Merge pull request #504 from zargham-ahmad/issue439

Change output csv types to tsv
RECETOX · Apr 16, 2024 · 4b8a43b · 4b8a43b
2 parents 79e9939 + 8d0a3d3
commit 4b8a43b
Show file tree

Hide file tree

Showing 30 changed files with 464 additions and 411 deletions.
diff --git a/.github/workflows/ci.yaml b/.github/workflows/ci.yaml
@@ -183,7 +183,7 @@ jobs:
     # This job runs on Linux
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/download-artifact@v3
+    - uses: actions/download-artifact@v4
       with:
         path: artifacts
     - uses: actions/setup-python@v5

diff --git a/.github/workflows/pr.yaml b/.github/workflows/pr.yaml
@@ -345,7 +345,7 @@ jobs:
       matrix:
         python-version: ['3.7']
     steps:
-    - uses: actions/download-artifact@v3
+    - uses: actions/download-artifact@v4
       with:
         path: artifacts
     - uses: actions/setup-python@v5

diff --git a/tools/matchms/matchms_metadata_export.xml b/tools/matchms/matchms_metadata_export.xml
@@ -1,4 +1,4 @@
-<tool id="matchms_metadata_export" name="matchms metadata export" version="@TOOL_VERSION@+galaxy1" profile="21.09">
+<tool id="matchms_metadata_export" name="matchms metadata export" version="@TOOL_VERSION@+galaxy2" profile="21.09">
     <description>extract all metadata from mass spectra file to tabular format</description>
     <macros>
         <import>macros.xml</import>
@@ -18,6 +18,7 @@
 <configfiles>
 <configfile name="matchms_python_cli">
 import matchms
+import pandas as pd
 from matchms.importing import load_from_msp, load_from_mgf
 from matchms.exporting.metadata_export import export_metadata_as_csv
 
@@ -28,6 +29,10 @@ if "$harmonize_metadata" == "False":
 spectra_list = list(load_from_${input_file.ext}("${input_file}", $harmonize_metadata))
 
 export_metadata_as_csv(spectra_list, "${output_file}")
+
+data = pd.read_csv("${output_file}")
+
+data.to_csv("${output_file}", sep='\t', index=False)
 </configfile>
 </configfiles>
 
@@ -38,19 +43,19 @@ export_metadata_as_csv(spectra_list, "${output_file}")
     </inputs>
 
     <outputs>
-        <data label="matchms extract metadata on ${on_string}" name="output_file" format="csv"/>
+        <data label="matchms extract metadata on ${on_string}" name="output_file" format="tsv"/>
     </outputs>
 
     <tests>
         <test>
             <param name="input_file" value="convert/mgf_out.mgf" ftype="mgf"/>
             <param name="harmonize_metadata" value="True"/>
-            <output name="output_file" file="convert/metadata.csv" ftype="csv" compare="sim_size" delta="0"/>
+            <output name="output_file" file="convert/metadata.tsv" ftype="tsv" compare="sim_size" delta="0"/>
         </test>
         <test>
             <param name="input_file" value="similarity/RECETOX_Exposome_pesticides_HR_MS_20220323.msp" ftype="msp"/>
             <param name="harmonize_metadata" value="True"/>
-            <output name="output_file" file="convert/metadata.csv" ftype="csv" compare="sim_size" delta="0"/>
+            <output name="output_file" file="convert/metadata.tsv" ftype="tsv" compare="sim_size" delta="0"/>
         </test>
     </tests>
 

diff --git a/tools/matchms/test-data/convert/metadata.csv b/tools/matchms/test-data/convert/metadata.csv
diff --git a/tools/matchms/test-data/convert/metadata.tsv b/tools/matchms/test-data/convert/metadata.tsv
diff --git a/tools/msmetaenhancer/msmetaenhancer.xml b/tools/msmetaenhancer/msmetaenhancer.xml
@@ -1,4 +1,4 @@
-<tool id="msmetaenhancer" name="MSMetaEnhancer" version="@TOOL_VERSION@+galaxy3">
+<tool id="msmetaenhancer" name="MSMetaEnhancer" version="@TOOL_VERSION@+galaxy4" profile="21.09">
     <description>annotate MS data</description>
 
