diff --git a/.nf-core.yml b/.nf-core.yml index 260014a..1641b31 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -30,5 +30,5 @@ template: outdir: . skip_features: - igenomes - version: 0.5.0 + version: 0.6.0 update: null diff --git a/CHANGELOG.md b/CHANGELOG.md index 67872fc..ada72ae 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -25,7 +25,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 10. Added an HTML report [#44](https://github.com/Plant-Food-Research-Open/genepal/issues/44) 11. Added content type as text/html for the MultiQC and genepal reports 12. Added sra-tools for RNASeq data download [#102](https://github.com/Plant-Food-Research-Open/genepal/issues/102) - + ### `Fixed` 1. Now using `${meta.id}_trim` as prefix for `FASTQC` files diff --git a/CITATION.cff b/CITATION.cff index c5c6c26..4a2ad92 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -31,7 +31,7 @@ authors: - family-names: "Thomson" given-names: "Susan" title: "genepal: A Nextflow pipeline for genome and pan-genome annotation" -version: 0.5.0 +version: 0.6.0 date-released: 2024-11-21 url: "https://github.com/Plant-Food-Research-Open/genepal" doi: 10.5281/zenodo.14195006 diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 8969c04..6682724 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,7 +1,7 @@ report_comment: > This report has been generated by the plant-food-research-open/genepal analysis pipeline. For information about how to interpret these results, please see the - documentation. + documentation. report_section_order: "plant-food-research-open-genepal-methods-description": diff --git a/conf/modules.config b/conf/modules.config index 5d38b7d..ca741e9 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -286,7 +286,7 @@ process { // SUBWORKFLOW: GFF_STORE } withName: '.*:GFF_STORE:EXTRACT_PROTEINS' { - ext.args = params.add_attrs_to_gffread_fastas ? '-F -D -y' : '-y' + ext.args = params.add_attrs_to_proteins_cds_fastas ? '-F -D -y' : '-y' ext.prefix = { "${meta.id}.pep" } publishDir = [ diff --git a/docs/parameters.md b/docs/parameters.md index 1c96a8b..ef2bce2 100644 --- a/docs/parameters.md +++ b/docs/parameters.md @@ -4,17 +4,20 @@ A Nextflow pipeline for consensus, phased and pan-genome annotation. ## Input/output options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------- | -------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `input` | Target assemblies listed in a CSV sheet | `string` | | True | | -| `protein_evidence` | Protein evidence provided as a fasta file or multiple fasta files listed in a plain txt file | `string` | | True | | -| `eggnogmapper_db_dir` | Eggnogmapper database directory | `string` | | | | -| `eggnogmapper_tax_scope` | Eggnogmapper taxonomy scopre. Eukaryota: 2759, Viridiplantae: 33090, Archaea: 2157, Bacteria: 2, root: 1 | `integer` | 1 | | | -| `rna_evidence` | FASTQ/BAM samples listed in a CSV sheet | `string` | | | | -| `liftoff_annotations` | Reference annotations listed in a CSV sheet | `string` | | | | -| `orthofinder_annotations` | Additional annotations for orthology listed in a CSV sheet | `string` | | | | -| `outdir` | The output directory where the results will be saved | `string` | | True | | -| `email` | Email address for completion summary. | `string` | | | True | +| Parameter | Description | Type | Default | Required | Hidden | +| ------------------------------------------ | ------------------------------------------------------------------------ | -------- | ------- | -------- | ------ | +| `input` | Target assemblies listed in a CSV sheet | `string` | | True | | +| `protein_evidence` | Protein evidence provided as a fasta file or multiple fasta files listed | +| in a plain txt file | `string` | | True | | +| `eggnogmapper_db_dir` | Eggnogmapper database directory | `string` | | | | +| `eggnogmapper_tax_scope` | Eggnogmapper taxonomy scopre. Eukaryota: 2759, Viridiplantae: | +| 