{
  "dataset": "MobiDB",
  "description": "MobiDB is a database of protein intrinsic disorder and related features. It integrates curated, derived, homology-based, and predicted annotations from multiple sources with explicit provenance tracking.",
  "version": "2026_07",
  "release_date": "2026-09-09",
  "url": "https://data.mobidb.org/releases/2026_07/",
  "schema_url": "https://data.mobidb.org/schemas/schema_2026_07.json",
  "homepage": "https://mobidb.org",
  "license": "CC-BY-4.0",
  "citation": {
    "text": "Piovesan D, et al. MobiDB: 10 years of intrinsically disordered proteins. Nucleic Acids Res. 2023;51(D1):D438-D444.",
    "doi": "10.1093/nar/gkac1065"
  },
  "coordinate_convention": "1-based inclusive (start and end positions are both included in the region)",
  "files": [
    {
      "name": "releases/2026_07/mobidb_silver.jsonl.gz",
      "size_bytes": 3539245882,
      "sha256": "ee8a2289ab43eb55b0537454f8488a6bbcfc89d6abe340a54bd2f7a270145edf",
      "format": "MobiDB JSON Lines (gzip-compressed)",
      "compression": "gzip",
      "description": "Complete MobiDB JSON records for the Silver tier (level >= 1, combining curated, homology, PDB-derived, and AlphaFold annotations). Full nested document structure.",
      "url": "https://data.mobidb.org/releases/2026_07/mobidb_silver.jsonl.gz"
    },
    {
      "name": "releases/2026_07/mobidblite_sprot.jsonl.gz",
      "size_bytes": 283078923,
      "sha256": "0a0f2e88d9bed3d724c7dda429e233133e685f2a8b5a87ca9befcf9ef90ef0a5",
      "format": "MobiDB JSON Lines (gzip-compressed)",
      "compression": "gzip",
      "description": "MobiDB-lite consensus disorder predictions for UniProt Swiss-Prot (reviewed canonical sequences).",
      "url": "https://data.mobidb.org/releases/2026_07/mobidblite_sprot.jsonl.gz"
    },
    {
      "name": "releases/2026_07/mobidblite_sprot_varsplic.jsonl.gz",
      "size_bytes": 33009595,
      "sha256": "b572b11ef638eaa4433651753d84531f5a017f9d1c5764dc28bf130c5d301007",
      "format": "MobiDB JSON Lines (gzip-compressed)",
      "compression": "gzip",
      "description": "MobiDB-lite consensus disorder predictions for UniProt Swiss-Prot alternative splice isoforms.",
      "url": "https://data.mobidb.org/releases/2026_07/mobidblite_sprot_varsplic.jsonl.gz"
    },
    {
      "name": "releases/2026_07/mobidblite_trembl.jsonl.gz",
      "size_bytes": 114303927133,
      "sha256": "e6b91b09e866f38c06f00e8c931bdfea5381c26a9207f9f04bf7f25d30d7bca2",
      "format": "MobiDB JSON Lines (gzip-compressed)",
      "compression": "gzip",
      "description": "MobiDB-lite consensus disorder predictions for UniProt TrEMBL (unreviewed sequences).",
      "url": "https://data.mobidb.org/releases/2026_07/mobidblite_trembl.jsonl.gz"
    },
    {
      "name": "releases/2026_07/proteins_silver_2026_07_annotations.parquet",
      "size_bytes": 874542879,
      "sha256": "79bd07c87a9c68fbadfa4a58a586be90280e4d3cca28c530f2682c2bbfa8eebd",
      "format": "Apache Parquet",
      "row_count": 151965897,
      "description": "One row per annotation region with provenance metadata (evidence level, source, feature type).",
      "url": "https://data.mobidb.org/releases/2026_07/proteins_silver_2026_07_annotations.parquet"
    },
    {
      "name": "releases/2026_07/proteins_silver_2026_07_residues.parquet",
      "size_bytes": 2717270505,
      "sha256": "02171ad725cace389644b6b1279e5f6b6e49670d2df213ad10e8fc6cf017197c",
      "format": "Apache Parquet",
      "row_count": 888855030,
      "description": "One row per residue position with binary annotation indicators and score columns for each feature.",
      "url": "https://data.mobidb.org/releases/2026_07/proteins_silver_2026_07_residues.parquet"
    }
  ]
}