Mercurial > repos > recetox > recetox_aplcms_compute_clusters
changeset 2:ce00e1d03c31 draft
planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox_aplcms commit 724ecb1b81ebd8a67488b8a9397177b2ff0357db
| author | recetox |
|---|---|
| date | Wed, 24 May 2023 14:48:47 +0000 |
| parents | 092bbb03a217 |
| children | a054eae3123c |
| files | help.xml macros.xml recetox_aplcms_compute_clusters.xml test-data/remove_noise_docker.parquet utils.R |
| diffstat | 5 files changed, 14 insertions(+), 66 deletions(-) [+] |
line wrap: on
line diff
--- a/help.xml Mon Apr 03 14:56:58 2023 +0000 +++ b/help.xml Wed May 24 14:48:47 2023 +0000 @@ -110,7 +110,6 @@ ================================= Group features with `mz` and `rt` using tolerances within the tolerance into clusters, creating larger features from raw data points. -Custom tolerances for `mz` and `rt` are computed based on the given parameters. The tool takes a collection of all detected features and computes the clusters over a global feature table, adding the `sample_id` and `cluster` columns to the table. Example Output @@ -133,7 +132,7 @@ recetox-aplcms - correct time ============================= -Apply spline-based retention time correction to a feature table given the template table and the computed `mz` and `rt` tolerances. +Apply spline-based retention time correction to a feature table given the template table and the `mz` and `rt` tolerances. Example Output --------------
--- a/macros.xml Mon Apr 03 14:56:58 2023 +0000 +++ b/macros.xml Wed May 24 14:48:47 2023 +0000 @@ -1,5 +1,5 @@ <macros> - <token name="@TOOL_VERSION@">0.10.3</token> + <token name="@TOOL_VERSION@">0.11.0</token> <xml name="requirements"> <requirements> <requirement type="package" version="@TOOL_VERSION@">r-recetox-aplcms</requirement> @@ -93,32 +93,11 @@ </section> </xml> - <xml name="compute_clusters_params"> - <conditional name="tolerances_input_method"> - <param name="input_method" type="select" display="radio" label="Tolerances input method" - help="Tolerances can be entered directly or loaded from a file."> - <option value="direct" selected="true">direct</option> - <option value="file">file</option> - </param> - <when value="direct"> - <param name="mz_tol_relative" type="float" optional="true" label="Relative m/z tolerance" - help="Relative m/z tolerance to use for grouping features. - If not provided, it is calculated from the data using kernel density estimation." /> - <param name="rt_tol_relative" type="float" optional="true" label="Relative rt tolerance [unit corresponds to the retention time]" - help="Relative retention time tolerance to use for grouping features. - If not provided, it is calculated from the data using kernel density estimation." /> - </when> - <when value="file"> - <param label="Input tolerances values" name="input_tolerances" type="data" format="parquet" - help="Table containing tolerance values." /> - </when> - </conditional> - <param name="mz_tol_absolute" type="float" label="Minimal absolute m/z tolerance [Da]" value="1e-05" - help="During the clustering, an m/z tolerance is computed based on the data and the specified relative tolerance. - This parameter allows the specification of a minimal value of this tolerance." /> - <param name="mz_max_diff" type="float" label="Maximal m/z difference [Da]" value="0.01" - help="Maximum allowed difference between feature m/z values to belong to the same cluster." /> - + <xml name="tolerances"> + <param name="mz_tol_relative_ppm" type="float" value="10" label="Relative m/z tolerance [ppm]" + help="Relative m/z tolerance to use for grouping features." /> + <param name="rt_tol" type="float" value="5" label="Retention time tolerance [unit corresponds to the retention time]" + help="Retention time tolerance to use for grouping features." /> </xml> <xml name="recover_weaker_params">
--- a/recetox_aplcms_compute_clusters.xml Mon Apr 03 14:56:58 2023 +0000 +++ b/recetox_aplcms_compute_clusters.xml Wed May 24 14:48:47 2023 +0000 @@ -22,42 +22,21 @@ feature_tables <- feature_tables[ordering] sample_names <- sample_names[ordering] - #if $tolerances_input_method.input_method == "file" - tolerances <- load_data_from_parquet_file('$input_tolerances') - #end if - - clusters <- compute_clusters( + clusters <- compute_clusters_simple( feature_tables = feature_tables, - #if $tolerances_input_method.input_method == "file" - mz_tol_relative = get_mz_tol(tolerances), - rt_tol_relative = get_rt_tol(tolerances), - #else - #if $tolerances_input_method.mz_tol_relative: - mz_tol_relative = $tolerances_input_method.mz_tol_relative, - #else: - mz_tol_relative = NA, - #end if - #if $tolerances_input_method.rt_tol_relative: - rt_tol_relative = $tolerances_input_method.rt_tol_relative, - #else: - rt_tol_relative = NA, - #end if - #end if - mz_max_diff = 10 * $mz_max_diff, - mz_tol_absolute = $mz_tol_absolute, sample_names = sample_names, - do.plot = FALSE + mz_tol_ppm = $mz_tol_relative_ppm, + rt_tol = $rt_tol ) save_parquet_collection(clusters, sample_names, "clustered") - save_tolerances(clusters, '$tolerances') ]]></configfile> </configfiles> <inputs> <param name="files" type="data_collection" collection_type="list" format="parquet" label="Input data" help="List of tables containing features." /> - <expand macro="compute_clusters_params"/> + <expand macro="tolerances"/> </inputs> <outputs> @@ -65,7 +44,6 @@ label="${tool.name} feature_tables on ${on_string}"> <discover_datasets pattern="__designation__" directory="clustered" format="parquet" /> </collection> - <data name="tolerances" format="parquet" label="${tool.name} on ${on_string} (updated tolerances)" /> </outputs> <tests>
--- a/utils.R Mon Apr 03 14:56:58 2023 +0000 +++ b/utils.R Wed May 24 14:48:47 2023 +0000 @@ -39,11 +39,11 @@ return(features) } -save_parquet_collection <- function(table, sample_names, subdir) { +save_parquet_collection <- function(feature_tables, sample_names, subdir) { dir.create(subdir) - for (i in seq_len(length(table$feature_tables))) { + for (i in seq_len(length(feature_tables))) { filename <- file.path(subdir, paste0(subdir, "_", sample_names[i], ".parquet")) - feature_table <- as.data.frame(table$feature_tables[[i]]) + feature_table <- as.data.frame(feature_tables[[i]]) feature_table <- save_sample_name(feature_table, sample_names[i]) arrow::write_parquet(feature_table, filename) } @@ -59,14 +59,6 @@ arrow::write_parquet(data.frame(mz_tolerance, rt_tolerance), tol_file) } -get_mz_tol <- function(tolerances) { - return(tolerances$mz_tolerance) -} - -get_rt_tol <- function(tolerances) { - return(tolerances$rt_tolerance) -} - save_aligned_features <- function(aligned_features, metadata_file, rt_file, intensity_file) { save_data_as_parquet_file(aligned_features$metadata, metadata_file) save_data_as_parquet_file(aligned_features$rt, rt_file)