Dp24 barcodes

assets/github_testing/test.yaml

@@ -1,6 +1,7 @@
 assembly_path: /home/runner/work/ascc/ascc/asccTinyTest/assembly/Pyoeliiyoelii17XNL_assembly.fa
 assembly_title: asccTinyTest
-pacbio_multiplexing_barcode_names: ""
+pacbio_barcodes: /home/runner/work/ascc/ascc/assets/pacbio_adaptors.fa
+pacbio_multiplexing_barcode_names: "bc1008_BAK8A_OA,bc1009_BAK8A_OA"
 pacbio_reads_path: /home/runner/work/ascc/ascc/asccTinyTest/pacbio/
 sci_name: "Plasmodium yoelii yoelii 17XNL"
 taxid: 352914

assets/test.yaml

@@ -1,6 +1,7 @@
 assembly_path: /lustre/scratch123/tol/resources/treeval/treeval-testdata/asccTinyTest/assembly/Pyoeliiyoelii17XNL_assembly.fa
 assembly_title: asccTinyTest
-pacbio_multiplexing_barcode_names: something
+pacbio_barcodes: /nfs/treeoflife-01/teams/tola/users/dp24/ascc/assets/pacbio_adaptors.fa
+pacbio_multiplexing_barcode_names: "bc1008_BAK8A_OA,bc1009_BAK8A_OA"
 pacbio_reads_path: /lustre/scratch123/tol/resources/treeval/treeval-testdata/asccTinyTest/pacbio/
 sci_name: "Plasmodium yoelii yoelii 17XNL"
 taxid: 352914

bin/pacbio_barcode_check.py

@@ -1,5 +1,10 @@
+#!/usr/bin/env python3
+
 """
-Notes: Forces sys.exit(1) to kill pipeline
+Pacbio Barcode Check
+------------------------
+Looks for Pacbio barcodes in ref and data.
+If supplied barcodes arn't in data then pipeline dies.
 
 Originally written by Eerik Aunin @eeaunin
 
@@ -21,7 +26,9 @@ def detect_barcodes_from_read_file_names(barcodes_fasta_path, pacbio_read_files)
     barcodes_fasta_data = gpf.l(barcodes_fasta_path)
     barcode_names = [n.split(">")[1] for n in barcodes_fasta_data if n.startswith(">")]
     if len(barcode_names) == 0:
-        print("NO BARCODES, KILL PIPELINE")
+        sys.stderr.write(
+            f"Failed to read PacBio multiplexing barcode names from the specified file {barcodes_fasta_data}\n"
+        )
         sys.exit(1)
     detected_barcodes = list()
     for barcode_name in barcode_names:
@@ -40,44 +47,48 @@ def check_if_barcodes_exist_in_barcodes_fasta(barcodes_list, barcodes_fasta_path
     barcode_names_in_fasta = [n.split(">")[1] for n in barcodes_fasta_data if n.startswith(">")]
     for barcode in barcodes_list:
         if barcode not in barcode_names_in_fasta:
-            # sys.stderr.write(f"The PacBio multiplexing barcode ({barcode}) was not found in the barcode sequences file ({barcodes_fasta_path})\n")
-            print("NO BARCODES, KILL PIPELINE")
+            sys.stderr.write(
+                f"The PacBio multiplexing barcode ({barcode}) was not found in the barcode sequences file ({barcodes_fasta_path})\n"
+            )
             sys.exit(1)
 
+    # If this print statement is reached, all user-supplied codes are present.
+    print("BARCODES FOUND\n")
+
 
 def main(barcodes_fasta_path, pacbio_read_files, pacbio_multiplexing_barcode_names):
     pacbio_read_files = pacbio_read_files.split(",")
 
     barcodes_list = []
-    if pacbio_multiplexing_barcode_names != "NA":
-        barcodes_list = pacbio_multiplexing_barcode_names.split(",")
-
-    current_script_dir = os.path.dirname(sys.argv[0])
+    if len(pacbio_multiplexing_barcode_names) > 0:
+        barcodes_list = pacbio_multiplexing_barcode_names.strip("[").strip("]").split(",")
 
