nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/sheynkmanlab/lrp2/master/nextflow_schema.json",
    "title": "sheynkmanlab/lrp2 pipeline parameters",
    "description": "Long-read proteogenomics pipeline for PacBio Iso-Seq data",
    "type": "object",
    "additionalProperties": true,
    "$defs": {
        "input_output_options": {
            "title": "Input/Output Options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": ["outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_input_bam.json",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "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 sample files. Required columns: 'sample_name', 'sample_path', 'condition', 'sample_type'. Each RNA sample must have a unique 'sample_name' value, which will be used to label count matrix columns. Protein samples with matching 'sample_name' and 'condition' will be grouped together for proteomics analysis.",
                    "fa_icon": "fas fa-file-csv"
                },
                "dataset_name": {
                    "type": "string",
                    "default": "merged",
                    "description": "Name for the merged dataset.",
                    "help_text": "This name will be used as a prefix for all output files. It should be a descriptive name for your project or experiment.",
                    "fa_icon": "fas fa-tag"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                    "fa_icon": "fas fa-folder-open"
                },
                "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})$"
                }
            }
        },
        "reference_genome_options": {
            "title": "Genome Reference Options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Reference genome related files and options required for the workflow.",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Name of genome reference. This automatically populates the paths for the reference FASTA and GTF files if using GENCODE references.",
                    "fa_icon": "fas fa-book",
                    "help_text": "If using a reference genome configured in the pipeline using GENCODE, 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."
                },
                "gtf": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to custom reference GTF file (optional).",
                    "help_text": "Path to the GTF file matching your reference genome. If not provided, will be automatically set from iGenomes configuration using the genome parameter.",
                    "fa_icon": "far fa-file-code"
                },
                "fasta": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to reference genome FASTA file (optional).",
                    "help_text": "Path to the genome FASTA file matching your reference genome. If not provided, will be automatically set from iGenomes configuration using the genome parameter.",
                    "fa_icon": "far fa-file-code"
                },
                "igenomes_ignore": {
                    "type": "boolean",
                    "description": "Do not load the iGenomes reference config.",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
                },
                "igenomes_base": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The base path to the igenomes reference files",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "default": "s3://ngi-igenomes/igenomes/"
                }
            }
        },
        "institutional_config_options": {
            "title": "Institutional config options",
            "type": "object",
            "fa_icon": "fas fa-university",
            "description": "Parameters used to describe centralised config profiles. These should not be edited.",
            "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
            "properties": {
                "custom_config_version": {
                    "type": "string",
                    "description": "Git commit id for Institutional configs.",
                    "default": "master",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "custom_config_base": {
                    "type": "string",
                    "description": "Base directory for Institutional configs.",
                    "default": "https://raw.githubusercontent.com/nf-core/configs/master",
                    "hidden": true,
                    "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_name": {
                    "type": "string",
                    "description": "Institutional config name.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_description": {
                    "type": "string",
                    "description": "Institutional config description.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_contact": {
                    "type": "string",
                    "description": "Institutional config contact information.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_url": {
                    "type": "string",
                    "description": "Institutional config URL link.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                }
            }
        },
        "isoseq_collapse_options": {
            "title": "S1 PacBio IsoCall Options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Options for the PacBio IsoCall transcript calling module.",
            "properties": {
                "min_read_support": {
                    "type": "integer",
                    "default": 3,
