{ "format_version": "1", "case": "microbiome", "title": "Microbiome study and sample finder", "question": "Find a shale microbiome study and inspect a sample of its biosamples.", "mode": "recorded", "simulation": false, "registry_revision": "2026-11-09", "generated_at": null, "replay_clock": "2026-11-09T00:00:00Z", "timestamp_note": "Envelope retrieval timestamps use a fixed replay clock, not publisher retrieval times. Actual fixture capture times appear in the manifest; null means unrecorded.", "fixtures": [ { "file": "nmdc-runtime.json", "sha256": "a47cb8d2a0a93dcec1b30c3de2eca0769c8e5fb4fe9eca8edda61eb580432b78", "captured_at": "2026-10-08T23:37:56.653277+00:00" } ], "limitations": [ "Study and sample metadata only; no sequences, assemblies or annotations were downloaded.", "At most five samples are shown; they do not establish study completeness or biological function.", "The publisher's access recipes distinguish dataset DOIs from award DOIs; a DOI alone does not establish free access." ], "steps": [ { "tool": "bio.search_studies", "args": { "text": "shale" }, "envelope": { "data": { "studies": [ { "study_id": "nmdc:sty-11-8fb6t785", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio and West Virginia, USA", "title": "Deep subsurface shale carbon reservoir microbial communities from Ohio and West Virginia, USA", "category": "research_study", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface" ], "description": "This project aims to improve the understanding of microbial diversity and metabolism in deep shale, with implications for novel enzyme discovery and energy development. This project was conducted along two Appalachian basin shales, the Marcellus and Utica/Point Pleasant formations in Pennsylvania and Ohio, respectively. Samples were collected from input and produced fluids up to a year after hydra\u2026", "investigators": [ { "name": "Kelly Wrighton", "orcid": "orcid:0000-0003-0434-4217" }, { "name": "Rebecca Daly", "orcid": "orcid:0000-0003-2223-7458" }, { "name": "Mikayla Borton", "orcid": "orcid:0000-0001-8037-4253" }, { "name": "Michael Wilkins", "orcid": "orcid:0000-0002-3595-0853" }, { "name": "David Hoyt", "orcid": "orcid:0000-0002-2857-719X" } ], "dois": [ { "doi": "10.25585/1487763", "category": "dataset_doi", "provider": "jgi" }, { "doi": "10.46936/jejc.proj.2014.48483/60005501", "category": "award_doi", "provider": "emsl" } ], "part_of": [] } ], "record_count": 1, "total_matches": 1, "studies_in_collection": 85, "offset": 0, "note": "Text matches every word in a study's name, title or description, without regard to case. Metadata only. Reads, assemblies and annotations are held at JGI, EMSL and the sequence archives; a study's DOIs in access_recipes lead to them and are never fetched here." }, "provenance": [ { "id": "source_01", "source_id": "nmdc-runtime", "steward": "Lawrence Berkeley National Laboratory", "funder": "Office of Science", "system": "National Microbiome Data Collaborative Runtime API", "dataset": "National Microbiome Data Collaborative Runtime API", "dataset_version": "current", "authority_level": "official_secondary", "access_path": "live", "source_updated_at": null, "retrieved_at": "2026-11-09T00:00:00Z", "cache_age_seconds": 0 } ], "evidence": [ { "id": "evidence_01", "source_ref": "source_01", "record_id": "nmdc:sty-11-8fb6t785", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": null, "transformations": [ "normalize", "drop_contact_details" ], "payload_hash": null, "raw_recovery": "available" } ], "coverage": { "registry": "covered", "execution": "complete", "pagination": "complete", "source_claim": "complete", "result": "hit", "sources_searched": [ "nmdc-runtime" ], "known_limitations": [ "Metadata, not sequence data. Reads, assemblies and annotations live in the sequence archives and at JGI, and are reached through a study's DOIs rather than through this source.", "Only 8 of 85 studies carry an ecosystem classification of their own; the rest are classified sample by sample. An ecosystem filter on studies therefore misses most of them, and the biosample filter is the one to use.", "Place is free text as submitted ('USA: Washington, Abby Road'), so a place search is a substring match and a state name may miss samples recorded only by site or coordinates.", "Studies