RNA detection for genomes_submit

.github/PULL_REQUEST_TEMPLATE.md

@@ -8,14 +8,14 @@ These are the most common things requested on pull requests (PRs).
 
 Remember that PRs should be made against the dev branch, unless you're preparing a pipeline release.
 
-Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/seqsubmit/tree/main/.github/CONTRIBUTING.md)
+Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/seqsubmit/tree/master/.github/CONTRIBUTING.md)
 -->
 
 ## PR checklist
 
 - [ ] This comment contains a description of changes (with reason).
 - [ ] If you've fixed a bug or added code that should be tested, add tests!
-- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/seqsubmit/tree/main/.github/CONTRIBUTING.md)
+- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/seqsubmit/tree/master/.github/CONTRIBUTING.md)
 - [ ] If necessary, also make a PR on the nf-core/seqsubmit _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository.
 - [ ] Make sure your code lints (`nf-core pipelines lint`).
 - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir <OUTDIR>`).

.nf-core.yml

@@ -6,6 +6,9 @@ lint:
     - params.input
   files_unchanged:
     - .github/PULL_REQUEST_TEMPLATE.md
+    - docs/images/nf-core-seqsubmit_logo_light.png
+    - docs/images/nf-core-seqsubmit_logo_dark.png
+    - assets/nf-core-seqsubmit_logo_light.png
 nf_core_version: 3.5.1
 repository_type: pipeline
 template:

assets/samplesheet_genomes.csv

@@ -1,3 +1,3 @@
-sample,fasta,accession,assembly_software,binning_software,binning_parameters,stats_generation_software,completeness,contamination,genome_coverage,metagenome,co-assembly,broad_environment,local_environment,environmental_medium,rRNA_presence,NCBI_lineage
+sample,fasta,accession,fastq_1,fastq_2,assembly_software,binning_software,binning_parameters,stats_generation_software,completeness,contamination,genome_coverage,metagenome,co-assembly,broad_environment,local_environment,environmental_medium,rRNA_presence,NCBI_lineage
 lachnospira_eligens,https://github.com/nf-core/test-datasets/raw/seqsubmit/test_data/bins/bin_lachnospira_eligens.fa.gz,SRR24458089,spades_v3.15.5,mags_v1,default,CheckM2_v1.0.1,61.0,0.21,32.07,sediment metagenome,False,marine,cable bacteria,marine sediment,False,d__Bacteria;p__Proteobacteria;c__Deltaproteobacteria;o__Desulfobacterales;f__Desulfobulbaceae;g__Candidatus Electrothrix;s__
 lachnospiraceae,https://github.com/nf-core/test-datasets/raw/seqsubmit/test_data/bins/bin_lachnospiraceae.fa.gz,SRR24458087,spades_v3.15.5,mags_v1,default,CheckM2_v1.0.1,92.81,1.09,66.04,sediment metagenome,False,marine,cable bacteria,marine sediment,False,d__Bacteria;p__Proteobacteria;c__Deltaproteobacteria;o__Desulfobacterales;f__Desulfobulbaceae;g__Candidatus Electrothrix;s__Candidatus Electrothrix marina