                    "description": "Minimum read support required for calling novel transcripts.",
                    "help_text": "Transcripts must be supported by at least this many reads to be called.",
                    "fa_icon": "fas fa-layer-group"
                },
                "max_bundles_per_gene": {
                    "type": "integer",
                    "default": 100,
                    "description": "Maximum bundles to use per gene during read sampling.",
                    "help_text": "Limits the number of read bundles processed per gene to improve performance.",
                    "fa_icon": "fas fa-boxes"
                },
                "isocall_config": {
                    "type": "string",
                    "format": "file-path",
                    "default": "${projectDir}/bin/isocall_config.toml",
                    "description": "Path to IsoCall configuration TOML file.",
                    "help_text": "Configuration file for IsoCall parameters. Uses default config if not specified.",
                    "fa_icon": "fas fa-file-code"
                }
            }
        },
        "sqanti_transcript_options": {
            "title": "S2 Transcriptome Options",
            "type": "object",
            "fa_icon": "fas fa-filter",
            "description": "Options for the SQANTI3 QC and filtering modules.",
            "properties": {
                "generate_hashids_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to hash ID generation R script.",
                    "help_text": "R script used to generate hash IDs for transcripts.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "filter_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to SQANTI filtering R script.",
                    "help_text": "R script used to filter SQANTI3 QC output.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "hashlib_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to hashlib ID generator Python script.",
                    "help_text": "Python script used to generate hash IDs for transcripts.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "sqanti_path": {
                    "type": "string",
                    "format": "directory-path",
                    "default": "/project/sheynkman/programs/SQANTI3-5.5/src/utilities/cupcake/",
                    "description": "Path to SQANTI3 installation directory.",
                    "help_text": "Path to the SQANTI3 cupcake utilities directory.",
                    "fa_icon": "fas fa-folder",
                    "hidden": true
                },
                "protein_coding_filter": {
                    "type": "boolean",
                    "default": true,
                    "description": "Filter to keep only protein-coding genes.",
                    "fa_icon": "fas fa-check"
                },
                "internal_priming_filter": {
                    "type": "boolean",
                    "default": true,
                    "description": "Filter to remove internal priming artifacts.",
                    "fa_icon": "fas fa-check"
                },
                "template_switching_filter": {
                    "type": "boolean",
                    "default": true,
                    "description": "Filter to remove template switching artifacts.",
                    "fa_icon": "fas fa-check"
                },
                "percent_polya_threshold": {
                    "type": "integer",
                    "default": 60,
                    "description": "Threshold for polyA percentage downstream of TTS.",
                    "fa_icon": "fas fa-percent"
                },
                "transcript_class_keep": {
                    "type": "string",
                    "default": "FSM,NIC,NNC",
                    "description": "Comma-separated transcript structural categories to retain (FSM, ISM, NIC, NNC, or 'ALL').",
                    "fa_icon": "fas fa-filter"
                }
            }
        },
        "predicted_proteome_options": {
            "title": "S3 Predicted Proteome Options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Options for CPAT ORF calling and protein classification.",
            "properties": {
                "species": {
                    "type": "string",
                    "default": "human",
                    "description": "Species for CPAT model selection (human or mouse).",
                    "fa_icon": "fas fa-fish",
                    "enum": ["human", "mouse"]
                },
                "human_hexamer": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to human hexamer table for CPAT.",
                    "help_text": "Hexamer table used by CPAT for ORF prediction in human samples.",
                    "fa_icon": "far fa-file-code"
                },
                "human_logit_model": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to human logit model for CPAT.",
                    "help_text": "Logit model used by CPAT for ORF prediction in human samples.",
                    "fa_icon": "far fa-file-code"
                },
                "mouse_hexamer": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to mouse hexamer table for CPAT.",
                    "help_text": "Hexamer table used by CPAT for ORF prediction in mouse samples.",
                    "fa_icon": "far fa-file-code"
                },
                "mouse_logit_model": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to mouse logit model for CPAT.",
                    "help_text": "Logit model used by CPAT for ORF prediction in mouse samples.",
