diff --git a/CHANGELOG.md b/CHANGELOG.md index 8693ee185d..593ac9df66 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -90,6 +90,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 - [#618](https://github.com/nf-core/sarek/pull/618) - Update test yml files - [#644](https://github.com/nf-core/sarek/pull/644) - Use `-Y` for `bwa-mem(2)` and remove `-M` - [#645](https://github.com/nf-core/sarek/pull/645) - Merge `tests/nextflow.config` in `conf/test.config` +- [#646](https://github.com/nf-core/sarek/pull/646) - Update `nextflow_schema.json` to reflect new parameters and functions, removes `--annotation_cache`, removes `--ascat_chromosomes` ### Fixed diff --git a/conf/modules.config b/conf/modules.config index 8a5aef2d0f..7c182551f9 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -944,7 +944,7 @@ process{ "purity": params.ascat_purity, "ploidy": params.ploidy, "minCounts": params.ascat_min_counts, - "chrom_names": meta.sex == 'XX' ? params.ascat_chromosomes : "c(1:22, 'X', 'Y')", + "chrom_names": meta.sex == 'XX' ? "c(1:22, 'X')" : "c(1:22, 'X', 'Y')", "min_base_qual": params.ascat_min_base_qual, "min_map_qual": params.ascat_min_map_qual ]} diff --git a/nextflow.config b/nextflow.config index d997e3dc72..c5e67d6780 100644 --- a/nextflow.config +++ b/nextflow.config @@ -51,7 +51,6 @@ params { // Variant Calling only_paired_variant_calling = false //if true, skips germline variant calling for normal-paired samples ploidy = 2 //null (in ascat, test this works) // Use default value, you can use 2,3,4 - ascat_chromosomes = "c(1:22, 'X')" // default value for ASCAT ascat_min_base_qual = 20 // default value for ASCAT ascat_min_counts = 10 // default value for ASCAT ascat_min_map_qual = 35 // default value for ASCAT @@ -67,8 +66,6 @@ params { pon_tbi = null // No default PON index for GATK Mutect2 ignore_soft_clipped_bases = false // no --dont-use-soft-clipped-bases for GATK Mutect2 wes = false // Set to true, if data is exome/targeted sequencing data. Used to use correct models in various variant callers - joint_germline = false // g.vcf & joint germline calling are not run by default if HaplotypeCaller is selected - // Annotation vep_out_format = 'vcf' @@ -84,7 +81,6 @@ params { spliceai_indel = null // No spliceai_indel file spliceai_indel_tbi = null // No spliceai_indel file index vep_spliceregion = null // spliceregion plugin disabled within VEP - annotation_cache = false // Annotation cache disabled snpeff_cache = null // No directory for snpEff cache vep_cache = null // No directory for VEP cache vep_include_fasta = false // Don't use fasta file for annotation with VEP diff --git a/nextflow_schema.json b/nextflow_schema.json index 0a23d33f62..adb0c27836 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -16,16 +16,15 @@ "type": "string", "default": "mapping", "fa_icon": "fas fa-play", - "description": "Starting step.", - "help_text": "Only one step.", + "description": "Starting step", + "help_text": "The pipeline starts from this step and then runs through the possible subsequent steps.", "enum": [ "mapping", "markduplicates", "prepare_recalibration", "recalibrate", "variant_calling", - "annotate", - "controlfreec" + "annotate" ] }, "input": { @@ -35,7 +34,7 @@ "pattern": "\\.csv$", "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information about the samples in the experiment.", - "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with a header row. See [usage docs](https://nf-co.re/sarek/usage#input).", + "help_text": "A design file with information about the samples in your experiment. Use this parameter to specify the location of the input files. It has to be a comma-separated file with a header row. See [usage docs](https://nf-co.re/sarek/usage#input).\n\nIf no input file is specified, sarek will attempt to locate one in the `{outdir}` directory.", "fa_icon": "fas fa-file-csv" }, "outdir": { @@ -50,71 +49,85 @@ "main_options": { "title": "Main options", "type": "object", - "description": "Option used for most of the pipeline.", + "description": "Most common options used for the pipeline", "default": "", "properties": { - "tools": { - "type": "string", - "fa_icon": "fas fa-toolbox", - "description": "Tools to use for variant calling and/or for annotation.", - "help_text": "Multiple separated with commas.\n\nGermline variant calling can currently only be performed with the following variant callers:\n- FreeBayes, HaplotypeCaller, Manta, mpileup, Strelka, TIDDIT\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- ASCAT, Control-FREEC, FreeBayes, Manta, MSIsensorpro, Mutect2, Strelka\n\n**NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\nTumor-only somatic variant calling can currently only be performed with the following variant callers:\n- Control-FREEC, Manta, mpileup, Mutect2, TIDDIT\n\nAnnotation is done using snpEff, VEP, or even both consecutively.\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted.\n\n> **NB** tools can be specified with no concern for case.", - "pattern": "^((ascat|cnvkit|controlfreec|deepvariant|dnascope|dnaseq|freebayes|haplotypecaller|manta|merge|mpileup|msisensorpro|mutect2|snpeff|strelka|tiddit|tnscope|vep)*,?)*$" + "split_fastq": { + "type": "integer", + "default": 0, + "fa_icon": "fas fa-clock", + "description": "Specify how many reads each split of a FastQ file contains. Set 0 to turn off splitting at all.", + "help_text": "Use the the tool FastP to split FASTQ file by number of reads. This parallelizes across fastq file shards speeding up mapping. " }, - "no_intervals": { + "wes": { "type": "boolean", - "fa_icon": "fas fa-ban", - "description": "Disable usage of intervals.", - "help_text": "Intervals are part of the genome chopped up, used to speed up preprocessing and variant calling. Cannot be combined with `--tools mutect2`" + "fa_icon": "fas fa-dna", + "description": "Enable when exome or panel data is provided.", + "help_text": "With this parameter flags in various tools are set for targeted sequencing data. It is recommended to enable for whole-exome and panel data analysis." + }, + "intervals": { + "type": "string", + "fa_icon": "fas fa-file-alt", + "help_text": "To speed up preprocessing and variant calling processes, the execution is parallelized across a reference chopped into smaller pieces.