nextflow_schema.json

{
    "$schema": "http://json-schema.org/draft-07/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/hic/master/nextflow_schema.json",
    "title": "nf-core/hic pipeline parameters",
    "description": "Analysis of Chromosome Conformation Capture data (Hi-C)",
    "type": "object",
    "definitions": {
        "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": [
                "input"
            ],
            "properties": {
                "input": {
                    "type": "string",
                    "fa_icon": "fas fa-dna",
                    "description": "Input FastQ files.",
                    "help_text": "Use this to specify the location of your input FastQ files. For example:\n\n```bash\n--input 'path/to/data/sample_*_{1,2}.fastq'\n```\n\nPlease note the following requirements:\n\n1. The path must be enclosed in quotes\n2. The path must have at least one `*` wildcard character\n3. When using the pipeline with paired end data, the path must use `{1,2}` notation to specify read pairs.\n\nIf left unspecified, a default pattern is used: `data/*{1,2}.fastq.gz`"
                },
                "input_paths": {
                    "type": "string",
                    "hidden": true,
                    "description": "Input FastQ files for test only",
                    "default": "undefined"
                },
                "outdir": {
                    "type": "string",
                    "description": "The output directory where the results will be saved.",
                    "default": "./results",
                    "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": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Options for the reference genome indices used to align reads.",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Name of iGenomes reference.",
                    "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."
                },
                "fasta": {
                    "type": "string",
                    "fa_icon": "fas fa-font",
                    "description": "Path to FASTA genome file.",
                    "help_text": "If you have no genome reference available, the pipeline can build one using a FASTA file. This requires additional time and resources, so it's better to use a pre-build index if possible."
                },
                "igenomes_base": {
                    "type": "string",
                    "description": "Directory / URL base for iGenomes references.",
                    "default": "s3://ngi-igenomes/igenomes",
                    "fa_icon": "fas fa-cloud-download-alt",
                    "hidden": true
                },
                "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`."
                },
                "bwt2_index": {
                    "type": "string",
                    "description": "Full path to directory containing Bowtie index including base name. i.e. `/path/to/index/base`.",
                    "fa_icon": "far fa-file-alt"
                }
            }
        },
        "digestion_hi_c": {
            "title": "Digestion Hi-C",
            "type": "object",
            "description": "Parameters for protocols based on restriction enzyme",
            "default": "",
            "properties": {
                "digestion": {
                    "type": "string",
                    "default": "hindiii",
                    "description": "Name of restriction enzyme to automatically set the restriction_site and ligation_site options"
                },
                "restriction_site": {
                    "type": "string",
                    "default": "'A^AGCTT'",
                    "description": "Restriction motifs used during digestion. Several motifs (comma separated) can be provided."
                },
                "ligation_site": {
                    "type": "string",
                    "default": "'AAGCTAGCTT",
                    "description": "Expected motif after DNA ligation.  Several motifs (comma separated) can be provided."
                },
                "chromosome_size": {
                    "type": "string",
                    "description": "Full path to file specifying chromosome sizes (tab separated with chromosome name and size)`.",
                    "fa_icon": "far fa-file-alt",
                    "help_text": "If not specified, the pipeline will build this file from the reference genome file"
                },
                "restriction_fragments": {
                    "type": "string",
                    "description": "Full path to restriction fragment (bed) file.",
                    "fa_icon": "far fa-file-alt",
                    "help_text": "This file depends on the Hi-C protocols and digestion strategy. If not provided, the pipeline will build it using the --restriction_site option"
                },
                "save_reference": {
                    "type": "boolean",
                    "description": "If generated by the pipeline save the annotation and indexes in the results directory.",
                    "help_text": "Use this parameter to save all annotations to your results folder. These can then be used for future pipeline runs, reducing processing times.",
                    "fa_icon": "fas fa-save"
                },
                "save_nonvalid_pairs": {
                    "type": "boolean",
                    "description": "Save the non valid pairs detected by HiC-Pro.",
                    "help_text": "Use this parameter to save non valid pairs detected by HiC-Pro (dangling-end, self-circle, re-ligation, filtered).",
                    "fa_icon": "fas fa-save"
                }
            }
        },
        "dnase_hi_c": {
            "title": "DNAse Hi-C",
            "type": "object",
            "description": "Parameters for protocols based on DNAse digestion",
            "default": "",
            "properties": {
                "dnase": {
                    "type": "boolean",
                    "description": "For Hi-C protocols which are not based on enzyme digestion such as DNase Hi-C"
                },
                "min_cis_dist": {
                    "type": "integer",
                    "description": "Minimum distance between loci to consider. Useful for --dnase mode to remove spurious ligation products. Only values > 0 are considered"
                }
            }
        },
        "alignments": {
            "title": "Alignments",
            "type": "object",
            "description": "Parameters for reads aligments",
            "default": "",
            "fa_icon": "fas fa-bahai",
            "properties": {
                "split_fastq": {
                    "type": "boolean",
                    "description": "Split the reads into chunks before running the pipelne",
                    "fa_icon": "fas fa-dna"
                },
                "fastq_chunks_size": {
                    "type": "integer",
                    "description": "Read number per chunks if split_fastq is used",
                    "default": 20000000
                },
                "min_mapq": {
                    "type": "integer",
                    "default": 10,
                    "description": "Keep aligned reads with a minimum quality value"
                },
                "bwt2_opts_end2end": {
                    "type": "string",
                    "default": "'--very-sensitive -L 30 --score-min L,-0.6,-0.2 --end-to-end --reorder'",
