Configuration file

fasta-lake init --template <name> writes an example fastalake.json; fasta-lake validate checks one. Three fields are required: database.sources, peptide_evidence.predictions_dir and output.directory. Everything else has a default. The templates below are generated from the code; the field semantics are documented in the fasta_lake.config module.

minimalmetaproteomicsclinicalfull

{
  "acquisition": "dda",
  "search_engine": "sage",
  "database": {
    "sources": [
      {
        "tag": "REF",
        "path": "proteins.fasta"
      }
    ]
  },
  "peptide_evidence": {
    "predictions_dir": "./predictions"
  },
  "output": {
    "directory": "./output"
  }
}

{
  "acquisition": "dda",
  "search_engine": "sage",
  "database": {
    "sources": [
      {
        "tag": "UHGG",
        "priority": 1,
        "path": "/data/uhgp-100.faa",
        "type": "reference"
      },
      {
        "tag": "GMGC",
        "priority": 2,
        "path": "/data/GMGC10.100AA.faa",
        "type": "reference"
      },
      {
        "tag": "GMSC",
        "priority": 3,
        "path": "/data/GMSC10.100AA.faa",
        "type": "reference"
      },
      {
        "tag": "Entrap_Arabidopsis",
        "priority": 100,
        "path": "/data/arabidopsis_thaliana.fasta",
        "type": "entrapment"
      }
    ],
    "output": "reference_lake.fasta"
  },
  "sequence_quality": {
    "reject_poly_runs": true,
    "reject_low_complexity": true
  },
  "peptide_evidence": {
    "predictions_dir": "/data/alphanovo_results",
    "min_length": 8,
    "max_length": 50,
    "min_score": 0.0,
    "top_percent": 0.3,
    "normalize_il": true
  },
  "complexity": {
    "enabled": true,
    "auto_recommend": true
  },
  "inference": {
    "strategy": "species_budget",
    "min_peptides": 1,
    "strain_resolution": false,
    "keep_entrapment": true
  },
  "entrapment": {
    "enabled": true,
    "method": "phylogenetic",
    "source": "/data/arabidopsis_thaliana.fasta",
    "n_proteins": 1000,
    "expected_fdr": 0.01
  },
  "clustering": {
    "enabled": true,
    "identity": 0.97,
    "coverage": 0.8
  },
  "output": {
    "directory": "./output",
    "write_stats": true,
    "write_hits_tsv": true,
    "write_audit_log": true,
    "provenance_tracking": true
  }
}

{
  "acquisition": "dda",
  "search_engine": "sage",
  "database": {
    "sources": [
      {
        "tag": "SwissProt",
        "priority": 1,
        "path": "/data/uniprot_sprot_human.fasta",
        "type": "reference"
      },
      {
        "tag": "TrEMBL",
        "priority": 2,
        "path": "/data/uniprot_trembl_human.fasta",
        "type": "reference"
      },
      {
        "tag": "gnomAD",
        "priority": 3,
        "path": "/data/gnomad_variants.fasta",
        "type": "variant"
      },
      {
        "tag": "cRAP",
        "priority": 99,
        "path": "/data/cRAP_contaminants.fasta",
        "type": "contaminant"
      },
      {
        "tag": "Entrap_Arabidopsis",
        "priority": 100,
        "path": "/data/arabidopsis_thaliana.fasta",
        "type": "entrapment"
      }
    ],
    "output": "clinical_lake.fasta"
  },
  "sequence_quality": {
    "min_length": 6,
    "max_length": 50000,
    "reject_poly_runs": true,
    "poly_run_length": 10,
    "reject_low_complexity": true,
    "low_complexity_threshold": 0.3,
    "reject_fragments": true,
    "fragment_length_threshold": 100
  },
  "peptide_evidence": {
    "predictions_dir": "/data/alphanovo_results",
    "min_length": 8,
    "max_length": 50,
    "min_score": 0.5,
    "top_percent": 0.5,
    "normalize_il": true
  },
  "complexity": {
    "enabled": true,
    "auto_recommend": true,
    "report_metrics": [
      "hit_rate",
      "species_richness",
      "peptide_diversity",
      "db_coverage"
    ]
  },
  "inference": {
    "strategy": "razor",
    "min_peptides": 1,
    "strain_resolution": true,
    "keep_contaminants": true,
    "keep_entrapment": true
  },
  "entrapment": {
    "enabled": true,
    "method": "phylogenetic",
    "source": "/data/arabidopsis_thaliana.fasta",
    "n_proteins": 1000,
    "expected_fdr": 0.01
  },
  "output": {
    "directory": "./output",
    "write_stats": true,
    "write_hits_tsv": true,
    "write_audit_log": true,
    "provenance_tracking": true
  }
}

{
  "database": {
    "sources": [
      {
        "tag": "UHGG",
        "priority": 1,
        "path": "/data/uhgp-100.faa"
      },
      {
        "tag": "GMGC",
        "priority": 2,
        "path": "/data/GMGC10.100AA.faa"
      }
    ],
    "output": "reference_lake.fasta"
  },
  "sequence_quality": {
    "min_length": 6,
    "max_length": 50000,
    "reject_poly_runs": false,
    "poly_run_length": 10,
    "reject_low_complexity": false,
    "low_complexity_threshold": 0.3,
    "reject_fragments": false,
    "fragment_length_threshold": 100
  },
  "peptide_evidence": {
    "predictions_dir": "/data/alphanovo_results",
    "min_length": 8,
    "max_length": 50,
    "min_score": 0.0,
    "top_percent": 0.3,
    "normalize_il": true
  },
  "complexity": {
    "enabled": false,
    "auto_recommend": true,
    "report_metrics": [
      "hit_rate",
      "species_richness",
      "peptide_diversity"
    ]
  },
  "inference": {
    "strategy": "species_budget",
    "min_peptides": 1,
    "strain_resolution": false,
    "keep_contaminants": true,
    "keep_entrapment": true
  },
  "entrapment": {
    "enabled": false,
    "method": "phylogenetic",
    "source": "",
    "n_proteins": 1000,
    "expected_fdr": 0.01
  },
  "clustering": {
    "enabled": true,
    "identity": 0.97,
    "coverage": 0.8
  },
  "output": {
    "directory": "./output",
    "write_stats": true,
    "write_hits_tsv": true,
    "write_audit_log": false,
    "provenance_tracking": true
  },
  "rust": {
    "fasta_extractor": null,
    "lake_builder": null,
    "threads": null
  }
}