nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/tnmquann/profiler_sourmash/main/nextflow_schema.json",
    "title": "Taxonomic Profiling Pipeline with Hostile and Sourmash",
    "description": "Pipeline for taxonomic profiling using Sourmash after cleaning reads with Hostile",
    "type": "object",
    "$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": ["input", "outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "exists": true,
                    "description": "Path to input CSV file containing sample information or directory containing FASTQ files"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "default": "./results",
                    "description": "The output directory where results will be saved"
                },
                "input_format": {
                    "type": "string",
                    "default": "csv",
                    "description": "Format of input files",
                    "enum": ["csv", "directory"]
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "description": "Method used to save pipeline results",
                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"]
                },
                "assembly_input": {
                    "type": "string",
                    "exists": true,
                    "description": "Path to CSV file containing pre-computed assemblies (optional). Skips preprocessing and assembly steps. Required columns: sample_id, run_id, group, assembler, fasta",
                    "help_text": "When supplied, only binning and downstream workflows are run. Must be used with --input_format csv. Reads must also be provided via --input parameter"
                }
            }
        },
        "database_options": {
            "title": "Database options",
            "type": "object",
            "description": "Reference database options required for taxonomic profiling",
            "properties": {
                "sourmash_database": {
                    "type": "string",
                    "pattern": "^.+$",
                    "exists": true,
                    "description": "Path to Sourmash database (.rocksdb, .zip, or directory)",
                    "help_text": "Required for bin classification and read-based profiling"
                },
                "sourmash_taxonomy_csv": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "description": "Path to taxonomy lineages CSV file for Sourmash",
                    "help_text": "Required when running workflows that use SOURMASH_TAXANNOTATE (READ_BASED, READ_BASED_SINGLERUN, BIN_CLASSIFICATION). The pipeline will error if missing."
                },
                "yacht_database": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to YACHT database configuration file",
                    "help_text": "Required only if using read-based profiling workflow"
                }
            }
        },
        "preprocessing_options": {
            "title": "Preprocessing options",
            "type": "object",
            "description": "Options for quality control and host removal",
            "properties": {
                "skip_preprocess": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip the entire preprocessing workflow (QC and host removal)",
                    "help_text": "When enabled, the pipeline will use input reads directly for downstream analysis, bypassing Fastp and Hostile steps"
                },
                "hostile_reference": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Directory containing Hostile reference files"
                },
                "hostile_index": {
                    "type": "string",
                    "default": "human-t2t-hla",
                    "description": "Name of the Hostile index to use"
                },
                "hostile_ref_name": {
                    "type": "string",
                    "default": "human-t2t-hla",
                    "description": "Reference name for Hostile (defaults to hostile_index if not set)"
                },
                "hostile_fetch_args": {
                    "type": "string",
                    "description": "Additional arguments for Hostile fetch"
                },
                "hostile_clean_args": {
                    "type": "string",
                    "default": "--debug",
                    "description": "Additional arguments for Hostile clean"
                },
                "fastp_adapter_fasta": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to adapter FASTA file for Fastp"
                },
                "fastp_save_trimmed_fail": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save reads that failed trimming"
                },
                "fastp_save_merged": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save merged paired-end reads"
                }
            }
        },
        "workflow_options": {
            "title": "Workflow options",
            "type": "object",
            "description": "Options controlling which workflows to run",
            "properties": {
                "enable_readbase": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run the read-based profiling subworkflow instead of assembly-based"
                },
                "enable_singlesketch": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable per-sample processing mode using SOURMASH_SKETCH and SOURMASH_GATHER instead of batch processing with SOURMASH_MANYSKETCH and SOURMASH_FASTMULTIGATHER. Useful for HPC environments where per-sample job control is needed."