                    "description": "Option for HiC-Pro end-to-end bowtie mapping"
                },
                "bwt2_opts_trimmed": {
                    "type": "string",
                    "default": "'--very-sensitive -L 20 --score-min L,-0.6,-0.2 --end-to-end --reorder'",
                    "description": "Option for HiC-Pro trimmed reads mapping"
                },
                "save_aligned_intermediates": {
                    "type": "boolean",
                    "description": "Save all BAM files during two-steps mapping"
                }
            }
        },
        "valid_pairs_detection": {
            "title": "Valid Pairs Detection",
            "type": "object",
            "description": "Options to call significant interactions",
            "default": "",
            "fa_icon": "fas fa-signature",
            "properties": {
                "keep_dups": {
                    "type": "boolean",
                    "description": "Keep duplicated reads"
                },
                "keep_multi": {
                    "type": "boolean",
                    "description": "Keep multi-aligned reads"
                },
                "max_insert_size": {
                    "type": "integer",
                    "description": "Maximum fragment size to consider. Only values > 0 are considered"
                },
                "min_insert_size": {
                    "type": "integer",
                    "description": "Minimum fragment size to consider. Only values > 0 are considered"
                },
                "max_restriction_fragment_size": {
                    "type": "integer",
                    "description": "Maximum restriction fragment size to consider. Only values > 0 are considered"
                },
                "min_restriction_fragment_size": {
                    "type": "integer",
                    "description": "Minimum restriction fragment size to consider. Only values > 0 are considered"
                },
                "save_interaction_bam": {
                    "type": "boolean",
                    "description": "Save a BAM file where all reads are flagged by their interaction classes"
                }
            }
        },
        "contact_maps": {
            "title": "Contact maps",
            "type": "object",
            "description": "Options to build Hi-C contact maps",
            "default": "",
            "fa_icon": "fas fa-chess-board",
            "properties": {
                "bin_size": {
                    "type": "string",
                    "pattern": "^(\\d+)(,\\d+)*$",
                    "default": "1000000,500000",
                    "description": "Resolution to build the maps (comma separated)"
                },
                "hicpro_maps": {
                    "type": "boolean",
                    "description": "Generate raw and normalized contact maps with HiC-Pro"
                },
                "ice_filter_low_count_perc": {
                    "type": "number",
                    "default": 0.02,
                    "description": "Filter low counts rows before HiC-Pro normalization"
                },
                "ice_filter_high_count_perc": {
                    "type": "integer",
                    "description": "Filter high counts rows before HiC-Pro normalization"
                },
                "ice_eps": {
                    "type": "number",
                    "default": 0.1,
                    "description": "Threshold for HiC-Pro ICE convergence"
                },
                "ice_max_iter": {
                    "type": "integer",
                    "default": 100,
                    "description": "Maximum number of iteraction for HiC-Pro ICE normalization"
                },
                "res_zoomify": {
                    "type": "string",
                    "default": "5000",
                    "description": "Maximum resolution to build mcool file"
                }
            }
        },
        "downstream_analysis": {
            "title": "Downstream Analysis",
            "type": "object",
            "description": "Set up downstream analysis from contact maps",
            "default": "",
            "properties": {
                "res_dist_decay": {
                    "type": "string",
                    "pattern": "^(\\d+)(,\\d+)*$",
                    "default": "1000000",
                    "description": "Resolution to build count/distance plot"
                },
                "tads_caller": {
                    "type": "string",
                    "default": "hicexplorer,insulation",
                    "description": "Define methods for TADs calling"
                },
                "res_tads": {
                    "type": "string",
                    "pattern": "^(\\d+)(,\\d+)*$",
                    "default": "40000,20000",
                    "description": "Resolution to run TADs callers (comma separated)"
                },
                "res_compartments": {
                    "type": "string",
                    "pattern": "^(\\d+)(,\\d+)*$",
                    "default": "250000",
                    "description": "Resolution for compartments calling"
                }
            }
        },
        "skip_options": {
            "title": "Skip options",
            "type": "object",
            "description": "Skip some steps of the pipeline",
            "default": "",
            "fa_icon": "fas fa-random",
            "properties": {
                "skip_maps": {
                    "type": "boolean",
                    "description": "Do not build contact maps"
                },
                "skip_dist_decay": {
                    "type": "boolean",
                    "description": "Do not run distance/decay plot"
                },
                "skip_tads": {
                    "type": "boolean",
                    "description": "Do not run TADs calling"
                },
                "skip_compartments": {
                    "type": "string",
                    "description": "Do not run compartments calling"
                },
                "skip_balancing": {
                    "type": "boolean",
                    "description": "Do not run cooler balancing normalization"
                },
                "skip_mcool": {
                    "type": "boolean",
                    "description": "Do not generate mcool file for Higlass visualization"
                },
                "skip_multiqc": {
                    "type": "boolean",
                    "description": "Do not generate MultiQC report"
                }
            }
        },
        "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": {
                "help": {
                    "type": "boolean",
                    "description": "Display help text.",
                    "hidden": true,
                    "fa_icon": "fas fa-question-circle"
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "hidden": true,
                    "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"
                    ]
                },
                "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
                },
                "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})$",
                    "hidden": true,
                    "help_text": "This works exactly as with `--email`, except emails are only sent if the workflow is not successful."
