nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/bigbio/quantmsdiann/main/nextflow_schema.json",
    "title": "bigbio/quantmsdiann pipeline parameters",
    "description": "DIA-NN quantitative mass spectrometry workflow built following nf-core guidelines",
    "type": "object",
    "$defs": {
        "input_output_options": {
            "title": "Input/output options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": ["input", "outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.(?:csv|tsv|sdrf)$",
                    "description": "URI/path to an SDRF file in SDRF format with .sdrf, .tsv, or .csv extension. For more info see help text or docs.",
                    "help_text": "Input is specified by using a path or URI to a PRIDE Sample to Data Relation Format file (SDRF), e.g. as part of a submitted and annotated PRIDE experiment (see [here](https://github.com/bigbio/proteomics-metadata-standard/tree/master/annotated-projects) for examples). Input files will be downloaded and cached from the URIs specified in the SDRF file.\n\nThe SDRF file can have .sdrf, .tsv, or .csv extensions. An OpenMS-style experimental design will be generated based on the factor columns of the SDRF.\n\nThe following parameters are read **exclusively** from the SDRF file (required columns):\n\n    * `acquisition_method` (from 'Proteomics Data Acquisition Method' column),\n    * `labelling_type` (from 'Label' column),\n    * `enzyme` (from 'Enzyme' column),\n    * `fixed_mods` (from 'FixedModifications' column)\n\nThe following parameters are read from SDRF but can be **overridden via command line**:\n\n    * `precursor_mass_tolerance` (from 'PrecursorMassTolerance' column),\n    * `precursor_mass_tolerance_unit` (from 'PrecursorMassToleranceUnit' column),\n    * `fragment_mass_tolerance` (from 'FragmentMassTolerance' column),\n    * `fragment_mass_tolerance_unit` (from 'FragmentMassToleranceUnit' column),\n    * `variable_mods` (from 'VariableModifications' column)",
                    "fa_icon": "fas fa-file-csv"
                },
                "outdir": {
                    "type": "string",
                    "description": "The output directory where the results will be saved.",
                    "default": "./results",
                    "fa_icon": "fas fa-folder-open",
                    "format": "directory-path"
                },
                "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})$"
                },
                "multiqc_title": {
                    "type": "string",
                    "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
                    "fa_icon": "fas fa-file-signature"
                },
                "root_folder": {
                    "type": "string",
                    "description": "Root folder in which the spectrum files specified in the SDRF are searched",
                    "fa_icon": "fas fa-folder",
                    "help_text": "This optional parameter can be used to specify a root folder in which the spectrum files specified in the SDRF are searched.\nIt is usually used if you have a local version of the experiment already. Note that this option does not support recursive\nsearching yet."
                },
                "local_input_type": {
                    "type": "string",
                    "description": "Overwrite the file type/extension of the filename as specified in the SDRF",
                    "fa_icon": "fas fa-file-invoice",
                    "default": "mzML",
                    "help_text": "If the above [`--root_folder`](#root_folder) was given to load local input files, this overwrites the file type/extension of\nthe filename as specified in the SDRF. Usually used in case you have an mzML-converted version of the files already. Needs to be\none of 'mzML', 'raw', 'd', or 'dia' (the letter cases should match your files exactly). Compressed variants (.gz, .tar, .tar.gz, .zip) are supported for 'mzML', 'raw', and 'd' formats."
