nextflow_schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/vmikk/NextITS/main/nextflow_schema.json",
  "title": "NextITS pipeline parameters",
  "description": "Pipeline to process fungal ITS amplicons sequenced with PacBio",
  "type": "object",
  "$defs": {
    "step_1_specific_parameters": {
      "title": "Step-1-specific parameters",
      "type": "object",
      "properties": {
        "input": {
          "type": "string",
          "format": "path",
          "exists": true,
          "mimetype": "text/csv",
          "description": "Path to input data: either a single FASTQ or BAM file containing multiplexed sequences, or a directory containing pre-demultiplexed FASTQ files.",
          "fa_icon": "fas fa-file-csv"
        },
        "barcodes": {
          "type": "string",
          "fa_icon": "fas fa-barcode",
          "description": "Path to the file with barcodes (in FASTA format) used for demultiplexing the input data."
        },
        "demultiplexed": {
          "type": "boolean",
          "fa_icon": "fas fa-align-justify",
          "description": "Whether input is multiplexed (`false`, single FASTQ file) or pre-demultiplexed (`true`, multiple FASTQ files)."
        },
        "seqplatform": {
          "type": "string",
          "default": "PacBio",
          "fa_icon": "fab fa-google-play",
          "description": "Sequencing platform used",
          "enum": ["PacBio", "Illumina"]
        },
        "qc_maxee": {
          "type": "number",
          "description": "Maximum expected errors allowed in a sequence. Sequences with higher error rates will be discarded.",
          "fa_icon": "fas fa-times"
        },
        "qc_maxeerate": {
          "type": "number",
          "default": 0.01,
          "description": "Maximum expected error rate per sequence (between 0 and 1). Sequences with higher error rates will be discarded.",
          "fa_icon": "fas fa-times"
        },
        "qc_maxhomopolymerlen": {
          "type": "integer",
          "default": 25,
          "description": "Threshold for a homopolymer region length in a sequence.",
          "fa_icon": "fas fa-redo"
        },
        "qc_maxn": {
          "type": "integer",
          "default": 4,
          "description": "Discard sequences with more than the specified number of ambiguous nucleotides (N's).",
          "fa_icon": "fas fa-minus-square"
        },
        "lima_barcodetype": {
          "type": "string",
          "default": "dual_symmetric",
          "fa_icon": "fab fa-slack-hash",
          "description": "Barcode configuration type used for multiplexing samples: 'single' if only one of the primers was tagged, 'dual_symmetric' if identical barcodes were used, 'dual_asymmetric' if different barcodes were used, 'dual' if both primers were tagged with a mixture of identical and different barcodes",
          "enum": ["single", "dual", "dual_symmetric", "dual_asymmetric"]
        },
        "lima_minscore": {
          "type": "integer",
          "default": 93,
          "minimum": 0,
          "maximum": 100,
          "fa_icon": "fas fa-balance-scale-left",
          "description": "Minimum barcode score (0-100) required for successful demultiplexing. Higher values mean stricter matching."
        },
        "lima_minendscore": {
          "type": "integer",
          "default": 50,
          "fa_icon": "fas fa-balance-scale-right",
          "description": "Minimum second barcode score (only for asymmetric and dual barcoding scheme)",
          "minimum": 0,
          "maximum": 100
        },
        "lima_minrefspan": {
          "type": "number",
          "default": 0.75,
          "fa_icon": "fas fa-random",
          "description": "Minimum read span relative to the barcode length",
          "minimum": 0,
          "maximum": 1
        },
        "lima_minscoringregions": {
          "type": "integer",
          "default": 2,
          "fa_icon": "fas fa-angle-down",
          "description": "Number of barcodes scored required for demultiplexing using dual barcodes",
          "minimum": 1,
          "maximum": 2
        },
        "lima_windowsize": {
          "type": "integer",
          "default": 70,
          "fa_icon": "fas fa-arrows-alt-h",
          "description": "Window size for barcode lookup, in base pairs",
          "minimum": 1
        },
        "lima_minlen": {
          "type": "integer",
          "default": 40,
          "fa_icon": "fas fa-compress-alt",
          "description": "Minimum sequence length after clipping barcodes.",
          "minimum": 1
        },
        "lima_remove_unknown": {
          "type": "boolean",
          "fa_icon": "fas fa-compress-alt",
          "description": "Remove unknown barcode combinations from the demultiplexed data (if false, unknown combinations will be named as tag IDs)."
