updates

Author: mwang87

Makefile

@@ -1,14 +1,5 @@
 run:
 	nextflow run ./nf_workflow.nf -resume -c nextflow.config
 
-run_importer_workflow:
-	nextflow run ./nf_workflow_importer.nf -resume -c nextflow.config
-
-run_slurm:
-	nextflow run ./nf_workflow.nf -resume -c nextflow_slurm.config
-
-run_docker:
-	nextflow run ./nf_workflow.nf -resume -with-docker <CONTAINER NAME>
-
 init_modules:
 	git submodule update --init --recursive

bin/NextflowModules

@@ -0,0 +1 @@
+wget https://external.gnps2.org/gnpslibrary/GNPS-EMBL-MCF.mgf

data/get_data.sh

@@ -2,7 +2,7 @@
 nextflow.enable.dsl=2
 
 // 
-params.input_spectra = "$baseDir/data/"
+params.input_libraries = "$baseDir/data/"
 
 //This publish dir is mostly  useful when we want to import modules in other workflows, keep it here usually don't change it
 params.publishdir = "$launchDir"
@@ -29,70 +29,11 @@ _publishdir = "${_publishdir}/nf_output"
 // the publishdir is a key word that we're using around all our modules to control where the output files will be saved
 include {summaryLibrary} from "$MODULES_FOLDER/nf_library_search_modules.nf" addParams(publishdir: _publishdir)
 
-process processDataPython {
-    /* This is a sample process that runs a python script.
-
-    For each process, you can specify the publishDir, which is the directory where the output files will be saved.
-    You can also specify the conda environment that will be used to run the process.
-    The input and output blocks define the input and output files for the process.
-    The script block contains the command that will be run in the process.
-    */
-
-    publishDir "$_publishdir", mode: 'copy'
-
-    conda "$TOOL_FOLDER/conda_env.yml"
-
-    input:
-    file input 
-
-    output:
-    file 'python_output.tsv'
-
-    script:
-    """
-    python $TOOL_FOLDER/python_script.py --input_filename $input --output_filename python_output.tsv
-    """
-}
-
-workflow Main{
-    // -------  -------
-    /* 
-    For each named workflow, add 'take' and 'main' blocks.
-
-    --take--
-    For the take block, you can specify the input parameters that will be passed to the workflow.
-    Another option instead of passing all the values, is to use a map, which is a dictionary of key-value pairs.
-
-    --main--
-    The main block is where the workflow is defined. You can call other processes and workflows from here.
-
-    --emit--
-    This is an optional block and if you are new to nextflow you can ignore it.
-    This is can be useful in future generations of nextflow, replacing the need for the 'publishDir' directive.
-    */
-
-    take: 
-    input_map
-
-    main:
-    libraries_ch = Channel.fromPath(input_map.input_spectra + "/*.mgf" )
-    // summaryLibrary(libraries_ch)
-    library_summary_ch = summaryLibrary(libraries_ch)
-    processDataPython(library_summary_ch)
-
-    emit:
-    library_summary_ch // doesn't need .out as it is already the output of summaryLibrary, assigned to library_summary_ch
-    py_out = processDataPython.out
-}
-
 workflow {
-    /* 
-    The input map is created to reduce the dependency of the other workflows to the `params`
-    */
-    input_map = [
-        input_spectra: params.input_spectra
-    ]
-    out = Main(input_map)
-    out[0].view() // library_summary_ch
-    out.py_out.view()
+    libraries_ch = Channel.fromPath(params.input_libraries + "/*.mgf")
+    // Get the first one
+    library_summary_ch = summaryLibrary(libraries_ch.first())
+
+    // merge summary files as tsv
+    library_summary_ch.collectFile(name: 'librarysummary.tsv', keepHeader: true, storeDir: _publishdir + "/librarysummary")
 }

nf_workflow.nf

@@ -1,23 +1,17 @@
-name: template_nextflow_workflow
-displayname: STUFF
+name: LibrarySummary_workflow
+displayname: LibrarySummary_workflow
 Views:
 -   name: Summary List
     displayname: Summary List
     viewname: summarylist
     displaytype: datatable
     parameters:
-        filename: nf_output/python_output.tsv
+        filename: nf_output/librarysummary/librarysummary.tsv
         columns:
-            -   title: "View LCMS"
-                data: filename
-            -   title: "filename"
-                data: filename
-            -   title: "OUTPUT"
-                data: OUTPUT
-            -   title: "OUTPUT2"
-                data: OUTPUT2
-        columnDefs: '[ {"targets": 0,"data": null,"render": function ( data, type, row, meta ) {
-            return `
-            <a target="_blank" href="/dashboards/lcms?usi=mzspec:GNPS2-${task}:${encodeURIComponent(row["filename"])}">View LCMS - mzspec:GNPS2-${task}:${row["filename"]}</a>
-            `;}}]'
+            -   title: "spectrum_id"
+                data: spectrum_id
+            -   title: "compound_name"
+                data: compound_name
+            -   title: "smiles"
+                data: smiles
 

workflowdisplay.yaml

@@ -1,5 +1,5 @@
-workflowname: template_nextflow_workflow
-workflowdescription: template_nextflow_workflow
+workflowname: LibrarySummary_workflow
+workflowdescription: LibrarySummary_workflow
 workflowlongdescription: This is a template nextflow workflow for GNPS2
 workflowversion: "2025.06.20"
 workflowfile: nf_workflow.nf
@@ -12,10 +12,10 @@ parameterlist:
 
     - displayname: Input Data Folder
       paramtype: fileselector
-      nf_paramname: input_spectra
+      nf_paramname: input_libraries
       formplaceholder: Enter the path to data
       formvalue: ""
-      targettaskfolder: input_spectra
+      targettaskfolder: input_libraries
       optional: false
       selectsinglefile: false
       folderunroll: true