{
  "dataset_key": "calcofi_2022-edna",
  "provider": {
    "key": "calcofi",
    "short": "CalCOFI",
    "name": "California Cooperative Oceanic Fisheries Investigations",
    "url": "https://calcofi.org",
    "registered": true
  },
  "dataset": "2022-edna",
  "dataset_name": "CalCOFI October 2022 Vertebrate eDNA",
  "dataset_name_short": "2022 Vertebrate eDNA",
  "category": {
    "name": "Genomics & eDNA",
    "realm": "bio",
    "icon": "cat-genomics",
    "order": 13,
    "description": "Metabarcoding and environmental DNA — ASV tables, eDNA-derived abundance and density",
    "registered": true
  },
  "color": "#2e8b57",
  "visibility": "public",
  "description_md": "eDNA metabarcoding survey of vertebrates from water samples collected during the October 2022 CalCOFI cruise. Water filters from CalCOFI/GEMCAP stations off Southern California were run through one or two molecular assays: a mitochondrial D-loop assay (cetacean detections, incl. Delphinus and Megaptera novaeangliae) and a 12S rRNA \"MiFish\" assay (fish detections). Published as an intercalibration exercise (source datasetID \"CalCOFI_Intercal\") on GBIF/OBIS, linked to Patin et al. 2026 (Methods in Ecology and Evolution, https://doi.org/10.1111/2041-210x.70370). Sequence read counts are a semi-quantitative signal of PCR-amplified DNA, not abundance, and are not comparable between assays. Published as detections only: edna_presence = 1 and the read counts. The source archive holds positive detections only, so the absence of a row for a filter and taxon is not a non-detection for this dataset (a filter or assay run with no detection is simply missing, and absence cannot be inferred); this differs from sio_cetacean-edna, where 0 means not detected in a sequenced sample.\n",
  "keywords": [
    "eDNA",
    "metabarcoding",
    "dolphins",
    "rare targets"
  ],
  "attribution": {
    "citation_main": "Patin N, ODonnell G (2026). CalCOFI October 2022 Vertebrate eDNA. Version 1.2. Occurrence dataset. https://doi.org/10.15468/n52j6r\n",
    "citation_others": [],
    "doi": "10.15468/n52j6r",
    "license": "CC-BY-4.0",
    "license_name": "Creative Commons Attribution 4.0 International",
    "license_url": "https://creativecommons.org/licenses/by/4.0/",
    "acknowledgement": "This work was made possible by the Office of Naval Research Multidisciplinary University Research Initiative (MURI) funding for MMARINeDNA (award no.: N00014-22-1-2719) with additional support from the National Science Foundation (award no.: OCE-2224726). It includes data generated at the UC San Diego IGM Genomics Center utilizing an Illumina NovaSeq 6000 that was purchased with funding from a National Institutes of Health SIG grant (no.: S10 OD026929). We thank the captain and crew of the NOAA Ship Reuben Lasker, Rachel Pound from CalCOFI and Harrison Huang and Dylan Inskeep from the California Department of Fish and Wildlife for their assistance with sample collection.\n",
    "contact": "mailto:nvpatin@ucsd.edu",
    "pi_names": [
      "Nastassia Patin"
    ],
    "creators": [
      {
        "name": "Nastassia Patin",
        "organization": "Scripps Institution of Oceanography, UC San Diego",
        "orcid": "0000-0001-8522-7682",
        "email": "nvpatin@ucsd.edu",
        "role": null
      },
      {
        "name": "Garret O'Donnell",
        "organization": "Scripps - California Cooperative Oceanic Fisheries Investigations",
        "orcid": "0009-0003-3710-8576",
        "email": "gdonnell@ucsd.edu",
        "role": null
      }
    ],
    "funding": "ONR MURI N00014-22-1-2719; NSF OCE-2224726",
    "source_accessed": "2026-10-01"
  },
  "links": {
    "calcofi_org": null,
    "data_source": "https://www.gbif.org/dataset/10524092-539d-4ea4-8539-2e91ad8581a9",
    "workflow": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html",
    "page": "https://calcofi.io/datasets/calcofi_2022-edna/"
  },
  "coverage": {
    "realm": "bio",
    "temporal": "2022-10 to 2022-10",
    "year_min": 2022,
    "year_max": 2022,
    "years": [
      {
        "year": 2022,
        "n_obs": 148,
        "n_roots": 47
      }
    ],
    "spatial": "33.8–36.3°N, 122.8–119.4°W",
    "bbox": {