        },
        "primer_forward": {
          "type": "string",
          "fa_icon": "fas fa-arrow-right",
          "description": "Sequence of the forward primer.",
          "default": "TACACACCGCCCGTCG",
          "help_text": "**Forward Primer:** `ITS9MUNngs` with sequence `TACACACCGCCCGTCG`  \nRefer to [Tedersoo & Lindahl, 2016 DOI:`10.1111/1758-2229.12438`](https://ami-journals.onlinelibrary.wiley.com/doi/10.1111/1758-2229.12438) for more details on these primers.  "
        },
        "primer_reverse": {
          "type": "string",
          "fa_icon": "fas fa-arrow-left",
          "description": "Sequence of the reverse primer.",
          "default": "CCTSCSCTTANTDATATGC",
          "help_text": "**Reverse Primer:** `ITS4ngsUni` with sequence `CCTSCSCTTANTDATATGC`  \nRefer to [Tedersoo & Lindahl, 2016 DOI:`10.1111/1758-2229.12438`](https://ami-journals.onlinelibrary.wiley.com/doi/10.1111/1758-2229.12438) for more details on these primers.  "
        },
        "primer_mismatches": {
          "type": "integer",
          "default": 2,
          "fa_icon": "fas fa-chevron-circle-down",
          "description": "Allowed number of mismatches for primers."
        },
        "primer_foverlap": {
          "type": "integer",
          "fa_icon": "fas fa-angle-right",
          "description": "Minimum overlap for the forward primer.",
          "default": null
        },
        "primer_roverlap": {
          "type": "integer",
          "fa_icon": "fas fa-angle-left",
          "description": "Minimum overlap for the reverse primer.",
          "default": null
        },
        "its_region": {
          "type": "string",
          "default": "full",
          "enum": [
            "full",
            "ITS1",
            "ITS2",
            "none",
            "ITS1_5.8S_ITS2",
            "SSU",
            "LSU"
          ],
          "description": "Target ITS region to extract: 'full' for complete ITS region, 'ITS1' or 'ITS2' for specific spacers, 'ITS1_5.8S_ITS2' for the partial ITS (in case of HMM profiles are not able to detect the full ITS region), 'SSU' or 'LSU' for 18S or 28S ribosomal genes, or 'none' to skip extraction (in this case, only the primers will be trimmed)",
          "fa_icon": "fas fa-arrows-alt-h"
        },
        "ITSx_tax": {
          "type": "string",
          "default": "all",
          "fa_icon": "fas fa-user-tag",
          "description": "Taxonomic profile for ITS extraction",
          "pattern": "^(?:all|(?:alveolata|bryophyta|bacillariophyta|amoebozoa|euglenozoa|fungi|chlorophyta|rhodophyta|phaeophyceae|marchantiophyta|metazoa|oomycota|haptophyceae|raphidophyceae|rhizaria|synurophyceae|tracheophyta|eustigmatophyceae|apusozoa|parabasalia)(?:,\\s*(?:alveolata|bryophyta|bacillariophyta|amoebozoa|euglenozoa|fungi|chlorophyta|rhodophyta|phaeophyceae|marchantiophyta|metazoa|oomycota|haptophyceae|raphidophyceae|rhizaria|synurophyceae|tracheophyta|eustigmatophyceae|apusozoa|parabasalia))*)$"
        },
        "ITSx_evalue": {
          "type": "number",
          "default": 0.1,
          "fa_icon": "fas fa-check-circle",
          "description": "Min E-value threshold for ITSx"
        },
        "ITSx_complement": {
          "type": "string",
          "default": "F",
          "fa_icon": "fas fa-check-circle",
          "description": "Check single strand (F, default) or both DNA strands (T) for matches to HMM-profiles",
          "enum": [
            "F",
            "T"
          ]
        },
        "ITSx_partial": {
          "type": "integer",
          "default": 0,
          "fa_icon": "fas fa-arrows-alt-h",
          "description": "Min length cutoff for partial ITS sequences to keep (0 = disabled, default)"
        },
        "ITSx_to_parquet": {
          "type": "boolean",
          "default": true,
          "fa_icon": "fas fa-database",
          "description": "Convert ITSx output (FASTA files) to Parquet"
        },
        "ITSx_chunk_size": {
          "type": "integer",
          "default": 10000,
          "fa_icon": "fas fa-database",
          "description": "Chunk size for distributed ITSx processing (number of dereplicated sequences per sample); set to 0 to disable chunking"
        },
        "hp": {
          "type": "boolean",
          "default": true,
          "description": "Enable homopolymer error correction in sequences"
        },
        "hp_similarity": {
          "type": "number",
          "default": 0.999,
          "minimum": 0.8,
          "maximum": 1,