                }
            }
        },
        "sdrf_validation": {
            "title": "SDRF validation",
            "type": "object",
            "description": "Settings for validating the input SDRF file.",
            "default": "",
            "properties": {
                "use_ols_cache_only": {
                    "type": "boolean",
                    "description": "Use cached version of the Ontology Lookup Service (OLS).",
                    "fa_icon": "far fa-check-square",
                    "help_text": "Use only the cached version of the Ontology Lookup Service (OLS) for ontology term validation. This is useful if you don't want the pipeline to query internet services.",
                    "default": true
                }
            }
        },
        "protein_database": {
            "title": "Protein database",
            "type": "object",
            "description": "Settings that relate to the mandatory protein database and the optional generation of decoy entries. Note: Decoys for DIA will be created internally.",
            "default": "",
            "properties": {
                "database": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/fasta",
                    "pattern": "^\\S+\\.(?:fasta|fa)$",
                    "description": "The `fasta` protein database used during database search. *Note:* For DIA data, it must not contain decoys.",
                    "fa_icon": "fas fa-file",
                    "help_text": "Since the database is not included in an SDRF, this parameter always needs to be given to specify the input protein database\nwhen you run the pipeline. Remember to include contaminants (and decoys if not in DIA mode and if not added in the pipeline with [`--add_decoys`](#add_decoys))\n\n```bash\n--database '[path to fasta protein database]'\n```"
                }
            },
            "fa_icon": "fas fa-database",
            "required": ["database"]
        },
        "spectrum_preprocessing": {
            "title": "Spectrum preprocessing",
            "type": "object",
            "description": "Configure file conversion and preprocessing options.",
            "default": "",
            "properties": {
                "reindex_mzml": {
                    "type": "boolean",
                    "default": true,
                    "description": "Force initial re-indexing of input mzML files. Also fixes some common mistakes in slightly incomplete/outdated mzMLs. (Default: true for safety)",
                    "fa_icon": "far fa-check-square",
                    "help_text": "Force re-indexing in the beginning of the pipeline to make sure that indices are up-to-date."
                },
                "mzml_statistics": {
                    "type": "boolean",
                    "description": "Compute MS1/MS2 statistics from mzML files. Only runs on mzML files, .d files are always skipped.",
                    "help_text": "Enable to generate *_ms_info.parquet statistics for QC reporting. Only available for mzML files, Bruker .d files are always excluded.",
                    "fa_icon": "far fa-check-square"
                },
                "mzml_features": {
                    "type": "boolean",
                    "description": "Compute with mzmlstatistics step the features at MS1 level and output to a RAW file, only available for mzML files",
                    "help_text": "Compute with mzmlstatistics step the features at MS1 level and output to a RAW file, only available for mzML files",
                    "fa_icon": "far fa-check-square"
                }
            },
            "fa_icon": "far fa-chart-bar"
        },
        "database_search": {
            "title": "Database search",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "met_excision": {
                    "type": "boolean",
                    "description": "Database searches accounted for N-terminal methionine excision, a common co-translational modification where the initial methionine is enzymatically removed from proteins.",
                    "default": true,
                    "fa_icon": "far fa-check-square",
                    "help_text": "Database searches account for N-terminal methionine excision."
                },
                "allowed_missed_cleavages": {
                    "type": "integer",
                    "description": "Specify the maximum number of allowed missed enzyme cleavages in a peptide. The parameter is not applied if `unspecific cleavage` is specified as enzyme.",
                    "default": 2,
                    "fa_icon": "fas fa-sliders-h"
                },
                "precursor_mass_tolerance": {
                    "type": "integer",
                    "description": "Precursor mass tolerance used for database search. For High-Resolution instruments a precursor mass tolerance value of 5 ppm is recommended (i.e. 5). See also [`--precursor_mass_tolerance_unit`](#precursor_mass_tolerance_unit).",
                    "default": 5,
                    "fa_icon": "fas fa-sliders-h",
                    "help_text": "This value can be overridden via command line. If not specified, the value from the SDRF file will be used."
                },
                "precursor_mass_tolerance_unit": {
                    "type": "string",
                    "description": "Precursor mass tolerance unit used for database search. Possible values are 'ppm' (default) and 'Da'.",
                    "default": "ppm",
                    "fa_icon": "fas fa-sliders-h",
                    "enum": ["Da", "ppm"],
                    "help_text": "This value can be overridden via command line. If not specified, the value from the SDRF file will be used."
                },
                "fragment_mass_tolerance": {
                    "type": "number",
                    "description": "Fragment mass tolerance used for database search. The default of 0.03 Da is for high-resolution instruments.",
                    "default": 0.03,
                    "fa_icon": "fas fa-sliders-h",
                    "help_text": "This value can be overridden via command line. If not specified, the value from the SDRF file will be used."