                },
                "enable_rgi_bwt": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable RGI BWT analysis for antimicrobial resistance genes"
                }
            }
        },
        "assembly_options": {
            "title": "Assembly options",
            "type": "object",
            "description": "Options controlling assembly workflows",
            "properties": {
                "skip_megahit": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip the MEGAHIT assembly"
                },
                "skip_spades": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip the SPAdes assembly"
                },
                "skip_quast": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip QUAST assembly quality assessment"
                },
                "megahit_options": {
                    "type": "string",
                    "description": "Additional command-line options to pass to MEGAHIT"
                },
                "spades_options": {
                    "type": "string",
                    "description": "Additional command-line options to pass to SPAdes"
                },
                "megahit_fix_cpu_1": {
                    "type": "boolean",
                    "default": false,
                    "description": "Force MEGAHIT to use a single CPU"
                },
                "spades_fix_cpus": {
                    "type": "integer",
                    "default": -1,
                    "description": "Set a fixed number of CPUs for SPAdes when >= 0"
                }
            }
        },
        "contig_analysis_options": {
            "title": "Contig analysis options",
            "type": "object",
            "description": "Options for analyzing assembled contigs",
            "properties": {
                "skip_contig_analysis": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip the entire contig analysis subworkflow"
                },
                "skip_contig_annotation": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip contig annotation"
                },
                "annotation_tool": {
                    "type": "string",
                    "default": "pyrodigal",
                    "description": "Tool for contig annotation",
                    "enum": ["pyrodigal", "prokka"]
                },
                "save_contig_annotations": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save gene annotations in results directory"
                },
                "skip_genomad_e2e": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip geNomad virus/plasmid identification"
                },
                "genomad_db": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to local geNomad database"
                },
                "save_genomad_db": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save downloaded geNomad database"
                },
                "genomad_min_score": {
                    "type": "number",
                    "default": 0.7,
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Minimum score for geNomad classification"
                },
                "genomad_splits": {
                    "type": "integer",
                    "default": 1,
                    "minimum": 1,
                    "description": "Number of splits for geNomad processing"
                },
                "skip_skani_search": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip SKANI ANI-based classification"
                },
                "skani_db": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to SKANI database"
                },
                "skip_tiara_contigqc": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip TIARA domain classification for contigs"
                },
                "tiara_min_length": {
                    "type": "integer",
                    "default": 3000,
                    "minimum": 1000,
                    "description": "Minimum contig length for TIARA classification"
                },
                "genomad_e2e_options": {
                    "type": "string",
                    "default": "--enable-score-calibration",
                    "description": "Additional command-line options for geNomad end-to-end analysis"
                }
            }
        },
        "binning_options": {
            "title": "Binning options",
            "type": "object",
            "description": "Options for metagenomic binning",
            "properties": {
                "skip_binning": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip the entire binning workflow"
                },
                "skip_binning_bamabund": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip mapping reads to assemblies for binning"
                },
                "binprepare_mappertool": {
                    "type": "string",
                    "default": "bowtie2",
                    "description": "Mapper tool for binning preparation",
                    "enum": ["bowtie2", "bwamem2"]
                },
                "bowtie2_mode": {
                    "type": "string",
                    "description": "Bowtie2 alignment mode (e.g., '--very-sensitive')"
                },
                "save_assembly_mapped_reads": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save BAM and BAI files from read mapping"
                },
                "skip_metabat2": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip MetaBAT2 binning"
                },
                "skip_maxbin2": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip MaxBin2 binning"
                },
                "skip_concoct": {
                    "type": "boolean",
                    "default": true,
                    "description": "Skip CONCOCT binning"
                },
                "skip_comebin": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip COMEBin binning"
                },
                "skip_semibin": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip SemiBin2 binning"
                },
                "skip_vamb": {
                    "type": "boolean",
                    "default": true,
                    "description": "Skip VAMB binning"
                },
                "min_contig_size": {
                    "type": "integer",
                    "default": 1500,
                    "minimum": 1000,
                    "description": "Minimum contig size for binning (bp)"
                },
                "min_length_unbinned_contigs": {
                    "type": "integer",
                    "default": 1000000,
                    "description": "Minimum length for splitting unbinned contigs"
                },
                "max_unbinned_contigs": {
                    "type": "integer",
                    "default": 100,
                    "description": "Maximum number of unbinned contigs to split"
                },
                "metabat_rng_seed": {
                    "type": "integer",
                    "default": 1,
                    "description": "Random seed for MetaBAT2"
                },
                "semibin_environment": {
                    "type": "string",
                    "default": "human_gut",
                    "description": "SemiBin2 environment preset"
                }
            }
        },
        "binning_refinement_options": {
            "title": "Binning refinement options",
            "type": "object",
            "description": "Options for refining bins using DAS Tool or Binette",
            "properties": {
                "skip_binning_refinement": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip binning refinement workflow"
                },
                "refine_tool": {
                    "type": "string",
                    "default": "binette",
                    "description": "Tool for bin refinement",
                    "enum": ["dastool", "binette"]
                },
                "refine_bins_dastool_threshold": {
                    "type": "number",
                    "default": 0.5,
                    "minimum": 0,
                    "maximum": 1,
                    "description": "DAS Tool score threshold"
                },
                "refine_bins_binette_min_completeness": {
                    "type": "number",
                    "default": 40,
                    "minimum": 0,
                    "maximum": 100,
                    "description": "Binette minimum completeness threshold"
                },
                "refine_bins_binette_contamination_weight": {
                    "type": "number",
                    "default": 5,
                    "minimum": 0,
                    "description": "Binette contamination weight"
                },
                "checkm2_db": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to CheckM2 database (optional; will be downloaded if needed for Binette or CheckM2 Bin QC)",
                    "help_text": "If omitted and binqc_tool=checkm2 or refine_tool=binette, the pipeline downloads and configures the CheckM2 database."
