to use in the kernel smoother.

R/recover.weaker.R

@@ -636,7 +636,7 @@ refine_selection <- function(target_rt, rectangle, aligned_mz, rt_tol, mz_tol) {
 #' The default value is NA, in which case 0.5 times the retention time tolerance in the aligned object will be used.
 #' @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 mz_tol The mz.tol parameter provided to the proc.cdf() function. This helps retrieve the intermediate file.
+#' @param mz_tol The mz.tol parameter provided to the remove_noise() function. This helps retrieve the intermediate file.
 #' @param min_bandwidth The minimum bandwidth to use in the kernel smoother.
 #' @param max_bandwidth The maximum bandwidth to use in the kernel smoother.
 #' @param bandwidth A value between zero and one. Multiplying this value to the length of the signal along the

R/proc.cdf.R → R/remove_noise.R

@@ -64,7 +64,7 @@ load_data <- function(filename,
 #' @param cache Whether to use cache
 #' @return A matrix with four columns: m/z value, retention time, intensity, and group number.
 #' @export
-proc.cdf <- function(filename,
+remove_noise <- function(filename,
                      min_pres,
                      min_run,
                      mz_tol,

R/semi.sup.R

@@ -14,12 +14,12 @@ NULL
 #' @param known.table A data frame containing the known metabolite ions and previously found features.
 #' @param n.nodes The number of CPU cores to be used
 #' @param min.exp If a feature is to be included in the final feature table, it must be present in at least this number of spectra.
-#' @param min.pres This is a parameter of thr run filter, to be passed to the function proc.cdf().
-#' @param min.run This is a parameter of thr run filter, to be passed to the function proc.cdf().
+#' @param min.pres This is a parameter of thr run filter, to be passed to the function remove_noise().
+#' @param min.run This is a parameter of thr run filter, to be passed to the function remove_noise().
 #' @param mz.tol The user can provide the m/z tolerance level for peak identification. This value is expressed 
 #'  as the percentage of the m/z value. This value, multiplied by the m/z value, becomes the cutoff level.
 #' @param baseline.correct.noise.percentile The perenctile of signal strength of those EIC that don't pass the run filter, 
-#'  to be used as the baseline threshold of signal strength. This parameter is passed to proc.cdf()
+#'  to be used as the baseline threshold of signal strength. This parameter is passed to remove_noise()
 #' @param shape.model The mathematical model for the shape of a peak. There are two choices - bi-Gaussian and Gaussian. 
 #'  When the peaks are asymmetric, the bi-Gaussian is better. The default is bi-Gaussian.
 #' @param BIC.factor the factor that is multiplied on the number of parameters to modify the BIC criterion. If 
@@ -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, 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))
+                processable<-try(this.prof<-remove_noise(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")

R/two.step.hybrid.R

@@ -390,12 +390,12 @@ semisup_to_hybrid_adapter <- function(batchwise, batches_idx) {
 #' @param batch.align.rt.tol The RT tolerance for between-batch alignment.
 #' @param known.table A data frame containing the known metabolite ions and previously found features.
 #' @param cluster The number of CPU cores to be used
-#' @param min.pres This is a parameter of the run filter, to be passed to the function proc.cdf().
-#' @param min.run This is a parameter of the run filter, to be passed to the function proc.cdf().
+#' @param min.pres This is a parameter of the run filter, to be passed to the function remove_noise().
+#' @param min.run This is a parameter of the run filter, to be passed to the function remove_noise().
 #' @param mz.tol The user can provide the m/z tolerance level for peak identification. This value is expressed as the 
 #'  percentage of the m/z value. This value, multiplied by the m/z value, becomes the cutoff level.
 #' @param baseline.correct.noise.percentile The perenctile of signal strength of those EIC that don't pass the run filter, 
-#'  to be used as the baseline threshold of signal strength. This parameter is passed to proc.cdf()
+#'  to be used as the baseline threshold of signal strength. This parameter is passed to remove_noise()
 #' @param shape.model The mathematical model for the shape of a peak. There are two choices - "bi-Gaussian" and "Gaussian". 
 #'  When the peaks are asymmetric, the bi-Gaussian is better. The default is "bi-Gaussian".
 #' @param baseline.correct This is a parameter in peak detection. After grouping the observations, the highest observation 

R/unsupervised.R

@@ -46,7 +46,7 @@ get_sample_name <- function(filename) {
 #' 
 #' @param filenames The CDF file names.
 #' @param min_occurrence A feature has to show up in at least this number of profiles to be included in the final result.
-#' @param min_pres This is a parameter of the run filter, to be passed to the function proc.cdf().
+#' @param min_pres This is a parameter of the run filter, to be passed to the function remove_noise().
 #' @param min_run Run filter parameter. The minimum length of elution time for a series of signals grouped by m/z 
 #'  to be considered a peak.
 #' @param mz_tol m/z tolerance level for the grouping of data points. This value is expressed as the fraction of 
@@ -135,7 +135,7 @@ unsupervised <- function(
 
   message("**** feature extraction ****")
   profiles <- snow::parLapply(cluster, filenames, function(filename) {
-      proc.cdf(
+      remove_noise(
           filename = filename,
           min_pres = min_pres,
           min_run = min_run,

R/utils.R

@@ -4,7 +4,7 @@ NULL
 
 register_functions_to_cluster <- function(cluster) {
     snow::clusterExport(cluster, list(
-        'proc.cdf',
+        'remove_noise',
         'prof.to.features',
         'load.lcms',
         'adaptive.bin',
@@ -123,4 +123,4 @@ get_num_workers <- function() {
         num_workers <- parallel::detectCores()
     }
     return(num_workers)
-}
+}

tests/testthat/test-benchmark-extract_features.R

@@ -25,7 +25,7 @@ patrick::with_parameters_test_that(
     res <- microbenchmark::microbenchmark(
         extract_feature = {
             profiles <- snow::parLapply(cluster, filenames, function(filename) {
-                proc.cdf(
+                remove_noise(
                     filename = filename,
                     min_pres = min_pres,
                     min_run = min_run,

tests/testthat/test-extract_features.R

@@ -22,7 +22,7 @@ patrick::with_parameters_test_that(
     register_functions_to_cluster(cluster)
 
     profiles <- snow::parLapply(cluster, filenames, function(filename) {
-        proc.cdf(
+        remove_noise(
             filename = filename,
             min_pres = min_pres,
             min_run = min_run,

tests/testthat/test-proc.cdf.R

@@ -1,12 +1,12 @@
 patrick::with_parameters_test_that(
-  "test proc.cdf",
+  "test remove_noise",
   {
     if(ci_skip == TRUE) skip_on_ci()
 
     testdata <- file.path("..", "testdata")
     input_path <- file.path(testdata, "input", filename)
 
-    sut <- proc.cdf(
+    sut <- remove_noise(
       input_path,
       min_pres = min_pres,
       min_run = min_run,