Merge pull request #130 from fmalmeida/dev

Release v3.4.1

Author: fmalmeida

conf/base.config

@@ -38,4 +38,14 @@ process {
         maxRetries    = 2
     }
 
+    // problematic module
+    withName: GET_NCBI_GENOME {
+        errorStrategy = { task.attempt > 3 ? 'retry' : 'ignore' }
+        maxRetries    = 2
+        maxErrors     = '-1'
+        cpus          = 2
+        memory        = 4.GB
+        time          = 2.h
+    }
+
 }

markdown/CHANGELOG.md

@@ -2,6 +2,13 @@
 
 The tracking for changes started in v2.1
 
+## v3.4.1 [14-November-2024]
+
+* [[[#127](https://github.com/fmalmeida/bacannot/issues/127)]]
+    * Allow `GET_NCBI_MODULE` fail to be ignored, and adjust resources
+    * Add parameter to skip `sourmash` workflow
+    * Adjust file permissions in module `GET_NCBI_MODULE`
+
 ## v3.4.0 [07-July-2024]
 
 * [[#30](https://github.com/fmalmeida/bacannot/issues/30)]

modules/generic/ncbi_genome.nf

@@ -35,5 +35,8 @@ process GET_NCBI_GENOME {
         name=\$( echo \$file | cut -d '_' -f 1,2 ) ;
         mv \$file \${name}.fna
     done
+
+    # fix permissions
+    chmod a+rw \${name}.fna
     """
 }

nextflow.config

@@ -108,7 +108,7 @@ manifest {
     homePage        = "https://github.com/fmalmeida/bacannot"
     mainScript      = "main.nf"
     nextflowVersion = "!>=22.10.1"
-    version         = '3.4.0'
+    version         = '3.4.1'
 }
 
 // Function to ensure that resource requirements don't go beyond

workflows/bacannot.nf

@@ -258,29 +258,44 @@ workflow BACANNOT {
 
       // species identification
       REFSEQ_MASHER( annotation_out_ch.genome )
-      SOURMASH_LCA(
-        dbs_ch,
-        annotation_out_ch.genome,
-        params.sourmash_scale,
-        params.sourmash_kmer
-      )
 
-      // mashing against samples and close related genomes
-      GET_NCBI_GENOME(
-        REFSEQ_MASHER.out.results
-        .map { it[1] }
-        .splitCsv( sep: '\t', header: true )
-        .map{ "${it.biosample}" }
-        .unique()
-      )
-      SOURMASH_ALL(
-        annotation_out_ch.genome
-        .map{ it[1] }
-        .mix( GET_NCBI_GENOME.out.genomes.collect() )
-        .collect(),
-        params.sourmash_scale,
-        params.sourmash_kmer
-      )
+      //
+      // BEGIN: sourmash-related modules
+      //
+      if (!params.skip_sourmash) {
+        SOURMASH_LCA(
+          dbs_ch,
+          annotation_out_ch.genome,
+          params.sourmash_scale,
+          params.sourmash_kmer
+        )
+
+        // mashing against samples and close related genomes
+        GET_NCBI_GENOME(
+          REFSEQ_MASHER.out.results
+          .map { it[1] }
+          .splitCsv( sep: '\t', header: true )
+          .map{ "${it.biosample}" }
+          .unique()
+        )
+
+        SOURMASH_ALL(
+          annotation_out_ch.genome
+          .map{ it[1] }
+          .mix( GET_NCBI_GENOME.out.genomes.collect() )
+          .collect(),
+          params.sourmash_scale,
+          params.sourmash_kmer
+        )
+
+        ch_sourmash_plot = SOURMASH_ALL.out.plot.first()
+      } else {
+        ch_sourmash_plot = []
+      }
+
+      //
+      // END: sourmash related modules
+      //
 
       // IS identification
       DIGIS( annotation_out_ch.genome.join(annotation_out_ch.gbk) )
@@ -408,7 +423,7 @@ workflow BACANNOT {
           .join( phast_output_ch,                 remainder: true )
           .join( MERGE_ANNOTATIONS.out.digis_gff                  )
           .join( ch_integron_finder_gff,          remainder: true ),
-        SOURMASH_ALL.out.plot.first() // make value channel
+        ch_sourmash_plot
       )
 
       //