sanger-tol · yumisims · May 19, 2025 · Mar 28, 2025 · Apr 3, 2025 · Apr 4, 2025
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -81,5 +81,6 @@ jobs:
         uses: jlumbroso/free-disk-space@54081f138730dfa15788a46383842cd2f914a1be # v1.3.1
 
       - name: "Run pipeline with test data ${{ matrix.NXF_VER }} | ${{ matrix.test_name }} | ${{ matrix.profile }}"
+        continue-on-error: ${{ matrix.NXF_VER == 'latest-everything' }}
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile ${{ matrix.test_name }},${{ matrix.profile }} --outdir ./results
diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml
@@ -53,15 +53,15 @@ jobs:
           pip install nf-core==${{ steps.read_yml.outputs['nf_core_version'] }}
 
       - name: Run nf-core pipelines lint
-        if: ${{ github.base_ref != 'master' }}
+        if: ${{ github.base_ref != 'main' }}
         env:
           GITHUB_COMMENTS_URL: ${{ github.event.pull_request.comments_url }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
           GITHUB_PR_COMMIT: ${{ github.event.pull_request.head.sha }}
         run: nf-core -l lint_log.txt pipelines lint --dir ${GITHUB_WORKSPACE} --markdown lint_results.md
 
       - name: Run nf-core pipelines lint --release
-        if: ${{ github.base_ref == 'master' }}
+        if: ${{ github.base_ref == 'main' }}
         env:
           GITHUB_COMMENTS_URL: ${{ github.event.pull_request.comments_url }}
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

diff --git a/.nf-core.yml b/.nf-core.yml
@@ -31,7 +31,7 @@ lint:
     - manifest.name
     - manifest.homePage
   template_strings: false
-nf_core_version: 3.2.0
+nf_core_version: 3.2.1
 repository_type: pipeline
 template:
   author: priyanka-surana
@@ -43,4 +43,4 @@ template:
   outdir: .
   skip_features:
     - igenomes
-  version: 0.7.1
+  version: 0.8.0
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -3,7 +3,36 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [[0.7.1](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.7.1)] – Psyduck (patch 1) – [2025-03-297
+## [[0.8.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.8.0)] – Sprigatito – [2025-05-19]
+
+### Enhancements & fixes
+
+- Runtime of the blast commands is now capped at 12 hours (#166)
+- Upgraded Busco and added an option to control the gene predictor used (#160, #174, #181)
+- nf-core template upgrade (to version 3.2.1) (#164, #176)
+- Documentation fixes (broken links) (#175)
+- Ability to run without any read data (#177)
+
+### Software dependencies
+
+Note, since the pipeline is using Nextflow DSL2, each process will be run with its own [Biocontainer](https://biocontainers.pro/#/registry). This means that on occasion it is entirely possible for the pipeline to be using different versions of the same tool. However, the overall software dependency changes compared to the last release have been listed below for reference. Only `Docker` or `Singularity` containers are supported, `conda` is not supported.
+
+| Dependency  | Old version | New version |
+| ----------- | ----------- | ----------- |
+| blobtoolkit | 4.4.4       | 4.4.6       |
+| busco       | 5.7.1       | 5.8.3       |
+
+### Parameters
+
+| Old parameter | New parameter          |
+| ------------- | ---------------------- |
+|               | --busco_gene_predictor |
+
+> **NB:** Parameter has been **updated** if both old and new parameter information is present. </br> **NB:** Parameter has been **added** if just the new parameter information is present. </br> **NB:** Parameter has been **removed** if new parameter information isn't present.
+
+## [[0.7.1](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.7.1)] – Psyduck (patch 1) – [2025-03-29]
+
+### Enhancements & fixes
 
 - Upgraded the blobtools version which contains a bugfix
 
@@ -17,6 +46,8 @@ Note, since the pipeline is using Nextflow DSL2, each process will be run with i
 
 ## [[0.7.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.7.0)] – Psyduck – [2025-03-19]
 
+### Enhancements & fixes
+
 - Fetch information about the chromosomes of the assemblies. Used to power
   "grid plots".
 - Fill in accurate read information in the blobDir. Users are now reqiured
@@ -54,6 +85,8 @@ Note, since the pipeline is using Nextflow DSL2, each process will be run with i
 
 ## [[0.6.0](https://github.com/sanger-tol/blobtoolkit/releases/tag/0.6.0)] – Bellsprout – [2024-09-13]
 
+### Enhancements & fixes
+
 The pipeline has now been validated for draft (unpublished) assemblies.
 