      "lat_min": 33.8101,
      "lat_max": 36.3464,
      "lon_min": -122.8364,
      "lon_max": -119.4034
    },
    "bbox_robust": {
      "lat_min": 33.8898665845,
      "lat_max": 36.34642,
      "lon_min": -122.6210783,
      "lon_max": -119.4034367,
      "n_positions": 148
    },
    "months": [
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      0,
      148,
      0,
      0
    ],
    "n_obs": 148,
    "n_roots": 47,
    "n_stations": 13,
    "n_variables": 3,
    "n_taxa": 19,
    "depth_min_m": 5,
    "depth_max_m": 380,
    "variables": [
      {
        "name": "edna_presence",
        "units": "dimensionless",
        "uri": null,
        "category": "Genomics & eDNA"
      },
      {
        "name": "edna_reads_12s",
        "units": "reads",
        "uri": null,
        "category": "Genomics & eDNA"
      },
      {
        "name": "edna_reads_dloop",
        "units": "reads",
        "uri": null,
        "category": "Genomics & eDNA"
      }
    ],
    "taxa": [
      {
        "taxon_key": "worms:137094",
        "scientific_name": "Delphinus delphis",
        "common_name": "Short-Beaked Common Dolphin",
        "rank": "Species",
        "n_obs": 56
      },
      {
        "taxon_key": "worms:137015",
        "scientific_name": "Delphinus",
        "common_name": "common dolphins",
        "rank": "Genus",
        "n_obs": 34
      },
      {
        "taxon_key": "worms:272286",
        "scientific_name": "Engraulis mordax",
        "common_name": "Northern anchovy",
        "rank": "Species",
        "n_obs": 10
      },
      {
        "taxon_key": "worms:254349",
        "scientific_name": "Leuroglossus",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 6
      },
      {
        "taxon_key": "worms:280366",
        "scientific_name": "Cololabis saira",
        "common_name": "Pacific saury",
        "rank": "Species",
        "n_obs": 6
      },
      {
        "taxon_key": "worms:126846",
        "scientific_name": "Coryphaena hippurus",
        "common_name": "Common dolphinfish",
        "rank": "Species",
        "n_obs": 4
      },
      {
        "taxon_key": "worms:137092",
        "scientific_name": "Megaptera novaeangliae",
        "common_name": "Humpback Whale",
        "rank": "Species",
        "n_obs": 4
      },
      {
        "taxon_key": "worms:137111",
        "scientific_name": "Tursiops truncatus",
        "common_name": "Bottlenose Dolphin",
        "rank": "Species",
        "n_obs": 4
      },
      {
        "taxon_key": "worms:272458",
        "scientific_name": "Merluccius productus",
        "common_name": "Pacific hake or whiting",
        "rank": "Species",
        "n_obs": 4
      },
      {
        "taxon_key": "worms:126063",
        "scientific_name": "Scomber",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:126065",
        "scientific_name": "Thunnus",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:137102",
        "scientific_name": "Orcinus orca",
        "common_name": "Killer Whale",
        "rank": "Species",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:137119",
        "scientific_name": "Physeter macrocephalus",
        "common_name": "Sperm Whale",
        "rank": "Species",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:158806",
        "scientific_name": "Haemulon",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:203974",
        "scientific_name": "Sardinops",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:270239",
        "scientific_name": "Paranthias",
        "common_name": null,
        "rank": "Genus",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:272733",
        "scientific_name": "Symbolophorus californiensis",
        "common_name": "California lanternfish",
        "rank": "Species",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:275234",
        "scientific_name": "Balistes polylepis",
        "common_name": "Finescale triggerfish",
        "rank": "Species",
        "n_obs": 2
      },
      {
        "taxon_key": "worms:275694",
        "scientific_name": "Citharichthys sordidus",
        "common_name": "Pacific sanddab",
        "rank": "Species",
        "n_obs": 2