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true,
                    "help_text": "Set to receive plain-text e-mails instead of HTML formatted."
                },
                "max_multiqc_email_size": {
                    "type": "string",
                    "description": "File size limit when attaching MultiQC reports to summary emails.",
                    "default": "25.MB",
                    "fa_icon": "fas fa-file-upload",
                    "hidden": true,
                    "help_text": "If file generated by pipeline exceeds the threshold, it will not be attached."
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true,
                    "help_text": "Set to disable colourful command line output and live life in monochrome."
                },
                "multiqc_config": {
                    "type": "string",
                    "description": "Custom config file to supply to MultiQC.",
                    "fa_icon": "fas fa-cog",
                    "hidden": true
                },
                "tracedir": {
                    "type": "string",
                    "description": "Directory to keep pipeline Nextflow logs and reports.",
                    "default": "${params.outdir}/pipeline_info",
                    "fa_icon": "fas fa-cogs",
                    "hidden": true
                },
                "show_hidden_params": {
                    "type": "boolean",
                    "fa_icon": "far fa-eye-slash",
                    "description": "Show all params when using `--help`",
                    "hidden": true,
                    "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."
                }
            }
        },
        "max_job_request_options": {
            "title": "Max job request options",
            "type": "object",
            "fa_icon": "fab fa-acquisitions-incorporated",
            "description": "Set the top limit for requested resources for any single job.",
            "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
            "properties": {
                "max_cpus": {
                    "type": "integer",
                    "description": "Maximum number of CPUs that can be requested    for any single job.",
                    "default": 16,
                    "fa_icon": "fas fa-microchip",
                    "hidden": true,
                    "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
                },
                "max_memory": {
                    "type": "string",
                    "description": "Maximum amount of memory that can be requested for any single job.",
                    "default": "128.GB",
                    "fa_icon": "fas fa-memory",
                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
                    "hidden": true,
                    "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",
                    "description": "Maximum amount of time that can be requested for any single job.",
                    "default": "240.h",
                    "fa_icon": "far fa-clock",
                    "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
                    "hidden": true,
                    "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'`"
                }
            }
        },
        "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",
                    "help_text": "Provide git commit id for custom Institutional configs hosted at `nf-core/configs`. This was implemented for reproducibility purposes. Default: `master`.\n\n```bash\n## Download and use config file with following git commit id\n--custom_config_version d52db660777c4bf36546ddb188ec530c3ada1b96\n```"
                },
                "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 the `custom_config_base` option. For example:\n\n```bash\n## Download and unzip the config files\ncd /path/to/my/configs\nwget https://github.com/nf-core/configs/archive/master.zip\nunzip master.zip\n\n## Run the pipeline\ncd /path/to/my/data\nnextflow run /path/to/pipeline/ --custom_config_base /path/to/my/configs/configs-master/\n```\n\n> Note that the nf-core/tools helper package has a `download` command to download all required pipeline files + singularity containers + institutional configs in one go for you, to make this process easier.",
                    "fa_icon": "fas fa-users-cog"
                },
                "hostnames": {
                    "type": "string",
                    "description": "Institutional configs hostname.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_name": {
                    "type": "string",
                    "description": "Institutional config name",
                    "hidden": true
                },
                "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"
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/definitions/input_output_options"
        },
        {
            "$ref": "#/definitions/reference_genome_options"
        },
        {
            "$ref": "#/definitions/digestion_hi_c"
        },
        {
            "$ref": "#/definitions/dnase_hi_c"
        },
        {
            "$ref": "#/definitions/alignments"
        },
        {
            "$ref": "#/definitions/valid_pairs_detection"
        },
        {
            "$ref": "#/definitions/contact_maps"
        },
        {
            "$ref": "#/definitions/downstream_analysis"
        },
        {
            "$ref": "#/definitions/skip_options"
        },
        {
            "$ref": "#/definitions/generic_options"
        },
        {
            "$ref": "#/definitions/max_job_request_options"
        },
        {
            "$ref": "#/definitions/institutional_config_options"
        }
    ]
}