Feature/euks support

CITATIONS.md

@@ -22,6 +22,24 @@
 
 > Chklovski A, Parks DH, Woodcroft BJ, Tyson GW. CheckM2: a rapid, scalable and accurate tool for assessing microbial genome quality using machine learning. Nat Methods. 2023;20(8):1203-1212. doi: 10.1038/s41592-023-01940-w. PubMed PMID: 37500759; PubMed Central PMCID: not available.
 
+- [EukCC](https://github.com/EBI-Metagenomics/EukCC)
+
+> Saary P, Mitchell AL, Finn RD. Estimating the quality of eukaryotic genomes recovered from metagenomic analysis with EukCC. Genome Biol. 2020;21(1):244. doi: 10.1186/s13059-020-02155-4. PubMed PMID: 32912302; PubMed Central PMCID: PMC7488429.
+
+- [MetaEuk](https://github.com/soedinglab/metaeuk)
+
+> Levy Karin E, Mirdita M, Söding J. MetaEuk-sensitive, high-throughput gene discovery, and annotation for large-scale eukaryotic metagenomics. Microbiome. 2020;8(1):48. doi: 10.1186/s40168-020-00808-x. PubMed PMID: 32245390; PubMed Central PMCID: PMC7126354.
+
+- [pplacer](https://matsen.fhcrc.org/pplacer/)
+
+> Matsen FA, Kodner RB, Armbrust EV. pplacer: linear time maximum-likelihood and Bayesian phylogenetic placement of sequences onto a fixed reference tree. BMC Bioinformatics. 2010;11:538. doi: 10.1186/1471-2105-11-538. PubMed PMID: 21034504; PubMed Central PMCID: PMC3098090.
+
+- [BUSCO](https://busco.ezlab.org)
+
+> Manni M, Berkeley MR, Seppey M, Simão FA, Zdobnov EM. BUSCO Update: Novel and Streamlined Workflows along with Broader and Deeper Phylogenetic Coverage for Scoring of Eukaryotic, Prokaryotic, and Viral Genomes. Mol Biol Evol. 2021;38(10):4647-4654. doi: 10.1093/molbev/msab199. PubMed PMID: 34320186; PubMed Central PMCID: PMC8476166.
+
+> Tegenfeldt F, Kuznetsov D, Manni M, Berkeley M, Zdobnov EM, Kriventseva EV. OrthoDB and BUSCO update: annotation of orthologs with wider sampling of genomes. Nucleic Acids Res. 2025;53(D1):D516-D522. doi: 10.1093/nar/gkae987. PubMed PMID: 39535043.
+
 - [CAT and BAT](https://doi.org/10.1186/s13059-019-1817-x)
 
 > von Meijenfeldt FAB, Arkhipova K, Cambuy DD, Coutinho FH, Dutilh BE. Robust taxonomic classification of uncharted microbial sequences and bins with CAT and BAT. Genome Biol. 2019;20(1):217. doi: 10.1186/s13059-019-1817-x. PubMed PMID: 31640809; PubMed Central PMCID: PMC6805573.

assets/schema_input_assembly.json

@@ -97,7 +97,7 @@
                 "type": "string",
                 "enum": ["metagenome", "metatranscriptome"],
                 "errorMessage": "Assembly type should be metagenome or metatranscriptome",
-                "description": "Assembly type: metagenome or metatranscriptome. Written to the ENA manifest as ASSEMBLY_TYPE 'primary metagenome' or 'metatranscriptome'. Default: metagenome",
+                "description": "Assembly type: `metagenome` or `metatranscriptome`. Written to the ENA assembly manifest as ASSEMBLY_TYPE 'primary metagenome' (ENA docs: https://ena-docs.readthedocs.io/en/latest/submit/assembly/metagenome/primary.html) or 'metatranscriptome' (ENA docs: https://ena-docs.readthedocs.io/en/latest/submit/assembly/metatranscriptome.html) respectively. Default: `metagenome`.",
                 "default": "metagenome",
                 "meta": ["assembly_type"]
             }