assets/schema_input_genome.json

@@ -25,6 +25,38 @@
                 "type": "string",
                 "description": "Run or assembly ENA accession"
             },
+            "fastq_1": {
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "format": "file-path",
+                        "exists": true,
+                        "pattern": "^\\S+\\.(fq|fastq)(\\.gz)?$"
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ],
+                "errorMessage": "FASTQ file must have extension '.fq' or '.fastq' (optionally gzipped)",
+                "description": "Forward reads if paired-end or single-end reads FASTQ file"
+            },
+            "fastq_2": {
+                "anyOf": [
+                    {
+                        "type": "string",
+                        "format": "file-path",
+                        "exists": true,
+                        "pattern": "^\\S+\\.(fq|fastq)(\\.gz)?$"
+                    },
+                    {
+                        "type": "string",
+                        "maxLength": 0
+                    }
+                ],
+                "errorMessage": "FASTQ file for reverse reads must have extension '.fq' or '.fastq' (optionally gzipped)",
+                "description": "Reverse reads FASTQ file if paired-end. Leave empty for single-end reads"
+            },
             "assembly_software": {
                 "type": "string",
                 "description": "Tool name and version that was used to assemble data"
@@ -58,8 +90,8 @@
                 "description": "ENA accepted metagenome name"
             },
             "co-assembly": {
-                "type": "boolean",
-                "description": "True if data was co-assembled, False otherwise"
+                "type": "string",
+                "description": "Yes if data was co-assembled, No otherwise"
             },
             "broad_environment": {
                 "type": "string",
@@ -73,15 +105,26 @@
                 "type": "string",
                 "description": "material displaced by the sample"
             },
-            "rRNA_presence": {
-                "type": "boolean",
-                "description": "True/False if rRNA genes detected"
+            "RNA_presence": {
+                "type": "string",
+                "description": "Yes/No if rRNA genes detected"
             },
             "NCBI_lineage": {
                 "type": "string",
                 "description": "full NCBI lineage - format: x;y;z"
             }
         },
-        "required": ["sample", "fasta"]
+        "required": [
+            "sample",
+            "fasta",
+            "assembly_software",
+            "co-assembly",
+            "binning_software",
+            "binning_parameters",
+            "metagenome",
+            "broad_environment",
+            "local_environment",
+            "environmental_medium"
+        ]
     }
 }

bin/count_rna.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python
+
+# This file is part of MGnify genome analysis pipeline.
+#
+# MGnify genome analysis pipeline is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# MGnify genome analysis pipeline is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU General Public License for more details.
+
+# You should have received a copy of the GNU General Public License
+# along with MGnify genome analysis pipeline. If not, see <https://www.gnu.org/licenses/>.
+
+
+import argparse
+
+AA = [
+    "Ala",
+    "Gly",
+    "Pro",
+    "Thr",
+    "Val",
+    "Ser",
+    "Arg",
+    "Leu",
+    "Phe",
+    "Asn",
+    "Lys",
+    "Asp",
+    "Glu",
+    "His",
+    "Gln",
+    "Ile",
+    "Met",
+    "Tyr",
+    "Cys",
+    "Trp",
+]
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Script detects counts of tRNA and rRNA")
+    parser.add_argument("-t", "--trna", dest="trna", help="trnas_stats.out from tRNAscan-SE",
+                        required=True)
+    parser.add_argument("-r", "--rrna", dest="rrna", help="GFF from barrnap",
+                        required=True)
+    parser.add_argument("-n", "--name", dest="name", help="FASTA Sequence identifier used for prediction",
+                        required=True)
+    parser.add_argument("-o", "--output", dest="output", help="Name of output file (default: rna_decision.tsv)",
+                        default="rna_decision.tsv", required=False)
+    parser.add_argument("--trna-limit", dest="trna_limit", help="Minimal required number of tRNA",
+                        required=True, type=int)
+    parser.add_argument("--rrna-limit", dest="rrna_limit", help="Minimal required number of tRNA",
+                        required=True, type=int)
+    return parser.parse_args()
+
+
+def parse_trna(trna_input):
+    with open(trna_input, "r") as f:
+        trnas = 0
+        flag = 0
+        for line in f:
+            if "Isotype / Anticodon" in line:
+                flag = 1
+            elif flag == 1:
+                cols = line.split()
+                if len(cols) > 1:
+                    aa_pred = line.split(":")[0].split()[0]
+                    counts = int(line.split(":")[1].split()[0])
+                    if aa_pred in AA:
+                        trnas += counts
+    return trnas
+
+
+def parse_rrna(rrna_input):
+    count = 0
+    with open(rrna_input, 'r') as file_in:
+        for line in file_in:
+            if 'rRNA' in line:
+                count+=1
+    return count
+
+def main():
+    args = parse_args()
+    # parsing tRNA
+    trna_count = parse_trna(trna_input=args.trna)
+    print(f"Found {trna_count} tRNA")
+    # parsing rRNA
+    rrna_count = parse_rrna(rrna_input=args.rrna)
+    print(f"Found {rrna_count} rRNA")
+
+    decision = "Yes" if trna_count >= int(args.trna_limit) and rrna_count >= int(args.rrna_limit) else "No"
+    print(f"RNA presented: {decision}")
+
+    with open(args.output, 'w') as file_out:
+        file_out.write(f"{args.name}\t{str(decision)}")
+
+
+if __name__ == "__main__":
+    main()