          "description": "Sequence similarity threshold for pre-clustering during homopolymer error correction (0.8-1.0)"
        },
        "hp_iddef": {
          "type": "number",
          "default": 2,
          "minimum": 0,
          "maximum": 4,
          "description": "Identity definition for homopolymer compression"
        },
        "chimera_methods": {
          "type": "string",
          "default": "ref,denovo",
          "description": "Which chimera removal methods to use",
          "enum": ["ref", "denovo", "ref,denovo", "denovo,ref", "none", "null"]
        },
        "chimera_db": {
          "type": "string",
          "fa_icon": "fas fa-database",
          "default": "Eukaryome_1.9.3_241222_FullITS_100-800.udb",
          "description": "Database for refrence-based chimera removal"
        },
        "chimera_rescueoccurrence": {
          "type": "integer",
          "default": 2,
          "description": "Occurrence threshold for rescuing reference-based chimeras"
        },
        "chimeranov_abskew": {
          "type": "number",
          "default": 2,
          "description": "abskew parameter for de novo chimera removal"
        },
        "chimeranov_dn": {
          "type": "number",
          "default": 1.4,
          "description": "dn parameter for de novo chimera removal"
        },
        "chimeranov_mindiffs": {
          "type": "number",
          "default": 3,
          "description": "mindiffs parameter for de novo chimera removal"
        },
        "chimeranov_mindiv": {
          "type": "number",
          "default": 0.8,
          "description": "mindiv parameter for de novo chimera removal"
        },
        "chimeranov_minh": {
          "type": "number",
          "default": 0.28,
          "description": "minh parameter for de novo chimera removal"
        },
        "chimeranov_xn": {
          "type": "number",
          "default": 8,
          "description": "xn parameter for de novo chimera removal"
        },
        "tj": {
          "type": "boolean",
          "default": true,
          "description": "Run tag-jump removal"
        },
        "tj_f": {
          "type": "number",
          "default": 0.01,
          "minimum": 0,
          "maximum": 1,
          "description": "UNCROSS parameter f for tag-jump removal"
        },
        "tj_p": {
          "type": "number",
          "default": 1,
          "description": "Parameter p for tag-jump removal"
        },
        "tj_id": {
          "type": "number",
          "default": 1,
          "minimum": 0,
          "maximum": 1,
          "description": "Sequence similarity threshold for tag-jump removal (1 = dereplication, < 1 = pre-clustering)"
        },
        "tj_iddef": {
          "type": "integer",
          "default": 2,
          "minimum": 0,
          "maximum": 4,
          "description": "Sequence identity definition for pre-clustering prior tag-jump removal"
        }
      },
      "fa_icon": "fas fa-bullseye"
    },
    "step_2_specific_parameters": {
      "title": "Step-2-specific parameters",
      "type": "object",
      "properties": {
        "data_path": {
          "type": "string",
          "format": "directory-path",
          "fa_icon": "fas fa-folder-open",
          "description": "Path to the Step-1 results",
          "default": "Step1_Results"
        },
        "merge_replicates": {
          "type": "boolean",
          "description": "Pool sample replicates (e.g., re-sequenced samples) in the final OTU table"
        },
        "ampliconlen_min": {
          "type": "integer",
          "description": "Minimum amplicon length for filtering"
        },
        "ampliconlen_max": {
          "type": "integer",
          "description": "Maximum amplicon length for filtering"
        },
        "chunking_n": {
          "type": "integer",
          "description": "Number of chunks to split the dataset into prior clustering"
        },
        "chunking_id": {
          "type": "number",
          "default": 0.6,
          "description": "Minimum sequence identity for clustering"
        },
        "preclustering": {
          "type": "string",
          "default": "none",
          "enum": ["none", "unoise", "dada2", "swarm_d1", "homopolymer"],
          "description": "Sequence denoising or pre-clustering method"
        },
        "unoise_alpha": {
          "type": "number",
          "default": 6,
          "description": "UNOISE alpha parameter"
        },
        "unoise_minsize": {
          "type": "integer",
          "default": 1,
          "description": "UNOISE minimum size parameter"
