feat: Add alignment step to align against ICEberg2 (#61)

* feat: Add module to align against ICEberg2 * feat: Add conf for iceberg alignment * fix: Add missing input * test: Fix inputs in ann test * fix: Change output folder * refactor: Change icebergdb to experimental
beiko-lab · Mar 10, 2023 · ed548cb · ed548cb
1 parent c8d37dc
commit ed548cb
Show file tree

Hide file tree

Showing 6 changed files with 66 additions and 7 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -169,6 +169,14 @@ process {
         ]
     }
 
+    withName: '.*ICEBERG_FILTER:CONCAT_ALIGNMENT' {
+        publishDir = [
+            path: { "${params.outdir}/annotation/iceberg2/" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: DIAMOND_BLAST_VFDB {
         ext.args = '--evalue 1e-06 --max-target-seqs 25 --more-sensitive'
         ext.prefix = { "${meta.id}_VFDB" }
@@ -189,6 +197,16 @@ process {
         ]
     }
 
+    withName: DIAMOND_BLAST_ICEBERG {
+        ext.args = '--evalue 1e-06 --max-target-seqs 25 --more-sensitive'
+        ext.prefix = { "${meta.id}_ICEBERG" }
+        publishDir = [
+            path: { "${params.outdir}/annotation/iceberg2/${meta.id}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     // PopPUNK
 
     withName: POPPUNK_VISUALISE {

diff --git a/modules/local/blast_databases.nf b/modules/local/blast_databases.nf
@@ -44,3 +44,20 @@ process GET_BACMET{
     touch BacMet2_EXP_database.fasta
     """
 }
+
+process GET_ICEBERG {
+    label 'process_low'
+    label 'error_retry_delay'
+
+    output:
+    path "ICE_aa_experimental.fas", emit: iceberg
+
+    script:
+    """
+    curl https://bioinfo-mml.sjtu.edu.cn/ICEberg2/download/ICE_aa_experimental.fas --output ICE_aa_experimental.fas
+    """
+    stub:
+    """
+    touch ICE_aa_experimental.fas
+    """
+}
diff --git a/modules/local/get_db_cache.nf b/modules/local/get_db_cache.nf
@@ -15,15 +15,17 @@ process GET_DB_CACHE {
         path "VFDB_setA_pro.fas.gz", emit: vfdb
         path "CAZyDB.07312020.fa", emit: cazydb
         path "BacMet2_predicted_database.fasta.gz", emit: bacmet
+        path "ICE_aa_experimental.fas", emit: iceberg
         path "card.json", emit: card_json
         path "card.version.txt", emit: card_version
         path("""k2_standard_8gb_20201202"""), emit: minikraken
-    
+
     script:
         """
         cp $dbcache/VFDB_setA_pro.fas.gz .
         cp $dbcache/CAZyDB.07312020.fa .
         cp $dbcache/BacMet2_predicted_database.fasta.gz .
+        cp $dbcache/ICE_aa_experimental.fas .
         cp $dbcache/card.json .
         cp $dbcache/card.version.txt .
         cp -r $dbcache/k2_standard_8gb_20201202 .
@@ -40,7 +42,7 @@ process GET_DB_CACHE {
 //         path "BacMet2_predicted_database.fasta.gz", emit: bacmet
 //         path "card.json", emit: card_json
 //         path "card.version.txt", emit: card_version
-    
+
 //     script:
 //         """
 //         cp VFDB_setB_pro.fas.gz .
@@ -57,7 +59,7 @@ process GET_DB_CACHE {
 
 //     output:
 //         path("""k2_standard_8gb_20201202"""), emit: minikraken
-    
+
 //     script:
 //         """
 //         cp -r $dbcache/k2_standard_8gb_20201202 .