                },
                "fragment_mass_tolerance_unit": {
                    "type": "string",
                    "description": "Fragment mass tolerance unit used for database search. Possible values are 'ppm' and 'Da' (default).",
                    "default": "Da",
                    "fa_icon": "fas fa-list-ol",
                    "help_text": "This value can be overridden via command line. If not specified, the value from the SDRF file will be used.",
                    "enum": ["Da", "ppm"]
                },
                "variable_mods": {
                    "type": "string",
                    "description": "A comma-separated list of variable modifications with their Unimod name to be searched during database search",
                    "default": "Oxidation (M)",
                    "fa_icon": "fas fa-tasks",
                    "help_text": "Specify which variable modifications should be applied to the database search (e.g. 'Oxidation (M)'). Use Unimod names in the style '({unimod name} ({optional term specificity} {optional origin})'. Multiple variable modifications can be specified comma separated (e.g. 'Carbamidomethyl (C),Oxidation (M)'). This value can be overridden via command line. If not specified, the value from the SDRF file will be used."
                },
                "min_precursor_charge": {
                    "type": "integer",
                    "description": "Minimum precursor ion charge. Omit the '+'",
                    "default": 2,
                    "fa_icon": "fas fa-sliders-h"
                },
                "max_precursor_charge": {
                    "type": "integer",
                    "description": "Maximum precursor ion charge. Omit the '+'",
                    "default": 4,
                    "fa_icon": "fas fa-sliders-h"
                },
                "min_peptide_length": {
                    "type": "integer",
                    "description": "Minimum peptide length to consider",
                    "default": 6,
                    "fa_icon": "fas fa-sliders-h"
                },
                "max_peptide_length": {
                    "type": "integer",
                    "description": "Maximum peptide length to consider",
                    "default": 40,
                    "fa_icon": "fas fa-sliders-h"
                },
                "max_mods": {
                    "type": "integer",
                    "description": "Maximum number of modifications per peptide. If this value is large, the search may take very long.",
                    "default": 3,
                    "fa_icon": "fas fa-sliders-h"
                },
                "min_pr_mz": {
                    "type": "number",
                    "description": "The minimum precursor m/z for the in silico library generation or library-free search",
                    "fa_icon": "fas fa-filter",
                    "default": 400
                },
                "max_pr_mz": {
                    "type": "number",
                    "description": "The maximum precursor m/z for the in silico library generation or library-free search",
                    "fa_icon": "fas fa-filter",
                    "default": 2400
                },
                "min_fr_mz": {
                    "type": "number",
                    "description": "The minimum fragment m/z for the in silico library generation or library-free search",
                    "fa_icon": "fas fa-filter",
                    "default": 100
                },
                "max_fr_mz": {
                    "type": "number",
                    "description": "The maximum fragment m/z for the in silico library generation or library-free search",
                    "fa_icon": "fas fa-filter",
                    "default": 1800
                }
            },
            "fa_icon": "fas fa-search"
        },
        "psm_re_scoring_general": {
            "title": "PSM re-scoring (general)",
            "type": "object",
            "description": "Choose between different rescoring/posterior probability calculation methods and set them up.",
            "default": "",
            "properties": {
                "pp_debug": {
                    "type": "integer",
                    "description": "Debug level when running the re-scoring. Logs become more verbose and at '>5' temporary files are kept.",
                    "fa_icon": "fas fa-bug",
                    "default": 0,
                    "hidden": true
                }
            },
            "fa_icon": "fas fa-star-half-alt"
        },
        "DIA-NN": {
            "title": "DIA-NN",
            "type": "object",
            "description": "Settings for DIA-NN - a universal software for data-independent acquisition (DIA) proteomics data processing.",
            "default": "",
            "properties": {
                "diann_version": {
                    "type": "string",