        },
        "dada2_pooling": {
          "type": "string",
          "default": "byrun",
          "enum": ["byrun", "global"],
          "description": "DADA2 pooling strategy"
        },
        "dada2_error_estimation": {
          "type": "string",
          "default": "per_bucket",
          "enum": ["per_bucket", "shared"],
          "description": "How DADA2 error rates are estimated for chunked runs: independently per bucket or once from a shared subset"
        },
        "dada2_nbases": {
          "type": "number",
          "default": 1000000,
          "description": "DADA2 number of bases"
        },
        "dada2_bandsize": {
          "type": "integer",
          "default": 16,
          "description": "DADA2 band size"
        },
        "dada2_detectsingletons": {
          "type": "boolean",
          "default": true,
          "description": "DADA2 detect singletons"
        },
        "dada2_omegaA": {
          "type": "number",
          "default": 1e-20,
          "description": "DADA2 omega A parameter"
        },
        "dada2_omegaC": {
          "type": "number",
          "default": 1e-40,
          "description": "DADA2 omega C parameter"
        },
        "dada2_omegaP": {
          "type": "number",
          "default": 0.0001,
          "description": "DADA2 omega P parameter"
        },
        "dada2_maxconsist": {
          "type": "integer",
          "default": 10,
          "description": "DADA2 maximum consistency"
        },
        "dada2_match": {
          "type": "integer",
          "default": 4,
          "description": "DADA2 match score"
        },
        "dada2_mismatch": {
          "type": "integer",
          "default": -5,
          "description": "DADA2 mismatch penalty"
        },
        "dada2_gappenalty": {
          "type": "integer",
          "default": -8,
          "description": "DADA2 gap penalty"
        },
        "clustering": {
          "type": "string",
          "default": "vsearch",
          "enum": ["none", "vsearch", "swarm", "shmatching"],
          "description": "Sequence clustering method"
        },
        "otu_id": {
          "type": "number",
          "default": 0.98,
          "description": "Sequence similarity threshold for OTU clustering",
          "minimum": 0,
          "maximum": 1
        },
        "otu_iddef": {
          "type": "integer",
          "default": 2,
          "description": "Sequence similarity definition type for OTU clustering",
          "minimum": 1,
          "maximum": 4
        },
        "otu_qmask": {
          "type": "string",
          "default": "dust",
          "description": "Quality masking for OTU clustering"
        },
        "swarm_d": {
          "type": "integer",
          "default": 1,
          "description": "SWARM distance parameter"
        },
        "swarm_fastidious": {
          "type": "boolean",
          "default": true,
          "description": "Enable SWARM fastidious mode"
        },
        "swarm_d1boundary": {
          "type": "integer",
          "default": 3,
          "description": "SWARM boundary parameter for fastidious mode"
        },
        "alignment_penalties": {
          "type": "string",
          "default": "default",
          "enum": ["default", "UNITE"],
          "description": "Alignment penalty configuration"
        },
        "vsearch_gapopen": {
          "type": "string",
          "default": "20I/2E",
          "description": "VSEARCH gap opening penalties"
        },
        "vsearch_gapext": {
          "type": "string",
          "default": "2I/1E",
          "description": "VSEARCH gap extension penalties"
        },
        "max_MEEP": {
          "type": "number",
          "default": 0.5,
          "description": "Maximum expected error as a percentage of read length (MEEP)  threshold for singleton removal"
        },
        "max_ChimeraScore": {
          "type": "number",
          "default": 0.6,
          "description": "Maximum de novo chimera score"
        },
        "recover_lowqsingletons": {
          "type": "boolean",
          "default": true,
          "description": "Allow recovery of singletons"
        },
        "recover_denovochimeras": {
          "type": "boolean",
          "default": true,
          "description": "Allow recovery of de novo chimeras"
        },
        "lulu": {
          "type": "boolean",
          "default": true,
          "description": "Post-clustering curation using LULU algorithm"
        },
        "lulu_match": {
          "type": "integer",