 - The pipeline now queries the NCBI database instead of GoaT to establish the

diff --git a/CITATION.cff b/CITATION.cff
@@ -1,48 +1,69 @@
-cff-version: 1.2.0
-title: sanger-tol/blobtoolkit v0.7.1
 authors:
-  - family-names: Butt
+  - affiliation: Wellcome Sanger Institute
+    family-names: Butt
     given-names: Zaynab
-    affiliation: Wellcome Sanger Institute
-    orcid: 0009-0009-7934-8440
-  - family-names: Chafin
+    orcid: https://orcid.org/0009-0009-7934-8440
+    website: https://github.com/zb32
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Chafin
     given-names: Tyler
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0001-8687-5905
-  - family-names: Challis
+    orcid: https://orcid.org/0000-0001-8687-5905
+    website: https://github.com/tkchafin
+  - affiliation: Wellcome Sanger Institute
+    family-names: Challis
     given-names: Rich
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0002-3502-1122
-  - family-names: Kumar
+    orcid: https://orcid.org/0000-0002-3502-1122
+    website: https://github.com/rjchallis
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Kumar
     given-names: Sujai
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0001-5902-6641
-  - family-names: Muffato
+    orcid: https://orcid.org/0000-0001-5902-6641
+    website: https://github.com/sujaikumar
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Muffato
     given-names: Matthieu
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0002-7860-3560
-  - family-names: Pointon
-    given-names: Damon-Lee
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0003-2949-6719
-  - family-names: Qi
+    orcid: https://orcid.org/0000-0002-7860-3560
+    website: https://github.com/muffato
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Qi
     given-names: Guoying
-    orcid: 0000-0003-1262-8973
-    affiliation: Wellcome Sanger Institute
-  - family-names: "Ramos D\xEDaz"
+    orcid: https://orcid.org/0000-0003-1262-8973
+    website: https://github.com/gq1
+  - email: [email protected]
+    family-names: "Ramos D\xEDaz"
     given-names: Alexander
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0001-6410-3349
-  - family-names: Surana
+    orcid: https://orcid.org/0000-0001-6410-3349
+    website: https://github.com/alxndrdiaz
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Sims
+    given-names: Yumi
+    orcid: https://orcid.org/0000-0003-4765-4872
+    website: https://github.com/yumisims
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Surana
     given-names: Priyanka
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0002-7167-0875
-  - family-names: Yates
+    orcid: https://orcid.org/0000-0002-7167-0875
+    website: https://github.com/priyanka-surana
+  - affiliation: Wellcome Sanger Institute
+    email: [email protected]
+    family-names: Yates
     given-names: Bethan
-    affiliation: Wellcome Sanger Institute
-    orcid: 0000-0003-1658-1762
-doi: 10.5281/zenodo.13758882
-repository-code: "https://github.com/sanger-tol/blobtoolkit"
+    orcid: https://orcid.org/0000-0003-1658-1762
+    website: https://github.com/BethYates
+cff-version: 1.2.0
+date-released: "2025-04-25"
+doi: 10.5281/zenodo.7949058
 license: MIT
-version: 0.7.1
-date-released: "2024-09-13"
+message: If you use this software, please cite it using the metadata from this file
+  and all references from CITATIONS.md .
+repository-code: https://github.com/sanger-tol/blobtoolkit
+title: sanger-tol/blobtoolkit v0.8.0 -
+type: software
+url: https://pipelines.tol.sanger.ac.uk/blobtoolkit
+version: 0.8.0
diff --git a/bin/generate_config.py b/bin/generate_config.py
@@ -53,8 +53,21 @@ def parse_args(args=None):
     parser.add_argument("--taxdump", help="Path to the taxonomy database", required=True)
     parser.add_argument("--precomputed_busco", action="append", help="Path to precomputed BUSCO outputs", required=False)
     parser.add_argument("--version", action="version", version="%(prog)s 2.0")
-    return parser.parse_args(args)
+    args = parser.parse_args(args)
+
+    if not args.read_id and not args.read_type and not args.read_layout and not args.read_path:
+        # All read arguments skipped, OK
+        pass
+    elif args.read_id and args.read_type and args.read_layout and args.read_path:
+        # All read arguments passed
+        if len(set([len(args.read_id), len(args.read_type), len(args.read_layout), len(args.read_path)])) != 1:
+            print(f"The --read_id, --read_type, --read_layout, and --read_path, must be passed the same number of times", file=sys.stderr)
+            sys.exit(1)
+    else:
+        print(f"The --read_id, --read_type, --read_layout, and --read_path, must be passed the same number of times", file=sys.stderr)
+        sys.exit(1)
 