                    "description": "Specify the DIA-NN version to be used in the workflow.",
                    "fa_icon": "fas fa-tag"
                },
                "enable_mod_localization": {
                    "type": "boolean",
                    "description": "Enable or disable modification localization scoring in DIA-NN.",
                    "fa_icon": "fas fa-map-marker-alt"
                },
                "mod_localization": {
                    "type": "string",
                    "description": "Specify the modification localization parameters for DIA-NN.",
                    "fa_icon": "fas fa-cogs"
                },
                "mass_acc_automatic": {
                    "type": "boolean",
                    "default": true,
                    "description": "Choosing the MS2 mass accuracy setting automatically",
                    "fa_icon": "fas fa-toggle-on"
                },
                "scan_window_automatic": {
                    "type": "boolean",
                    "description": "Choosing scan_window setting automatically",
                    "default": true,
                    "fa_icon": "fas fa-toggle-on"
                },
                "scan_window": {
                    "type": "integer",
                    "description": "Set the scan window radius to a specific value",
                    "fa_icon": "fas fa-filter",
                    "help_text": " Ideally, should be approximately equal to the average number of data points per peak",
                    "default": 8
                },
                "mass_acc_ms2": {
                    "type": "number",
                    "description": "Set the MS2 mass accuracy (tolerance) to a specific value in ppm.",
                    "fa_icon": "fas fa-bullseye",
                    "help_text": "If specified, this overrides the automatic calibration. Corresponds to the --mass-acc parameter in DIA-NN.",
                    "default": 15
                },
                "mass_acc_ms1": {
                    "type": "number",
                    "description": "Set the MS1 mass accuracy (tolerance) to a specific value in ppm.",
                    "fa_icon": "fas fa-bullseye",
                    "help_text": "If specified, this overrides the automatic calibration. Corresponds to the --mass-acc-ms1 parameter in DIA-NN.",
                    "default": 15
                },
                "performance_mode": {
                    "type": "boolean",
                    "description": "Set Low RAM & High Speed Mode for DIANN, including min-corr, corr-diff, and time-corr-only three parameters",
                    "fa_icon": "far fa-check-square",
                    "default": true
                },
                "quick_mass_acc": {
                    "type": "boolean",
                    "description": "when choosing the MS2 mass accuracy setting automatically, DIA-NN will use a fast heuristical algorithm instead of IDs number optimisation",
                    "fa_icon": "far fa-check-square",
                    "default": true
                },
                "pg_level": {
                    "type": "integer",
                    "description": "Controls the protein inference mode",
                    "fa_icon": "fas fa-list-ol",
                    "enum": [0, 1, 2],
                    "default": 2
                },
                "precursor_qvalue": {
                    "type": "number",
                    "description": "Precursor-level q-value filtering threshold for the DIA-NN main report. Maps to --qvalue.",
                    "default": 0.01,
                    "fa_icon": "fas fa-filter",
                    "help_text": "Controls how strictly precursor identifications are filtered in the DIA-NN main report. For proteogenomics with variant databases, the standard 0.01 (1%) is recommended."
                },
                "matrix_qvalue": {
                    "type": "number",
                    "description": "Q-value threshold for DIA-NN output matrices (pr_matrix, pg_matrix, etc.). Maps to --matrix-qvalue.",
                    "default": 0.01,
                    "fa_icon": "fas fa-filter",
                    "help_text": "Controls the global q-value filtering applied when generating the quantification matrices. Default matches DIA-NN's built-in default of 1%."
                },
                "matrix_spec_q": {
                    "type": "number",
                    "description": "Run-specific protein q-value filter for protein/gene matrices. Maps to --matrix-spec-q.",
                    "default": 0.05,
                    "fa_icon": "fas fa-filter",
                    "help_text": "An additional run-specific protein-level FDR filter applied to the protein and gene matrices. Default matches DIA-NN's built-in default of 5%. For proteogenomics/variant detection, consider setting to 1.0 to retain variant proteins that lack sufficient unique peptides for protein-level confidence."