assets/schema_input_genome.json

@@ -79,7 +79,7 @@
             "stats_generation_software": {
                 "type": "string",
                 "default": null,
-                "description": "Tool, including version, that was used to calculate completeness and contamination, e.g. CheckM2_v1.0.0",
+                "description": "Tool, including version, that was used to calculate completeness and contamination, e.g. CheckM2_v1.0.0. Several tools are separated by `;`, e.g. busco_v6.1.0;eukcc_v2.2.0. If the pipeline runs additional tools for this genome, they are appended to the provided value.",
                 "meta": ["stats_generation_software"]
             },
             "completeness": {
@@ -165,7 +165,7 @@
                     }
                 ],
                 "default": null,
-                "description": "Presence or absence of the 23S, 16S, and 5S rRNA genes and at least 18 tRNAs. This is used for MISAG/MIMAG assembly quality classification. Options: 'true' or 'false'",
+                "description": "Presence or absence of the 23S, 16S, and 5S rRNA genes (prokaryotes) or the 28S, 18S, 5.8S and 5S rRNA genes (eukaryotes) and at least 18 tRNAs. This is used for MISAG/MIMAG assembly quality classification. Options: true or false.",
                 "meta": ["RNA_presence"]
             },
             "NCBI_lineage": {

bin/count_rna.py

@@ -6,6 +6,7 @@
 
 import argparse
 import logging
+import re
 
 
 # Expected rRNA gene lengths
@@ -18,6 +19,13 @@
     "5_8S_rRNA": 155,
 }
 
+# rRNA genes required per domain (gene names as reported by barrnap for each --kingdom)
+REQUIRED_RRNA = {
+    "bac": ["16S_rRNA", "23S_rRNA", "5S_rRNA"],
+    "arc": ["16S_rRNA", "23S_rRNA", "5S_rRNA"],
+    "euk": ["18S_rRNA", "28S_rRNA", "5_8S_rRNA", "5S_rRNA"],
+}
+
 AA = [
     "Ala",
     "Gly",
@@ -41,14 +49,17 @@
     "Trp",
 ]
 
+TRNASCAN_REGEXP = r"^\s*(\S+)\s*:\s*(\d+)"
+
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
 def parse_args():
     parser = argparse.ArgumentParser(
         description="Script parses tRNAscan-SE output and barrnap GFF output, and writes a decision "
         "of whether RNA genes are present in the genome. Decision is 'True' if number of tRNA genes "
-        "is at least --trna-limit and 16S, 23S, and 5S rRNA genes have more than --rrna-limit percentage "
-        "of gene length recovered, and 'False' otherwise."
+        "is at least --trna-limit and all rRNA genes required for --domain (16S, 23S and 5S for bac/arc; "
+        "18S, 28S, 5.8S and 5S for euk) have at least --rrna-limit percentage of gene length recovered, "
+        "and 'False' otherwise."
     )
     parser.add_argument("-t", "--trna", dest="trna", help="trnas_stats.out from tRNAscan-SE",
                         required=True)
@@ -60,8 +71,10 @@ def parse_args():
                         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="Minimum percentage of 16S, 23S, and 5S rRNA gene length recovered to count the gene as present.",
-                        required=True, type=int)
+    parser.add_argument("--rrna-limit", dest="rrna_limit", help="Minimum percentage of rRNA gene length recovered to count the gene as present.",
+                        required=True, type=float)
+    parser.add_argument("-d", "--domain", dest="domain", help="Taxonomic domain of the genome, defines which rRNA genes are required (default: bac)",
+                        choices=sorted(REQUIRED_RRNA), default="bac", required=False)
     return parser.parse_args()
 
 
@@ -87,18 +100,18 @@ def parse_trna(trna_input):
             if "Isotype / Anticodon" in line:
                 start_parsing = True
             elif start_parsing:
-                cols = line.split()
-                if len(cols) > 1:
-                    aa_pred = line.split()[0]
-                    counts = int(line.split()[2])
-                    if aa_pred in AA:
+                match = re.match(TRNASCAN_REGEXP, line)
+                if match:
+                    aa_pred = match.group(1)
+                    counts = int(match.group(2))
+                    if any(i in aa_pred for i in AA):
                         trnas += counts
                         logging.info(f"Found {counts} tRNA genes for amino acid {aa_pred}")
     return trnas
 