-    if barcodes_fasta_path is None:
-        barcodes_fasta_path = f"{current_script_dir}/third_party_files/pacbio_barcode_screen/pacbio_adaptors.fa"
-    else:
-        if os.path.isfile(barcodes_fasta_path) is False:
-            print("NO BARCODES, KILL PIPELINE")
-            sys.exit(1)
+    if os.path.isfile(barcodes_fasta_path) is False:
+        sys.stderr.write(
+            "FASTA file with PacBio multiplexing barcode sequences ({barcodes_fasta_path}) was not found\n"
+        )
+        sys.exit(1)
 
-    if barcodes_list == []:
+    if len(barcodes_list) == 0:
         barcodes_list = detect_barcodes_from_read_file_names(barcodes_fasta_path, pacbio_read_files)
+
     if len(barcodes_list) == 0:
-        print("NO BARCODES, KILL PIPELINE")
-        sys.exit(1)
+        sys.stderr.write(
+            "Skipping the PacBio barcodes check, as no barcodes were specified by the user and no barcodes were found in PacBio read file names\n"
+        )
+        sys.exit(0)
 
-    check_if_barcodes_exist_in_barcodes_fasta(
-        barcodes_list, barcodes_fasta_path
-    )  # This is a TRUE | FALSE check, if FALSE kill pipeline.
-    print("BARCODES FOUND!")
+    check_if_barcodes_exist_in_barcodes_fasta(barcodes_list, barcodes_fasta_path)
 
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument("barcode_fasta", type=str, help="Pacbio Barcode FASTA file")
-    parser.add_argument("pacbio_reads", type=str, help="Pacbio Read FASTA.gz files")
-    parser.add_argument("multiplex_name", type=str, help="Pacbio Multiplex Barcode Name")
+    parser.add_argument("-b", "--barcode_fasta", type=str, help="Pacbio Barcode FASTA file")
+
+    parser.add_argument("-p", "--pacbio_reads", type=str, help="Pacbio Read FASTA.gz files")
+
+    parser.add_argument("-m", "--multiplex_name", type=str, help="Pacbio Multiplex Barcode Name")
+
     parser.add_argument("-v", action="version", version="1.0")
     args = parser.parse_args()
     main(args.barcode_fasta, args.pacbio_reads, args.multiplex_name)

conf/modules.config

@@ -26,6 +26,10 @@ process {
         ext.args = 'nucleotide'
     }
 
+    withName: BLAST_MAKEBLASTDB {
+        ext.args = { "-dbtype nucl" }
+    }
+
     withName: BLAST_BLASTN {
         ext.args = { "-outfmt '6 qseqid staxids bitscore std' -max_target_seqs 10 -max_hsps 1 -evalue 1e-25 -dust yes -lcase_masking" }
     }

modules/local/check_barcode.nf

@@ -8,22 +8,23 @@ process CHECK_BARCODE {
         'biocontainers/python:3.9' }"
 
     input:
-    tuple val(meta)     , path(barcodes)
-    tuple val(meta2)    , path(pacbio_dir)
-    tuple val(meta3)    , path(multiplex_csv)
+    tuple val(meta) , path(pacbio_dir)
+    path barcodes
+    val multiplex_csv
 
     output:
-    stdout              , emit: debarcoded
+    env OUTPUT          , emit: result
     path "versions.yml" , emit: versions
 
     script:
-    def prefix  = task.ext.prefix   ?: "${meta.id}"
-    def args    = task.ext.args     ?: ''
+    def prefix      = task.ext.prefix   ?: "${meta.id}"
+    def args        = task.ext.args     ?: ''
     """
-    pacbio_barcode_check.py \\
-        ${barcode_fasta} \\
-        ${pacbio_dir} \\
-        ${multiplex_csv}
+    OUTPUT=\$(\\
+        pacbio_barcode_check.py \\
+            -b ${barcodes} \\
+            -p ${pacbio_dir} \\
+            -m ${multiplex_csv})
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -34,7 +35,7 @@ process CHECK_BARCODE {
 
     stub:
     """
-    echo "BARCODES FOUND!"
+    OUTPUT="BARCODES FOUND"
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/filter_barcode.nf

@@ -2,43 +2,44 @@ process FILTER_BARCODE {
     tag "${meta.id}"
     label 'process_low'
 