33090, Archaea: 2157, Bacteria: 2, root: 1 | `integer` | 1 | | | +| `rna_evidence` | FASTQ/BAM samples listed in a CSV sheet | `string` | | | | +| `liftoff_annotations` | Reference annotations listed in a CSV sheet | `string` | | | | +| `orthofinder_annotations` | Additional annotations for orthology listed in a CSV sheet | +| `string` | | | | +| `outdir` | The output directory where the results will be saved | `string` | | True | | +| `email` | Email address for completion summary. | `string` | | | True | ## Repeat annotation options @@ -27,69 +30,84 @@ A Nextflow pipeline for consensus, phased and pan-genome annotation. ## RNASeq pre-processing options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------ | ------------------------------------------------------------------ | --------- | ----------------------------------------- | -------- | ------ | -| `fastqc_skip` | Skip FASTQC or not? | `boolean` | True | | | -| `fastp_skip` | Skip trimming by FASTQP or not? | `boolean` | | | | -| `min_trimmed_reads` | Exclude a sample if its reads after trimming are below this number | `integer` | 10000 | | | -| `fastp_extra_args` | Extra FASTP arguments | `string` | | | | -| `save_trimmed` | Save FASTQ files after trimming or not? | `boolean` | | | | -| `remove_ribo_rna` | Remove Ribosomal RNA or not? | `boolean` | | | | -| `save_non_ribo_reads` | Save FASTQ files after Ribosomal RNA removal or not? | `boolean` | | | | -| `ribo_database_manifest` | Ribosomal RNA fastas listed in a text sheet | `string` | ${projectDir}/assets/rrna-db-defaults.txt | | | +| Parameter | Description | Type | Default | Required | Hidden | +| ----------------------------------------- | ------------------------------------------------------------------ | --------- | ------- | -------- | ------ | +| `fastqc_skip` | Skip FASTQC or not? | `boolean` | True | | | +| `fastp_skip` | Skip trimming by FASTQP or not? | `boolean` | | | | +| `min_trimmed_reads` | Exclude a sample if its reads after trimming are below this number | +| `integer` | 10000 | | | +| `fastp_extra_args` | Extra FASTP arguments | `string` | | | | +| `save_trimmed` | Save FASTQ files after trimming or not? | `boolean` | | | | +| `remove_ribo_rna` | Remove Ribosomal RNA or not? | `boolean` | | | | +| `save_non_ribo_reads` | Save FASTQ files after Ribosomal RNA removal or not? | `boolean` | | +| | +| `ribo_database_manifest` | Ribosomal RNA fastas listed in a text sheet | `string` | +| ${projectDir}/assets/rrna-db-defaults.txt | | | ## RNASeq alignment options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------ | ------------------------------------------------- | --------- | ------- | -------- | ------ | -| `star_max_intron_length` | Maximum intron length for STAR alignment | `integer` | 16000 | | | -| `star_align_extra_args` | EXTRA arguments for STAR | `string` | | | | -| `star_save_outputs` | Save BAM files from STAR or not? | `boolean` | | | | -| `save_cat_bam` | SAVE a concatenated BAM file per assembly or not? | `boolean` | | | | +| Parameter | Description | Type | Default | Required | Hidden | +| ------------------------ | ---------------------------------------- | --------- | ------- | -------- | ------ | +| `star_max_intron_length` | Maximum intron length for STAR alignment | `integer` | 16000 | | + +| +| `star_align_extra_args` | EXTRA arguments for STAR | `string` | | | | +| `star_save_outputs` | Save BAM files from STAR or not? | `boolean` | | | | +| `save_cat_bam` | SAVE a concatenated BAM file per assembly or not? | `boolean` | | | | ## Annotation options -| Parameter | Description | Type | Default | Required | Hidden | -| --------------------- | --------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `braker_extra_args` | Extra arguments for BRAKER | `string` | | | | -| `liftoff_coverage` | Liftoff coverage parameter | `number` | 0.9 | | | -| `liftoff_identity` | Liftoff identity parameter | `number` | 0.9 | | | -| `eggnogmapper_evalue` | Only report alignments below or equal the e-value threshold | `number` | 1e-05 | | | -| `eggnogmapper_pident` | Only report alignments above or equal to the given percentage of identity (0-100) | `integer` | 35 | | | +| Parameter | Description | Type | Default | Required | Hidden | +| --------------------- | ---------------------------------------------------------------- | -------- | ------- | -------- | ------ | +| `braker_extra_args` | Extra arguments for BRAKER | `string` | | | | +| `liftoff_coverage` | Liftoff coverage parameter | `number` | 0.9 | | | +| `liftoff_identity` | Liftoff identity parameter | `number` | 0.9 | | | +| `eggnogmapper_evalue` | Only report alignments below or equal the e-value threshold | `number` | +| 1e-05 | | | +| `eggnogmapper_pident` | Only report alignments above or equal to the given percentage of | +| identity (0-100) | `integer` | 35 | | | ## Post-annotation filtering options -| Parameter | Description | Type | Default | Required | Hidden | -| ----------------------------- | ----------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `allow_isoforms` | Allow multiple isoforms for gene models | `boolean` | True | | | -| `enforce_full_intron_support` | Require every model to have external evidence for all its introns | `boolean` | True | | | -| `filter_liftoff_by_hints` | Use BRAKER hints to filter Liftoff models | `boolean` | True | | | -| `eggnogmapper_purge_nohits` | Purge transcripts which do not have a hit against eggnog | `boolean` | | | | +| Parameter | Description | Type | Default | Required | Hidden | +| ----------------------------- | --------------------------------------------------------- | --------- | ------- | -------- | ------ | +| `allow_isoforms` | Allow multiple isoforms for gene models | `boolean` | True | | | +| `enforce_full_intron_support` | Require every model to have external evidence for all its | +| introns | `boolean` | True | | | +| `filter_liftoff_by_hints` | Use BRAKER hints to filter Liftoff models | `boolean` | True | | + +| +| `eggnogmapper_purge_nohits` | Purge transcripts which do not have a hit against eggnog | +`boolean` | | | | ## Annotation output options -| Parameter | Description | Type | Default | Required | Hidden | -| ----------------------------- | ------------------------------------ | --------- | ------- | -------- | ------ | -| `braker_save_outputs` | Save BRAKER files | `boolean` | | | | -| `add_attrs_to_proteins_fasta` | Add gff attributes to proteins fasta | `boolean` | | | | +| Parameter | Description | Type | Default | Required | Hidden | +| ---------------------------------- | --------------------------------------------- | --------- | ------- | -------- | ------ | +| `braker_save_outputs` | Save BRAKER files | `boolean` | | | | +| `add_attrs_to_proteins_cds_fastas` | Add gff attributes to proteins/cDNA/cds fasta | `boolean` | +| | | | ## Evaluation options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------ | --------------------------------------------------------------------------- | --------- | --------------- | -------- | ------ | -| `busco_skip` | Skip evaluation by BUSCO | `boolean` | | | | -| `busco_lineage_datasets` | BUSCO lineages as a space-separated list: 'fungi_odb10 microsporidia_odb10' | `string` | eukaryota_odb10 | | | +| Parameter | Description | Type | Default | Required | Hidden | +| ------------------------ | ------------------------------------------------------ | --------------- | ------- | -------- | ------ | +| `busco_skip` | Skip evaluation by BUSCO | `boolean` | | | | +| `busco_lineage_datasets` | BUSCO lineages as a space-separated list: 'fungi_odb10 | +| microsporidia_odb10' | `string` | eukaryota_odb10 | | | ## Institutional config options Parameters used to describe centralised config profiles. These should not be edited. -| Parameter | Description | Type | Default | Required | Hidden | -| ---------------------------- | ----------------------------------------- | -------- | -------------------------------------------------------- | -------- | ------ | -| `custom_config_version` | Git commit id for Institutional configs. | `string` | master | | True | -| `custom_config_base` | Base directory for Institutional configs. | `string` | https://raw.githubusercontent.com/nf-core/configs/master | | True | -| `config_profile_name` | Institutional config name. | `string` | | | True | -| `config_profile_description` | Institutional config description. | `string` | | | True | +| Parameter | Description | Type | Default | Required | Hidden | +| -------------------------------------------------------- | ----------------------------------------- | -------- | ------- | -------- | ------ | +| `custom_config_version` | Git commit id for Institutional configs. | `string` | master | | +| True | +| `custom_config_base` | Base directory for Institutional configs. | `string` | +| https://raw.githubusercontent.com/nf-core/configs/master | | True | +| `config_profile_name` | Institutional config name. | `string` | | | True | +| `config_profile_description` | Institutional config description. | `string` | | | True | ## Generic options @@ -98,9 +116,12 @@ Less common options for the pipeline, typically set in a config file. | Parameter | Description | Type | Default | Required | Hidden | | ------------------------ | ----------------------------------------------------------------- | --------- | ------- | -------- | ------ | | `version` | Display version and exit. | `boolean` | | | True | -| `publish_dir_mode` | Method used to save pipeline results to output directory. | `string` | copy | | True | -| `email_on_fail` | Email address for completion summary, only when pipeline fails. | `string` | | | True | +| `publish_dir_mode` | Method used to save pipeline results to output directory. | `string` | +| copy | | True | +| `email_on_fail` | Email address for completion summary, only when pipeline fails. | `string` | +| | True | | `plaintext_email` | Send plain-text email instead of HTML. | `boolean` | | | True | -| `max_multiqc_email_size` | File size limit when attaching MultiQC reports to summary emails. | `string` | 25.MB | | True | +| `max_multiqc_email_size` | File size limit when attaching MultiQC reports to summary emails. | +| `string` | 25.MB | | True | | `monochrome_logs` | Do not use coloured log outputs. | `boolean` | | | True | | `hook_url` | Incoming hook URL for messaging service | `string` | | | True | diff --git a/nextflow.config b/nextflow.config index 91c9962..c91980e 100644 --- a/nextflow.config +++ b/nextflow.config @@ -57,7 +57,7 @@ params { // Annotation output options braker_save_outputs = false - add_attrs_to_gffread_fastas = false + add_attrs_to_proteins_cds_fastas = false // Evaluation options busco_skip = false @@ -261,7 +261,7 @@ manifest { description = """A Nextflow pipeline for consensus, phased and pan-genome annotation.""" mainScript = 'main.nf' nextflowVersion = '!>=24.04.2' - version = '0.5.0' + version = '0.6.0' doi = 'https://doi.org/10.5281/zenodo.14195006' } diff --git a/nextflow_schema.json b/nextflow_schema.json index 0258683..2092f00 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -287,10 +287,10 @@ "description": "Save BRAKER files", "fa_icon": "fas fa-question-circle" }, - "add_attrs_to_proteins_fasta": { + "add_attrs_to_proteins_cds_fastas": { "type": "boolean", - "fa_icon": "fas fa-question-circle", - "description": "Add gff attributes to proteins fasta" + "description": "Add gff attributes to proteins/cDNA/cds fasta", + "fa_icon": "fas fa-question-circle" } } }, diff --git a/tests/minimal/main.nf.test.snap b/tests/minimal/main.nf.test.snap index 02c228f..b1f61c8 100644 --- a/tests/minimal/main.nf.test.snap +++ b/tests/minimal/main.nf.test.snap @@ -2,7 +2,7 @@ "profile - test": { "content": [ { - "successful tasks": 18, + "successful tasks": 20, "versions": { "AGAT_CONVERTSPGFF2GTF": { "agat": "v1.4.0" @@ -25,6 +25,12 @@ "CAT_PROTEIN_FASTAS": { "pigz": "2.3.4" }, + "EXTRACT_CDNA": { + "gffread": "0.12.7" + }, + "EXTRACT_CDS": { + "gffread": "0.12.7" + }, "EXTRACT_PROTEINS": { "gffread": "0.12.7" }, @@ -55,10 +61,12 @@ "tsebra": "1.1.2.5" }, "Workflow": { - "plant-food-research-open/genepal": "v0.5.0" + "plant-food-research-open/genepal": "v0.6.0" } }, "stable paths": [ + "a_thaliana.cdna.fasta:md5,12b9bef973e488640aec8c04ba3882fe", + "a_thaliana.cds.fasta:md5,b81060419355a590560f92aec8536281", "a_thaliana.gt.gff3:md5,8ab16549095f605ff8715ac4a3de58ed", "a_thaliana.pep.fasta:md5,4994c0393ca0245a1c57966d846d101e", "a_thaliana.gff3:md5,d23d16cd86499d48a30ffb981ed27891", @@ -67,6 +75,8 @@ "stable names": [ "annotations", "annotations/a_thaliana", + "annotations/a_thaliana/a_thaliana.cdna.fasta", + "annotations/a_thaliana/a_thaliana.cds.fasta", "annotations/a_thaliana/a_thaliana.gt.gff3", "annotations/a_thaliana/a_thaliana.pep.fasta", "etc", @@ -81,9 +91,9 @@ } ], "meta": { - "nf-test": "0.9.0", - "nextflow": "24.04.4" + "nf-test": "0.9.2", + "nextflow": "24.04.2" }, - "timestamp": "2024-11-19T11:35:02.477202" + "timestamp": "2024-12-05T07:51:43.818374" } -} +} \ No newline at end of file diff --git a/tests/stub/main.nf.test.snap b/tests/stub/main.nf.test.snap index 524ce21..3d3949b 100644 --- a/tests/stub/main.nf.test.snap +++ b/tests/stub/main.nf.test.snap @@ -2,7 +2,7 @@ "full - stub": { "content": [ { - "successful tasks": 154, + "successful tasks": 162, "versions": { "AGAT_CONVERTSPGFF2GTF": { "agat": "v1.4.0" @@ -55,6 +55,12 @@ "EGGNOGMAPPER": { "eggnog-mapper": "2.1.12" }, + "EXTRACT_CDNA": { + "gffread": "0.12.7" + }, + "EXTRACT_CDS": { + "gffread": "0.12.7" + }, "EXTRACT_PROTEINS": { "gffread": "0.12.7" }, @@ -143,25 +149,33 @@ "tsebra": "1.1.2.5" }, "Workflow": { - "plant-food-research-open/genepal": "v0.5.0" + "plant-food-research-open/genepal": "v0.6.0" } }, "stable paths": [ + "donghong.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "donghong.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", "donghong.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e", "donghong.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e", "donghong.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e", "donghong.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e", "donghong.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red5_v2p1.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red5_v2p1.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v2p1.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v2p1.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v2p1.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v2p1.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v2p1.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red5_v3.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red5_v3.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v3.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v3.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v3.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v3.gt.gff3:md5,d41d8cd98f00b204e9800998ecf8427e", "red5_v3.pep.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red7_v5.cdna.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", + "red7_v5.cds.fasta:md5,d41d8cd98f00b204e9800998ecf8427e", "red7_v5.emapper.annotations:md5,d41d8cd98f00b204e9800998ecf8427e", "red7_v5.emapper.hits:md5,d41d8cd98f00b204e9800998ecf8427e", "red7_v5.emapper.seed_orthologs:md5,d41d8cd98f00b204e9800998ecf8427e", @@ -188,9 +202,9 @@ } ], "meta": { - "nf-test": "0.9.0", - "nextflow": "24.04.4" + "nf-test": "0.9.2", + "nextflow": "24.04.2" }, - "timestamp": "2024-11-21T12:34:14.056074" + "timestamp": "2024-12-05T07:56:38.915238" } -} +} \ No newline at end of file