 
-def parse_rrna(rrna_input, rrna_limit):
-    """Parses barrnap GFF output and counts 16S, 23S, and 5S rRNA genes that have more than --rrna-limit percentage of gene length recovered.
+def parse_rrna(rrna_input, rrna_limit, required_genes):
+    """Parses barrnap GFF output and counts required rRNA genes that have at least --rrna-limit percentage of gene length recovered.
 
     File example:
     ##gff-version 3
@@ -128,8 +141,7 @@ def parse_rrna(rrna_input, rrna_limit):
                         break
 
                 # Check if gene length meets the threshold
-                # For now we only consider bacterial/archaeal rRNA genes
-                if gene_name in ["16S_rRNA", "23S_rRNA", "5S_rRNA"]:
+                if gene_name in required_genes:
                     expected_length = EXPECTED_LENGTHS[gene_name]
                     percentage_recovered = (gene_length / expected_length) * 100
                     logging.info(f"Found {gene_name} with length {gene_length} bp, which is {percentage_recovered:.2f}% of expected length.")
@@ -147,11 +159,13 @@ def main():
     logging.info(f"Found {trna_count} tRNA in total")
     # parsing rRNA
     logging.info(f"Parsing rRNA genes from {args.rrna}")
-    rrna_count = parse_rrna(rrna_input=args.rrna, rrna_limit=args.rrna_limit)
-    logging.info(f"Found {rrna_count} rRNA subunit types in total")
+    required_genes = REQUIRED_RRNA[args.domain]
+    logging.info(f"Required rRNA genes for domain '{args.domain}': {', '.join(required_genes)}")
+    rrna_count = parse_rrna(rrna_input=args.rrna, rrna_limit=args.rrna_limit, required_genes=required_genes)
+    logging.info(f"Found {rrna_count} of {len(required_genes)} required rRNA subunit types")
 
-    # rrna_count should be 3 to make sure all 3 rRNA genes are present
-    decision = "True" if trna_count >= args.trna_limit and rrna_count == 3 else "False"
+    # all required rRNA genes must be present
+    decision = "True" if trna_count >= args.trna_limit and rrna_count == len(required_genes) else "False"
     logging.info(f"RNA presented: {decision}")
 
     with open(args.output, 'w') as file_out:

conf/containers_conda_lock_files_amd64.config

@@ -1 +1,2 @@
+process { withName: 'BUSCO_BUSCO' { container = 'modules/nf-core/busco/busco/.conda-lock/linux_amd64-bd-6d1f7006d91892b3_1.txt' } }
 process { withName: 'MULTIQC' { conda = 'modules/nf-core/multiqc/.conda-lock/linux_amd64-bd-c17fb751507e9dfc_1.txt' } }

conf/containers_docker_amd64.config

@@ -1 +1,2 @@
+process { withName: 'BUSCO_BUSCO' { container = 'community.wave.seqera.io/library/busco:6.1.0--6d1f7006d91892b3' } }
 process { withName: 'MULTIQC' { container = 'community.wave.seqera.io/library/multiqc:1.35--c17fb751507e9dfc' } }

conf/containers_singularity_https_amd64.config

@@ -1 +1,2 @@
+process { withName: 'BUSCO_BUSCO' { container = 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/96/963bad66c10646cf0adb1967cc462ad04d02789ddbfae4fbb94182291dbddf8c/data' } }
 process { withName: 'MULTIQC' { container = 'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/c8/c8e346f4f6080eadf1253505e6ff09ef004454fc18e8d672006fd7b222cc412e/data' } }

conf/containers_singularity_oras_amd64.config

@@ -1 +1,2 @@
+process { withName: 'BUSCO_BUSCO' { container = 'oras://community.wave.seqera.io/library/busco:6.1.0--c7528d5825eb19b5' } }
 process { withName: 'MULTIQC' { container = 'oras://community.wave.seqera.io/library/multiqc:1.35--c680f2aea25ccec2' } }

conf/modules.config

@@ -43,6 +43,7 @@ process {
     }
 
     withName: 'CATPACK_BINS' {
+        ext.args = '--no_stars'
         publishDir = [
             path: { "${params.outdir}/${params.mode}/${meta.id}/taxonomy" },
             mode: params.publish_dir_mode,
@@ -67,7 +68,7 @@ process {
         ]
     }
 
