Mercurial > repos > recetox > recetox_aplcms_hybrid

changeset 10:27853894eeac draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox_aplcms commit 46f606d8d234807e603b55eb2791f76663b551ee"
author recetox
date Thu, 21 Oct 2021 15:03:51 +0000
parents d62f052efae6
children ab2b7948bdb7
files main.R recetox_aplcms_hybrid.xml recetox_aplcms_macros.xml test-data/hybrid.recetox.parquet test-data/unsupervised.recetox.parquet
diffstat 5 files changed, 52 insertions(+), 9 deletions(-) [+]
line wrap: on
line diff
--- a/main.R	Tue Oct 05 13:13:20 2021 +0000
+++ b/main.R	Thu Oct 21 15:03:51 2021 +0000
@@ -1,4 +1,5 @@
 library(recetox.aplcms)
+library(dplyr)
 
 save_extracted_features <- function(df, filename) {
   df <- as.data.frame(df)
@@ -6,11 +7,37 @@
   arrow::write_parquet(df[columns], filename)
 }
 
-save_feature_sample_table <- function(df, filename) {
+save_aligned_feature_table <- function(df, filename) {
   columns <- c("feature", "mz", "rt", "sample", "sample_rt", "sample_intensity")
   arrow::write_parquet(df[columns], filename)
 }
 
+save_recovered_feature_table <- function(df, filename, out_format) {
+  columns <- c("feature", "mz", "rt", "sample", "sample_rt", "sample_intensity")
+  if (out_format == "recetox") {
+    peak_table <- df[columns]
+    recetox_peak_table <- rcx_aplcms_to_rcx_xmsannotator(peak_table)
+    arrow::write_parquet(recetox_peak_table, filename)
+  } else {
+    arrow::write_parquet(df[columns], filename)
+  }
+}
+
+rcx_aplcms_to_rcx_xmsannotator <- function(peak_table) {
+    col_base <- c("feature", "mz", "rt")
+    output_table <- peak_table %>% distinct(across(any_of(col_base)))
+
+    for (level in levels(peak_table$sample)) {
+        subdata <- peak_table %>%
+            filter(sample == level) %>%
+            select(any_of(c(col_base, "sample_intensity"))) %>%
+            rename(!!level := "sample_intensity")
+        output_table <- inner_join(output_table, subdata, by = col_base)
+    }
+    output_table <- output_table %>% rename(peak = feature)
+    return(output_table)
+}
+
 known_table_columns <- function() {
   c("chemical_formula", "HMDB_ID", "KEGG_compound_ID", "mass", "ion.type",
     "m.z", "Number_profiles_processed", "Percent_found", "mz_min", "mz_max",
@@ -47,7 +74,7 @@
   mapply(save_extracted_features, dfs, filenames)
 }
 
-unsupervised_main <- function(sample_files, aligned_file, recovered_file, ...) {
+unsupervised_main <- function(sample_files, aligned_file, recovered_file, out_format, ...) {
   sample_files <- sort_samples_by_acquisition_number(sample_files)
 
   res <- unsupervised(filenames = sample_files, ...)
@@ -55,11 +82,11 @@
   save_all_extracted_features(res$extracted_features, sample_files)
   save_all_corrected_features(res$corrected_features, sample_files)
 
-  save_feature_sample_table(res$aligned_feature_sample_table, aligned_file)
-  save_feature_sample_table(res$recovered_feature_sample_table, recovered_file)
+  save_aligned_feature_table(res$aligned_feature_sample_table, aligned_file)
+  save_recovered_feature_table(res$recovered_feature_sample_table, recovered_file, out_format)
 }
 
-hybrid_main <- function(sample_files, known_table_file, updated_known_table_file, pairing_file, aligned_file, recovered_file, ...) {
+hybrid_main <- function(sample_files, known_table_file, updated_known_table_file, pairing_file, aligned_file, recovered_file, out_format, ...) {
   sample_files <- sort_samples_by_acquisition_number(sample_files)
 
   known <- read_known_table(known_table_file)
@@ -71,6 +98,6 @@
   save_all_extracted_features(res$extracted_features, sample_files)
   save_all_corrected_features(res$corrected_features, sample_files)
 