                    "fa_icon": "far fa-file-code"
                },
                "cpat_coding_threshold": {
                    "type": "number",
                    "description": "CPAT coding probability threshold.",
                    "help_text": "Coding probability threshold for CPAT. Auto-set based on species if not specified (human=0.364, mouse=0.44).",
                    "fa_icon": "fas fa-balance-scale"
                },
                "min_orf": {
                    "type": "integer",
                    "default": 75,
                    "description": "Minimum ORF length in nucleotides.",
                    "fa_icon": "fas fa-ruler"
                },
                "top_orf": {
                    "type": "integer",
                    "default": 5,
                    "description": "Number of top ORFs to retain per transcript.",
                    "fa_icon": "fas fa-sort-numeric-down"
                },
                "filter_cpat_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to CPAT filtering R script.",
                    "help_text": "R script used to filter CPAT output and call best ORFs.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "sqanti_protein_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to SQANTI protein classification Python script.",
                    "help_text": "Python script used for SQANTI3 protein classification.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "protein_class_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to protein classification R script.",
                    "help_text": "R script used for 5'UTR and protein classification.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "protein_class_keep": {
                    "type": "string",
                    "default": "FPM,IPM,NPC,NPE",
                    "description": "Comma-separated list of protein classifications to keep.",
                    "help_text": "Protein classification categories to retain (e.g., FPM,IPM,NPC,NPE).",
                    "fa_icon": "fas fa-filter"
                },
                "min_junctions_after_stop_codon": {
                    "type": "integer",
                    "default": 0,
                    "description": "Minimum number of junctions after stop codon for filtering.",
                    "fa_icon": "fas fa-filter"
                }
            }
        },
        "differential_analysis_options": {
            "title": "S4 Multisample Analysis Options",
            "type": "object",
            "fa_icon": "fas fa-chart-line",
            "description": "Options for multi-sample differential expression and splicing analysis.",
            "properties": {
                "min_samples_per_intron": {
                    "type": "integer",
                    "default": 2,
                    "description": "Minimum number of samples per intron for leafcutter differential splicing.",
                    "fa_icon": "fas fa-filter"
                },
                "min_samples_per_group": {
                    "type": "integer",
                    "default": 1,
                    "description": "Minimum number of samples per group for leafcutter differential splicing.",
                    "fa_icon": "fas fa-users"
                },
                "min_usage_ratio": {
                    "type": "number",
                    "default": 0.01,
                    "description": "Minimum junction usage ratio for minicutter filtering.",
                    "fa_icon": "fas fa-percent"
                },
                "lr_leafcutter_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to long-read leafcutter R script.",
                    "help_text": "R script used for long-read leafcutter clustering analysis.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "leafcutter_ds_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to leafcutter differential splicing Python script.",
                    "help_text": "Python script used for leafcutter differential splicing analysis (leafcutter_ds.py).",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "multisample_script": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to multi-sample analysis R script.",
                    "help_text": "R script used for differential expression and usage analysis with edgeR and DRIMSeq.",
                    "fa_icon": "far fa-file-code",
                    "hidden": true
                },
                "leafcutter_threads": {
                    "type": "integer",
                    "default": 12,
                    "description": "Number of threads for leafcutter differential splicing.",
                    "help_text": "Specify the number of threads to use for leafcutter differential splicing analysis. If not specified, defaults to using the number of CPUs allocated to the process (12 for process_high).",
                    "fa_icon": "fas fa-microchip"
                },
                "drimseq_min_gene_expr": {
                    "type": "integer",
                    "default": 10,
                    "description": "Minimum gene-level expression for DRIMSeq filtering.",
                    "help_text": "Genes with total counts below this threshold will be filtered out before differential usage analysis.",
                    "fa_icon": "fas fa-filter"
                },
                "drimseq_min_isoform_prop": {
                    "type": "number",
                    "default": 0.05,
                    "description": "Minimum isoform/feature proportion for DRIMSeq filtering.",