                },
                "species_genes": {
                    "type": "boolean",
                    "description": "Instructs DIA-NN to add the organism identifier to the gene names",
                    "fa_icon": "far fa-check-square"
                },
                "speclib": {
                    "type": "string",
                    "description": "The spectral library to use for DIA-NN",
                    "fa_icon": "fas fa-file",
                    "help_text": "If passed, will use that spectral library to carry out the DIA-NN search, instead of predicting one from the fasta file.",
                    "hidden": false
                },
                "report_decoys": {
                    "type": "boolean",
                    "description": "Save decoy PSMs to the main .parquet report for DIA-NN 2.0.*",
                    "fa_icon": "far fa-check-square",
                    "hidden": false
                },
                "export_xic": {
                    "type": "boolean",
                    "description": "instructs DIA-NN to extract MS1/fragment chromatograms for identified precursors within X seconds from the elution apex, with X set to 10s if not provided;equivalent to the 'XICs' option in the GUI",
                    "fa_icon": "far fa-check-square",
                    "hidden": false
                },
                "quantums": {
                    "type": "boolean",
                    "description": "Use legacy DIA-NN quantification algorithms (DIA-NN parameter --direct-quant); if true, QuantUMS is enabled.",
                    "fa_icon": "far fa-check-square",
                    "hidden": false
                },
                "quantums_train_runs": {
                    "type": "string",
                    "description": "Run index range for QuantUMS training (e.g., '0:5').",
                    "fa_icon": "fas fa-sliders-h",
                    "help_text": "Sets the DIA-NN parameter '--quant-train-runs'. Format: '[N1]:[N2]'. Instructs QuantUMS to train its parameters on runs with indices in the range N1 to N2 (inclusive).",
                    "hidden": false
                },
                "quantums_sel_runs": {
                    "type": "integer",
                    "description": "Number of automatically selected runs for QuantUMS training.",
                    "fa_icon": "fas fa-sliders-h",
                    "help_text": "Sets the DIA-NN parameter --quant-sel-runs. Format: [N]. QuantUMS will train its parameters on N automatically selected runs to speed up training in large experiments. N must be 6 or greater.",
                    "hidden": false
                },
                "quantums_params": {
                    "type": "string",
                    "description": "Pre-calculated QuantUMS parameters.",
                    "fa_icon": "fas fa-sliders-h",
                    "help_text": "Sets the DIA-NN parameter --quant-params. Provide previously obtained QuantUMS parameters to use instead of training new ones.",
                    "hidden": false
                },
                "scoring_mode": {
                    "type": "string",
                    "default": "generic",
                    "enum": ["generic", "proteoforms", "peptidoforms"],
                    "description": "DIA-NN scoring mode. 'generic' maximizes IDs (default). 'proteoforms' validates single-residue differences — recommended for proteogenomics/variant detection (requires DIA-NN >= 2.0). 'peptidoforms' provides extra peptidoform q-values for PTM analysis.",
                    "fa_icon": "fas fa-bullseye",
                    "help_text": "Controls DIA-NN's decoy generation strategy. In 'generic' mode, decoys are fully shuffled sequences. In 'proteoforms' mode, decoys differ by a single residue — directly modelling the confusion between canonical and variant peptides (e.g., COSMIC missense mutations). In 'peptidoforms' mode, generic q-values are calculated plus extra peptidoform-level q-values for PTM localization."
                },
                "aa_eq": {
                    "type": "boolean",
                    "default": false,
                    "description": "Treat I&L, Q&E, N&D as equivalent amino acids during reannotation. Essential for entrapment FDR benchmarks.",
                    "fa_icon": "fas fa-equals",
                    "help_text": "Maps to DIA-NN's --aa-eq flag. When enabled, peptides are matched to proteins considering isoleucine/leucine, glutamine/glutamic acid, and asparagine/aspartic acid as equivalent. This is essential when benchmarking FDR using entrapment databases, as without it the assessment measures the ability to distinguish deamidated peptides rather than true FDR."