main.nf

@@ -39,16 +39,10 @@ workflow NFCORE_SEQSUBMIT {
     // WORKFLOW: Run pipeline
     //
     // Depending on the input type (mags/bins or metagenomic_assemblies), one or the another workflow will be triggered
-    if (params.mode == "mags") {
+    if (params.mode == "mags" || params.mode == "bins") {
         GENOMESUBMIT (
             samplesheet,
-            "mags"
-        )
-        ch_multiqc_report = GENOMESUBMIT.out.multiqc_report
-    } else if (params.mode == "bins") {
-        GENOMESUBMIT (
-            samplesheet,
-            "bins"
+            params.mode
         )
         ch_multiqc_report = GENOMESUBMIT.out.multiqc_report
     } else if (params.mode == "metagenomic_assemblies") {
@@ -59,7 +53,6 @@ workflow NFCORE_SEQSUBMIT {
     }
 
 
-
     emit:
     multiqc_report = ch_multiqc_report // channel: /path/to/multiqc_report.html
 }

modules.json

@@ -5,6 +5,11 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "barrnap": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
+                    },
                     "coverm/contig": {
                         "branch": "master",
                         "git_sha": "27e31681fdbf1e511257355a236037a8cd9c2b2e",
@@ -20,6 +25,11 @@
                         "branch": "master",
                         "git_sha": "af27af1be706e6a2bb8fe454175b0cdf77f47b49",
                         "installed_by": ["modules"]
+                    },
+                    "trnascanse": {
+                        "branch": "master",
+                        "git_sha": "41dfa3f7c0ffabb96a6a813fe321c6d1cc5b6e46",
+                        "installed_by": ["modules"]
                     }
                 }
             },

modules/local/count_rna/main.nf

@@ -0,0 +1,35 @@
+/*
+ * Calculate number of tRNA and rRNA detected
+*/
+process COUNT_RNA {
+
+    label 'process_low'
+    tag "${meta.id}"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/biopython:1.75':
+        'quay.io/biocontainers/biopython:1.75' }"
+
+    input:
+    tuple val(meta), path(trnas_stats), path(rrna_gff)
+
+    output:
+    tuple val(meta), path("*rna_decision.tsv"), emit: rna_decision
+    path "versions.yml",                        emit: versions
+
+    script:
+    """
+    count_rna.py \\
+       --trna ${trnas_stats} \\
+       --rrna ${rrna_gff} \\
+       --name ${meta.id} \\
+       --trna-limit ${params.trna_limit} \\
+       --rrna-limit ${params.rrna_limit} \\
+       --output ${meta.id}_rna_decision.tsv
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        python: \$(python --version 2>&1 | sed 's/Python //g')
+        biopython: \$(python -c "import pkg_resources; print(pkg_resources.get_distribution('biopython').version)")
+    END_VERSIONS
+    """
+}

modules/local/genome_upload/main.nf

@@ -1,14 +1,14 @@
 process GENOME_UPLOAD {
-    tag "$meta.id"
+    tag "${mags_or_bins_flag}"
     label 'process_low'
 
-    container "community.wave.seqera.io/library/pip_genome-uploader:e2815984bcdc3e83"
+    container "quay.io/biocontainers/genome-uploader:2.5.1--pyhdfd78af_1"
 
     secret 'WEBIN_ACCOUNT'
     secret 'WEBIN_PASSWORD'
 
     input:
-    tuple val(meta), path(mags)
+    path(mags)
     path(table_for_upload)
     val(mags_or_bins_flag)
 

modules/local/registerstudy/main.nf

@@ -21,13 +21,14 @@ process REGISTERSTUDY {
     def args2 = task.ext.args2 ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     """
+    echo "Generate study XMLs"
     study_xmls \\
         $args \\
         --study ${study} \\
         --library ${library} \\
         --center ${center} \\
 
-
+    echo "Submit study to ENA"
     submit_study \\
         $args2 \\
         --directory ${study}_upload \\