Updating chewbbaca schema installation to filter for ESFA cgMLST reco…

…mmendations rather than full wgMLST
bio-raum · Jan 24, 2025 · 62e7a34 · 62e7a34
1 parent e208fa2
commit 62e7a34
Show file tree

Hide file tree

Showing 9 changed files with 83 additions and 26 deletions.
diff --git a/bin/chewbbaca_filter_schema.py b/bin/chewbbaca_filter_schema.py
@@ -3,7 +3,8 @@
 
 import glob
 import argparse
-
+import pathlib
+import os
 
 parser = argparse.ArgumentParser(description="Script options")
 parser.add_argument("--list", help="List of valid alleles")
@@ -15,13 +16,18 @@
 
 def main(list, schema, output):
 
-    alleles = glob.glob("*/*.fasta")
-
+    pathlib.Path(output).mkdir(parents=True, exist_ok=True)
+
+    alleles = glob.glob(schema + "/*/*.fasta")
+
     with open(list) as file:
         valid = [line.rstrip() for line in file]
-
-    for keep in valid:
-
+
+    for allele in alleles:
+        allele_name = os.path.basename(allele)
+        # There probably is a pythonier way to do this
+        if allele_name in valid:
+            os.system("cp " + allele + " " + output + "/")
 
 
 if __name__ == '__main__':

diff --git a/bin/gabi.py b/bin/gabi.py
@@ -334,36 +334,36 @@ def main(yaml, template, output, reference, version, call, wd):
 
             if "total" in jdata["mosdepth"]:
                 coverage = float(jdata["mosdepth"]["total"]["mean"])
-                if coverage >= 40:
+                if coverage >= 40.0:
                     coverage_status = status["pass"]
-                elif coverage >= 20:
+                elif coverage >= 20.0:
                     coverage_status = status["warn"]
                 else:
-                    coverage_status = status["pass"]
+                    coverage_status = status["fail"]
 
             if "illumina" in jdata["mosdepth"]:
                 coverage_illumina = float(jdata["mosdepth"]["illumina"]["mean"])
-                if coverage_illumina >= 40:
+                if coverage_illumina >= 40.0:
                     coverage_illumina_status = status["pass"]
-                elif coverage_illumina >= 20:
+                elif coverage_illumina >= 20.0:
                     coverage_illumina_status = status["warn"]
                 else:
                     coverage_illumina_status = status["fail"]
 
             if "nanopore" in jdata["mosdepth"]:
                 coverage_nanopore = float(jdata["mosdepth"]["nanopore"]["mean"])
-                if coverage_nanopore >= 40:
+                if coverage_nanopore >= 40.0:
                     coverage_nanopore_status = status["pass"]
-                elif coverage_nanopore >= 20:
+                elif coverage_nanopore >= 20.0:
                     coverage_nanopore_status = status["warn"]
                 else:
                     coverage_nanopore_status = status["fail"]
 
             if "pacbio" in jdata["mosdepth"]:
                 coverage_pacbio = float(jdata["mosdepth"]["pacbio"]["mean"])
-                if coverage_pacbio >= 40:
+                if coverage_pacbio >= 40.0:
                     coverage_pacbio_status = status["pass"]
-                elif coverage_pacbio >= 20:
+                elif coverage_pacbio >= 20.0:
                     coverage_pacbio_status = status["warn"]
                 else:
                     coverage_pacbio_status = status["fail"]

diff --git a/conf/modules/installation.config b/conf/modules/installation.config
@@ -24,8 +24,8 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
     }
-    withName: CHEWBBACA_DOWNLOADSCHEMA {
-        ext.args = "--date ${params.chewbbaca_schema_date}"
+    withName: 'CHEWBBACA_DOWNLOADSCHEMA|CHEWBBACA_FILTER_SCHEMA' {
+        ext.args = "${params.chewbbaca_schema_date}"
         publishDir = [
             path: { "${params.reference_base}/gabi/${params.reference_version}/chewbbaca" },
             mode: params.publish_dir_mode,

diff --git a/conf/resources.config b/conf/resources.config
@@ -187,10 +187,10 @@ params {
     campylobacter_jejuni = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_4/Campylobacter_jejuni_INNUENDO_wgMLST"
     campylobacter_coli = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_4/Campylobacter_jejuni_INNUENDO_wgMLST"
     campylobacter_lari = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_4/Campylobacter_jejuni_INNUENDO_wgMLST"
-    escherichia_coli = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_5/Escherichia_coli_INNUENDO_wgMLST"
+    escherichia_coli = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_5_cgMLST"
     listeria_monocytogenes = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_6/Listeria_monocytogenes_Pasteur_cgMLST"
     yersinia_enterocolitica = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_7/Yersinia_enterocolitica_INNUENDO_wgMLST"
-    salmonella_enterica = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_8/Salmonella_enterica_INNUENDO_cgMLST"
+    salmonella_enterica = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_8_cgMLST"
     streptococcus_agalactiae = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_9/Streptococcus_agalactiae_wgMLST"
     brucella_melitensis = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_10/Brucella_melitensis_Bm_cgMLST_95"
     brucella = "${params.reference_base}/gabi/${params.reference_version}/chewbbaca/schema_11/Brucella_Brucella_cgMLST"