\n\nParts of preprocessing and variant calling are done by these intervals, the different resulting files are then merged.\nThis can parallelize processes, and push down wall clock time significantly.\n\nWe are aligning to the whole genome, and then run Base Quality Score Recalibration and Variant Calling on the supplied regions.\n\n**Whole Genome Sequencing:**\n\nThe (provided) intervals are chromosomes cut at their centromeres (so each chromosome arm processed separately) also additional unassigned contigs.\n\nWe are ignoring the `hs37d5` contig that contains concatenated decoy sequences.\n\nThe calling intervals can be defined using a .list or a BED file.\nA .list file contains one interval per line in the format `chromosome:start-end` (1-based coordinates).\nA BED file must be a tab-separated text file with one interval per line.\nThere must be at least three columns: chromosome, start, and end (0-based coordinates).\nAdditionally, the score column of the BED file can be used to provide an estimate of how many seconds it will take to call variants on that interval.\nThe fourth column remains unused.\n\n```\n|chr1|10000|207666|NA|47.3|\n```\nThis indicates that variant calling on the interval chr1:10001-207666 takes approximately 47.3 seconds.\n\nThe runtime estimate is used in two different ways.\nFirst, when there are multiple consecutive intervals in the file that take little time to compute, they are processed as a single job, thus reducing the number of processes that needs to be spawned.\nSecond, the jobs with largest processing time are started first, which reduces wall-clock time.\nIf no runtime is given, a time of 1000 nucleotides per second is assumed. See `-nucleotides_per_second` on how to customize this.\nActual figures vary from 2 nucleotides/second to 30000 nucleotides/second.\nIf you prefer, you can specify the full path to your reference genome when you run the pipeline:\n\n> **NB** If none provided, will be generated automatically from the FASTA reference\n> **NB** Use --no_intervals to disable automatic generation.\n\n**Targeted Sequencing:**\n\nThe recommended flow for targeted sequencing data is to use the workflow as it is, but also provide a `BED` file containing targets for all steps using the `--intervals` option. In addition, the parameter `--wes` should be set.\nIt is advised to pad the variant calling regions (exons or target) to some extent before submitting to the workflow.\n\nThe procedure is similar to whole genome sequencing, except that only BED file are accepted. See above for formatting description.\nAdding every exon as an interval in case of `WES` can generate >200K processes or jobs, much more forks, and similar number of directories in the Nextflow work directory. These are appropriately grouped together to reduce number of processes run in parallel (see above and `--nucleotides_per_second` for details). \nFurthermore, primers and/or baits are not 100% specific, (certainly not for MHC and KIR, etc.), quite likely there going to be reads mapping to multiple locations.\nIf you are certain that the target is unique for your genome (all the reads will certainly map to only one location), and aligning to the whole genome is an overkill, it is actually better to change the reference itself.", + "description": "Path to target bed file in case of whole exome or targeted sequencing or intervals file." }, "nucleotides_per_second": { "type": "number", "fa_icon": "fas fa-clock", "description": "Estimate interval size.", - "help_text": "Intervals are part of the genome chopped up, used to speed up preprocessing and variant calling.", + "help_text": "Intervals are parts of the chopped up genome used to speed up preprocessing and variant calling. See `--intervals` for more info. \n\nChanging this parameter, changes the number of intervals that are grouped and processed together. Bed files from target sequencing can contain thousands or small intervals. Spinning up a new process for each can be quite resource intensive. Instead it can be desired to process small intervals together on larger nodes. \nIn order to make use of this parameter, no runtime estimate can be present in the bed file (column 5). ", "default": 1000 }, + "no_intervals": { + "type": "boolean", + "fa_icon": "fas fa-ban", + "description": "Disable usage of intervals.", + "help_text": "Intervals are parts of the chopped up genome used to speed up preprocessing and variant calling. See `--intervals` for more info. \n\nIf `--no_intervals` is set no intervals will be taken into account for speed up or data processing." + }, + "tools": { + "type": "string", + "fa_icon": "fas fa-toolbox", + "description": "Tools to use for variant calling and/or for annotation.", + "help_text": "Multiple tools separated with commas.\n\n**Variant Calling:**\n\nGermline variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: DeepVariant, FreeBayes, HaplotypeCaller, mpileup, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit\n\nTumor-only somatic variant calling can currently be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, mpileup, Mutect2, Strelka\n- Structural Variants: Manta, TIDDIT\n- Copy-number: CNVKit, ControlFREEC\n\nSomatic variant calling can currently only be performed with the following variant callers:\n- SNPs/Indels: FreeBayes, Mutect2, Strelka2\n- Structural variants: Manta, TIDDIT\n- Copy-Number: ASCAT, CNVKit, Control-FREEC\n- Microsatellite Instability: MSIsensorpro\n\n> **NB** Mutect2 for somatic variant calling cannot be combined with `--no_intervals`\n\n**Annotation:**\n \n- snpEff, VEP, merge (both consecutively).\n\n> **NB** As Sarek will use bgzip and tabix to compress and index VCF files annotated, it expects VCF files to be sorted when starting from `--step annotate`.", + "pattern": "^((ascat|cnvkit|controlfreec|deepvariant|freebayes|haplotypecaller|manta|merge|mpileup|msisensorpro|mutect2|snpeff|strelka|tiddit|vep)*,?)*$" + }, "skip_tools": { "type": "string", "fa_icon": "fas fa-forward", "description": "Disable specified tools.", - "help_text": "Multiple tools can be specified, separated by commas.