+    return args
 
 def make_dir(path):
     if len(path) > 0:
@@ -360,7 +373,7 @@ def main(args=None):
     if sequence_report:
         print_tsvs(args.output_prefix, sequence_report)
 
-    reads = zip(args.read_id, args.read_type, args.read_layout, args.read_path)
+    reads = zip(args.read_id, args.read_type, args.read_layout, args.read_path) if args.read_id else []
 
     print_yaml(
         f"{args.output_prefix}.yaml",

diff --git a/conf/base.config b/conf/base.config
@@ -105,15 +105,14 @@ process {
     }
 
     withName: "BLAST_BLASTN" {
-
-        // There are blast failures we don't know how to fix. We just give up after 3 attempts
-        errorStrategy = { task.exitStatus in ((130..145) + 104) ? (task.attempt == 3 ? 'ignore' : 'retry') : 'finish' }
-
-
-        // Most jobs complete quickly but some need a lot longer. For those outliers,
-        // the CPU usage remains usually low, averaging a single CPU
-        cpus   = { task.attempt == 1 ? 4 : 1 }
+        cpus   = 4
         memory = 2.GB
-        time   = { task.attempt == 1 ? 4.h : ( task.attempt == 2 ? 47.h : 167.h ) }
+        time   = 12.h
+    }
+
+    withName: "NOHIT_LIST" {
+        cpus   = { task.attempt }
+        memory = { 1.GB * Math.pow(4, task.attempt) }
+        time   = { 1.h * Math.pow(8, task.attempt) }
     }
 }
diff --git a/conf/modules.config b/conf/modules.config
@@ -85,11 +85,15 @@ process {
     withName: "BUSCO_BUSCO" {
         // Obey "use_work_dir_as_temp", except for large genomes
         scratch = { !params.use_work_dir_as_temp || (meta.genome_size < 2000000000) }
-        ext.args = { 'test' in workflow.profile.tokenize(',') || 'test_raw' in workflow.profile.tokenize(',') || 'test_nobusco' in workflow.profile.tokenize(',') ?
-                        // Additional configuration to speed processes up during testing.
-                        // Note: BUSCO *must* see the double-quotes around the parameters
-                        '--force --metaeuk --metaeuk_parameters \'"-s=2"\' --metaeuk_rerun_parameters \'"-s=2"\''
-                    : '--force --metaeuk'  }
+        ext.args = {
+            def base = '--force'
+            // is a certain predictor requested ?
+            if (params.busco_gene_predictor) {
+                base += ' --' + params.busco_gene_predictor
+            }
+            // otherwise, let's go with the default (miniprot)
+            return base
+        }
     }
 
     withName: "RESTRUCTUREBUSCODIR" {

diff --git a/docs/usage.md b/docs/usage.md
@@ -45,13 +45,29 @@ sample3,ont,ont.cram,SINGLE
 | `datafile`       | Full path to read data file.                                                                                                                                                          |
 | `library_layout` | Layout of the library. Must be one of `SINGLE`, `PAIRED`.                                                                                                                             |
 
-An [example samplesheet](assets/test/samplesheet.csv) has been provided with the pipeline.
+An [example samplesheet](../assets/test/samplesheet.csv) has been provided with the pipeline.
 