NMDC has ingested, not every microbiome study. Most of the 85 are JGI or EMSL projects and a consortium study such as NEON's appears once with thousands of samples, so counts describe NMDC's holdings rather than the field." ] }, "warnings": [ { "code": "terms_note", "message": "No published rate limit and no data-use statement on the API itself; the data portal's usage terms were not found in a scripted read.", "source_id": "nmdc-runtime" } ], "access_recipes": [ { "kind": "doi", "uri": "https://doi.org/10.25585/1487763", "label": "Deep subsurface shale carbon reservoir microbial communities (dataset_doi)", "instructions": "Minted by jgi; returned as data and never fetched here.", "requires_account": false, "approximate_size": null }, { "kind": "doi", "uri": "https://doi.org/10.46936/jejc.proj.2014.48483/60005501", "label": "Deep subsurface shale carbon reservoir microbial communities (award_doi)", "instructions": "Minted by emsl; returned as data and never fetched here.", "requires_account": false, "approximate_size": null } ], "_execution": { "server": "doe-mcp", "server_version": "0.1.0.dev0", "tool": "bio.search_studies", "tool_contract_version": "1", "envelope_version": "1", "adapters": { "osti_family": "1", "opendatasoft": "1", "json_document": "1", "curated": "1", "eia_v2": "1", "fueleconomy": "1", "text_feed": "1", "postgrest": "1", "federal_register": "1", "vips": "1", "daymet": "1", "essdive": "1", "esgf": "1", "sage": "1", "optimade": "1", "basis_sets": "1", "facility_status": "1", "gcam_csv": "1", "nmdc": "1", "none": "1", "self_registry": "1" }, "registry_revision": "2026-11-09", "request_id": "recorded-workflow" } } }, { "tool": "bio.search_biosamples", "args": { "study_id": "nmdc:sty-11-8fb6t785", "rows": 5 }, "envelope": { "data": { "biosamples": [ { "sample_id": "nmdc:bsm-11-gvp5zp51", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio, USA - Utica-2 Time Series 2014_10_11", "studies": [ "nmdc:sty-11-8fb6t785" ], "collected": "2014-10-11", "latitude": 40.178, "longitude": -81.073, "place": "USA: Ohio", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface", "Shale gas reservoir", "Flow back/Produced fluids" ], "env_broad_scale": "ENVO:00000446", "env_local_scale": "ENVO:01000941", "env_medium": "ENVO:00002194", "depth_m": { "value": 2000.0 } }, { "sample_id": "nmdc:bsm-11-yvzvbr38", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio, USA - Utica-2 Time Series 2014_10_10", "studies": [ "nmdc:sty-11-8fb6t785" ], "collected": "2014-10-10", "latitude": 40.178, "longitude": -81.073, "place": "USA: Ohio", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface", "Shale gas reservoir", "Flow back/Produced fluids" ], "env_broad_scale": "ENVO:00000446", "env_local_scale": "ENVO:01000941", "env_medium": "ENVO:00002194", "depth_m": { "value": 2000.0 } }, { "sample_id": "nmdc:bsm-11-7b566r47", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio, USA - Utica-2 Time Series 2014_10_18", "studies": [ "nmdc:sty-11-8fb6t785" ], "collected": "2014-10-18", "latitude": 40.178, "longitude": -81.073, "place": "USA: Ohio", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface", "Shale gas reservoir", "Flow back/Produced fluids" ], "env_broad_scale": "ENVO:00000446", "env_local_scale": "ENVO:01000941", "env_medium": "ENVO:00002194", "depth_m": { "value": 2000.0 } }, { "sample_id": "nmdc:bsm-11-byzpm179", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio, USA - Utica-2 Time Series 2014_10_16", "studies": [ "nmdc:sty-11-8fb6t785" ], "collected": "2014-10-16", "latitude": 40.178, "longitude": -81.073, "place": "USA: Ohio", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface", "Shale gas reservoir", "Flow back/Produced fluids" ], "env_broad_scale": "ENVO:00000446", "env_local_scale": "ENVO:01000941", "env_medium": "ENVO:00002194", "depth_m": { "value": 2000.0 } }, { "sample_id": "nmdc:bsm-11-kmpwgz16", "name": "Deep subsurface shale carbon reservoir microbial communities from Ohio, USA - Utica-2 Time Series 2014_10_20", "studies": [ "nmdc:sty-11-8fb6t785" ], "collected": "2014-10-20", "latitude": 40.178, "longitude": -81.073, "place": "USA: Ohio", "ecosystem": [ "Environmental", "Terrestrial", "Deep subsurface", "Shale gas reservoir", "Flow back/Produced