Ncbi Datasets Tools#

Configuration File: ncbi_datasets_tools.json Tool Type: Local Tools Count: 8

This page contains all tools defined in the ncbi_datasets_tools.json configuration file.

Available Tools#

NCBIDatasets_get_gene (Type: NCBIDatasetsTool)#

Get comprehensive gene information from the National Center for Biotechnology Information (NCBI) …

NCBIDatasets_get_gene tool specification

Tool Information:

  • Name: NCBIDatasets_get_gene

  • Type: NCBIDatasetsTool

  • Description: Get comprehensive gene information from the National Center for Biotechnology Information (NCBI) by Gene ID. Returns gene symbol, description, chromosomal location, genomic coordinates, cross-references to UniProt/Ensembl/OMIM, synonyms, and annotation details. Covers all organisms in the NCBI Gene database. No API key is required; optionally set NCBI_API_KEY for a higher request-rate limit. Example: gene_id 7157 returns TP53 (tumor protein p53) on chromosome 17.

Parameters:

  • gene_id (string) (required) NCBI Gene ID (numeric). Examples: ‘7157’ (TP53), ‘672’ (BRCA1), ‘3630’ (INS), ‘22059’ (mouse Trp53).

Example Usage:

query = {
    "name": "NCBIDatasets_get_gene",
    "arguments": {
        "gene_id": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_get_gene_by_symbol (Type: NCBIDatasetsTool)#

Look up gene information by gene symbol and organism. Searches NCBI Gene database using official …

NCBIDatasets_get_gene_by_symbol tool specification

Tool Information:

  • Name: NCBIDatasets_get_gene_by_symbol

  • Type: NCBIDatasetsTool

  • Description: Look up gene information by gene symbol and organism. Searches NCBI Gene database using official gene symbols. Specify the species with taxon (or its synonyms organism/species) as a common name (human, mouse, rat) or taxonomy ID. IMPORTANT – the species defaults to HUMAN when none is given, so a gene symbol shared across species returns the human gene unless you say otherwise; metadata.query_taxon_defaulted is true whenever that default was applied, and metadata.query_taxon echoes the species actually used. Every returned row also carries its own tax_id/taxname, which is the authoritative check. Returns gene ID, description, chromosomal location, and database cross-references.

Parameters:

  • symbol (string) (required) Gene symbol. Examples: ‘TP53’, ‘BRCA1’, ‘INS’, ‘EGFR’.

  • taxon (string) (optional) Organism as common name or taxonomy ID. Examples: ‘human’, ‘mouse’, ‘rat’, ‘9606’, ‘10090’. Default: ‘human’ (reported as metadata.query_taxon_defaulted). Synonyms organism and species are accepted.

  • organism (string) (optional) Synonym for taxon. Used when taxon is not supplied.

  • species (string) (optional) Synonym for taxon. Used when neither taxon nor organism is supplied.

Example Usage:

query = {
    "name": "NCBIDatasets_get_gene_by_symbol",
    "arguments": {
        "symbol": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_get_genome_assembly (Type: NCBIDatasetsTool)#

Get genome assembly metadata for an assembly accession (RefSeq GCF_ or GenBank GCA_) from the NCB…

NCBIDatasets_get_genome_assembly tool specification

Tool Information:

  • Name: NCBIDatasets_get_genome_assembly

  • Type: NCBIDatasetsTool

  • Description: Get genome assembly metadata for an assembly accession (RefSeq GCF_ or GenBank GCA_) from the NCBI Datasets v2 API. Returns organism/strain, assembly name/level/status, RefSeq category (e.g. reference genome), release date, submitter, BioProject, and assembly statistics (total length, chromosome count, contig/scaffold N50, GC%, annotation provider). Use to characterize a specific genome assembly across any organism (bacteria, fungi, plant, animal). No API key required.

Parameters:

  • accession (string) (required) Assembly accession, e.g. ‘GCF_000005845.2’ (E. coli K-12) or ‘GCF_000001405.40’ (human GRCh38.p14).

Example Usage:

query = {
    "name": "NCBIDatasets_get_genome_assembly",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_get_orthologs (Type: NCBIDatasetsTool)#

Get orthologous genes across species for a given NCBI Gene ID. Returns orthologs identified by NC…

NCBIDatasets_get_orthologs tool specification

Tool Information:

  • Name: NCBIDatasets_get_orthologs

  • Type: NCBIDatasetsTool

  • Description: Get orthologous genes across species for a given NCBI Gene ID. Returns orthologs identified by NCBI’s Ortholog pipeline, including gene symbols, species, and gene types for each ortholog. Useful for comparative genomics and cross-species gene function studies. Example: gene_id 7157 (TP53) returns mouse Trp53, rat Tp53, zebrafish tp53, etc.

Parameters:

  • gene_id (string) (required) NCBI Gene ID (numeric). Examples: ‘7157’ (TP53), ‘672’ (BRCA1), ‘3630’ (INS).

  • page_size (integer) (optional) Maximum number of orthologs to return (1-100). Default: 20.