                },
                "postbinning_input": {
                    "type": "string",
                    "default": "both",
                    "description": "Which bins to use for downstream analysis",
                    "enum": ["raw_bins_only", "refined_bins_only", "both"]
                }
            }
        },
        "bin_domain_classification_options": {
            "title": "Bin domain classification options",
            "type": "object",
            "description": "Options for classifying bins by domain",
            "properties": {
                "bin_domain_classification": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable bin domain classification workflow"
                },
                "bin_domain_classification_tool": {
                    "type": "string",
                    "default": "tiara",
                    "description": "Tool for domain classification",
                    "enum": ["tiara"]
                }
            }
        },
        "bin_qc_options": {
            "title": "Bin quality control options",
            "type": "object",
            "description": "Options for assessing bin quality",
            "properties": {
                "skip_binqc": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip bin quality control"
                },
                "binqc_tool": {
                    "type": "string",
                    "default": "checkm2",
                    "description": "Tool for bin quality assessment",
                    "enum": ["busco", "checkm", "checkm2"]
                },
                "busco_db": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to BUSCO database"
                },
                "busco_db_lineage": {
                    "type": "string",
                    "default": "auto",
                    "description": "BUSCO lineage dataset"
                },
                "save_busco_db": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save downloaded BUSCO database"
                },
                "busco_clean": {
                    "type": "boolean",
                    "default": true,
                    "description": "Clean up BUSCO temporary files"
                },
                "checkm_db": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to CheckM database"
                },
                "checkm_download_url": {
                    "type": "string",
                    "default": "https://zenodo.org/records/7401545/files/checkm_data_2015_01_16.tar.gz",
                    "description": "URL for CheckM database download"
                },
                "save_checkm_data": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save downloaded CheckM database"
                },
                "checkm2_db_version": {
                    "type": "integer",
                    "default": 14897628,
                    "description": "Zenodo record ID for CheckM2 database"
                },
                "save_checkm2_data": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save downloaded CheckM2 database"
                },
                "run_gunc": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run GUNC chimera detection"
                },
                "gunc_db": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Path to GUNC database"
                },
                "gunc_database_type": {
                    "type": "string",
                    "default": "progenomes",
                    "description": "GUNC database type",
                    "enum": ["progenomes", "gtdb"]
                },
                "gunc_save_db": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save downloaded GUNC database"
                },
                "assembly_stats_params": {
                    "type": "string",
                    "description": "Additional parameters for assembly statistics"
                }
            }
        },
        "bin_annotation_options": {
            "title": "Bin annotation options",
            "type": "object",
            "description": "Options for annotating bins",
            "properties": {
                "skip_bin_annotation": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip bin annotation workflow"
                },
                "bin_annotation_tool": {
                    "type": "string",
                    "default": "prokka",
                    "description": "Tool for bin annotation",
                    "enum": ["prokka", "bakta"]
                },
                "save_bin_annotations": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save annotation results"
                },
                "annotation_bakta_db": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to Bakta database"
                },
                "annotation_bakta_db_downloadtype": {
                    "type": "string",
                    "default": "full",
                    "description": "Bakta database type",
                    "enum": ["full", "light"]
                },
                "save_bakta_db": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save downloaded Bakta database"
                },
                "annotation_bakta_mincontiglen": {
                    "type": "integer",
                    "default": 1,
                    "minimum": 1,
                    "description": "Minimum contig length for Bakta (bp)"
                },
                "prokka_bins_fast_mode": {
                    "type": "boolean",
                    "default": false,
                    "description": "Use Prokka fast mode"
                },
                "annotation_bakta_gram": {
                    "type": "string",
                    "default": "?",
                    "description": "Gram staining for Bakta annotation",
                    "enum": ["+", "-", "?"]