                    "help_text": "Isoforms/features with proportion below this threshold will be filtered out before differential usage analysis.",
                    "fa_icon": "fas fa-percentage"
                }
            }
        },
        "multisample_only_inputs": {
            "title": "Multisample Analysis Only Mode",
            "type": "object",
            "fa_icon": "fas fa-play-circle",
            "description": "Parameters for running only multisample analysis with pre-computed inputs from a previous LRP2 run.",
            "help_text": "Use these parameters to re-run only the multisample analysis subworkflow using outputs from a previous full pipeline run. All four file parameters must be provided together to enable this mode. The --input samplesheet parameter is not required in this mode.",
            "properties": {
                "transcripts_gtf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Pre-computed filtered GTF file from TRANSCRIPTOME subworkflow.",
                    "help_text": "Path to the filtered GTF file (typically named *_corrected_filtered.gtf) from a previous LRP2 run. This file is output by the FILTER_TRANSCRIPTOME module in the TRANSCRIPTOME subworkflow.",
                    "fa_icon": "far fa-file-code"
                },
                "transcript_counts": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Pre-computed transcript count matrix from TRANSCRIPTOME subworkflow.",
                    "help_text": "Path to the transcript count matrix file (typically named *_hashids_with_cpm_filtered.txt) from a previous LRP2 run. This file contains CPM-normalized transcript counts.",
                    "fa_icon": "far fa-file-alt"
                },
                "orf_counts": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Pre-computed ORF count matrix from PREDICTED_PROTEOME subworkflow.",
                    "help_text": "Path to the ORF count matrix file (typically named *.predicted.proteome.high_confidence_ORF_cpm.txt) from a previous LRP2 run. This file contains CPM-normalized ORF counts.",
                    "fa_icon": "far fa-file-alt"
                },
                "multisample_metadata": {
                    "type": "string",
                    "format": "file-path",
                    "description": "RNA sample metadata CSV file for multisample analysis.",
                    "help_text": "Path to a CSV file with RNA sample metadata. Accepts two formats: (1) Simplified format with columns 'name', 'sample_path', 'group', 'sample_type', or (2) Standard samplesheet format with columns 'sample_name', 'sample_path', 'condition', 'sample_type', 'mass_spec_type'. The pipeline auto-detects which format you're using. You can use the auto-generated *_rna_samples_metadata.csv file from a previous LRP2 run, your original samplesheet (if RNA-only), or a custom metadata file in either format.",
                    "fa_icon": "fas fa-file-csv"
                }
            }
        },
        "proteomics_options": {
            "title": "S5 Proteomics Options",
            "type": "object",
            "fa_icon": "fas fa-microscope",
            "description": "Options for mass spectrometry proteomics analysis.",
            "properties": {
                "metamorpheus_config": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to MetaMorpheus task configuration TOML file.",
                    "help_text": "Configuration file specifying MetaMorpheus search parameters (mass tolerance, modifications, FDR thresholds, etc.).",
                    "fa_icon": "far fa-file-code"
                },
                "msconvert_peak_picking": {
                    "type": "boolean",
                    "default": true,
                    "description": "Apply peak picking filter during MS file conversion.",
                    "help_text": "When enabled, applies vendor peak picking algorithm during conversion from raw to mzML format.",
                    "fa_icon": "fas fa-chart-line"
                },
                "protein_fasta": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to reference protein FASTA file.",
                    "help_text": "Reference protein database for proteomics searches. If not provided and a GENCODE genome is specified, will automatically use the protein FASTA from the GENCODE genome configuration.",
                    "fa_icon": "far fa-file-code"
                },
                "no_gencode": {
                    "type": "boolean",
                    "description": "Exclude GENCODE reference from proteome database.",
                    "help_text": "When enabled, only LRP-predicted or custom protein sequences will be used for proteomics searches, excluding GENCODE reference proteins.",
                    "fa_icon": "fas fa-ban"
                },
                "lrp_protein_fasta": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to pre-computed LRP protein FASTA for proteomics-only runs.",
                    "help_text": "Pre-computed LRP protein FASTA file (headers: transcript_id|gene_id|gene_name|pclass|status). Use this for proteomics-only runs with previously generated LRP protein sequences.",
                    "fa_icon": "far fa-file-code"
                },
                "lrp_gtf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to LRP CDS GTF from a previous run.",
                    "help_text": "LRP CDS GTF file from a previous run, paired with lrp_protein_fasta for proteomics-only runs.",
                    "fa_icon": "far fa-file-code"