     <macros>
@@ -84,7 +84,7 @@
             <change_format>
                 <when input="input_file.ext" value="mgf" format="mgf" />
                 <when input="input_file.ext" value="json" format="json" />
-                <when input="input_file.ext" value="csv" format="csv" />
+                <when input="input_file.ext" value="csv" format="tsv" />
                 <when input="input_file.ext" value="tsv" format="tsv" />
                 <when input="input_file.ext" value="xlsx" format="xlsx" />
             </change_format>

diff --git a/tools/msmetaenhancer/msmetaenhancer_wrapper.py b/tools/msmetaenhancer/msmetaenhancer_wrapper.py
@@ -56,7 +56,10 @@ def main(argv):
     if args.file_format == 'xlsx':
         handle_xlsx_file(app, args.output_file)
     else:
-        app.save_data(args.output_file, file_format=args.file_format)
+        if args.file_format == 'csv':
+            app.save_data(args.output_file, file_format="tsv")
+        else:
+            app.save_data(args.output_file, file_format=args.file_format)
     return 0
 
 

diff --git a/tools/ramclustr/ramclustr.xml b/tools/ramclustr/ramclustr.xml
@@ -1,4 +1,4 @@
-<tool id="ramclustr" name="RAMClustR" version="@TOOL_VERSION@+galaxy3" profile="21.09">
+<tool id="ramclustr" name="RAMClustR" version="@TOOL_VERSION@+galaxy4" profile="21.09">
     <description>A feature clustering algorithm for non-targeted mass spectrometric metabolomics data.</description>
     <macros>
         <import>macros.xml</import>
@@ -153,7 +153,7 @@
     </inputs>
 
     <outputs>
-        <data label="Spec Abundance of ${on_string}" name="spec_abundance" format="csv" />
+        <data label="Spec Abundance of ${on_string}" name="spec_abundance" format="tsv" />
         <expand macro="output_msp"/>
     </outputs>
 
@@ -175,7 +175,7 @@
                 <param name="ExpDes" value="lc-ramclustr-define-experiment.csv" ftype="csv"/>
             </section>
             <output name="mass_spectra_merged" file="test1_fill_xcms_1.msp" ftype="msp"/>
-            <output name="spec_abundance" file="test1_spec_abundance_xcms_1.csv" ftype="csv" compare="sim_size" delta="100"/>
+            <output name="spec_abundance" file="test1_spec_abundance_xcms_1.tsv" ftype="tsv" compare="sim_size" delta="100"/>
         </test>
         <test expect_num_outputs="2"><!-- TEST 2 -->
             <section name="filetype">
@@ -196,7 +196,7 @@
                 </section>
             </section>
             <output name="mass_spectra_merged" file="test2_fill_xcms_2.msp" ftype="msp" compare="sim_size" delta="100"/>
-            <output name="spec_abundance" file="test2_spec_abundance_xcms_2.csv" ftype="csv" compare="sim_size" delta="100"/>
+            <output name="spec_abundance" file="test2_spec_abundance_xcms_2.tsv" ftype="tsv" compare="sim_size" delta="100"/>
         </test>
         <test expect_num_outputs="2"><!-- TEST 3 -->
             <section name="filetype">
@@ -214,7 +214,7 @@
                 <param name="mult" value="1"/>
             </section>
             <output name="mass_spectra_merged" file="test3_spectra_csv_1.msp" ftype="msp"/>
-            <output name="spec_abundance" file="test3_spec_abundance_csv_1.csv" ftype="csv"/>
+            <output name="spec_abundance" file="test3_spec_abundance_csv_1.tsv" ftype="tsv"/>
         </test>
         <test expect_num_outputs="2"><!-- TEST 4 -->
             <section name="filetype">

diff --git a/tools/ramclustr/ramclustr_wrapper.R b/tools/ramclustr/ramclustr_wrapper.R
@@ -3,9 +3,9 @@ store_output <- function(ramclustr_obj,
                          output_spec_abundance,
                          msp_file) {
   RAMClustR::write.msp(ramclustr_obj, one.file = output_merge_msp)
-  write.csv(ramclustr_obj$SpecAbund,
+  write.table(ramclustr_obj$SpecAbund,
     file = output_spec_abundance,
-    row.names = TRUE, quote = FALSE
+    row.names = TRUE, quote = FALSE, col.names = NA, sep = "\t"
   )
 
   if (!is.null(msp_file)) {