Example Usage:

query = {
    "name": "NCBIDatasets_get_orthologs",
    "arguments": {
        "gene_id": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_get_sequence_reports (Type: NCBIDatasetsTool)#

Get a page of per-sequence (chromosome/plasmid/scaffold) reports for a genome assembly via the NC…

NCBIDatasets_get_sequence_reports tool specification

Tool Information:

  • Name: NCBIDatasets_get_sequence_reports

  • Type: NCBIDatasetsTool

  • Description: Get a page of per-sequence (chromosome/plasmid/scaffold) reports for a genome assembly via the NCBI Datasets v2 API. Returns each molecule’s chromosome name, role, location type, RefSeq and GenBank accessions, length, and GC%, plus total_available and next_page_token metadata. Use next_page_token to retrieve additional pages for assemblies with many sequences. Use to map an assembly to its individual sequence accessions (e.g. resolve E. coli K-12 to NC_000913.3, or human chromosomes to their RefSeq NC_ accessions). No API key required.

Parameters:

  • accession (string) (required) Assembly accession, e.g. ‘GCF_000005845.2’.

  • page_size ([‘integer’, ‘null’]) (optional) Maximum sequence records in this page (default 100, maximum 1000).

  • page_token ([‘string’, ‘null’]) (optional) Opaque next_page_token returned by a previous call. Omit for the first page.

Example Usage:

query = {
    "name": "NCBIDatasets_get_sequence_reports",
    "arguments": {
        "accession": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_get_taxonomy (Type: NCBIDatasetsTool)#

Get detailed taxonomy information from NCBI by taxonomy ID. Returns organism name, rank, full lin…

NCBIDatasets_get_taxonomy tool specification

Tool Information:

  • Name: NCBIDatasets_get_taxonomy

  • Type: NCBIDatasetsTool

  • Description: Get detailed taxonomy information from NCBI by taxonomy ID. Returns organism name, rank, full lineage (as bare ancestor tax_ids in lineage, and as resolved organism_name/rank pairs in lineage_names), current counts of genes/assemblies/RNA types, and child taxa. Covers all organisms in NCBI Taxonomy including bacteria, archaea, eukaryotes, and viruses. Example: tax_id 9606 returns Homo sapiens and its root-to-parent lineage.

Parameters:

  • tax_id (string) (required) NCBI Taxonomy ID (numeric). Examples: ‘9606’ (Homo sapiens), ‘10090’ (Mus musculus), ‘7227’ (Drosophila melanogaster), ‘562’ (E. coli).

Example Usage:

query = {
    "name": "NCBIDatasets_get_taxonomy",
    "arguments": {
        "tax_id": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_list_genomes_by_taxon (Type: NCBIDatasetsTool)#

List genome assemblies available for a taxon (NCBI tax id or scientific name) via the NCBI Datase…

NCBIDatasets_list_genomes_by_taxon tool specification

Tool Information:

  • Name: NCBIDatasets_list_genomes_by_taxon

  • Type: NCBIDatasetsTool

  • Description: List genome assemblies available for a taxon (NCBI tax id or scientific name) via the NCBI Datasets v2 API. Returns a summary list of assemblies (accession, assembly name/level, RefSeq category, release date, total length, N50, GC%) plus the total count available. Use to discover what genomes exist for an organism or clade, e.g. all Escherichia coli or Mycobacterium tuberculosis assemblies. Set reference_only to restrict to reference/representative genomes. No API key required.

Parameters:

  • taxon (string) (required) NCBI tax id or scientific name, e.g. ‘562’, ‘Escherichia coli’, ‘Saccharomyces cerevisiae’.

  • limit ([‘integer’, ‘null’]) (optional) Max assemblies to return (default 20, max 100).

  • reference_only ([‘boolean’, ‘null’]) (optional) If true, return only reference/representative genomes.

Example Usage:

query = {
    "name": "NCBIDatasets_list_genomes_by_taxon",
    "arguments": {
        "taxon": "example_value"
    }
}
result = tu.run(query)

NCBIDatasets_suggest_taxonomy (Type: NCBIDatasetsTool)#

Suggest taxonomic names matching a query string. Searches NCBI Taxonomy for organisms by partial …

NCBIDatasets_suggest_taxonomy tool specification

Tool Information:

  • Name: NCBIDatasets_suggest_taxonomy

  • Type: NCBIDatasetsTool

  • Description: Suggest taxonomic names matching a query string. Searches NCBI Taxonomy for organisms by partial name, returning matching scientific names, taxonomy IDs, common names, and ranks. Useful for finding taxonomy IDs from partial organism names. Example: ‘drosophila’ returns D. melanogaster (7227), D. simulans (7240), etc.

Parameters:

  • query (string) (required) Partial organism name to search. Examples: ‘drosophila’, ‘escherichia’, ‘arabidopsis’, ‘saccharomyces’.

Example Usage:

query = {
    "name": "NCBIDatasets_suggest_taxonomy",
    "arguments": {
        "query": "example_value"
    }
}
result = tu.run(query)