                },
                "custom_protein_fasta": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to user-provided custom protein FASTA.",
                    "help_text": "User-provided custom protein FASTA file (headers: transcript_id|gene_id at minimum) for proteomics analysis.",
                    "fa_icon": "far fa-file-code"
                },
                "custom_gtf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to user-provided custom GTF with CDS entries.",
                    "help_text": "User-provided custom GTF file with CDS entries, paired with custom_protein_fasta.",
                    "fa_icon": "far fa-file-code"
                },
                "protein_search": {
                    "type": "string",
                    "default": "fragpipe",
                    "description": "Protein search engine to use for proteomics analysis.",
                    "help_text": "Choose between 'fragpipe' (supports DDA and DIA) or 'metamorpheus' (DDA only).",
                    "fa_icon": "fas fa-search",
                    "enum": ["fragpipe", "metamorpheus"]
                },
                "fragpipe_tools_dir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Directory to store FragPipe tools (MSFragger, IonQuant, DiaTracer).",
                    "help_text": "Location where FragPipe JAR files will be cached. These files are downloaded once and reused in future runs.",
                    "fa_icon": "fas fa-folder"
                },
                "fragpipe_first_name": {
                    "type": "string",
                    "description": "User's first name for FragPipe registration (optional for interactive mode).",
                    "help_text": "Required for non-interactive FragPipe setup. Leave empty for interactive mode.",
                    "fa_icon": "fas fa-user",
                    "hidden": true
                },
                "fragpipe_last_name": {
                    "type": "string",
                    "description": "User's last name for FragPipe registration (optional for interactive mode).",
                    "help_text": "Required for non-interactive FragPipe setup. Leave empty for interactive mode.",
                    "fa_icon": "fas fa-user",
                    "hidden": true
                },
                "fragpipe_email": {
                    "type": "string",
                    "description": "Email address for FragPipe registration (optional for interactive mode).",
                    "help_text": "Required for non-interactive FragPipe setup. Leave empty for interactive mode.",
                    "fa_icon": "fas fa-envelope",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
                    "hidden": true
                },
                "fragpipe_institution": {
                    "type": "string",
                    "description": "Institution/organization for FragPipe registration (optional for interactive mode).",
                    "help_text": "Required for non-interactive FragPipe setup. Leave empty for interactive mode.",
                    "fa_icon": "fas fa-university",
                    "hidden": true
                },
                "fragpipe_token": {
                    "type": ["string", "integer"],
                    "description": "6-digit verification token for FragPipe (optional for interactive mode).",
                    "help_text": "Required for non-interactive FragPipe setup. You'll receive this via email after registration. Leave empty for interactive mode.",
                    "fa_icon": "fas fa-key",
                    "pattern": "^[0-9]{6}$"
                },
                "fragpipe_license_accept": {
                    "type": "boolean",
                    "default": false,
                    "description": "Accept FragPipe license terms (required for non-interactive mode).",
                    "help_text": "Set to true to accept FragPipe license terms for non-interactive setup.",
                    "fa_icon": "fas fa-file-contract",
                    "hidden": true
                },
                "fragpipe_workflow": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to custom FragPipe workflow file (optional).",
                    "help_text": "Custom .workflow file for FragPipe. If not provided, default workflows will be auto-downloaded (LFQ-MBR for DDA, DIA_SpecLib_Quant for DIA).",
                    "fa_icon": "fas fa-file"
                },
                "fragpipe_threads": {
                    "type": "integer",
                    "description": "Number of threads for FragPipe.",
                    "help_text": "Number of threads for FragPipe analysis. If not specified, defaults to using task.cpus from process label.",
                    "fa_icon": "fas fa-microchip"
                },
                "fragpipe_decoy_tag": {
                    "type": "string",
                    "default": "rev_",
                    "description": "Decoy tag prefix for protein database.",
                    "help_text": "Prefix used to identify decoy sequences in the protein database.",
                    "fa_icon": "fas fa-tag"
                }
            }
        },
        "hpc_cluster_options": {
            "title": "HPC cluster options",
            "type": "object",
            "fa_icon": "fas fa-server",
            "description": "Options for HPC cluster execution.",
            "help_text": "These parameters can override default executor settings in slurm.config or lsf.config.",