-    withName: 'RENAME_FASTA_FOR_CATPACK|CAT_DB_UNTAR' {
+    withName: 'RENAME_FASTA_FOR_CATPACK|CAT_DB_UNTAR|DB_UNTAR' {
         publishDir = [
             enabled: false
         ]
@@ -86,6 +87,7 @@ process {
     }
 
     withName: 'TRNASCANSE' {
+        ext.args = { [euk: '-E', arc: '-A', bac: '-B'].get(meta.domain, '-G') }
         publishDir = [
             path: { "${params.outdir}/${params.mode}/${meta.id}/rna/trnascanse" },
             mode: params.publish_dir_mode,
@@ -103,6 +105,39 @@ process {
     // GENOME QUALITY ASSESSMENT SUBWORKFLOW
     //
 
+    withName: BUSCO_BUSCO {
+        tag        = { "${meta.domain}-${meta.id}" }
+        ext.args   = params.busco_db ? '--offline' : ''
+        publishDir = [
+            [
+                path: { "${params.outdir}/${params.mode}/${meta.id}/busco/${meta.domain}-${meta.id}" },
+                mode: params.publish_dir_mode,
+                pattern: "*{.txt,.json,.log}",
+            ],
+            [
+                path: { "${params.outdir}/${params.mode}/${meta.id}/busco" },
+                mode: params.publish_dir_mode,
+                overwrite: false,
+                pattern: "busco_downloads/lineages/*",
+                enabled: params.save_busco_db,
+            ],
+        ]
+    }
+
+    withName: 'EUKCC_SINGLE' {
+        publishDir = [
+            path: { "${params.outdir}/${params.mode}/${meta.id}/eukcc" },
+            mode: params.publish_dir_mode,
+            pattern: "*_eukcc_results/eukcc.tsv",
+        ]
+    }
+
+    withName: 'GUNZIP_FASTA' {
+        publishDir = [
+            enabled: false
+        ]
+    }
+
     withName: 'CHECKM2_PREDICT' {
         publishDir = [
             path: { "${params.outdir}/${params.mode}/${meta.id}/checkm2" },

conf/test.config

@@ -16,19 +16,22 @@ process {
         memory: '12.GB',
         time: '1.h'
     ]
+
+    withName: 'REGISTERSTUDY|SUBMIT|CREATE_MANIFESTS' {
+          ext.when = false
+    }
 }
 
 params {
     config_profile_name        = 'Test profile for minimal pipeline test'
-    config_profile_description = 'Runs --mode mags with multiple mags and missing metadata'
+    config_profile_description = 'Runs --mode mags with multiple mags and missing metadata. Test skips all modules using ENA queries.'
 
     // Input data
     input            = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/mag_multiple_bins_missing_metadata.csv'
     outdir           = 'test_output'
 
     mode             = "mags"
-    submission_study = null
-    study_metadata   = params.pipelines_testdata_base_path + 'seqsubmit/test_data/study_metadata/study_metadata.json'
+    submission_study = "TEST_STUDY"
     centre_name      = "TEST_CENTER"
 
     test_upload      = true

conf/test_full.config

@@ -9,6 +9,11 @@
 
 ----------------------------------------------------------------------------------------
 */
+process {
+    withName: 'REGISTERSTUDY|SUBMIT|CREATE_MANIFESTS' {
+          ext.when = false
+    }
+}
 
 params {
     config_profile_name        = 'Full test profile'
@@ -19,8 +24,7 @@ params {
     outdir           = 'test_output'
 
     mode             = "mags"
-    submission_study = null
-    study_metadata   = params.pipelines_testdata_base_path + 'seqsubmit/test_data/study_metadata/study_metadata.json'
+    submission_study = "TEST_STUDY"
     centre_name      = "TEST_CENTER"
 
     test_upload      = true

conf/test_mag_complete_metadata.config

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/seqsubmit -profile test_mag_complete_metadata,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_mag_complete_metadata_existing_study.conf