          "default": 95,
          "description": "Minimum sequence similarity threshold for LULU"
        },
        "lulu_ratio": {
          "type": "integer",
          "default": 1,
          "description": "Minimum sequence abundance ratio for LULU"
        },
        "lulu_ratiotype": {
          "type": "string",
          "default": "min",
          "description": "Abundance ratio type for LULU",
          "enum": ["min", "avg"]
        },
        "lulu_relcooc": {
          "type": "number",
          "default": 0.95,
          "description": "Relative co-occurrence threshold for LULU",
          "minimum": 0,
          "maximum": 1
        },
        "lulu_maxhits": {
          "type": "integer",
          "default": 0,
          "description": "Maximum number of hits for LULU (0 = unlimited)"
        },
        "sh": {
          "type": "boolean",
          "default": true,
          "description": "Species-hypothesis (SH) matching [not implemented yet]"
        },
        "sh_thresholds": {
          "type": "string"
        },
        "sh_coveragevariation": {
          "type": "number",
          "default": 0.96
        }
      }
    },
    "common_parameters": {
      "title": "Common parameters for both steps",
      "type": "object",
      "properties": {
        "outdir": {
          "type": "string",
          "format": "directory-path",
          "description": "Path to the directory where the analysis results will be saved.",
          "fa_icon": "fas fa-folder-open",
          "default": "Step2_Results"
        },
        "step": {
          "type": "string",
          "enum": ["Step1", "Step2", "seqstats"],
          "description": "The step of the pipeline to run.",
          "fa_icon": "fas fa-step-forward",
          "default": "Step1"
        },
        "storagemode": {
          "type": "string",
          "default": "rellink",
          "fa_icon": "fas fa-boxes",
          "enum": ["symlink", "copy", "move", "rellink", "link"],
          "description": "How to store output files: 'symlink' for symbolic links, 'copy' to copy files, 'move' to move files, 'rellink' for relative links, 'link' for hard links"
        },
        "gzip_compression": {
          "type": "number",
          "default": 7,
          "minimum": 1,
          "maximum": 9,
          "fa_icon": "fas fa-file-archive",
          "description": "Controls GZIP compression level in output files."
        },
        "max_cpus": {
          "type": "integer",
          "default": 40,
          "fa_icon": "fas fa-microchip",
          "description": "Maximum number of CPUs that can be requested (for any single job).",
          "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`",
          "minimum": 1,
          "maximum": 200
        },
        "max_memory": {
          "type": "string",
          "default": "132.GB",
          "fa_icon": "fas fa-memory",
          "description": "Maximum amount of memory that can be requested (for any single job).",
          "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
          "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
        },
        "max_time": {
          "type": "string",
          "default": "240.h",
          "fa_icon": "fas fa-clock",
          "description": "Maximum amount of time that can be requested (for any single job).",
          "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
          "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
        },
        "tracedir": {
          "type": "string",
          "fa_icon": "fas fa-folder-minus",
          "description": "Directory to store pipeline execution logs"
        },
        "version": {
          "type": "boolean",
          "description": "Display version and exit",
          "fa_icon": "fas fa-question-circle",
          "hidden": true
        },
        "help": {
          "type": "boolean",
          "description": "Display help text",
          "fa_icon": "fas fa-question-circle",
          "hidden": true
        },
        "helpMsg": {
          "type": "boolean",
          "fa_icon": "far fa-question-circle",
          "description": "Custom help message"
        },
        "monochrome_logs": {
          "type": "boolean",
          "description": "Do not use coloured log outputs",
          "fa_icon": "fas fa-palette",
          "hidden": true
        },
        "validate_params": {
          "type": "boolean",
          "description": "Boolean whether to validate parameters against the schema at runtime",
          "default": true,
