Merge pull request #19 from ajmaurais/single_final_sky

Single final sky
mriffle · Sep 16, 2024 · bca28cd · bca28cd
2 parents abaea2b + 586a531
commit bca28cd
Show file tree

Hide file tree

Showing 5 changed files with 53 additions and 76 deletions.
diff --git a/main.nf b/main.nf
@@ -10,7 +10,6 @@ include { diann_search } from "./workflows/diann_search"
 include { get_mzmls as get_narrow_mzmls } from "./workflows/get_mzmls"
 include { get_mzmls as get_wide_mzmls } from "./workflows/get_mzmls"
 include { skyline_import } from "./workflows/skyline_import"
-include { skyline_annotate_doc } from "./workflows/skyline_annotate_document"
 include { skyline_reports } from "./workflows/skyline_run_reports"
 include { generate_dia_qc_report } from "./workflows/generate_qc_report"
 include { panorama_upload_results } from "./workflows/panorama_upload"
@@ -88,7 +87,6 @@ workflow {
         }
     }
 
-
     // if accessing panoramaweb and running on aws, set up an aws secret
     if(workflow.profile == 'aws' && is_panorama_used) {
         GET_AWS_USER_ID()
@@ -324,19 +322,13 @@ workflow {
                 skyline_template_zipfile,
                 fasta,
                 final_elib,
-                wide_mzml_ch
+                wide_mzml_ch,
+                replicate_metadata
             )
             proteowizard_version = skyline_import.out.proteowizard_version
         }
 
-        // annotate skyline document if replicate_metadata was specified
-        if(params.replicate_metadata != null || params.pdc.study_id != null) {
-            skyline_annotate_doc(skyline_import.out.skyline_results,
-                                 replicate_metadata)
-            final_skyline_file = skyline_annotate_doc.out.skyline_results
-        } else {
-            final_skyline_file = skyline_import.out.skyline_results
-        }
+        final_skyline_file = skyline_import.out.skyline_results
 
         // generate QC report
         if(!params.qc_report.skip) {

diff --git a/modules/qc_report.nf b/modules/qc_report.nf
@@ -47,42 +47,26 @@ process PARSE_REPORTS {
     script:
     def metadata_arg = replicate_metadata.name == 'EMPTY' ? '' : "-m $replicate_metadata"
 
-    if(params.qc_report.normalization_method == null)
-        """
-        dia_qc parse --ofname qc_report_data.db3 ${metadata_arg} \
-            --groupBy ${params.skyline.group_by_gene ? 'gene' : 'protein'} \
-            '${replicate_report}' '${precursor_report}' \
-            > >(tee "parse_data.stdout") 2> >(tee "parse_data.stderr")
-
-        dia_qc qc_qmd ${format_flags(params.qc_report.standard_proteins, '--addStdProtein')} \
-            ${format_flags(params.qc_report.color_vars, '--addColorVar')} \
-            qc_report_data.db3 \
-            > >(tee "make_qmd.stdout") 2> >(tee "make_qmd.stderr")
-
-        # get dia_qc version and git info
-        dia_qc --version|awk '{print \$3}'|xargs -0 printf 'dia_qc_version=%s' > dia_qc_version.txt
-        echo "dia_qc_git_repo='\$GIT_REPO - \$GIT_BRANCH [\$GIT_SHORT_HASH]'" >> dia_qc_version.txt
-        """
-
-    else
-        """
-        dia_qc parse --ofname qc_report_data.db3 ${metadata_arg} \
-            --groupBy ${params.skyline.group_by_gene ? 'gene' : 'protein'} \
-            '${replicate_report}' '${precursor_report}' \
-            > >(tee "parse_data.stdout") 2> >(tee "parse_data.stderr")
+    """
+    dia_qc parse --ofname qc_report_data.db3 ${metadata_arg} \
+        --groupBy ${params.skyline.group_by_gene ? 'gene' : 'protein'} \
+        '${replicate_report}' '${precursor_report}' \
+        > >(tee "parse_data.stdout") 2> >(tee "parse_data.stderr")
 
+    if ${params.qc_report.normalization_method == null ? 'false' : 'true'} ; then
         dia_qc normalize -m=${params.qc_report.normalization_method} qc_report_data.db3 \
             > >(tee "normalize_db.stdout") 2> >(tee "normalize_db.stderr" >&2)
+    fi
 
-        dia_qc qc_qmd ${format_flags(params.qc_report.standard_proteins, '--addStdProtein')} \
-            ${format_flags(params.qc_report.color_vars, '--addColorVar')} \
-            qc_report_data.db3 \
-            > >(tee "make_qmd.stdout") 2> >(tee "make_qmd.stderr")
+    dia_qc qc_qmd ${format_flags(params.qc_report.standard_proteins, '--addStdProtein')} \
+        ${format_flags(params.qc_report.color_vars, '--addColorVar')} \
+        qc_report_data.db3 \
+        > >(tee "make_qmd.stdout") 2> >(tee "make_qmd.stderr")
 
