Add workflow Metadata and Sequences from BioProjectIDs

workflows/data-fetching/metadata-and-sequences-from-BioProjectIDs/.dockstore.yml

@@ -0,0 +1,11 @@
+version: 1.2
+workflows:
+- name: main
+  subclass: Galaxy
+  publish: true
+  primaryDescriptorPath: /metadata-and-sequences-from-BioProjectIDs.ga
+  testParameterFiles:
+  - /metadata-and-sequences-from-BioProjectIDs-tests.yml
+  authors:
+  - name: Giuseppe Defazio
+    orcid: 0000-0002-9356-5224

workflows/data-fetching/metadata-and-sequences-from-BioProjectIDs/.workflowhub.yml

@@ -0,0 +1,5 @@
+version: '0.1'
+registries:
+- url: https://workflowhub.eu
+  project: iwc
+  workflow: metadata-and-sequences-from-BioProjectsIDs/main

workflows/data-fetching/metadata-and-sequences-from-BioProjectIDs/CHANGELOG.md

@@ -0,0 +1,5 @@
+# Changelog
+
+## [0.1] - 2026-03-23
+
+- Added workflow

workflows/data-fetching/metadata-and-sequences-from-BioProjectIDs/README.md

@@ -0,0 +1,17 @@
+# Metadata and Sequences from BioProjectIDs
+
+This workflow takes BioProject IDs as input and is able to retrieve SRA tables and FASTQ files from IDs using pysradb and SRA fetching.
+The workflow may be very useful in Meta-analysis and reanalysis scenarios, giving the possibility to collect metadata and data from BioProject IDs of studies with the same design.
+
+## Input
+
+The workflow needs a single tabular input dataset (uploaded as txt file as well), without header, with the first column reporting one or more BioProject IDs.
+
+
+## Outputs
+
+There are 3 main outputs:
+
+- Data collection for SRA manifest of input BioProject ID(s)
+- Data collection for Paired End FASTQ files
+- Data collection for Single End FASTQ files

workflows/data-fetching/metadata-and-sequences-from-BioProjectIDs/metadata-and-sequences-from-BioProjectIDs-tests.yml

@@ -0,0 +1,95 @@
+- doc: Test 1 for Metadata-and-Sequences-from-BioProjectIDs
+  job:
+    BioProject IDs:
+      class: File
+      path: test-data/test1_single_prj_pe.txt
+      filetype: tabular
+    --assay (metadata download): false
+    --desc (metadata download): false
+    --detailed (metadata download): true
+    --expand (metadata download): false
+    Group by Experiments (fastq download): false
+    Group by Sample (fastq download): false
+  outputs:
+    metadata_file:
+      element_tests:
+        split_file_000000.txt:
+          path: test-data/test1_metadata_file_split_file_000000.txt.tsv
+    paired_end_collection:
+      element_tests:
+        split_file_000000.txt:
+          elements:
+            SRR37073390:
+              elements:
+                forward:
+                  path: test-data/test1_paired_end_collection_forward.fastq
+                  decompress: true
+                  compare: contains
+                reverse:
+                  path: test-data/test1_paired_end_collection_reverse.fastq
+                  decompress: true
+                  compare: contains
+    single_end_collection:
+      element_tests:
+        split_file_000000.txt:
+          elements: {}
+
+- doc: Test 2 for Metadata-and-Sequences-from-BioProjectIDs
+  job:
+    BioProject IDs:
+      class: File
+      path: test-data/test2_multiple_prj_mixed.txt
+      filetype: txt
+    --assay (metadata download): false
+    --desc (metadata download): false
+    --detailed (metadata download): true
+    --expand (metadata download): false
+    Group by Experiments (fastq download): false
+    Group by Sample (fastq download): false
+  outputs:
+    metadata_file:
+      element_tests:
+        split_file_000000.txt:
+          path: test-data/test2_metadata_file_split_file_000000.txt.tsv
+          compare: contains
+        split_file_000001.txt:
+          path: test-data/test2_metadata_file_split_file_000001.txt.tsv
+          compare: contains
+    paired_end_collection:
+      element_tests:
+        split_file_000000.txt:
+          elements:
+            SRR37273407:
+              elements:
+                forward:
+                  path: test-data/test2_SRR37273407_forward.fastq
+                  decompress: true
+                  compare: contains
+            SRR37273408:
+              elements:
+                forward:
+                  path: test-data/test2_SRR37273408_forward.fastq
+                  decompress: true
+                  compare: contains
+                reverse:
+                  path: test-data/test2_SRR37273408_reverse.fastq
+                  decompress: true
+                  compare: contains
+        split_file_000001.txt:
+          elements:
+            SRR37073390:
+              elements:
+                forward:
+                  path: test-data/test2_SRR37073390_forward.fastq
+                  decompress: true
+                  compare: contains
+                reverse:
+                  path: test-data/test2_SRR37073390_reverse.fastq
+                  decompress: true
+                  compare: contains
+    single_end_collection:
+      element_tests:
+        split_file_000000.txt:
+          elements: {}
+        split_file_000001.txt:
+          elements: {}