\n\n> **NB** `--skip_tools baserecalibrator_report` is actually just not saving the reports.\n> **NB** `--skip_tools markduplicates_report` does not skip `MarkDuplicates` but prevent the collection of duplicate metrics that slows down performance.\n> **NB** tools can be specified with no concern for case.", + "help_text": "Multiple tools can be specified, separated by commas.\n\n> **NB** `--skip_tools baserecalibrator_report` is actually just not saving the reports.\n> **NB** `--skip_tools markduplicates_report` does not skip `MarkDuplicates` but prevent the collection of duplicate metrics that slows down performance.", "pattern": "^((baserecalibrator|baserecalibrator_report|bcftools|documentation|fastqc|markduplicates|markduplicates_report|mosdepth|multiqc|samtools|vcftools|versions)*(,)*)*$" - }, - "wes": { - "type": "boolean", - "fa_icon": "fas fa-dna", - "description": "Enable when exome or panel data is provided." } }, "fa_icon": "fas fa-user-cog" }, - "trim_split_fastq": { - "title": "Trim/split FASTQ", + "fastq_preprocessing": { + "title": "FASTQ Preprocessing", "type": "object", - "description": "", + "description": "Trim fastq file or handle UMIs", "default": "", "fa_icon": "fas fa-cut", "properties": { "trim_fastq": { "type": "boolean", "fa_icon": "fas fa-cut", - "description": "Run Trim Galore.", - "help_text": "Use this to perform adapter trimming with Trim Galore.\ncf [Trim Galore User Guide](https://github.com/FelixKrueger/TrimGalore/blob/master/Docs/Trim_Galore_User_Guide.md).", + "description": "Run FastP for read trimming", + "help_text": "Use this to perform adapter trimming. Adapter are detected automatically by using the FastP flag `--detect_adapter_for_pe`. For more info see [FastP](https://github.com/OpenGene/fastp) ", "hidden": true }, "clip_r1": { "type": "integer", "default": 0, "fa_icon": "fas fa-cut", - "description": "Remove bp from the 5' end of read 1.", - "help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end.", + "description": "Remove bp from the 5' end of read 1", + "help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. Corresponds to the FastP flag `--trim_front1`.", "hidden": true }, "clip_r2": { "type": "integer", "default": 0, - "description": "Remove bp from the 5' end of read 2.", - "help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end.", + "description": "Remove bp from the 5' end of read 2", + "help_text": "This may be useful if the qualities were very poor, or if there is some sort of unwanted bias at the 5' end. Corresponds to the FastP flag `--trim_front2`.", "fa_icon": "fas fa-cut", "hidden": true }, @@ -122,24 +135,24 @@ "type": "integer", "default": 0, "fa_icon": "fas fa-cut", - "description": "Remove bp from the 3' end of read 1 AFTER adapter/quality trimming has been performed.", - "help_text": "This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality.", + "description": "Remove bp from the 3' end of read 1", + "help_text": "This may remove some unwanted bias from the 3'. Corresponds to the FastP flag `--three_prime_clip_r1`.", "hidden": true }, "three_prime_clip_r2": { "type": "integer", "default": 0, "fa_icon": "fas fa-cut", - "description": "Remove bp from the 3' end of read 2 AFTER adapter/quality trimming has been performed.", - "help_text": "This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality.", + "description": "Remove bp from the 3' end of read 2", + "help_text": "This may remove some unwanted bias from the 3' end. Corresponds to the FastP flag `--three_prime_clip_r2`.", "hidden": true }, "trim_nextseq": { "type": "integer", "default": 0, "fa_icon": "fas fa-cut", - "description": "Apply the --nextseq=X option, to trim based on quality after removing poly-G tails.", - "help_text": "This may remove some unwanted bias from the 3' end that is not directly related to adapter sequence or basecall quality.", + "description": "Removing poly-G tails.", + "help_text": "DetectS polyG in read tails and trim them. Corresponds to the FastP flag `--trim_poly_g`.", "hidden": true }, "save_trimmed": { @@ -148,20 +161,6 @@ "description": "Save trimmed FastQ file intermediates.", "hidden": true }, - "split_fastq": { - "type": "integer", - "default": 0, - "fa_icon": "fas fa-cut", - "description": "Specify how many reads each split of a FastQ file contains. Set 0 to turn of splitting at all.", - "help_text": "Use the the tools seqkit/split2 to split FASTQ file by number of reads.", - "hidden": true - }, - "save_split_fastqs": { - "type": "boolean", - "fa_icon": "fas fa-vial", - "description": "If set, publishes split FASTQ files. Intended for testing purposes.", - "hidden": true - }, "umi_read_structure": { "type": "string", "fa_icon": "fas fa-tape", @@ -171,7 +170,16 @@ "group_by_umi_strategy": { "type": "string", "default": "Adjacency", - "description": "Default strategy with UMI.", + "description": "Strategy to group reads that appear to have come from the same original molecule.", + "hidden": true, + "enum": ["Identity", "Edit", "Adjacency", "Paired"], + "help_text": "For more information see [FgBio](http://fulcrumgenomics.github.io/fgbio/tools/latest/GroupReadsByUmi.html).", + "fa_icon": "fab fa-blackberry" + }, + "save_split_fastqs": { + "type": "boolean", + "fa_icon": "fas fa-vial", + "description": "If set, publishes split FASTQ files. Intended for testing purposes.", "hidden": true } } @@ -179,7 +187,7 @@ "preprocessing": { "title": "Preprocessing", "type": "object", - "description": "", + "description": "Configure preprocessing tools", "default": "", "fa_icon": "fas fa-toolbox", "properties": { @@ -189,13 +197,14 @@ "fa_icon": "fas fa-puzzle-piece", "enum": ["bwa-mem", "bwa-mem2", "dragmap"], "description": "Specify aligner to be used to map reads to reference genome.", - "help_text": "> **WARNING** Current indices for `bwa` in AWS iGenomes are not compatible with `bwa-mem2` and `dragmap`.\n> `Sarek` will build them automatically if not provided.