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/seqsubmit -profile test_mag_complete_metadata_existing_study,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */

conf/test_mag_no_taxonomy.conf → conf/test_mag_missing_metadata.config

@@ -19,11 +19,11 @@ process {
 }
 
 params {
-    config_profile_name        = 'Test --mode mags no_taxonomy profile'
-    config_profile_description = 'Single-case MAG test with missing NCBI_lineage value'
+    config_profile_name        = 'Test profile for minimal pipeline test'
+    config_profile_description = 'Runs --mode mags with multiple mags and missing metadata with ENA test upload'
 
     // Input data
-    input            = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/mag_no_taxonomy.csv'
+    input            = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/mag_multiple_bins_missing_metadata.csv'
     outdir           = 'test_output'
 
     mode             = "mags"

conf/test_mag_no_coverage_paired_reads.conf → conf/test_mag_no_coverage_pe_skip_ena_queries.conf

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/seqsubmit -profile test_mag_no_coverage_pe_skip_ena_queries,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
@@ -16,19 +16,22 @@ process {
         memory: '12.GB',
         time: '1.h'
     ]
+
+    withName: 'REGISTERSTUDY|SUBMIT|CREATE_MANIFESTS' {
+          ext.when = false
+    }
 }
 
 params {
     config_profile_name        = 'Test --mode mags no_coverage_paired_reads profile'
-    config_profile_description = 'Single-case MAG test with missing genome_coverage and paired-end reads'
+    config_profile_description = 'Single-case MAG test with missing genome_coverage and paired-end reads. Test skips all modules using ENA queries.'
 
     // Input data
     input            = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/mag_no_coverage_paired_reads.csv'
     outdir           = 'test_output'
 
     mode             = "mags"
-    submission_study = null
-    study_metadata   = params.pipelines_testdata_base_path + 'seqsubmit/test_data/study_metadata/study_metadata.json'
+    submission_study = "TEST_STUDY"
     centre_name      = "TEST_CENTER"
 
     test_upload      = true

conf/test_mag_no_coverage_single_reads.conf → conf/test_mag_no_coverage_se_skip_ena_queries.conf

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/seqsubmit -profile test_mag_no_coverage_se_skip_ena_queries,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */
@@ -16,19 +16,22 @@ process {
         memory: '12.GB',
         time: '1.h'
     ]
+
+    withName: 'REGISTERSTUDY|SUBMIT|CREATE_MANIFESTS' {
+          ext.when = false
+    }
 }
 
 params {
     config_profile_name        = 'Test --mode mags no_coverage_single_reads profile'
-    config_profile_description = 'Single-case MAG test with missing genome_coverage and single-end reads'
+    config_profile_description = 'Single-case MAG test with missing genome_coverage and single-end reads.  Test skips all modules using ENA queries.'
 
     // Input data
     input            = params.pipelines_testdata_base_path + 'seqsubmit/samplesheets/mag_no_coverage_single_reads.csv'
     outdir           = 'test_output'
 
     mode             = "mags"
-    submission_study = null
-    study_metadata   = params.pipelines_testdata_base_path + 'seqsubmit/test_data/study_metadata/study_metadata.json'
+    submission_study = "TEST_STUDY"
     centre_name      = "TEST_CENTER"
 
     test_upload      = true

conf/test_mag_no_quality.conf

@@ -5,7 +5,7 @@
     Defines input files and everything required to run a fast and simple pipeline test.
 
     Use as follows:
-        nextflow run nf-core/seqsubmit -profile test,<docker/singularity> --outdir <OUTDIR>
+        nextflow run nf-core/seqsubmit -profile test_mag_no_quality,<docker/singularity> --outdir <OUTDIR>
 
 ----------------------------------------------------------------------------------------
 */