Aurora-MCP

{ "version": "1.0", "description": "Aurora-MCP data catalog with canonical fields, aliases, and join semantics.", "datasets": { "coconut": { "title": "COCONUT natural products (Nordic subset)", "source": "https://coconut.naturalproducts.net/", "description": "Subset of COCONUT compounds mapped to Nordic plant organisms with SMILES metadata.", "license": "CC0 (COCONUT); retain attribution when redistributing", "last_update": "2025-09", "path": "data/coconut_csv-09-2025_FI_NO_plants.csv", "delimiter": "TAB", "encoding": "UTF-8", "primary_key": ["identifier"], "fields": { "identifier": { "type": "string", "canonical": "coconut_id" }, "name": { "type": "string", "canonical": "compound_name", "aliases": ["compound"] }, "canonical_smiles": { "type": "string", "canonical": "smiles" }, "organisms": { "type": "string", "semantics": "species_list_pipe" } }, "notes": [ "Despite the .csv extension the file is TAB-delimited.", "Organism names are pipe-separated and normalized to lowercase during ingest." ] }, "coconut_all": { "title": "COCONUT natural products (all compounds)", "source": "https://coconut.naturalproducts.net/", "description": "Full COCONUT export used for broader compound-to-organism joins.", "license": "CC0 (COCONUT); retain attribution when redistributing", "last_update": "2025-09", "path": "data/coconut_csv-09-2025.csv", "delimiter": "TAB", "encoding": "UTF-8", "primary_key": ["identifier"], "fields": { "identifier": { "type": "string", "canonical": "coconut_id" }, "name": { "type": "string", "canonical": "compound_name", "aliases": ["compound"] }, "organisms": { "type": "string", "semantics": "species_list_pipe" } }, "notes": [ "Despite the .csv extension the file is TAB-delimited.", "Identifier is dropped by downstream apps after load." ] }, "laji": { "title": "Laji.fi species (Finland) — filtered export", "source": "https://laji.fi/", "description": "Species-level Laji.fi export with Finland observation counts for join with GBIF.", "license": "CC BY (Laji.fi; respect upstream terms)", "last_update": "2025-09", "path": "data/laji2_fi.txt", "delimiter": "TAB", "encoding": "UTF-8", "primary_key": ["Identifier"], "fields": { "Scientific name": { "type": "string", "canonical": "species_name" }, "Identifier": { "type": "string", "canonical": "laji_id" }, "Observation count from Finland": { "type": "integer", "canonical": "obs_fi_laji" }, "Genus, Scientific name": { "type": "string", "canonical": "genus_laji" } }, "derived_columns": { "name": "Lowercased copy of 'Scientific name'.", "url_laji": "https://laji.fi/taxon/{Identifier}/occurrence" } }, "gbif": { "title": "GBIF plants (Finland/Norway merged)", "source": "https://www.gbif.org/", "description": "Merged GBIF slice for plants observed in Finland and Norway with latitude-band counts.", "license": "GBIF per-record licensing (CC0 / CC-BY / CC-BY-NC); retain provenance.", "last_update": "2025-09", "path": "data/gbif_plants_FI_NO_merged.tsv", "delimiter": "TAB", "encoding": "UTF-8", "primary_key": ["speciesKey"], "fields": { "canonicalName": { "type": "string", "canonical": "species_name", "aliases": ["scientificName"] }, "genus": { "type": "string", "canonical": "genus" }, "genusKey": { "type": "integer", "canonical": "genus_key" }, "speciesKey": { "type": "integer", "canonical": "species_key" }, "obs_FI": { "type": "integer", "canonical": "obs_fi_gbif" }, "obs_NO": { "type": "integer", "canonical": "obs_no_gbif" }, "count_FI_60N": { "type": "integer", "canonical": "obs_fi_60" }, "count_NO_60N": { "type": "integer", "canonical": "obs_no_60" }, "count_FI_66N": { "type": "integer", "canonical": "obs_fi_66" }, "count_NO_66N": { "type": "integer", "canonical": "obs_no_66" } }, "derived_columns": { "name": "Lowercased copy of canonicalName.", "genus_gbif": "Lowercased copy of genus.", "url_gbif": "https://www.gbif.org/species/{speciesKey}" } }, "plants_genera": { "title": "Nordic plant genera list", "source": "Derived from Laji.fi and GBIF exports", "description": "Lowercased plant genera used as a whitelist for filtering COCONUT organisms.", "license": "CC0 (derived list); verify upstream licensing when redistributing", "last_update": "2025-09", "path": "data/plants_genera.txt", "delimiter": "NEWLINE", "encoding": "UTF-8", "primary_key": ["genus"], "fields": { "genus": { "type": "string" } }, "usage": [ "Filter COCONUT organisms to Nordic plant genera.", "Support genus-level aggregations." ] }, "inhibitors": { "title": "All mitochondrial Complex I inhibitors (AI-augmented PubMed mining)", "description": "Aggregated list of compounds linked to Complex I inhibition via PubMed mining and curation.", "creator": "Daniel Nicorici", "institution": "University of Helsinki, Klefström Lab", "date_created": "2025-10-13", "license": "CC BY 4.0 — attribution required for reuse or redistribution", "path": "data/all_mito_complex_I_inhibitors.txt", "delimiter": "TAB", "encoding": "UTF-8", "primary_key": ["compound"], "fields": { "compound": { "type": "string", "canonical": "compound_name", "aliases": ["name"] }, "pubmed_references": { "type": "integer" }, "known_status": { "type": "string", "enum": ["known", "new"] }, "confidence": { "type": "string", "enum": ["low", "low-medium", "medium", "high"] }, "pubmed_ids": { "type": "string", "semantics": "pmid_list_semicolon" } }, "data_origin": { "sources": [ "PubMed baseline and update XMLs (NCBI)", "AI classification using GPT-4.1-mini (YES/probablyYES → inhibitor)", "Manual curation of high-confidence outputs", "Known inhibitors reference list" ], "extraction_method": "Generative AI screening of PubMed abstracts referencing Complex I inhibition followed by manual review." }, "intended_use": [ "Benchmarking mitochondrial Complex I inhibitor discovery.", "Cross-linking with COCONUT or Aurora domain datasets." ], "notes": [ "File is TAB-delimited with a single header row.", "pubmed_ids contains ';'-separated unique PMIDs sorted ascending." ] } }, "joins": [ { "name": "species_join_laji_gbif", "left": { "dataset": "laji", "field": "Scientific name" }, "right": { "dataset": "gbif", "field": "canonicalName" }, "key_semantics": "species_name_normalized", "transforms": ["lowercase", "strip"] }, { "name": "genus_join_laji_gbif", "left": { "dataset": "laji", "field": "Genus, Scientific name" }, "right": { "dataset": "gbif", "field": "genus" }, "key_semantics": "genus_name_normalized", "transforms": ["lowercase", "strip", "unhyphen", "remove_cross_sign"] }, { "name": "coconut_species_to_laji", "left": { "dataset": "coconut", "field": "organisms" }, "right": { "dataset": "laji", "field": "Scientific name" }, "key_semantics": "species_list_pipe→species_name_normalized", "transforms": ["split_pipe", "lowercase", "strip"] }, { "name": "coconut_species_to_gbif", "left": { "dataset": "coconut", "field": "organisms" }, "right": { "dataset": "gbif", "field": "canonicalName" }, "key_semantics": "species_list_pipe→species_name_normalized", "transforms": ["split_pipe", "lowercase", "strip"] }, { "name": "coconut_all_species_to_laji", "left": { "dataset": "coconut_all", "field": "organisms" }, "right": { "dataset": "laji", "field": "Scientific name" }, "key_semantics": "species_list_pipe→species_name_normalized", "transforms": ["split_pipe", "lowercase", "strip"] }, { "name": "coconut_all_species_to_gbif", "left": { "dataset": "coconut_all", "field": "organisms" }, "right": { "dataset": "gbif", "field": "canonicalName" }, "key_semantics": "species_list_pipe→species_name_normalized", "transforms": ["split_pipe", "lowercase", "strip"] }, { "name": "inhibitors_to_coconut_by_compound", "left": { "dataset": "inhibitors", "field": "compound" }, "right": { "dataset": "coconut", "field": "name" }, "key_semantics": "compound_name_normalized", "transforms": ["lowercase", "strip", "collapse_spaces"] }, { "name": "inhibitors_to_coconut_all_by_compound", "left": { "dataset": "inhibitors", "field": "compound" }, "right": { "dataset": "coconut_all", "field": "name" }, "key_semantics": "compound_name_normalized", "transforms": ["lowercase", "strip", "collapse_spaces"] } ], "semantics": { "species_name_normalized": "Lowercased, trimmed scientific name (DwC:scientificName).", "genus_name_normalized": "Lowercased, trimmed genus (DwC:genus), punctuation/cross sign removed.", "species_list_pipe": "Pipe-separated list of scientific names in a single cell.", "compound_name_normalized":"Lowercased, trimmed compound name with multiple spaces collapsed.", "pmid_list_semicolon": "Semicolon-separated list of PubMed IDs stored as a single string." }, "transforms_supported": { "lowercase": "Convert to lower case.", "strip": "Trim leading/trailing whitespace.", "unhyphen": "Replace '-' with a single space.", "remove_cross_sign": "Remove the multiplication sign '×'.", "split_pipe": "Split field on '|' and explode to multiple rows before join.", "collapse_spaces": "Collapse consecutive spaces to a single space." }, "standards": { "species_name": "dwc:scientificName", "genus": "dwc:genus" } }