\n\n> **WARNING** BWA-mem2 is in active development\n> Sarek might not be able to require the right amount of resources for it at the moment\n> We recommend to use pre-built indexes.", + "help_text": "Parameter chooses the mapper used. We recommend using pre-build indices. If they are not part of the available `igenome.config` they can be provided with `--bwa`, `--bwamem2`, or `--dragmap`. \nIf none are provided, `Sarek` will build them automatically.", "hidden": true }, "save_bam_mapped": { "type": "boolean", "fa_icon": "fas fa-download", - "description": "Save Mapped BAMs." + "description": "Save mapped BAMs.", + "help_text": "If the parameter `--split-fastq` is used, the sharded bam files are merged before saving them." }, "save_output_as_bam": { "type": "boolean", @@ -205,8 +214,8 @@ "use_gatk_spark": { "type": "string", "fa_icon": "fas fa-forward", - "description": "Tools for which to enable usage of GATK Spark implementation.", - "help_text": "Multiple separated with commas.\n\n GATK4 BQSR tools are currently only available as Beta release. Use with caution!", + "description": "Enable usage of GATK Spark implementation for duplicate marking and/or base quality score recalibration", + "help_text": "Multiple separated with commas.\n\n> The GATK4 Base Quality Score recalibration tools `Baserecalibrator` and `ApplyBQSR` are currently available as Beta release. Use with caution!", "pattern": "^((baserecalibrator|markduplicates)*,?)*$" } } @@ -214,91 +223,121 @@ "variant_calling": { "title": "Variant Calling", "type": "object", - "description": "", + "description": "Configure variant calling tools", "default": "", "fa_icon": "fas fa-toolbox", "properties": { "only_paired_variant_calling": { "type": "boolean", - "fa_icon": "fas fa-angle-double-right", - "description": "If true, skips germline variant calling for matched normal to tumor sample. Normal samples without matched tumor will still be processed through germline variant calling tools." + "fa_icon": "fas fa-forward", + "description": "If true, skips germline variant calling for matched normal to tumor sample. Normal samples without matched tumor will still be processed through germline variant calling tools.", + "help_text": "This can speed up computation for somatic variant calling with matched normal samples. If false, all normal samples are processed as well through the germline variantcalling tools. If true, only somatic variant calling is done." }, "ploidy": { "type": "number", "fa_icon": "fas fa-bacon", "default": 2, - "description": "genome ploidy; In case of doubt, you can set different values and Control-FREEC will select the one that explains most observed CNAs.", - "hidden": true + "description": "Genome ploidy used by ASCAT and ControlFREEC", + "hidden": true, + "help_text": "ControLFREEC: In case of doubt, you can set different values and Control-FREEC will select the one that explains most observed CNAs\n Example: ploidy=2 , ploidy=2,3,4\n\nASCAT: optional argument to override ASCAT optimization and supply psi parameter\n(expert parameter, don\u2019t adapt unless you know what you\u2019re doing). See [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)" + }, + "ascat_min_base_qual": { + "type": "number", + "default": 20, + "fa_icon": "fas fa-greater-than", + "description": "Overwrite Ascat min base quality required for a read to be counted.", + "hidden": true, + "help_text": "For more details see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)" + }, + "ascat_min_counts": { + "type": "number", + "default": 10, + "fa_icon": "fas fa-align-center", + "description": "Overwrite Ascat minimum depth required in the normal for a SNP to be considered.", + "hidden": true, + "help_text": "For more details, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)." + }, + "ascat_min_map_qual": { + "type": "number", + "default": 35, + "fa_icon": "fas fa-balance-scale-left", + "description": "Overwrite Ascat min mapping quality required for a read to be counted.", + "hidden": true, + "help_text": "For more details, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf)." }, "ascat_purity": { "type": "number", - "fa_icon": "fas fa-wrench", + "fa_icon": "fas fa-broom", "description": "Overwrite ASCAT purity.", - "help_text": "Requires that `--ascat_ploidy` is set." + "help_text": "Overwrites ASCAT's `rho_manual` parameter. Expert use only, see [here](https://raw.githubusercontent.com/VanLoo-lab/ascat/master/man/ASCAT-manual.pdf) for details.\nRequires that `--ascat_ploidy` is set.", + "hidden": true }, "cf_coeff": { "type": "number", "default": 0.05, "fa_icon": "fas fa-wrench", "description": "Overwrite Control-FREEC coefficientOfVariation", - "hidden": true + "hidden": true, + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)." }, "cf_contamination_adjustment": { "type": "boolean", - "fa_icon": "fas fa-wrench", + "fa_icon": "fas fa-broom", "description": "Overwrite Control-FREEC contaminationAdjustement", - "hidden": true + "hidden": true, + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)." }, "cf_contamination": { "type": "number", "default": 0, - "fa_icon": "fas fa-wrench", + "fa_icon": "fas fa-broom", "description": "Design known contamination value for Control-FREEC", - "hidden": true + "hidden": true, + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)." }, "cf_minqual": { "type": "number", "default": 0, "fa_icon": "fas fa-greater-than", "hidden": true, - "description": "Minimal sequencing quality for a position to be considered in BAF analysis." + "description": "Minimal sequencing quality for a position to be considered in BAF analysis.", + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)." }, "cf_mincov": { "type": "number", "default": 0, "fa_icon": "fas fa-align-center", "hidden": true, - "description": "Minimal read coverage for a position to be considered in BAF analysis." + "description": "Minimal read coverage for a position to be considered in BAF analysis.", + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html)." }, "cf_window": { "type": "number", - "fa_icon": "fas fa-wrench", + "fa_icon": "fas fa-window-maximize", "description": "Overwrite Control-FREEC window size.", - "help_text": "It is recommended to use a window size of 0 for exome data.", + "help_text": "Details, see [ControlFREEC manual](http://boevalab.inf.ethz.ch/FREEC/tutorial.html).", "hidden": true }, - "joint_germline": { - "type": "boolean", - "fa_icon": "fas fa-align-justify", - "description": "Enables GATK4 joint germline variant calling and g.vcf generation, if also Haplotypecaller is selected." - }, "pon": { "type": "string", "fa_icon": "fas fa-file", "description": "Panel-of-normals VCF (bgzipped) for GATK Mutect2", - "help_text": "Without PON, there will be no calls with PASS in the INFO field, only an unfiltered VCF is written.