-    conda "conda-forge::python=3.9"
+    conda "conda-forge::python=3.9 conda-forge::biopython=1.78"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/python:3.9' :
-        'biocontainers/python:3.9' }"
+        'https://depot.galaxyproject.org/singularity/biopython:1.78' :
+        'biocontainers/biopython:1.78' }"
 
     input:
-    tuple val(meta), path(fasta)
-    tuple val(meta2), path(barcodes)
+    tuple val(meta) , path(fasta)
+    tuple val(meta2), path(blast_data)
+    val barcodes
 
     output:
-    tuple val(meta), path( "*txt" ) , emit: debarcoded
-    path "versions.yml"             , emit: versions
+    tuple val(meta), path( "*filtered.txt" )    , emit: debarcoded
+    path "versions.yml"                         , emit: versions
 
     script:
-    def prefix  = task.ext.prefix   ?: "${meta.id}"
     def args    = task.ext.args     ?: ''
-    def prefix  = task.ext.prefix   ?: "${meta.id}.debarcoded" // args is for `pacbio_multiplexing_barcodes_check_${meta.barcode}.txt`
+    def prefix  = task.ext.prefix   ?: "${meta.id}"
     """
     filter_barcode_blast_results.py \\
         --input ${fasta} \\
-        --barcodes ${barcodes} \\
+        --barcode ${barcodes} \\
         --blast ${blast_data} \\
-        --output ${prefix}.txt
+        --output ${prefix}_${barcodes}_filtered.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         python: \$(python --version | sed 's/Python //g')
+        biopython: \$(python3 -c 'import Bio; print(Bio.__version__)')
         filter_barcode_blast_results: \$(filter_barcode_blast_results.py -v)
     END_VERSIONS
     """
 
     stub:
-    def prefix  = task.ext.prefix   ?: "${meta.id}"
-    def args    = task.ext.args     ?: ''
-    def prefix  = task.ext.prefix   ?: "${meta.id}.debarcoded" // args is for `pacbio_multiplexing_barcodes_check_${meta.barcode}.txt`
+    def args        = task.ext.args     ?: ''
+    def prefix      = task.ext.prefix   ?: "${meta.id}"
+    def barcodes    = "bc1008_BAK8A_OA"
     """
-    touch ${prefix}.txt
+    touch ${prefix}-${barcodes}-filtered.txt
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/local/gc_content.nf

@@ -12,7 +12,7 @@ process GC_CONTENT {
 
     output:
     tuple val(meta), path( "*-gc.txt" ) , emit: txt
-    path "versions.yml"               , emit: versions
+    path "versions.yml"                 , emit: versions
 
     script:
     def prefix = task.ext.prefix ?: "${meta.id}"

modules/local/get_lineage_for_kraken.nf

@@ -31,6 +31,7 @@ process GET_LINEAGE_FOR_KRAKEN {
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         python: \$(python --version | sed 's/Python //g')
+        pandas: \$(python3 -c 'import pandas; print(pandas.__version__)')
         general_purpose_functions.py: \$(general_purpose_functions.py --version | cut -d' ' -f2)
         get_lineage_for_kraken_results.py: \$(get_lineage_for_kraken_results.py --version | cut -d' ' -f2)
     END_VERSIONS

subworkflows/local/extract_nt_blast.nf

@@ -1,6 +1,5 @@
 // MODULE IMPORT BLOCK
 include { BLAST_BLASTN          } from '../../modules/nf-core/blast/blastn/main'
-
 include { SEQKIT_SLIDING        } from '../../modules/nf-core/seqkit/sliding/main'
 include { BLAST_CHUNK_TO_FULL   } from '../../modules/local/blast_chunk_to_full'
 include { REFORMAT_FULL_OUTFMT6 } from '../../modules/local/reformat_full_outfmt6'

subworkflows/local/extract_tiara_hits.nf

@@ -1,7 +1,5 @@
 include { TIARA_TIARA } from '../../modules/nf-core/tiara/tiara/main'
 
-
-
 workflow EXTRACT_TIARA_HITS {
 
     take:
@@ -19,4 +17,4 @@ workflow EXTRACT_TIARA_HITS {
     ch_tiara            = TIARA_TIARA.out.classifications
     versions            = ch_versions.ifEmpty(null)
 