          "fa_icon": "fas fa-check-square",
          "hidden": true
        },
        "show_hidden_params": {
          "type": "boolean",
          "description": "Show all params when using `--help`",
          "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters.",
          "fa_icon": "fas fa-eye-slash"
        },
        "enable_conda": {
          "type": "boolean",
          "fa_icon": "fas fa-adjust",
          "hidden": true
        },
        "email": {
          "type": "string",
          "description": "Email address for completion summary.",
          "fa_icon": "fas fa-envelope",
          "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
          "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
          "hidden": true
        },
        "email_on_fail": {
          "type": "string",
          "description": "Email address for completion summary, only when pipeline fails.",
          "fa_icon": "fas fa-exclamation-triangle",
          "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
          "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
          "hidden": true
        },
        "plaintext_email": {
          "type": "boolean",
          "description": "Send plain-text email instead of HTML.",
          "fa_icon": "fas fa-remove-format",
          "hidden": true
        },
        "schema_ignore_params": {
          "type": "string"
        }
      },
      "required": ["step"],
      "fa_icon": "fab fa-creative-commons-share"
    },
    "illumina_specific_parameters": {
      "title": "Illumina-specific parameters",
      "type": "object",
      "properties": {
        "input_R1": {
          "type": "string",
          "description": "File with R1 reads for Illumina"
        },
        "input_R2": {
          "type": "string",
          "description": "File with R2 reads for Illumina"
        },
        "qc_avgphred": {
          "type": "boolean",
          "description": "Average Phred score (for Illumina PE reads only)"
        },
        "qc_twocolor": {
          "type": "boolean",
          "description": "Reduced resolution Phred-scores (two-color Illumina chemistry)"
        },
        "pe_minoverlap": {
          "type": "integer",
          "default": 20,
          "description": "Paired-end reads minimum overlap (Illumina only)"
        },
        "pe_diffperclimit": {
          "type": "integer",
          "default": 20,
          "description": "Paired-end reads max percentage difference for the overlap (Illumina only)"
        },
        "pe_difflimit": {
          "type": "integer",
          "default": 5,
          "description": "Paired-end reads max difference for the overlap (Illumina only)"
        },
        "pe_nlimit": {
          "type": "integer",
          "default": 10
        },
        "pe_minlen": {
          "type": "integer",
          "default": 30
        },
        "barcode_errors": {
          "type": "integer",
          "default": 1,
          "description": "Number of allowed erros in demultiplexing (Illumina only)"
        },
        "illumina_keep_notmerged": {
          "type": "boolean",
          "default": true
        },
        "illumina_joinpadgap": {
          "type": "string",
          "default": "NNNNNNNNNN"
        },
        "illumina_joinpadqual": {
          "type": "string",
          "default": "IIIIIIIIII"
        },
        "barcode_window": {
          "type": "integer",
          "default": 30,
          "description": "(Illumina only)"
        },
        "barcode_overlap": {
          "type": "integer",
          "default": 11,
          "description": "(Illumina only)"
        },
        "trim_minlen": {
          "type": "integer",
          "default": 10
        },
        "qc_phredmin": {
          "type": "integer",
          "description": "Min Phred score threshold of unqualified bases (for two-color Illumina only)"
        },
        "qc_phredperc": {
          "type": "integer",
          "description": "Max percentage of unqualified bases per read (for two-color Illumina only)"
        },
        "qc_polyglen": {
          "type": "integer",
          "description": "Max poly-G length (for two-color Illumina only)"
        }
      },
      "description": "EXPERIMENTAL",
      "fa_icon": "fas fa-flask"
    }
  },
  "allOf": [
    {
      "$ref": "#/$defs/step_1_specific_parameters"
    },
    {
      "$ref": "#/$defs/step_2_specific_parameters"
    },
    {
      "$ref": "#/$defs/common_parameters"
    },
    {
      "$ref": "#/$defs/illumina_specific_parameters"
    }
  ]
}