\nIt is recommended to make your own PON, as it depends on sequencer and library preparation.\nFor tests in iGenomes there is a dummy PON file in the Annotation/GermlineResource directory, but it should not be used as a real PON file.\n\nSee [PON documentation](https://gatk.broadinstitute.org/hc/en-us/articles/360042479112-CreateSomaticPanelOfNormals-BETA)\n> **NB** PON file should be bgzipped." + "help_text": "Without PON, there will be no calls with PASS in the INFO field, only an unfiltered VCF is written.\nIt is highly recommended to make your own PON, as it depends on sequencer and library preparation.\n\nThe pipeline is shipped with a panel-of-normals for `--genome GATK.GRCh38` provided by [GATK](https://gatk.broadinstitute.org/hc/en-us/articles/360035890631-Panel-of-Normals-PON-). \n\nSee [PON documentation](https://gatk.broadinstitute.org/hc/en-us/articles/360042479112-CreateSomaticPanelOfNormals-BETA)\n> **NB** PON file should be bgzipped.", + "hidden": true }, "pon_tbi": { "type": "string", "fa_icon": "fas fa-file", "description": "Index of PON panel-of-normals VCF.", - "help_text": "If none provided, will be generated automatically from the PON bgzipped VCF file." + "help_text": "If none provided, will be generated automatically from the PON bgzipped VCF file.", + "hidden": true }, "ignore_soft_clipped_bases": { "type": "boolean", "fa_icon": "fas fa-ban", "description": "Do not analyze soft clipped bases in the reads for GATK Mutect2.", - "help_text": "use the `--dont-use-soft-clipped-bases` params with GATK." + "help_text": "use the `--dont-use-soft-clipped-bases` params with GATK Mutect2.", + "hidden": true } } }, @@ -311,81 +350,85 @@ "properties": { "vep_include_fasta": { "type": "boolean", - "fa_icon": "fas fa-database", - "description": "Allow usage of fasta file for annotation with VEP.\ncf https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#fasta", - "hidden": true + "fa_icon": "fas fa-file", + "description": "Allow usage of fasta file for annotation with VEP", + "hidden": true, + "help_text": "By pointing VEP to a FASTA file, it is possible to retrieve reference sequence locally. This enables VEP to retrieve HGVS notations (--hgvs), check the reference sequence given in input data, and construct transcript models from a GFF or GTF file without accessing a database.\n\nFor details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_cache.html#fasta)." }, "vep_dbnsfp": { "type": "boolean", "fa_icon": "fas fa-database", "description": "Enable the use of the VEP dbNSFP plugin.", - "hidden": true + "hidden": true, + "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp)." }, "dbnsfp": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to dbNSFP processed file.", "help_text": "To be used with `--vep_dbnsfp`.\ndbNSFP files and more information are available at https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#dbnsfp and https://sites.google.com/site/jpopgen/dbNSFP/", "hidden": true }, "dbnsfp_tbi": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to dbNSFP tabix indexed file.", "help_text": "To be used with `--vep_dbnsfp`.", "hidden": true }, "dbnsfp_consequence": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-arrow-alt-circle-right", "description": "Consequence to annotate with", "help_text": "To be used with `--vep_dbnsfp`.\nThis params is used to filter/limit outputs to a specific effect of the variant.\nThe set of consequence terms is defined by the Sequence Ontology and an overview of those used in VEP can be found here: https://www.ensembl.org/info/genome/variation/prediction/predicted_data.html\nIf one wants to filter using several consequences, then separate those by using '&' (i.e. 'consequence=3_prime_UTR_variant&intron_variant'.", "hidden": true }, "dbnsfp_fields": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-border-all", "description": "Fields to annotate with", "default": "rs_dbSNP,HGVSc_VEP,HGVSp_VEP,1000Gp3_EAS_AF,1000Gp3_AMR_AF,LRT_score,GERP++_RS,gnomAD_exomes_AF", - "help_text": "To be used with `--vep_dbnsfp`.\nThis params can be used to retrieve individual values from the dbNSFP file. The values correspond to the name of the columns in the dbNSFP file and are separated by comma.\nThe column names might differ between the different dbNSFP versions. Please check the Readme.txt file, which is provided with the dbNSFP file, to obtain the correct column names. The Readme file contains also a short description of the provided values and the version of the tools used to generate them.\nDefault value are explained below;/nrs_dbSNP - rs number from dbSNP/nHGVSc_VEP - HGVS coding variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_transcriptid/nHGVSp_VEP - HGVS protein variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_proteinid/n1000Gp3_EAS_AF - Alternative allele frequency in the 1000Gp3 East Asian descendent samples/n1000Gp3_AMR_AF - Alternative allele counts in the 1000Gp3 American descendent samples/nLRT_score - Original LRT two-sided p-value (LRTori), ranges from 0 to 1/nGERP++_RS - Conservation score. The larger the score, the more conserved the site, ranges from -12.3 to 6.17/ngnomAD_exomes_AF - Alternative allele frequency in the whole gnomAD exome samples/n.", + "help_text": "To be used with `--vep_dbnsfp`.\nThis params can be used to retrieve individual values from the dbNSFP file. The values correspond to the name of the columns in the dbNSFP file and are separated by comma.\nThe column names might differ between the different dbNSFP versions. Please check the Readme.txt file, which is provided with the dbNSFP file, to obtain the correct column names. The Readme file contains also a short description of the provided values and the version of the tools used to generate them.