diff --git a/modules/helper/chewbbaca_filter_schema/environment.yml b/modules/helper/chewbbaca_filter_schema/environment.yml
@@ -0,0 +1,7 @@
+name: chewbbaca_filter_schema
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - bioconda::multiqc=1.23
diff --git a/modules/helper/chewbbaca_filter_schema/main.nf b/modules/helper/chewbbaca_filter_schema/main.nf
@@ -0,0 +1,25 @@
+process CHEWBBACA_FILTER_SCHEMA {
+    label 'short_serial'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/multiqc:1.23--pyhdfd78af_0' :
+        'quay.io/biocontainers/multiqc:1.23--pyhdfd78af_0' }"
+
+    input:
+    tuple val(meta), path(schema_dir), path(list)
+
+    output:
+    tuple val(meta), path(results) , emit: schema
+
+    when:
+
+    script:
+    def args = task.ext.args ?: ''
+    results = schema_dir.name + "_cgMLST"
+
+    """
+    chewbbaca_filter_schema.py --schema $schema_dir --list $list --output $results
+    
+    """
+}
diff --git a/nextflow.config b/nextflow.config
@@ -46,7 +46,7 @@ params {
     ont_min_q               = 10
     ont_min_reads           = 1000
 
-    chewbbaca_schema_date   = "2025-01-01T00:00:00"
+    chewbbaca_schema_date   = "--latest"
 
     reference_base          = null
     help                    = false
@@ -86,7 +86,7 @@ params {
 
 manifest {
     name = "bio-raum/gabi"
-    version = "0.9.3"
+    version = "0.9.4"
     description = "GABI Pipeline for assembly and profiling of bacterial isolates"
     author = "Marc Hoeppner"
     homePage = "https://github.com/bio-raum/gabi"

diff --git a/workflows/build_references.nf b/workflows/build_references.nf
@@ -8,6 +8,7 @@ include { STAGE_FILE as DOWNLOAD_SOURMASH_DB }              from './../modules/h
 include { STAGE_FILE as DOWNLOAD_SOURMASH_NR_DB }           from './../modules/helper/stage_file'
 include { GUNZIP as GUNZIP_GENOME }                         from './../modules/gunzip'
 include { BIOBLOOM_MAKER }                                  from './../modules/biobloom/maker'
+include { CHEWBBACA_FILTER_SCHEMA }                         from './../modules/helper/chewbbaca_filter_schema'
 
 kraken_db_url       = Channel.fromPath(params.references['kraken2'].url)
 confindr_db_url     = Channel.fromPath(params.references['confindr'].url)
@@ -30,9 +31,9 @@ chewie_ids = Channel.fromList([
     [ [ taxon: "Brucella melitensis" ], 10],
     [ [ taxon: "Brucella" ], 11],
     [ [ taxon: "Clostridium perfringens" ], 12], 
-    [ [ taxon: "Clostridium chauvoei" ], 13]
+    [ [ taxon: "Clostridium chauvoei" ], 13],
     [ [ taxon: "Bacillus anthracis" ], 14], 
-    [ [ taxon: "Klebsiella oxytoca" ], 15]
+    [ [ taxon: "Klebsiella oxytoca" ], 15],
     [ [ taxon: "Clostridium neonatale" ], 16],
     [ [ taxon: "Shewanella" ], 17],
     [ [ taxon: "Neisseria meningitidis" ], 18]
@@ -97,6 +98,24 @@ workflow BUILD_REFERENCES {
     CHEWBBACA_DOWNLOADSCHEMA(
         chewie_ids
     )
+
+    // See if any schema has a filter list configured
+    CHEWBBACA_DOWNLOADSCHEMA.out.schema.map { m, s ->
+        def taxon = m.taxon.toLowerCase().replaceAll(/ /, "_")
+        def ffile = null
+        if (params.chewbbaca_filters[taxon]) {
+            ffile = params.chewbbaca_filters[taxon]
+        }
+        tuple(m, s, ffile)
+    }.branch { m, s, ffile ->
+        fail: ffile == null
+        pass: ffile
+    }.set { chewie_schema_with_filter }
+
+    // Filter that schema using the filter list
+    CHEWBBACA_FILTER_SCHEMA(
+        chewie_schema_with_filter.pass
+    )
 }
 
 if (params.build_references) {

diff --git a/workflows/gabi.nf b/workflows/gabi.nf
@@ -377,7 +377,7 @@ workflow GABI {
     */
     if (!params.skip_serotyping) {
         SEROTYPING(
-            ch_assemblies_without_plasmids_with_taxa
+            ch_assemblies_clean_with_taxa
         )
         ch_versions     = ch_versions.mix(SEROTYPING.out.versions)
         ch_report       = ch_report.mix(SEROTYPING.out.reports)
@@ -390,7 +390,7 @@ workflow GABI {
     */
     if (!params.skip_mlst) {
         MLST_TYPING(
-            ch_assemblies_without_plasmids_with_taxa
+            ch_assemblies_clean_with_taxa
         )
         ch_mlst = MLST_TYPING.out.report
         ch_versions = ch_versions.mix(MLST_TYPING.out.versions)
@@ -405,7 +405,7 @@ workflow GABI {
     ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     */
     ANNOTATE(
-        ch_assemblies_without_plasmids_with_taxa,
+        ch_assemblies_clean_with_taxa,
         ch_prokka_proteins,
         ch_prokka_prodigal
     )