diff --git a/subworkflows/local/annotation.nf b/subworkflows/local/annotation.nf
@@ -6,13 +6,16 @@ include { BAKTA_BAKTA as BAKTA } from '../../modules/nf-core/bakta/bakta/main'
 include { BAKTA_BAKTADBDOWNLOAD as BAKTADBDOWNLOAD } from '../../modules/nf-core/bakta/baktadbdownload/main'
 include { GET_CAZYDB;
           GET_VFDB;
-          GET_BACMET} from '../../modules/local/blast_databases.nf'
+          GET_BACMET;
+          GET_ICEBERG } from '../../modules/local/blast_databases.nf'
 include { DIAMOND_MAKEDB as DIAMOND_MAKE_CAZY;
           DIAMOND_MAKEDB as DIAMOND_MAKE_VFDB;
-          DIAMOND_MAKEDB as DIAMOND_MAKE_BACMET } from '../../modules/nf-core/diamond/makedb/main'
+          DIAMOND_MAKEDB as DIAMOND_MAKE_BACMET;
+          DIAMOND_MAKEDB as DIAMOND_MAKE_ICEBERG } from '../../modules/nf-core/diamond/makedb/main'
 include { DIAMOND_BLASTX as DIAMOND_BLAST_CAZY;
           DIAMOND_BLASTX as DIAMOND_BLAST_VFDB;
-          DIAMOND_BLASTX as DIAMOND_BLAST_BACMET } from '../../modules/nf-core/diamond/blastx/main'
+          DIAMOND_BLASTX as DIAMOND_BLAST_BACMET;
+          DIAMOND_BLASTX as DIAMOND_BLAST_ICEBERG } from '../../modules/nf-core/diamond/blastx/main'
 //
 // MODULE: Local to the pipeline
 //
@@ -26,7 +29,8 @@ include { MOB_RECON } from '../../modules/local/mobsuite'
 //
 include { FILTER_ALIGNMENT as CAZY_FILTER;
           FILTER_ALIGNMENT as VFDB_FILTER;
-          FILTER_ALIGNMENT as BACMET_FILTER; } from './concatenate_matches'
+          FILTER_ALIGNMENT as BACMET_FILTER;
+          FILTER_ALIGNMENT as ICEBERG_FILTER } from './concatenate_matches'
 
 
 
@@ -37,6 +41,7 @@ workflow ANNOTATE_ASSEMBLIES {
         vfdb_cache
         cazydb_cache
         bacmet_cache
+        icebergdb_cache
         card_json_cache
         card_version_cache
 
@@ -81,6 +86,13 @@ workflow ANNOTATE_ASSEMBLIES {
                 GET_CAZYDB()
                 GET_CAZYDB.out.cazydb.set { ch_cazy_db }
             }
+            if (icebergdb_cache){
+                icebergdb_cache.set{ ch_iceberg_db }
+            }
+            else{
+                GET_ICEBERG()
+                GET_ICEBERG.out.iceberg.set { ch_iceberg_db }
+            }
         }
         /*
         * Load RGI for AMR annotation
@@ -161,7 +173,12 @@ workflow ANNOTATE_ASSEMBLIES {
             DIAMOND_MAKE_CAZY(ch_cazy_db)
             DIAMOND_BLAST_CAZY(ch_ffn_files, DIAMOND_MAKE_CAZY.out.db, "txt", blast_columns)
             CAZY_FILTER(DIAMOND_BLAST_CAZY.out.txt, "CAZY", blast_columns)
+
+            DIAMOND_MAKE_ICEBERG(ch_iceberg_db)
+            DIAMOND_BLAST_ICEBERG(ch_ffn_files, DIAMOND_MAKE_ICEBERG.out.db, "txt", blast_columns)
+            ICEBERG_FILTER(DIAMOND_BLAST_ICEBERG.out.txt, "ICEBERG", blast_columns)
         }
+
         ch_software_versions = ch_software_versions.mix(DIAMOND_MAKE_VFDB.out.versions.ifEmpty(null))
 
     emit:

diff --git a/tests/subworkflows/local/annotation.nf.test b/tests/subworkflows/local/annotation.nf.test
@@ -23,6 +23,7 @@ nextflow_workflow {
                 input[4] = []
                 input[5] = []
                 input[6] = []
+                input[7] = []
                 """
             }
         }

diff --git a/workflows/arete.nf b/workflows/arete.nf
@@ -143,6 +143,7 @@ workflow ARETE {
             GET_DB_CACHE.out.vfdb,
             GET_DB_CACHE.out.cazydb,
             GET_DB_CACHE.out.bacmet,
+            GET_DB_CACHE.out.iceberg,
             GET_DB_CACHE.out.card_json,
             GET_DB_CACHE.out.card_version
             )
@@ -165,6 +166,7 @@ workflow ARETE {
             [],
             [],
             [],
+            [],
             []
             )
     }
@@ -330,6 +332,7 @@ workflow ANNOTATION {
             GET_DB_CACHE.out.vfdb,
             GET_DB_CACHE.out.cazydb,
             GET_DB_CACHE.out.bacmet,
+            GET_DB_CACHE.out.iceberg,
             GET_DB_CACHE.out.card_json,
             GET_DB_CACHE.out.card_version
             )
@@ -346,6 +349,7 @@ workflow ANNOTATION {
             [],
             [],
             [],
+            [],
             []
             )
     }