\n\nDefault value are explained below:\n\nrs_dbSNP - rs number from dbSNP\nHGVSc_VEP - HGVS coding variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_transcriptid\nHGVSp_VEP - HGVS protein variant presentation from VEP. Multiple entries separated by ';', corresponds to Ensembl_proteinid\n1000Gp3_EAS_AF - Alternative allele frequency in the 1000Gp3 East Asian descendent samples\n1000Gp3_AMR_AF - Alternative allele counts in the 1000Gp3 American descendent samples\nLRT_score - Original LRT two-sided p-value (LRTori), ranges from 0 to 1\nGERP++_RS - Conservation score. The larger the score, the more conserved the site, ranges from -12.3 to 6.17\ngnomAD_exomes_AF - Alternative allele frequency in the whole gnomAD exome samples.", "hidden": true }, "vep_loftee": { "type": "boolean", "fa_icon": "fas fa-database", "description": "Enable the use of the VEP LOFTEE plugin.", - "hidden": true + "hidden": true, + "help_text": "For details, see [here](https://github.com/konradjk/loftee)." }, "vep_spliceai": { "type": "boolean", "fa_icon": "fas fa-database", "description": "Enable the use of the VEP SpliceAI plugin.", - "hidden": true + "hidden": true, + "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceai)." }, "spliceai_snv": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to spliceai raw scores snv file.", "help_text": "To be used with `--vep_spliceai`.", "hidden": true }, "spliceai_snv_tbi": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to spliceai raw scores snv tabix indexed file.", "help_text": "To be used with `--vep_spliceai`.", "hidden": true }, "spliceai_indel": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to spliceai raw scores indel file.", "help_text": "To be used with `--vep_spliceai`.", "hidden": true }, "spliceai_indel_tbi": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to spliceai raw scores indel tabix indexed file.", "help_text": "To be used with `--vep_spliceai`.", "hidden": true @@ -394,25 +437,19 @@ "type": "boolean", "fa_icon": "fas fa-database", "description": "Enable the use of the VEP SpliceRegion plugin.", - "hidden": true - }, - "annotation_cache": { - "type": "boolean", - "fa_icon": "fas fa-database", - "description": "Enable the use of cache for annotation.", - "help_text": "And disable usage of Sarek snpeff and vep specific containers for annotation\n\nTo be used with `--snpeff_cache` and/or `--vep_cache`.", - "hidden": true + "hidden": true, + "help_text": "For details, see [here](https://www.ensembl.org/info/docs/tools/vep/script/vep_plugins.html#spliceregion) and [here](https://www.ensembl.info/2018/10/26/cool-stuff-the-vep-can-do-splice-site-variant-annotation/)." }, "snpeff_cache": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to snpEff cache.", "help_text": "To be used with `--annotation_cache`.", "hidden": true }, "vep_cache": { "type": "string", - "fa_icon": "fas fa-database", + "fa_icon": "fas fa-file", "description": "Path to VEP cache.", "help_text": "To be used with `--annotation_cache`.", "hidden": true @@ -423,7 +460,8 @@ "description": "VEP output-file format.", "enum": ["json", "tab", "vcf"], "help_text": "Sets the format of the output-file from VEP. Available formats: json, tab and vcf.", - "fa_icon": "fas fa-table" + "fa_icon": "fas fa-table", + "hidden": true } } }, @@ -440,99 +478,89 @@ "fa_icon": "fas fa-book", "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`.\n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details." }, - "ascat_alleles": { - "type": "string", - "fa_icon": "fas fa-file", - "description": "Path to ASCAT allele zip file. If you use AWS iGenomes, this has already been set for you appropriately." - }, - "ascat_chromosomes": { - "type": "string", - "description": "Chromosomes to run ASCAT on.", - "fa_icon": "fa-solid fa-text", - "default": "c(1:22, 'X')", - "help_text": "Specify specific chromosomes to run ASCAT on, i.e 'c('21', '22')'." - }, "ascat_genome": { "type": "string", "fa_icon": "fa-solid fa-text", "description": "ASCAT genome.", - "help_text": "Must be set to run ASCAT, either hg19 or hg38. If you use AWS iGenomes, this has already been set for you appropriately." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nMust be set to run ASCAT, either hg19 or hg38. If you use AWS iGenomes, this has already been set for you appropriately.", + "hidden": true + }, + "ascat_alleles": { + "type": "string", + "fa_icon": "fas fa-file", + "description": "Path to ASCAT allele zip file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "ascat_loci": { "type": "string", "fa_icon": "fas fa-file", - "description": "Path to ASCAT loci zip file. If you use AWS iGenomes, this has already been set for you appropriately." + "description": "Path to ASCAT loci zip file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "ascat_loci_gc": { "type": "string", "fa_icon": "fas fa-file", - "description": "Path to ASCAT GC content correction file. If you use AWS iGenomes, this has already been set for you appropriately." + "description": "Path to ASCAT GC content correction file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "ascat_loci_rt": { "type": "string", "fa_icon": "fas fa-file", - "description": "Path to ASCAT RT (replictiming) correction file. If you use AWS iGenomes, this has already been set for you appropriately." - }, - "ascat_min_base_qual": { - "type": "number", - "default": 20, - "fa_icon": "fas fa-wrench", - "description": "Overwrite Ascat min base quality required for a read to be counted.", - "hidden": true - }, - "ascat_min_counts": { - "type": "number", - "default": 10, - "fa_icon": "fas fa-wrench", - "description": "Overwrite Ascat minimum depth required in the normal for a SNP to be considered.", - "hidden": true - }, - "ascat_min_map_qual": { - "type": "number", - "default": 35, - "fa_icon": "fas fa-wrench", - "description": "Overwrite Ascat min mapping quality required for a read to be counted.", - "hidden": true + "description": "Path to ASCAT RT (replictiming) correction file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "bwa": { "type": "string", "fa_icon": "fas fa-copy", "description": "Path to BWA mem indices.", - "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nIf you wish to recompute indices available on igenomes, set `--bwa false`.