                },
                "annotation_bakta_translationtable": {
                    "type": "integer",
                    "default": 11,
                    "description": "Translation table for Bakta annotation"
                }
            }
        },
        "bin_classification_options": {
            "title": "Bin classification options",
            "type": "object",
            "description": "Options for taxonomic classification of bins",
            "properties": {
                "skip_bin_classification": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip bin taxonomic classification"
                },
                "sourmash_output_format": {
                    "type": "string",
                    "default": "csv_summary",
                    "description": "Sourmash output format",
                    "enum": ["csv_summary", "krona", "lineage_summary"]
                },
                "sourmash_ksize": {
                    "type": "integer",
                    "default": 31,
                    "description": "k-mer size for Sourmash sketching"
                },
                "sourmash_thresholdbp": {
                    "type": "integer",
                    "description": "Threshold in base pairs for Sourmash gather"
                },
                "sourmash_profile": {
                    "type": "string",
                    "default": "dna,k=31,k=51,scaled=1000,abund",
                    "description": "Sourmash sketch profile"
                },
                "enable_copysketch": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save batch sketch files to output"
                },
                "enable_copysketch_singles": {
                    "type": "boolean",
                    "default": true,
                    "description": "Save individual single sketch files to output"
                },
                "skip_yacht": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip YACHT-based filtering and read-based results processing",
                    "help_text": "When enabled, the pipeline will skip YACHT analysis"
                },
                "yacht_ksize": {
                    "type": "integer",
                    "default": 31,
                    "description": "k-mer size for YACHT analysis (must match sourmash_ksize when using both)",
                    "help_text": "This value should be consistent with sourmash_ksize to ensure compatibility between Sourmash and YACHT workflows"
                }
            }
        },
        "rgi_options": {
            "title": "RGI options",
            "type": "object",
            "description": "Options for antimicrobial resistance gene identification",
            "properties": {
                "rgi_aligner": {
                    "type": "string",
                    "default": "kma",
                    "description": "RGI aligner",
                    "enum": ["kma", "bowtie2", "bwa"]
                },
                "rgi_include_wildcard": {
                    "type": "boolean",
                    "default": true,
                    "description": "Include wildcard variants in RGI"
                },
                "rgi_include_other_models": {
                    "type": "boolean",
                    "default": true,
                    "description": "Include other model types in RGI"
                },
                "rgi_bwt_args": {
                    "type": "string",
                    "default": "--clean",
                    "description": "Additional RGI BWT arguments"
                },
                "rgi_preparecarddb_dir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Directory for RGI database"
                }
            }
        },
        "pyrodigal_options": {
            "title": "Pyrodigal annotation options",
            "type": "object",
            "description": "Options for Pyrodigal gene prediction",
            "properties": {
                "annotation_pyrodigal_singlemode": {
                    "type": "boolean",
                    "default": false,
                    "description": "Use single-genome mode"
                },
                "annotation_pyrodigal_closed": {
                    "type": "boolean",
                    "default": false,
                    "description": "Disallow partial genes on contig edges"
                },
                "annotation_pyrodigal_transtable": {
                    "type": "integer",
                    "default": 11,
                    "description": "Translation table"
                },
                "annotation_pyrodigal_forcenonsd": {
                    "type": "boolean",
                    "default": false,
                    "description": "Force scan for motifs"
                }
            }
        },
        "prokka_options": {
            "title": "Prokka annotation options",
            "type": "object",
            "description": "Options for Prokka gene annotation",
            "properties": {
                "annotation_prokka_kingdom": {
                    "type": "string",
                    "default": "Bacteria",
                    "description": "Prokka kingdom",