                },
                "tims_sum": {
                    "type": "boolean",
                    "description": "Enable '--quant-tims-sum' for slice/scanning timsTOF methods (highly recommended for Synchro-PASEF).",
                    "fa_icon": "far fa-check-square",
                    "default": false
                },
                "im_window": {
                    "type": "number",
                    "description": "Set '--im-window' to ensure the IM extraction window is not smaller than the specified value.",
                    "fa_icon": "fas fa-filter"
                },
                "use_quant": {
                    "type": "boolean",
                    "description": "Set '--use-quant' to reuse existing .quant files if available.",
                    "fa_icon": "far fa-check-square",
                    "default": true
                },

                "channel_run_norm": {
                    "type": "boolean",
                    "description": "Set '--channel-run-norm'. Run-specific normalisation for multiplexing (e.g., Protein Turnover SILAC)",
                    "fa_icon": "far fa-check-square",
                    "default": false
                },
                "channel_spec_norm": {
                    "type": "boolean",
                    "description": "Set '--channel-spec-norm'. Channel-specific normalisation for multiplexing (Independent Samples)",
                    "fa_icon": "far fa-check-square",
                    "default": false
                },
                "skip_preliminary_analysis": {
                    "type": "boolean",
                    "description": "Skip the preliminary analysis step, thus use the passed spectral library as-is instead of generating a local consensus library.",
                    "fa_icon": "fas fa-forward",
                    "hidden": false
                },
                "debug_level": {
                    "type": "integer",
                    "description": "Debug level",
                    "default": 3,
                    "fa_icon": "fas fa-bug",
                    "enum": [0, 1, 2, 3, 4],
                    "hidden": true
                },
                "normalize": {
                    "type": "boolean",
                    "description": "Enable cross-run normalization between runs by diann.",
                    "default": true,
                    "fa_icon": "far fa-check-square"
                },
                "random_preanalysis": {
                    "type": "boolean",
                    "description": "Enable random selection of spectrum files to generate empirical library.",
                    "fa_icon": "far fa-check-square"
                },
                "random_preanalysis_seed": {
                    "type": "integer",
                    "description": "Set the random seed for the random selection of spectrum files to generate the empirical library.",
                    "default": 42,
                    "fa_icon": "fas fa-filter"
                },
                "empirical_assembly_ms_n": {
                    "type": "integer",
                    "description": "The number of randomly selected spectrum files.",
                    "default": 200,
                    "fa_icon": "fas fa-filter",
                    "hidden": true
                },
                "extra_args": {
                    "type": "string",
                    "description": "Extra arguments appended to all DIA-NN steps. Flags incompatible with specific steps are automatically stripped with a warning.",
                    "fa_icon": "fas fa-terminal",
                    "hidden": false,
                    "help_text": "Pass additional DIA-NN command-line arguments that will be appended to all DIA-NN steps (INSILICO_LIBRARY_GENERATION, PRELIMINARY_ANALYSIS, ASSEMBLE_EMPIRICAL_LIBRARY, INDIVIDUAL_ANALYSIS, FINAL_QUANTIFICATION). Flags that conflict with a specific step are automatically stripped with a warning. For step-specific overrides, use custom Nextflow config files with ext.args."
                },
                "dda": {
                    "type": "boolean",
                    "description": "Explicitly enable DDA mode. Normally auto-detected from the SDRF acquisition method column. Use only when SDRF lacks this column. Requires DIA-NN >= 2.3.2.",
                    "fa_icon": "fas fa-flask",
                    "default": false
                },
                "light_models": {
                    "type": "boolean",
                    "description": "Enable --light-models for 10x faster in-silico library generation (DIA-NN >= 2.0).",
                    "fa_icon": "fas fa-bolt",
                    "default": false
                },
                "export_quant": {
                    "type": "boolean",
                    "description": "Enable --export-quant for fragment-level parquet data export (DIA-NN >= 2.0).",
                    "fa_icon": "fas fa-file-export",
                    "default": false
                },
                "site_ms1_quant": {
                    "type": "boolean",
                    "description": "Enable --site-ms1-quant to use MS1 apex intensities for PTM site quantification (DIA-NN >= 2.0).",
                    "fa_icon": "fas fa-crosshairs",
                    "default": false
                },
                "enable_fine_tuning": {
                    "type": "boolean",
                    "description": "Enable DL model fine-tuning before the main analysis. Runs a tuning search on a file subset, fine-tunes RT/IM models, then runs the full pipeline with tuned models. Requires DIA-NN >= 2.3.2.",
                    "fa_icon": "fas fa-brain",
                    "default": false,
                    "help_text": "When enabled, Phase 0 runs before the main pipeline: (1) in-silico library generation with default models, (2) preliminary analysis + assembly on a subset of files (controlled by --tune_n_files), (3) fine-tuning RT/IM models on the resulting empirical library, (4) re-generation of the in-silico library with tuned models. The main pipeline then runs from preliminary analysis using the tuned library."