-        # get dia_qc version and git info
-        dia_qc --version|awk '{print \$3}'|xargs -0 printf 'dia_qc_version=%s' > dia_qc_version.txt
-        echo "dia_qc_git_repo='\$GIT_REPO - \$GIT_BRANCH [\$GIT_SHORT_HASH]'" >> dia_qc_version.txt
-        """
+    # get dia_qc version and git info
+    dia_qc --version|awk '{print \$3}'|xargs -0 printf 'dia_qc_version=%s' > dia_qc_version.txt
+    echo "dia_qc_git_repo='\$GIT_REPO - \$GIT_BRANCH [\$GIT_SHORT_HASH]'" >> dia_qc_version.txt
+    """
 
     stub:
     """

diff --git a/modules/skyline.nf b/modules/skyline.nf
@@ -86,7 +86,7 @@ process SKYLINE_ADD_LIB {
 }
 
 process SKYLINE_IMPORT_MZML {
-    publishDir "${params.result_dir}/skyline/import-spectra", failOnError: true, mode: 'copy'
+    publishDir "${params.result_dir}/skyline/import-spectra", pattern: '*.std[oe][ur][tr]', failOnError: true, mode: 'copy'
     label 'process_medium'
     label 'process_high_memory'
     label 'process_short'
@@ -123,7 +123,7 @@ process SKYLINE_IMPORT_MZML {
 }
 
 process SKYLINE_MERGE_RESULTS {
-    publishDir "${params.result_dir}/skyline/import-spectra", failOnError: true, mode: 'copy'
+    publishDir "${params.result_dir}/skyline/import-spectra", enabled: params.replicate_metadata == null && params.pdc.study_id == null, failOnError: true, mode: 'copy'
     label 'process_high'
     label 'error_retry'
     container params.images.proteowizard
@@ -175,7 +175,7 @@ process SKYLINE_MERGE_RESULTS {
 }
 
 process ANNOTATION_TSV_TO_CSV {
-    publishDir "${params.result_dir}/skyline/annotate", failOnError: true, mode: 'copy'
+    publishDir "${params.result_dir}/skyline/import-spectra", failOnError: true, mode: 'copy'
     label 'process_low'
     label 'error_retry'
     container params.images.qc_pipeline
@@ -199,6 +199,7 @@ process ANNOTATION_TSV_TO_CSV {
 }
 
 process SKYLINE_MINIMIZE_DOCUMENT {
+    publishDir "${params.result_dir}/skyline/minimize", failOnError: true, mode: 'copy'
     label 'error_retry'
     label 'process_high'
     container params.images.proteowizard
@@ -238,7 +239,7 @@ process SKYLINE_MINIMIZE_DOCUMENT {
 }
 
 process SKYLINE_ANNOTATE_DOCUMENT {
-    publishDir "${params.result_dir}/skyline/annotate", failOnError: true, mode: 'copy'
+    publishDir "${params.result_dir}/skyline/import-spectra", failOnError: true, mode: 'copy'
     label 'process_memory_high_constant'
     container params.images.proteowizard
 

diff --git a/workflows/skyline_annotate_document.nf b/workflows/skyline_annotate_document.nf
diff --git a/workflows/skyline_import.nf b/workflows/skyline_import.nf
@@ -2,6 +2,9 @@
 include { SKYLINE_ADD_LIB } from "../modules/skyline"
 include { SKYLINE_IMPORT_MZML } from "../modules/skyline"
 include { SKYLINE_MERGE_RESULTS } from "../modules/skyline"
+include { ANNOTATION_TSV_TO_CSV } from "../modules/skyline"
+include { SKYLINE_MINIMIZE_DOCUMENT } from "../modules/skyline"
+include { SKYLINE_ANNOTATE_DOCUMENT } from "../modules/skyline"
 
 workflow skyline_import {
 
@@ -10,9 +13,13 @@ workflow skyline_import {
         fasta
         elib
         wide_mzml_file_ch
+        replicate_metadata
 
     emit:
         skyline_results
+        skyline_results_hash
+        skyline_minimized_results
+        skyline_minimized_results_hash
         proteowizard_version
 
     main:
@@ -32,6 +39,28 @@ workflow skyline_import {
             fasta
         )
 
-        skyline_results = SKYLINE_MERGE_RESULTS.out.final_skyline_zipfile
+        if(params.replicate_metadata != null || params.pdc.study_id != null) {
+            ANNOTATION_TSV_TO_CSV(replicate_metadata)
+
+            SKYLINE_ANNOTATE_DOCUMENT(SKYLINE_MERGE_RESULTS.out.final_skyline_zipfile,
+                                      ANNOTATION_TSV_TO_CSV.out.annotation_csv,
+                                      ANNOTATION_TSV_TO_CSV.out.annotation_definitions)
+
+            skyline_results = SKYLINE_ANNOTATE_DOCUMENT.out.final_skyline_zipfile
+            skyline_results_hash = SKYLINE_ANNOTATE_DOCUMENT.out.file_hash
+        } else {
+            skyline_results = SKYLINE_MERGE_RESULTS.out.final_skyline_zipfile
+            skyline_results_hash = SKYLINE_MERGE_RESULTS.out.file_hash
+        }
+
+        if(params.skyline.minimize) {
+            SKYLINE_MINIMIZE_DOCUMENT(skyline_results)
+            skyline_minimized_results = SKYLINE_MINIMIZE_DOCUMENT.out.final_skyline_zipfile
+            skyline_minimized_results_hash = SKYLINE_MINIMIZE_DOCUMENT.out.file_hash
+        } else {
+            skyline_minimized_results = Channel.empty()
+            skyline_minimized_results_hash = Channel.empty()
+        }
+
         proteowizard_version = SKYLINE_ADD_LIB.out.version
 }