 ### Support for [nf-core/fetchngs](https://nf-co.re/fetchngs)
 
 The pipeline can also accept a samplesheet generated by the [nf-core/fetchngs](https://nf-co.re/fetchngs) pipeline (tested with version 1.11.0).
 The pipeline then needs the `--fetchngs_samplesheet true` option _and_ `--align true`, since the data files would all be unaligned.
 
+## BUSCO
+
+BUSCO is an important part of the assessment done by the pipeline.
+
+### Gene prediction method
+
+Busco starts with a quick gene prediction run, for which it has the following options (by decreasing speed):
+
+- Miniprot
+- Metaeuk
+- Augustus
+
+The default value has changed across Busco versions (and may change in the future).
+The pipeline exposes the `--busco_gene_predictor` option to force a specific method to be used.
+Otherwise, the pipeline will default to Busco's own default (currently Miniprot).
+
 ### Support for pre-computed `BUSCO` outputs
 
 The pipeline may be optionally run with a set of pre-computed [`BUSCO`](https://busco.ezlab.org) runs, provided using the `--precomputed_busco` parameter. These can be provided as either a directory path, or a `.tar.gz` compressed archive. The contents should be each `run_` output directory (directly from `BUSCO`) named as `run_[odb_dabasase_name]`:
@@ -261,31 +277,31 @@ see <https://training.nextflow.io/basic_training/config/> for some examples.
 Here is a full list of snakemake subworkflows and their Nextflow couterparts:
 
 - **`minimap.smk`**
-  - Implemented as [`minimap_alignment.nf`](subworkflows/local/minimap_alignment.nf).
+  - Implemented as [`minimap_alignment.nf`](../subworkflows/local/minimap_alignment.nf).
   - Optimised alignment is done using the [sanger-tol/readmapping](https://github.com/sanger-tol/readmapping) pipeline.
 - **`windowmasker.smk`**
-  - Implemented as part of [`prepare_genome.nf`](subworkflows/local/prepare_genome.nf).
+  - Implemented as part of [`prepare_genome.nf`](../subworkflows/local/prepare_genome.nf).
   - Genomes downloaded by [sanger-tol/insdcdownload](https://github.com/sanger-tol/insdcdownload) are already masked.
 - **`chunk_stats.smk`**
-  - Modified implementation as part of [`coverage_stats.nf`](subworkflows/local/coverage_stats.nf).
+  - Modified implementation as part of [`coverage_stats.nf`](../subworkflows/local/coverage_stats.nf).
   - BED file and additional statistics calculated using [`fasta_windows`](https://github.com/tolkit/fasta_windows).
 - **`busco.smk`**
-  - Implemented as [`busco_diamond_blastp.nf`](subworkflows/local/busco_diamond_blastp.nf).
+  - Implemented as [`busco_diamond_blastp.nf`](../subworkflows/local/busco_diamond_blastp.nf).
 - **`cov_stats.smk`**
-  - Implemented as part of [`coverage_stats.nf`](subworkflows/local/coverage_stats.nf).
-  - Combining the various tsv files is done in subworkflow [`collate_stats.nf`](subworkflows/local/collate_stats.nf).
+  - Implemented as part of [`coverage_stats.nf`](../subworkflows/local/coverage_stats.nf).
+  - Combining the various tsv files is done in subworkflow [`collate_stats.nf`](../subworkflows/local/collate_stats.nf).
 - **`window_stats.smk`**
-  - Implemented as part of [`collate_stats.nf`](subworkflows/local/collate_stats.nf).
+  - Implemented as part of [`collate_stats.nf`](../subworkflows/local/collate_stats.nf).
 - **`diamond_blastp.smk`**
-  - Implemented as [`busco_diamond_blastp.nf`](subworkflows/local/busco_diamond_blastp.nf).
+  - Implemented as [`busco_diamond_blastp.nf`](../subworkflows/local/busco_diamond_blastp.nf).
 - **`diamond.smk`**
-  - Implemented as [`run_blastx.nf`](subworkflows/local/run_blastx.nf).
+  - Implemented as [`run_blastx.nf`](../subworkflows/local/run_blastx.nf).
 - **`blastn.smk`**
-  - Implemented as [`run_blastn.nf`](subworkflows/local/run_blastn.nf).
+  - Implemented as [`run_blastn.nf`](../subworkflows/local/run_blastn.nf).
 - **`blobtools.smk`**
-  - Implemented as [`blobtools.nf`](subworkflows/local/blobtools.nf).
+  - Implemented as [`blobtools.nf`](../subworkflows/local/blobtools.nf).
 - **`view.smk`**
-  - Implemented as [`view.nf`](subworkflows/local/view.nf).
+  - Implemented as [`view.nf`](../subworkflows/local/view.nf).
 