                },
                "tune_n_files": {
                    "type": "integer",
                    "description": "Number of files to use for the fine-tuning search. Use the largest/best-quality files.",
                    "fa_icon": "fas fa-layer-group",
                    "default": 3
                },
                "tune_fr": {
                    "type": "boolean",
                    "description": "Also fine-tune the fragmentation model (quality-sensitive — verify results vs base model).",
                    "fa_icon": "fas fa-flask",
                    "default": false
                },
                "tune_lr": {
                    "type": "number",
                    "description": "Fine-tuning learning rate (default in DIA-NN: 0.0005). Maps to --tune-lr.",
                    "fa_icon": "fas fa-sliders-h"
                },
                "enable_infin_dia": {
                    "type": "boolean",
                    "description": "Enable InfinDIA for ultra-large search spaces (DIA-NN >= 2.3.0). Experimental.",
                    "fa_icon": "fas fa-infinity",
                    "default": false
                },
                "pre_select": {
                    "type": "integer",
                    "description": "Set --pre-select N precursor limit for InfinDIA pre-search.",
                    "fa_icon": "fas fa-filter"
                },
                "save_speclib_tsv": {
                    "type": "boolean",
                    "default": false,
                    "description": "Save the TSV spectral library from the in-silico library generation step.",
                    "fa_icon": "fas fa-save",
                    "help_text": "When enabled, the human-readable TSV version of the spectral library produced by DIA-NN during the INSILICO_LIBRARY_GENERATION step is published to the output directory under `library_generation/`. By default this file is discarded as an intermediate."
                }
            },
            "fa_icon": "fas fa-braille"
        },
        "quality_control": {
            "title": "Quality control",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "enable_pmultiqc": {
                    "type": "boolean",
                    "description": "Enable generation of pmultiqc report? default: true",
                    "fa_icon": "fas fa-toggle-on",
                    "default": true
                },
                "pmultiqc_idxml_skip": {
                    "type": "boolean",
                    "description": "Skip idXML files (do not generate search engine scores) in pmultiqc report? default: 'true'",
                    "fa_icon": "fas fa-toggle-on",
                    "default": true
                },
                "contaminant_string": {
                    "type": "string",
                    "description": "Contaminant affix string for pmultiqc report. This parameter maps to --contaminant_affix in pmultiqc. default: 'CONT'",
                    "default": "CONT"
                }
            },
            "fa_icon": "fas fa-file-medical-alt"
        },
        "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"
                }
            }
        },
        "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
                },
                "skip_table_plots": {
                    "type": "boolean",
                    "description": "Skip protein/peptide table plots with pmultiqc for large dataset.",
                    "fa_icon": "fas fa-toggle-on"
                },
                "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 fa-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/protein_database"
        },
        {
            "$ref": "#/$defs/sdrf_validation"
        },
        {
            "$ref": "#/$defs/spectrum_preprocessing"
        },
        {
            "$ref": "#/$defs/database_search"
        },
        {
            "$ref": "#/$defs/psm_re_scoring_general"
        },
        {
            "$ref": "#/$defs/DIA-NN"
        },
        {
            "$ref": "#/$defs/quality_control"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}