-}
+}

subworkflows/local/generate_genome.nf

@@ -11,6 +11,7 @@ include { GET_LARGEST_SCAFF     } from '../../modules/local/get_largest_scaff'
 workflow GENERATE_GENOME {
     take:
     to_chromsize    // tuple [[meta.id], file]
+    barcodes
 
     main:
     ch_versions     = Channel.empty()

subworkflows/local/pacbio_barcode_check.nf

@@ -0,0 +1,102 @@
+//
+// PACBIO_BARCODE_CHECK IDENTIFIED LOCATIONS OF BARCODE SEQUENCES IN THE INPUT ASSEMBLY
+//
+
+//
+// MODULE IMPORT BLOCK
+//
+include { CHECK_BARCODE          } from '../../modules/local/check_barcode'
+include { BLAST_MAKEBLASTDB      } from '../../modules/nf-core/blast/makeblastdb'
+include { BLAST_BLASTN           } from '../../modules/nf-core/blast/blastn'
+include { FILTER_BARCODE         } from '../../modules/local/filter_barcode'
+
+workflow PACBIO_BARCODE_CHECK {
+    take:
+    reference_tuple             // tuple    [[meta.id], reference ]
+    pacbio_tuple                // tuple    [[meta.id], pacbio-files]
+    barcodes                    // tuple    [[meta.id], barcode-file]
+    barcode_multiplex           // val      (csv-list-string)
+
+    main:
+    ch_versions             = Channel.empty()
+
+    //
+    // MODULE: CHECK FOR KNOWN BARCODES IN SAMPLE DATA
+    //
+    CHECK_BARCODE (
+        pacbio_tuple,
+        barcodes.map{it[1]},
+        barcode_multiplex
+    )
+    ch_versions     = ch_versions.mix(CHECK_BARCODE.out.versions)
+
+    //
+    // LOGIC: INCASE THE PIPELINE MANAGES TO CONTINUE AFTER FAILING CHECK_BARCODE
+    //          HERE WE ENSURE THE REST OF THE SUBWORKFLOW DOES NOT RUN
+    //
+    CHECK_BARCODE.out.result
+        .branch {
+            valid   :   it.toString().contains('BARCODES FOUND')
+            invalid :   it.toString().contains('FAILED')
+        }
+        .set { gatekeeping }
+
+    //
+    // LOGIC: ENSURE THE VALID CHANNEL IS MIXED WITH THE BARCODES CHANNEL
+    //          ACTS AS A GATEKEEPER FOR THE FLOW
+    //
+    gatekeeping.valid
+        .combine( barcodes )
+        .map {str, meta, file ->
+                file
+        }
+        .set {ch_new_barcodes}
+
+    //
+    // MODULE: GENERATE BLAST DB ON ORGANELLAR GENOME
+    //
+    BLAST_MAKEBLASTDB (
+        ch_new_barcodes
+    )
+    ch_versions     = ch_versions.mix(BLAST_MAKEBLASTDB.out.versions)
+
+    //
+    // MODULE: RUN BLAST WITH GENOME AGAINST ORGANELLAR GENOME
+    //
+    BLAST_BLASTN (
+        reference_tuple,
+        BLAST_MAKEBLASTDB.out.db
+    )
+    ch_versions     = ch_versions.mix(BLAST_BLASTN.out.versions)
+
+    //
+    // LOGIC: FOR I (MAPPED TO OTHER CHANNELS) IN CSV LIST RUN FILTER BLAST
+    //
+    barcode_multiplex
+        .map { it ->
+            tuple( it.split(',') )
+        }
+        .flatten()
+        .combine( reference_tuple )
+        .combine( BLAST_BLASTN.out.txt )
+        .multiMap { code, ref_meta, ref, blast_meta, blast ->
+            barcodes: code
+            reference: tuple( ref_meta, ref )
+            blastdata: tuple( blast_meta, blast )
+        }
+        .set {testing}
+
+    //
+    // MODULE: CREATE A FILTERED BLAST OUTPUT PER BARCODE
+    //
+    FILTER_BARCODE (
+        testing.reference,
+        testing.blastdata,
+        testing.barcodes
+    )
+    ch_versions     = ch_versions.mix(FILTER_BARCODE.out.versions)
+
+    emit:
+    filtered        = FILTER_BARCODE.out.debarcoded
+    versions        = ch_versions.ifEmpty(null)
+}