\n\n> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "bwamem2": { "type": "string", "fa_icon": "fas fa-copy", "description": "Path to bwa-mem2 mem indices.", - "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference, if `--aligner bwa-mem2` is specified. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nIf you wish to recompute indices available on igenomes, set `--bwamem2 false`.\n\n> **NB** If none provided, will be generated automatically from the FASTA reference, if `--aligner bwa-mem2` is specified. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "chr_dir": { "type": "string", "fa_icon": "fas fa-folder-open", - "description": "Path to chromosomes folder." + "description": "Path to chromosomes folder used with ControLFREEC.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "dbsnp": { "type": "string", "fa_icon": "fas fa-file", - "description": "Path to dbsnp file." + "description": "Path to dbsnp file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "dbsnp_tbi": { "type": "string", "fa_icon": "fas fa-file", "description": "Path to dbsnp index.", - "help_text": "> **NB** If none provided, will be generated automatically from the dbsnp file. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n> **NB** If none provided, will be generated automatically from the dbsnp file. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "dict": { "type": "string", "fa_icon": "fas fa-file", "description": "Path to FASTA dictionary file.", - "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "dragmap": { "type": "string", "fa_icon": "fas fa-copy", "description": "Path to dragmap indices.", - "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference, if `--aligner dragmap` is specified. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nIf you wish to recompute indices available on igenomes, set `--dragmap false`.\n\n> **NB** If none provided, will be generated automatically from the FASTA reference, if `--aligner dragmap` is specified. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "fasta": { "type": "string", @@ -540,95 +568,104 @@ "mimetype": "text/plain", "pattern": "\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", - "help_text": "This parameter is *mandatory* if `--genome` is not specified.", + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nThis parameter is *mandatory* if `--genome` is not specified.", "fa_icon": "far fa-file-code" }, "fasta_fai": { "type": "string", "fa_icon": "fas fa-file", - "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.", + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.", "description": "Path to FASTA reference index." }, "germline_resource": { "type": "string", "fa_icon": "fas fa-file", "description": "Path to GATK Mutect2 Germline Resource File.", - "help_text": "The germline resource VCF file (bgzipped and tabixed) needed by GATK4 Mutect2 is a collection of calls that are likely present in the sample, with allele frequencies.\nThe AF info field must be present.\nYou can find a smaller, stripped gnomAD VCF file (most of the annotation is removed and only calls signed by PASS are stored) in the AWS iGenomes Annotation/GermlineResource folder." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nThe germline resource VCF file (bgzipped and tabixed) needed by GATK4 Mutect2 is a collection of calls that are likely present in the sample, with allele frequencies.\nThe AF info field must be present.\nYou can find a smaller, stripped gnomAD VCF file (most of the annotation is removed and only calls signed by PASS are stored) in the AWS iGenomes Annotation/GermlineResource folder.", + "hidden": true }, "germline_resource_tbi": { "type": "string", "fa_icon": "fas fa-file", "description": "Path to GATK Mutect2 Germline Resource Index.", - "help_text": "> **NB** If none provided, will be generated automatically from the Germline Resource file, if provided. Combine with `--save_reference` to save for future runs." - }, - "intervals": { - "type": "string", - "fa_icon": "fas fa-file-alt", - "help_text": "To speed up preprocessing and variant calling processes, the execution is parallelized across a reference chopped into smaller pieces.\n\nParts of preprocessing and variant calling are done by these intervals, and the different resulting files are then merged.\nThis can parallelize processes, and push down wall clock time significantly.\n\nThis parameter does _not_ imply that the workflow is running alignment or variant calling only for the supplied regions. Instead, we are aligning to the whole genome, and selecting variants only at the very end by intersecting with the provided file.\n\n**Whole Genome Sequencing:**\n\nThe (provided) intervals are chromosomes cut at their centromeres (so each chromosome arm processed separately) also additional unassigned contigs.\n\nWe are ignoring the `hs37d5` contig that contains concatenated decoy sequences.\n\nThe calling intervals can be defined using a .list or a BED file.\nA .list file contains one interval per line in the format `chromosome:start-end` (1-based coordinates).\nA BED file must be a tab-separated text file with one interval per line.\nThere must be at least three columns: chromosome, start, and end (0-based coordinates).\nAdditionally, the score column of the BED file can be used to provide an estimate of how many seconds it will take to call variants on that interval.\nThe fourth column remains unused.\n\n```\n|chr1|10000|207666|NA|47.3|\n```\nThis indicates that variant calling on the interval chr1:10001-207666 takes approximately 47.3 seconds.\n\nThe runtime estimate is used in two different ways.\nFirst, when there are multiple consecutive intervals in the file that take little time to compute, they are processed as a single job, thus reducing the number of processes that needs to be spawned.\nSecond, the jobs with largest processing time are started first, which reduces wall-clock time.\nIf no runtime is given, a time of 1000 nucleotides per second is assumed.