{"database": "MABPAT_dataset", "private": false, "path": "/MABPAT_dataset", "size": 115957760, "tables": [{"name": "Applicants", "columns": ["Applicant_name", "Applicant_type", "Applicant_country"], "primary_keys": ["Applicant_name"], "count": 1326, "hidden": false, "fts_table": "Applicants_fts", "foreign_keys": {"incoming": [{"other_table": "Applications", "column": "Applicant_name", "other_column": "Applicant_name"}], "outgoing": []}, "private": false}, {"name": "Applications", "columns": ["Patent_application_number", "Applicant_name", "Year_of_application", "Patent_system"], "primary_keys": ["Patent_application_number"], "count": 4779, "hidden": false, "fts_table": "Applications_fts", "foreign_keys": {"incoming": [{"other_table": "Applications_Sequences", "column": "Patent_application_number", "other_column": "Patent_application_number"}], "outgoing": [{"other_table": "Applicants", "column": "Applicant_name", "other_column": "Applicant_name"}]}, "private": false}, {"name": "Applications_Sequences", "columns": ["Patent_application_number", "Sequence_accession_number", "ID"], "primary_keys": ["ID"], "count": 557532, "hidden": false, "fts_table": "Applications_Sequences_fts", "foreign_keys": {"incoming": [], "outgoing": [{"other_table": "Sequences", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}, {"other_table": "Applications", "column": "Patent_application_number", "other_column": "Patent_application_number"}]}, "private": false}, {"name": "Marine_Sequences", "columns": ["Sequence_accession_number", "Species_name", "GC_content", "Sequence_length", "Sequence_status", "Is_protein_coding_sequence", "Is_annotated"], "primary_keys": ["Sequence_accession_number"], "count": 104467, "hidden": false, "fts_table": "Marine_Sequences_fts", "foreign_keys": {"incoming": [{"other_table": "Marine_Sequences_Protein_Annotations", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}], "outgoing": [{"other_table": "Sequences", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}, {"other_table": "Marine_Species", "column": "Species_name", "other_column": "Species_name"}]}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations", "columns": ["Sequence_accession_number", "f_header", "sseqid", "stitle", "pident", "evalue", "qcovs", "annotation_source"], "primary_keys": ["Sequence_accession_number"], "count": 71149, "hidden": false, "fts_table": "Marine_Sequences_Protein_Annotations_fts", "foreign_keys": {"incoming": [], "outgoing": [{"other_table": "Marine_Sequences", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}]}, "private": false}, {"name": "Marine_Species", "columns": ["Species_name", "Domain", "Phylum", "Taxonomic_source", "Is_deep_sea", "Deep_sea_source", "is_ABNJ_present"], "primary_keys": ["Species_name"], "count": 1639, "hidden": false, "fts_table": "Marine_Species_fts", "foreign_keys": {"incoming": [{"other_table": "Marine_Sequences", "column": "Species_name", "other_column": "Species_name"}], "outgoing": []}, "private": false}, {"name": "Sequences", "columns": ["Sequence_accession_number", "Species_name", "Is_marine_species"], "primary_keys": ["Sequence_accession_number"], "count": 557484, "hidden": false, "fts_table": "Sequences_fts", "foreign_keys": {"incoming": [{"other_table": "Applications_Sequences", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}, {"other_table": "Marine_Sequences", "column": "Sequence_accession_number", "other_column": "Sequence_accession_number"}], "outgoing": []}, "private": false}, {"name": "Applicants_fts", "columns": ["Applicant_name", "Applicants_fts", "rank"], "primary_keys": [], "count": 1326, "hidden": true, "fts_table": "Applicants_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applicants_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applicants_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 12, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applicants_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 1326, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applicants_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 10, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_Sequences_fts", "columns": ["Patent_application_number", "Sequence_accession_number", "Applications_Sequences_fts", "rank"], "primary_keys": [], "count": 557532, "hidden": true, "fts_table": "Applications_Sequences_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_Sequences_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_Sequences_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 2028, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_Sequences_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 557532, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_Sequences_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 2161, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_fts", "columns": ["Patent_application_number", "Applicant_name", "Applications_fts", "rank"], "primary_keys": [], "count": 4779, "hidden": true, "fts_table": "Applications_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 39, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 4779, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Applications_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 37, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations_fts", "columns": ["Sequence_accession_number", "Marine_Sequences_Protein_Annotations_fts", "rank"], "primary_keys": [], "count": 71149, "hidden": true, "fts_table": "Marine_Sequences_Protein_Annotations_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 174, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 71149, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_Protein_Annotations_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 172, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_fts", "columns": ["Sequence_accession_number", "Species_name", "Marine_Sequences_fts", "rank"], "primary_keys": [], "count": 104467, "hidden": true, "fts_table": "Marine_Sequences_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 632, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 104467, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Sequences_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 509, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Species_fts", "columns": ["Species_name", "Marine_Species_fts", "rank"], "primary_keys": [], "count": 1639, "hidden": true, "fts_table": "Marine_Species_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Species_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Species_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 23, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Species_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 1639, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Marine_Species_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 21, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Sequences_fts", "columns": ["Sequence_accession_number", "Species_name", "Sequences_fts", "rank"], "primary_keys": [], "count": 557484, "hidden": true, "fts_table": "Sequences_fts", "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Sequences_fts_config", "columns": ["k", "v"], "primary_keys": ["k"], "count": 1, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Sequences_fts_data", "columns": ["id", "block"], "primary_keys": ["id"], "count": 3127, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Sequences_fts_docsize", "columns": ["id", "sz"], "primary_keys": ["id"], "count": 557484, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}, {"name": "Sequences_fts_idx", "columns": ["segid", "term", "pgno"], "primary_keys": ["segid", "term"], "count": 2208, "hidden": true, "fts_table": null, "foreign_keys": {"incoming": [], "outgoing": []}, "private": false}], "hidden_count": 35, "views": [{"name": "View_MarineSequences_Applicants", "private": false}, {"name": "View_MarineSequences_Species", "private": false}, {"name": "View_MarineSequences_Annotations", "private": false}], "queries": [{"sql": "SELECT\n  Applicants.Applicant_name,\n  Applicants.Applicant_type,\n  Applicants.Applicant_country,\n  Applications.Patent_application_number,\n  Applications.Year_of_application,\n  Applications.Patent_system,\n  Marine_Sequences.Sequence_accession_number,\n  Marine_Sequences.Species_name AS Marine_Species_name,\n  Marine_Sequences.GC_content,\n  Marine_Sequences.Sequence_length,\n  Marine_Sequences.Sequence_status,\n  Marine_Sequences.Is_protein_coding_sequence,\n  Marine_Sequences.Is_annotated,\n  Marine_Species.Domain,\n  Marine_Species.Phylum,\n  Marine_Species.Taxonomic_source,\n  Marine_Species.Is_deep_sea,\n  Marine_Species.Deep_sea_source,\n  Marine_Species.Is_ABNJ_present,\n  Marine_Sequences_Protein_Annotations.f_header,\n  Marine_Sequences_Protein_Annotations.sseqid,\n  Marine_Sequences_Protein_Annotations.stitle,\n  Marine_Sequences_Protein_Annotations.pident,\n  Marine_Sequences_Protein_Annotations.evalue,\n  Marine_Sequences_Protein_Annotations.qcovs,\n  Marine_Sequences_Protein_Annotations.annotation_source\nFROM\n  Applications\nINNER JOIN Applicants ON Applications.Applicant_name = Applicants.Applicant_name\nINNER JOIN Applications_Sequences ON Applications.Patent_application_number = Applications_Sequences.Patent_application_number\nINNER JOIN Marine_Sequences ON Applications_Sequences.Sequence_accession_number = Marine_Sequences.Sequence_accession_number\nINNER JOIN Marine_Species ON Marine_Sequences.Species_name = Marine_Species.Species_name\nLEFT JOIN Marine_Sequences_Protein_Annotations ON Marine_Sequences.Sequence_accession_number = Marine_Sequences_Protein_Annotations.Sequence_accession_number\nWHERE\n  Marine_Species.Species_name IN ('Idiomarina zobellii', 'Moritella marina', 'Moritella abyssi', 'Psychroflexus torquis', 'Shewanella violacea')\nORDER BY\n  Applicants.Applicant_name;\n", "title": "All database records with sequences derived from species uniquely present in ABNJ", "description_html": "This pre-canned SQL query retrieves all database records that contain sequences derived from species that are uniquely present in Areas Beyond National Jurisdiction (ABNJ).