fluids" ], "env_broad_scale": "ENVO:00000446", "env_local_scale": "ENVO:01000941", "env_medium": "ENVO:00002194", "depth_m": { "value": 2000.0 } } ], "record_count": 5, "total_matches": 23, "page": 1, "filter_applied": { "associated_studies": "nmdc:sty-11-8fb6t785" }, "note": "Sample metadata as submitted. ecosystem_type matches NMDC's whole value without regard to case ('soil', 'Freshwater'); env_medium and place match a substring without regard to case; collected matches the start of the date as written ('2017', '2017-06'). Depth is reported only where it was stated in metres. Metadata only. Reads, assemblies and annotations are held at JGI, EMSL and the sequence archives; a study's DOIs in access_recipes lead to them and are never fetched here." }, "provenance": [ { "id": "source_01", "source_id": "nmdc-runtime", "steward": "Lawrence Berkeley National Laboratory", "funder": "Office of Science", "system": "National Microbiome Data Collaborative Runtime API", "dataset": "National Microbiome Data Collaborative Runtime API", "dataset_version": "current", "authority_level": "official_secondary", "access_path": "live", "source_updated_at": null, "retrieved_at": "2026-11-09T00:00:00Z", "cache_age_seconds": 0 } ], "evidence": [ { "id": "evidence_01", "source_ref": "source_01", "record_id": "nmdc:bsm-11-gvp5zp51", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": "2014-10-11", "transformations": [ "normalize" ], "payload_hash": null, "raw_recovery": "available" }, { "id": "evidence_02", "source_ref": "source_01", "record_id": "nmdc:bsm-11-yvzvbr38", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": "2014-10-10", "transformations": [ "normalize" ], "payload_hash": null, "raw_recovery": "available" }, { "id": "evidence_03", "source_ref": "source_01", "record_id": "nmdc:bsm-11-7b566r47", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": "2014-10-18", "transformations": [ "normalize" ], "payload_hash": null, "raw_recovery": "available" }, { "id": "evidence_04", "source_ref": "source_01", "record_id": "nmdc:bsm-11-byzpm179", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": "2014-10-16", "transformations": [ "normalize" ], "payload_hash": null, "raw_recovery": "available" }, { "id": "evidence_05", "source_ref": "source_01", "record_id": "nmdc:bsm-11-kmpwgz16", "locator": null, "retrieved_at": "2026-11-09T00:00:00Z", "effective_at": "2014-10-20", "transformations": [ "normalize" ], "payload_hash": null, "raw_recovery": "available" } ], "coverage": { "registry": "covered", "execution": "complete", "pagination": "truncated", "source_claim": "complete", "result": "hit", "sources_searched": [ "nmdc-runtime" ], "known_limitations": [ "Metadata, not sequence data. Reads, assemblies and annotations live in the sequence archives and at JGI, and are reached through a study's DOIs rather than through this source.", "Only 8 of 85 studies carry an ecosystem classification of their own; the rest are classified sample by sample. An ecosystem filter on studies therefore misses most of them, and the biosample filter is the one to use.", "Place is free text as submitted ('USA: Washington, Abby Road'), so a place search is a substring match and a state name may miss samples recorded only by site or coordinates.", "Studies NMDC has ingested, not every microbiome study. Most of the 85 are JGI or EMSL projects and a consortium study such as NEON's appears once with thousands of samples, so counts describe NMDC's holdings rather than the field." ] }, "warnings": [ { "code": "terms_note", "message": "No published rate limit and no data-use statement on the API itself; the data portal's usage terms were not found in a scripted read.", "source_id": "nmdc-runtime" } ], "_execution": { "server": "doe-mcp", "server_version": "0.1.0.dev0", "tool": "bio.search_biosamples", "tool_contract_version": "1", "envelope_version": "1", "adapters": { "osti_family": "1", "opendatasoft": "1", "json_document": "1", "curated": "1", "eia_v2": "1", "fueleconomy": "1", "text_feed": "1", "postgrest": "1", "federal_register": "1", "vips": "1", "daymet": "1", "essdive": "1", "esgf": "1", "sage": "1", "optimade": "1", "basis_sets": "1", "facility_status": "1", "gcam_csv": "1", "nmdc": "1", "none": "1", "self_registry": "1" }, "registry_revision": "2026-11-09", "request_id": "recorded-workflow" } } } ] }