diff --git a/nextflow_schema.json b/nextflow_schema.json index fcd324a3a2..da44d82521 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -361,6 +361,18 @@ "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 Mutect2." }, + "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 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." + }, + "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." + }, "sentieon_haplotyper_emit_mode": { "type": "string", "default": "variant", @@ -567,7 +579,7 @@ "title": "Reference genome options", "type": "object", "fa_icon": "fas fa-dna", - "description": "Reference genome related files and options required for the workflow.", + "description": "Reference genome related files and options required for the workflow. If you use AWS iGenomes, this has already been set for you appropriately.", "properties": { "genome": { "type": "string", @@ -578,9 +590,8 @@ }, "ascat_genome": { "type": "string", - "fa_icon": "fa-solid fa-text", "description": "ASCAT genome.", - "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.", + "help_text": "Must be set to run ASCAT, either hg19 or hg38.\n\nIf you use AWS iGenomes, this has already been set for you appropriately.", "enum": ["hg19", "hg38"] }, "ascat_alleles": { @@ -611,7 +622,7 @@ "type": "string", "fa_icon": "fas fa-copy", "description": "Path to BWA mem indices.", - "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." + "help_text": "If 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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "bwamem2": { "type": "string", @@ -635,7 +646,7 @@ "type": "string", "fa_icon": "fas fa-file", "description": "Path to dbsnp index.", - "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." + "help_text": "> **NB** If none provided, will be generated automatically from the dbsnp file. Combine with `--save_reference` to save for future runs.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "dbsnp_vqsr": { "type": "string", @@ -646,13 +657,13 @@ "type": "string", "fa_icon": "fas fa-file", "description": "Path to FASTA dictionary 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 FASTA reference. Combine with `--save_reference` to save for future runs." + "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "dragmap": { "type": "string", "fa_icon": "fas fa-copy", "description": "Path to dragmap indices.", - "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." + "help_text": "If 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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "fasta": { "type": "string", @@ -661,89 +672,108 @@ "mimetype": "text/plain", "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", - "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.", + "help_text": "This parameter is *mandatory* if `--genome` is not specified.\n\nIf you use AWS iGenomes, this has already been set for you appropriately.", "fa_icon": "fas fa-file" }, "fasta_fai": { "type": "string", "fa_icon": "fas fa-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 FASTA reference. Combine with `--save_reference` to save for future runs.", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", + "help_text": "> **NB** If none provided, will be generated automatically from the FASTA reference. Combine with `--save_reference` to save for future runs.\n\nIf you use AWS iGenomes, this has already been set for you appropriately.", "description": "Path to FASTA reference index." }, "germline_resource": { "type": "string", "fa_icon": "fas fa-file", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to GATK Mutect2 Germline Resource File.", - "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." + "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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "germline_resource_tbi": { "type": "string", "fa_icon": "fas fa-file", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to GATK Mutect2 Germline Resource Index.", - "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." + "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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "known_indels": { "type": "string", "fa_icon": "fas fa-copy", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to known indels file.", "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", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to known indels file index.", - "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." + "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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "known_indels_vqsr": { "type": "string", "fa_icon": "fas fa-book", - "description": "If you use AWS iGenomes, this has already been set for you appropriately.\n\n1st label string for VariantRecalibration (haplotypecaller joint variant calling)" + "description": "1st label string for VariantRecalibration (haplotypecaller joint variant calling)\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "known_snps": { "type": "string", "fa_icon": "fas fa-copy", - "description": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nPath to known snps file." + "format": "file-path", + "exists": true, + "mimetype": "text/plain", + "description": "Path to known snps file.", + "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "known_snps_tbi": { "type": "string", "fa_icon": "fas fa-copy", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to known snps file snps.", - "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." + "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.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "known_snps_vqsr": { "type": "string", "fa_icon": "fas fa-book", - "description": "If you use AWS iGenomes, this has already been set for you appropriately.\n\nlabel string for VariantRecalibration (haplotypecaller joint variant calling)" + "description": "label string for VariantRecalibration (haplotypecaller joint variant calling).\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "mappability": { "type": "string", "fa_icon": "fas fa-file", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to Control-FREEC mappability file.", "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, "ngscheckmate_bed": { "type": "string", "fa_icon": "fas fa-file", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Path to SNP bed file for sample checking with NGSCheckMate", "help_text": "If you use AWS iGenomes, this has already been set for you appropriately." }, - "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 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." - }, - "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." - }, "sentieon_dnascope_model": { "type": "string", "fa_icon": "fas fa-file", + "format": "file-path", + "exists": true, + "mimetype": "text/plain", "description": "Machine learning model for Sentieon Dnascope.", - "help_text": " It is recommended to use DNAscope with a machine learning model to perform variant calling with higher accuracy by improving the candidate detection and filtering. Sentieon can provide you with a model trained using a subset of the data from the GiAB truth-set found in https://github.com/genome-in-a-bottle. In addition, Sentieon can assist you in the creation of models using your own data, which will calibrate the specifics of your sequencing and bio-informatics processing." + "help_text": " It is recommended to use DNAscope with a machine learning model to perform variant calling with higher accuracy by improving the candidate detection and filtering. Sentieon can provide you with a model trained using a subset of the data from the GiAB truth-set found in https://github.com/genome-in-a-bottle. In addition, Sentieon can assist you in the creation of models using your own data, which will calibrate the specifics of your sequencing and bio-informatics processing.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "snpeff_cache": { "type": "string", @@ -751,13 +781,13 @@ "fa_icon": "fas fa-cloud-download-alt", "default": "s3://annotation-cache/snpeff_cache/", "description": "Path to snpEff cache.", - "help_text": "Path to snpEff cache which should contain the relevant genome and build directory in the path ${snpeff_species}.${snpeff_version}" + "help_text": "Path to snpEff cache which should contain the relevant genome and build directory in the path ${snpeff_species}.${snpeff_version}\n\nIf 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": "This is used to specify the database to be use to annotate with.\nAlternatively databases' names can be listed with the `snpEff databases`.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "vep_cache": { "type": "string", @@ -765,25 +795,25 @@ "fa_icon": "fas fa-cloud-download-alt", "default": "s3://annotation-cache/vep_cache/", "description": "Path to VEP cache.", - "help_text": "Path to VEP cache which should contain the relevant species, genome and build directories at the path ${vep_species}/${vep_genome}_${vep_cache_version}" + "help_text": "Path to VEP cache which should contain the relevant species, genome and build directories at the path ${vep_species}/${vep_genome}_${vep_cache_version}\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "vep_cache_version": { "type": "string", "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": "Alternative cache version can be used to specify the correct Ensembl Genomes version number as these differ from the concurrent Ensembl/VEP version numbers.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "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 looking for local cache, or cloud based cache." + "help_text": "This is used to specify the genome when looking for local cache, or cloud based cache.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." }, "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": "Alternatively species listed in Ensembl Genomes caches can be used.\n\nIf you use AWS iGenomes, this has already been set for you appropriately." } }, "help_text": "The pipeline config files come bundled with paths to the Illumina iGenomes reference index files.\nThe configuration is set up to use the AWS-iGenomes resource\ncf https://ewels.github.io/AWS-iGenomes/."