\nActual figures vary from 2 nucleotides/second to 30000 nucleotides/second.\nIf you prefer, you can specify the full path to your reference genome when you run the pipeline:\n\n> **NB** If none provided, will be generated automatically from the FASTA reference\n> **NB** Use --no_intervals to disable automatic generation.\n\n\n**Targeted Sequencing:**\n\nThe recommended flow for targeted sequencing data is to use the workflow as it is, but also provide a `BED` file containing targets for all steps using the `--intervals` option. In addition, the parameter `--wes` should be set.\nIt is advised to pad the variant calling regions (exons or target) to some extent before submitting to the workflow.\n\nThe procedure is similar to whole genome sequencing, except that only BED file are accepted. See above for formatting description.\nAdding every exon as an interval in case of `WES` can generate >200K processes or jobs, much more forks, and similar number of directories in the Nextflow work directory. These are appropriately grouped together to reduce number of processes run in parallel (see above and `--nucleotides_per_second` for details. \nFurthermore, primers and/or baits are not 100% specific, (certainly not for MHC and KIR, etc.), quite likely there going to be reads mapping to multiple locations.\nIf you are certain that the target is unique for your genome (all the reads will certainly map to only one location), and aligning to the whole genome is an overkill, it is actually better to change the reference itself.", - "description": "Path to target bed file in case of whole exome or targeted sequencing or intervals file." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n> **NB** If none provided, will be generated automatically from the Germline Resource file, if provided. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "known_indels": { "type": "string", "fa_icon": "fas fa-copy", - "description": "Path to known indels file." + "description": "Path to known indels file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "known_indels_tbi": { "type": "string", "fa_icon": "fas fa-copy", "description": "Path to known indels file index.", - "help_text": "> **NB** If none provided, will be generated automatically from the known index file, if provided. Combine with `--save_reference` to save for future runs." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n> **NB** If none provided, will be generated automatically from the known index file, if provided. Combine with `--save_reference` to save for future runs.", + "hidden": true }, "mappability": { "type": "string", "fa_icon": "fas fa-file", - "description": "Path to Control-FREEC mappability file." + "description": "Path to Control-FREEC mappability file.", + "hidden": true, + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "snpeff_db": { "type": "string", "fa_icon": "fas fa-database", "description": "snpEff DB version.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the database to be use to annotate with.\nAlternatively databases' names can be listed with the `snpEff databases`." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the database to be use to annotate with.\nAlternatively databases' names can be listed with the `snpEff databases`.", + "hidden": true }, "snpeff_genome": { "type": "string", "fa_icon": "fas fa-microscope", "description": "snpEff genome.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when using the container with pre-downloaded cache." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when using the container with pre-downloaded cache.", + "hidden": true }, "snpeff_version": { "type": "string", "fa_icon": "fas fa-tag", "description": "snpEff version.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the snpeff version when using the container with pre-downloaded cache." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the snpeff version when using the container with pre-downloaded cache.", + "hidden": true }, "vep_genome": { "type": "string", "fa_icon": "fas fa-microscope", "description": "VEP genome.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when using the container with pre-downloaded cache." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the genome when using the container with pre-downloaded cache.", + "hidden": true }, "vep_species": { "type": "string", "fa_icon": "fas fa-microscope", "description": "VEP species.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nAlternatively species listed in Ensembl Genomes caches can be used." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nAlternatively species listed in Ensembl Genomes caches can be used.", + "hidden": true }, "vep_cache_version": { "type": "number", "fa_icon": "fas fa-tag", "description": "VEP cache version.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nAlternatively cache version can be use to specify the correct Ensembl Genomes version number as these differ from the concurrent Ensembl/VEP version numbers" + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nAlternatively cache version can be use to specify the correct Ensembl Genomes version number as these differ from the concurrent Ensembl/VEP version numbers", + "hidden": true }, "vep_version": { "type": "string", "fa_icon": "fas fa-tag", "description": "VEP version.", - "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the VEP version when using the container with pre-downloaded cache." + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately.\nThis is used to specify the VEP version when using the container with pre-downloaded cache.", + "hidden": true }, "save_reference": { "type": "boolean", "fa_icon": "fas fa-download", - "description": "Save built references." + "description": "Save built references.", + "help_text": "Set this parameter, if you wish to save all computed reference files. This is useful to avoid re-computation on future runs." }, "igenomes_base": { "type": "string", @@ -849,7 +886,7 @@ "$ref": "#/definitions/main_options" }, { - "$ref": "#/definitions/trim_split_fastq" + "$ref": "#/definitions/fastq_preprocessing" }, { "$ref": "#/definitions/preprocessing"