      }
    ],
    "life_stages": [],
    "contributes_to": []
  },
  "tables": [
    "sample",
    "obs",
    "sample_measurement",
    "taxon",
    "dataset_taxon",
    "measurement_type"
  ],
  "objects": [
    {
      "table": "obs",
      "scope": "partition",
      "shared": false,
      "path": "ducklake/tables/obs/dataset_key=calcofi_2022-edna/f4bd530899502d593fd4a585/data_0.parquet",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/obs/dataset_key=calcofi_2022-edna/f4bd530899502d593fd4a585/data_0.parquet",
      "table_description": "The occurrence-headline long table: one scalar measurement per row, environmental (`realm = 'env'`) and biological (`realm = 'bio'`) together.",
      "bytes": 5879,
      "sha256": "d633639338a6a7700e84cfa8aac31f395a2a6e788a37bd62ee9d941f021ae38f",
      "since": "v2026.10.05"
    }
  ],
  "since_version": "v2026.10.05",
  "distributions": [
    {
      "kind": "service",
      "url": "https://storage.googleapis.com/calcofi-db/stac/collections/calcofi_2022-edna/collection.json",
      "format": "stac",
      "id": "calcofi_2022-edna",
      "title": "STAC collection",
      "status": "current"
    },
    {
      "kind": "download",
      "url": "https://storage.googleapis.com/calcofi-db/ducklake/tables/obs/dataset_key=calcofi_2022-edna/f4bd530899502d593fd4a585/data_0.parquet",
      "format": "parquet",
      "table": "obs",
      "scope": "partition",
      "shared": false,
      "title": "obs (this dataset's rows)",
      "table_description": "The occurrence-headline long table: one scalar measurement per row, environmental (`realm = 'env'`) and biological (`realm = 'bio'`) together.",
      "bytes": 5879,
      "sha256": "d633639338a6a7700e84cfa8aac31f395a2a6e788a37bd62ee9d941f021ae38f",
      "since": "v2026.10.05",
      "status": "current"
    },
    {
      "kind": "notebook",
      "url": "https://calcofi.io/workflows/ingest_calcofi_2022-edna.html",
      "format": "html",
      "title": "ingest notebook",
      "status": "current"
    },
    {
      "kind": "source",
      "url": "https://www.gbif.org/dataset/10524092-539d-4ea4-8539-2e91ad8581a9",
      "portal": "other",
      "title": "source",
      "status": "external"
    }
  ],
  "registrations": [
    {
      "portal": "erddap",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "obis",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "edi",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "ncei",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "caloos",
      "status": "n/a",
      "issues": []
    },
    {
      "portal": "zenodo",
      "status": "published",
      "url": "https://doi.org/10.5281/zenodo.22281994",
      "id": "10.5281/zenodo.22281994",
      "title": "CalCOFI Integrated Database (the release deposit)",
      "note": "as part of the integrated database release"
    }
  ],
  "status": {
    "stage": "validated",
    "priority": null,
    "gh_issue": null,
    "blockers": "Un-held 2026-10-04 (Ben): ships in the next release as detections only (edna_presence = 1 and read counts; the archive holds positive detections only, so no row is not a non-detection). Q08 (omitted zero-detection runs) stays open, now high; Q07 (read filtering, controls) and Q06 (ASV/PCR-replicate summing) stay open. 2026-10-01 rework of PR #118 (review decision B4): obs = one row per filter x taxon x measurement_type -- edna_presence (shared with sio_cetacean-edna; 1 only, positive detections) + edna_reads_dloop / edna_reads_12s (reads summed over ASVs and PCR replicates); no obs_attribute; sample_key calcofi_2022-edna:filter:<parentEventID>; sample_measurement carries nutrients/chl_fluor/oxygen_mg_l/dna_concentration + per-assay raw and filtered read totals; 'OTUs or ASVs assigned to taxa' held back (Q04: equals the summed reads). Rendered + uploaded to gs://calcofi-db/ingest/calcofi_2022-edna/ 2026-10-01: sample 47 / obs 148 / sample_measurement 482. site_key/parent_sample_key NULL pending Q05.",
    "publish_policy": null,
    "updated": "2026-10-01",
    "questions_open": 8,
    "questions_dataset": [
      {
        "label": "Q10",
        "field": "citation_main",
        "status": "open"
      }
    ]
  }
}