 ### Software dependencies
 

diff --git a/modules.json b/modules.json
@@ -13,7 +13,7 @@
                     },
                     "busco/busco": {
                         "branch": "master",
-                        "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
+                        "git_sha": "05954dab2ff481bcb999f24455da29a5828af08d",
                         "installed_by": ["modules"],
                         "patch": "modules/nf-core/busco/busco/busco-busco.diff"
                     },

diff --git a/modules/local/blobtoolkit/chunk.nf b/modules/local/blobtoolkit/chunk.nf
@@ -5,7 +5,7 @@ process BLOBTOOLKIT_CHUNK {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         exit 1, "BLOBTOOLKIT_CHUNK module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
-    container "docker.io/genomehubs/blobtoolkit:4.4.5"
+    container "docker.io/genomehubs/blobtoolkit:4.4.6"
 
     input:
     tuple val(meta) , path(fasta)

diff --git a/modules/local/blobtoolkit/countbuscos.nf b/modules/local/blobtoolkit/countbuscos.nf
@@ -5,7 +5,7 @@ process BLOBTOOLKIT_COUNTBUSCOS {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         exit 1, "BLOBTOOLKIT_COUNTBUSCOS module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
-    container "docker.io/genomehubs/blobtoolkit:4.4.5"
+    container "docker.io/genomehubs/blobtoolkit:4.4.6"
 
     input:
     tuple val(meta), path(table, stageAs: 'dir??/*')

diff --git a/modules/local/blobtoolkit/createblobdir.nf b/modules/local/blobtoolkit/createblobdir.nf
@@ -5,7 +5,7 @@ process BLOBTOOLKIT_CREATEBLOBDIR {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         exit 1, "BLOBTOOLKIT_BLOBDIR module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
-    container "docker.io/genomehubs/blobtoolkit:4.4.5"
+    container "docker.io/genomehubs/blobtoolkit:4.4.6"
 
     input:
     tuple val(meta), path(window, stageAs: 'windowstats/*')

diff --git a/modules/local/blobtoolkit/extractbuscos.nf b/modules/local/blobtoolkit/extractbuscos.nf
@@ -5,7 +5,7 @@ process BLOBTOOLKIT_EXTRACTBUSCOS {
     if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
         exit 1, "BLOBTOOLKIT_EXTRACTBUSCOS module does not support Conda. Please use Docker / Singularity / Podman instead."
     }
-    container "docker.io/genomehubs/blobtoolkit:4.4.5"
+    container "docker.io/genomehubs/blobtoolkit:4.4.6"
 
     input:
     tuple val(meta), path(fasta)