                    "enum": ["Bacteria", "Archaea", "Mitochondria", "Viruses"]
                },
                "annotation_prokka_gcode": {
                    "type": "integer",
                    "default": 11,
                    "description": "Prokka genetic code"
                },
                "annotation_prokka_mincontiglen": {
                    "type": "integer",
                    "default": 1,
                    "minimum": 1,
                    "description": "Minimum contig size for annotation (bp)"
                },
                "annotation_prokka_compliant": {
                    "type": "boolean",
                    "default": true,
                    "description": "Force Genbank/ENA/DDJB compliance for Prokka annotation"
                },
                "annotation_prokka_coverage": {
                    "type": "integer",
                    "default": 80,
                    "minimum": 0,
                    "maximum": 100,
                    "description": "Minimum coverage percentage for Prokka annotation"
                },
                "annotation_prokka_evalue": {
                    "type": "number",
                    "default": 0.000001,
                    "minimum": 0,
                    "description": "E-value cut-off for Prokka similarity searches"
                }
            }
        },
        "misc_options": {
            "title": "Miscellaneous options",
            "type": "object",
            "description": "Other pipeline options",
            "properties": {
                "cleanup": {
                    "type": "boolean",
                    "default": false,
                    "description": "Clean up intermediate files after completion"
                },
                "cleanup_patterns": {
                    "type": "array",
                    "items": {
                        "type": "string"
                    },
                    "default": ["work", "intermediate_files", ".nextflow*", ".command.*", "process_tmp"],
                    "description": "List of file/directory patterns to clean up when cleanup is enabled"
                },
                "email": {
                    "type": "string",
                    "format": "email",
                    "description": "Email address for completion notification"
                },
                "enable_copymergedseqs": {
                    "type": "boolean",
                    "default": true,
                    "description": "Copy merged sequences to output"
                },
                "enable_copyintermediate": {
                    "type": "boolean",
                    "default": true,
                    "description": "Copy intermediate files to output"
                },
                "config_profile_name": {
                    "type": "string",
                    "description": "Institutional config name"
                },
                "config_profile_description": {
                    "type": "string",
                    "description": "Institutional config description"
                },
                "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
                }
            }
        },
        "resource_options": {
            "title": "Resource options",
            "type": "object",
            "description": "Global and profile-specific resource allocation limits",
            "properties": {
                "max_cpus": {
                    "type": "integer",
                    "default": 25,
                    "minimum": 1,
                    "description": "Maximum number of CPUs that can be requested for any process"
                },
                "max_memory": {
                    "type": "string",
                    "default": "120.GB",
                    "pattern": "^\\d+(\\.\\d+)?\\s*\\.?\\s*(K|M|G|T)?B$",
                    "description": "Maximum memory allocation that can be requested for any process"
                },
                "max_time": {
                    "type": "string",
                    "default": "24.h",
                    "pattern": "^\\d+(\\.\\d+)?\\s*\\.?\\s*(s|m|h|d)$",
                    "description": "Maximum time limit that can be requested for any process"
                }
            }
        }
    },
    "allOf": [
        { "$ref": "#/$defs/input_output_options" },
        { "$ref": "#/$defs/database_options" },
        { "$ref": "#/$defs/preprocessing_options" },
        { "$ref": "#/$defs/workflow_options" },
        { "$ref": "#/$defs/assembly_options" },
        { "$ref": "#/$defs/contig_analysis_options" },
        { "$ref": "#/$defs/binning_options" },
        { "$ref": "#/$defs/binning_refinement_options" },
        { "$ref": "#/$defs/bin_domain_classification_options" },
        { "$ref": "#/$defs/bin_qc_options" },
        { "$ref": "#/$defs/bin_annotation_options" },
        { "$ref": "#/$defs/bin_classification_options" },
        { "$ref": "#/$defs/rgi_options" },
        { "$ref": "#/$defs/pyrodigal_options" },
        { "$ref": "#/$defs/prokka_options" },
        { "$ref": "#/$defs/resource_options" },
        { "$ref": "#/$defs/misc_options" }
    ]
}