-  save_feature_sample_table(res$aligned_feature_sample_table, aligned_file)
-  save_feature_sample_table(res$recovered_feature_sample_table, recovered_file)
+  save_aligned_feature_table(res$aligned_feature_sample_table, aligned_file)
+  save_recovered_feature_table(res$recovered_feature_sample_table, recovered_file, out_format)
 }
--- a/recetox_aplcms_hybrid.xml	Tue Oct 05 13:13:20 2021 +0000
+++ b/recetox_aplcms_hybrid.xml	Thu Oct 21 15:03:51 2021 +0000
@@ -1,4 +1,4 @@
-<tool id="recetox_aplcms_hybrid" name="RECETOX apLCMS Hybrid" version="@TOOL_VERSION@+galaxy1">
+<tool id="recetox_aplcms_hybrid" name="RECETOX apLCMS Hybrid" version="@TOOL_VERSION@+galaxy2">
     <description>generate a feature table from LC/MS spectra</description>
     <macros>
         <import>recetox_aplcms_macros.xml</import>
@@ -25,6 +25,7 @@
                 pairing_file = '${feature_known_table_pairing}',
                 aligned_file = '${aligned_feature_sample_table}',
                 recovered_file = '${recovered_feature_sample_table}',
+                out_format = '$output_format.out_format',
                 min_exp = $noise_filtering.min_exp,
                 min_pres = $noise_filtering.min_pres,
                 min_run = $noise_filtering.min_run,
@@ -61,6 +62,7 @@
         <expand macro="feature_detection" />
         <expand macro="peak_alignment" />
         <expand macro="weak_signal_recovery" />
+        <expand macro="output_format" />
     </expand>
 
     <outputs>
@@ -75,6 +77,14 @@
             <param name="files" value="mbr_test0.mzml,mbr_test1.mzml,mbr_test2.mzml" ftype="mzml" />
             <output name="recovered_feature_sample_table" file="hybrid_recovered_feature_sample_table.parquet" ftype="parquet" />
         </test>
+        <test>
+            <param name="known_table" value="known_table.parquet" ftype="parquet" />
+            <param name="files" value="mbr_test0.mzml,mbr_test1.mzml,mbr_test2.mzml" ftype="mzml" />
+            <section name="output_format">
+                <param name="out_format" value="recetox" />
+            </section>
+            <output name="recovered_feature_sample_table" file="hybrid.recetox.parquet" ftype="parquet" />
+        </test>
     </tests>
 
     <help>
--- a/recetox_aplcms_macros.xml	Tue Oct 05 13:13:20 2021 +0000
+++ b/recetox_aplcms_macros.xml	Thu Oct 21 15:03:51 2021 +0000
@@ -5,6 +5,7 @@
             <requirement type="package" version="4.1.0">r-base</requirement>
             <requirement type="package" version="4.0.1">r-arrow</requirement>
             <requirement type="package" version="0.9.3">r-recetox-aplcms</requirement>
+            <requirement type="package" version="1.0.7">r-dplyr</requirement>
         </requirements>
     </xml>
 
@@ -19,7 +20,7 @@
             <param name="files" type="data" format="mzdata,mzml,mzxml,netcdf" multiple="true" min="3" label="data"
                    help="Mass spectrometry files for peak extraction." />
             <yield />
-        </inputs>
+       </inputs>
     </xml>
 
     <xml name="history_db">
@@ -132,6 +133,11 @@
                    help="The minimum number of raw data points to be considered as a true feature." />
         </section>
     </xml>
+    <xml name="output_format">
+       <section name="output_format" title="Output Format">
+              <param name="out_format" type="boolean" checked="false" truevalue="recetox" falsevalue="original" label="Use custom RECETOX output format?" />
+       </section>
+    </xml>
 
     <xml name="unsupervised_outputs">
         <data name="recovered_feature_sample_table" format="parquet" label="${tool.name} recovered_feature_sample_table on ${on_string}" />
Binary file test-data/hybrid.recetox.parquet has changed
Binary file test-data/unsupervised.recetox.parquet has changed