Merge pull request #109 from sanger-tol/patch

Skip blastn if there are no chunks

CHANGELOG.md

@@ -3,6 +3,12 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [[0.5.1](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.5.1)] – Snorlax (patch 1) – [2024-08-22]
+
+### Enhancements & fixes
+
+- Bugfix: skip BLASTN if there are no chunks to align
+
 ## [[0.5.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.5.0)] – Snorlax – [2024-07-31]
 
 General tidy up of the configuration and the pipeline

nextflow.config

@@ -243,7 +243,7 @@ manifest {
     description     = """Quality assessment of genome assemblies"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=23.04.0'
-    version         = '0.5.0'
+    version         = '0.5.1'
     doi             = '10.5281/zenodo.7949058'
 }
 

subworkflows/local/run_blastn.nf

@@ -41,10 +41,14 @@ workflow RUN_BLASTN {
     BLOBTOOLKIT_CHUNK ( SEQTK_SUBSEQ.out.sequences, [[],[]] )
     ch_versions = ch_versions.mix ( BLOBTOOLKIT_CHUNK.out.versions.first() )
 
+    // Check that there are still sequences left after chunking (which excludes masked regions)
+    BLOBTOOLKIT_CHUNK.out.chunks
+    | filter { it[1].size() > 0 }
+    | set { ch_chunks }
 
     // Run blastn search
     // run blastn excluding taxon_id
-    BLASTN_TAXON ( BLOBTOOLKIT_CHUNK.out.chunks, blastn, taxon_id )
+    BLASTN_TAXON ( ch_chunks, blastn, taxon_id )
     ch_versions = ch_versions.mix ( BLASTN_TAXON.out.versions.first() )
 
     // check if blastn output table is empty
@@ -56,7 +60,8 @@ workflow RUN_BLASTN {
     | set { ch_blastn_taxon_out }
 
     // repeat the blastn search without excluding taxon_id
-    ch_blastn_taxon_out.empty.join ( BLOBTOOLKIT_CHUNK.out.chunks )
+    ch_blastn_taxon_out.empty
+    | join ( ch_chunks )
     | map { meta, txt, fasta -> [meta, fasta] }
     | set { ch_blast_blastn_input }