\n", "name": "abnj_species", "private": false}, {"sql": "SELECT \n  Applicants.Applicant_name,\n  Applicants.Applicant_type,\n  Applicants.Applicant_country,\n  Applications.Patent_application_number,\n  Applications.Year_of_application,\n  Applications.Patent_system,\n  Marine_Sequences.Sequence_accession_number,\n  Marine_Sequences.Species_name AS Marine_Species_name,\n  Marine_Sequences.GC_content,\n  Marine_Sequences.Sequence_length,\n  Marine_Sequences.Sequence_status,\n  Marine_Sequences.Is_protein_coding_sequence,\n  Marine_Sequences.Is_annotated,\n  Marine_Species.Domain,\n  Marine_Species.Phylum,\n  Marine_Species.Taxonomic_source,\n  Marine_Species.Is_deep_sea,\n  Marine_Species.Deep_sea_source,\n  Marine_Species.Is_ABNJ_present,\n  Marine_Sequences_Protein_Annotations.f_header,\n  Marine_Sequences_Protein_Annotations.sseqid,\n  Marine_Sequences_Protein_Annotations.stitle,\n  Marine_Sequences_Protein_Annotations.pident,\n  Marine_Sequences_Protein_Annotations.evalue,\n  Marine_Sequences_Protein_Annotations.qcovs,\n  Marine_Sequences_Protein_Annotations.annotation_source\nFROM \n  Applications\nINNER JOIN \n  Applicants ON Applications.Applicant_name = Applicants.Applicant_name\nINNER JOIN \n  Applications_Sequences ON Applications.Patent_application_number = Applications_Sequences.Patent_application_number\nINNER JOIN \n  Sequences ON Applications_Sequences.Sequence_accession_number = Sequences.Sequence_accession_number\nLEFT JOIN \n  Marine_Sequences ON Sequences.Sequence_accession_number = Marine_Sequences.Sequence_accession_number\nINNER JOIN \n  Marine_Species ON Marine_Sequences.Species_name = Marine_Species.Species_name\nLEFT JOIN \n  Marine_Sequences_Protein_Annotations ON Marine_Sequences.Sequence_accession_number =       Marine_Sequences_Protein_Annotations.Sequence_accession_number\nWHERE\n  Applicants.Applicant_name LIKE '%' || :text || '%' \nORDER BY \n  Applicants.Applicant_name\nLIMIT\n  5000;\n", "title": "Unified query search for patent applicant names across all dataset tables", "description_html": "This SQL query provides a comprehensive view of a dataset by joining multiple tables related to patent applications, marine species, and genetic sequences. It allows for detailed searches on applicant names in the dataset, and organizes a wide array of information in a single query result.\n", "name": "applicants_search", "private": false}, {"sql": "SELECT \n  Applicants.Applicant_name,\n  Applicants.Applicant_type,\n  Applicants.Applicant_country,\n  Applications.Patent_application_number,\n  Applications.Year_of_application,\n  Applications.Patent_system,\n  Marine_Sequences.Sequence_accession_number,\n  Marine_Sequences.Species_name AS Marine_Species_name,\n  Marine_Sequences.GC_content,\n  Marine_Sequences.Sequence_length,\n  Marine_Sequences.Sequence_status,\n  Marine_Sequences.Is_protein_coding_sequence,\n  Marine_Sequences.Is_annotated,\n  Marine_Species.Domain,\n  Marine_Species.Phylum,\n  Marine_Species.Taxonomic_source,\n  Marine_Species.Is_deep_sea,\n  Marine_Species.Deep_sea_source,\n  Marine_Species.Is_ABNJ_present,\n  Marine_Sequences_Protein_Annotations.f_header,\n  Marine_Sequences_Protein_Annotations.sseqid,\n  Marine_Sequences_Protein_Annotations.stitle,\n  Marine_Sequences_Protein_Annotations.pident,\n  Marine_Sequences_Protein_Annotations.evalue,\n  Marine_Sequences_Protein_Annotations.qcovs,\n  Marine_Sequences_Protein_Annotations.annotation_source\nFROM \n  Applications\nINNER JOIN \n  Applicants ON Applications.Applicant_name = Applicants.Applicant_name\nINNER JOIN \n  Applications_Sequences ON Applications.Patent_application_number = Applications_Sequences.Patent_application_number\nINNER JOIN \n  Marine_Sequences ON Applications_Sequences.Sequence_accession_number = Marine_Sequences.Sequence_accession_number\nINNER JOIN \n  Marine_Species ON Marine_Sequences.Species_name = Marine_Species.Species_name\nLEFT JOIN \n  Marine_Sequences_Protein_Annotations ON Marine_Sequences.Sequence_accession_number =       Marine_Sequences_Protein_Annotations.Sequence_accession_number\nWHERE\n  Marine_Species.Species_name LIKE '%' || :text || '%' \nORDER BY \n  Applicants.Applicant_name\nLIMIT\n  5000;\n", "title": "Unified query search for marine species names across all dataset tables", "description_html": "This SQL query provides a comprehensive view of a dataset by joining multiple tables related to patent applications, marine species, and genetic sequences. It allows for detailed searches on marine species in the dataset, and organizes a wide array of information in a single query result.\n", "name": "marine_species_search", "private": false}], "allow_execute_sql": true, "query_ms": 135.87801530957222, "source": "Novel dataset reveals growing prominence of deep-sea life for marine bioprospecting", "source_url": "https://doi.org/10.21203/rs.3.rs-3136354/v1", "license": "CC BY 4.0", "license_url": "https://creativecommons.org/licenses/by/4.0/"}