            "properties": {
                "hpc_executor": {
                    "type": "string",
                    "description": "Override executor type (e.g., 'slurm', 'lsf', 'local').",
                    "help_text": "Specify the executor to use for job submission on HPC clusters.",
                    "fa_icon": "fas fa-cogs"
                },
                "hpc_queue": {
                    "type": "string",
                    "description": "Override queue/partition name for job submission.",
                    "help_text": "Specify the queue or partition to use for job submission on HPC clusters.",
                    "fa_icon": "fas fa-list"
                },
                "hpc_cluster_options": {
                    "type": "string",
                    "description": "Override cluster-specific options (e.g., '--account=myaccount').",
                    "help_text": "Additional cluster-specific options to pass to the job scheduler.",
                    "fa_icon": "fas fa-sliders-h"
                }
            }
        },
        "generic_options": {
            "title": "Generic options",
            "type": "object",
            "fa_icon": "fas fa-file-import",
            "description": "Less common options for the pipeline, typically set in a config file.",
            "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
            "properties": {
                "version": {
                    "type": "boolean",
                    "description": "Display version and exit.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "description": "Method used to save pipeline results to output directory.",
                    "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                    "fa_icon": "fas fa-copy",
                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                    "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})$",
                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
                    "hidden": true
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true
                },
                "max_multiqc_email_size": {
                    "type": "string",
                    "description": "File size limit when attaching MultiQC reports to summary emails.",
                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
                    "default": "25.MB",
                    "fa_icon": "fas fa-file-upload",
                    "hidden": true
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true
                },
                "hook_url": {
                    "type": "string",
                    "description": "Incoming hook URL for messaging service",
                    "fa_icon": "fas fa-people-group",
                    "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
                    "hidden": true
                },
                "multiqc_config": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Custom config file to supply to MultiQC.",
                    "fa_icon": "fas fa-cog",
                    "hidden": true
                },
                "multiqc_logo": {
                    "type": "string",
                    "description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file",
                    "fa_icon": "fas fa-image",
                    "hidden": true
                },
                "multiqc_methods_description": {
                    "type": "string",
                    "description": "Custom MultiQC yaml file containing HTML including a methods description.",
                    "fa_icon": "fas fa-cog"
                },
                "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
                },
                "pipelines_testdata_base_path": {
                    "type": "string",
                    "fa_icon": "far fa-check-circle",
                    "description": "Base URL or local path to location of pipeline test dataset files",
                    "default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
                    "hidden": true
                },
                "trace_report_suffix": {
                    "type": "string",
                    "fa_icon": "far calendar",
                    "description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
                    "hidden": true
                },
                "help": {
                    "type": ["boolean", "string"],
                    "description": "Display the help message."
                },
                "help_full": {
                    "type": "boolean",
                    "description": "Display the full detailed help message."
                },
                "show_hidden": {
                    "type": "boolean",
                    "description": "Display hidden parameters in the help message (only works when --help or --help_full are provided)."
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/reference_genome_options"
        },
        {
            "$ref": "#/$defs/isoseq_collapse_options"
        },
        {
            "$ref": "#/$defs/sqanti_transcript_options"
        },
        {
            "$ref": "#/$defs/predicted_proteome_options"
        },
        {
            "$ref": "#/$defs/proteomics_options"
        },
        {
            "$ref": "#/$defs/differential_analysis_options"
        },
        {
            "$ref": "#/$defs/multisample_only_inputs"
        },
        {
            "$ref": "#/$defs/hpc_cluster_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}