Ncbi Nucleotide Tools

Configuration File: ncbi_nucleotide_tools.json Tool Type: Local Tools Count: 3

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

Available Tools

NCBI_fetch_accessions (Type: NCBINucleotideSearchTool)

Convert GenBank UIDs to accession numbers (U00096, NC_045512, etc.). Takes UIDs from NCBI_search_…

NCBI_fetch_accessions tool specification

Tool Information:

  • Name: NCBI_fetch_accessions

  • Type: NCBINucleotideSearchTool

  • Description: Convert GenBank UIDs to accession numbers (U00096, NC_045512, etc.). Takes UIDs from NCBI_search_nucleotide and returns actual accession numbers that can be used with database tools. Returns both EMBL/GenBank accessions (U*, M*, AJ*) that work with ENA Browser tools, and RefSeq accessions (NC_*, NM_*) for NCBI tools. Use this as second step after NCBI_search_nucleotide to get usable accession numbers.

Parameters:

  • operation (unknown) (required) Operation type (fixed: fetch_accession)

  • uids (unknown) (required) GenBank UID(s) from NCBI_search_nucleotide. Can be single UID or array of UIDs.

Example Usage:

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

NCBI_get_sequence (Type: NCBINucleotideSearchTool)

Retrieve DNA/RNA sequence data from NCBI by accession number. Returns sequences in specified form…

NCBI_get_sequence tool specification

Tool Information:

  • Name: NCBI_get_sequence

  • Type: NCBINucleotideSearchTool

  • Description: Retrieve DNA/RNA sequence data from NCBI by accession number. Returns sequences in specified format (fasta, gb, embl). Works with both EMBL/GenBank accessions (U00096, M15390) and RefSeq accessions (NC_045512, NM_000546). Use this to get actual sequence data after finding accessions with NCBI_search_nucleotide. Returns full sequence with annotations depending on format.

Parameters:

  • operation (unknown) (required) Operation type (fixed: fetch_sequence)

  • accession (string) (required) NCBI accession number (e.g., ‘U00096’, ‘NC_045512’, ‘NM_000546’). Works with GenBank, EMBL, and RefSeq accessions.

  • format (string) (optional) Sequence format: ‘fasta’ for FASTA, ‘gb’ for GenBank, ‘embl’ for EMBL, ‘gp’ for GenPept protein. Default: fasta

Example Usage:

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

NCBI_search_nucleotide (Type: NCBINucleotideSearchTool)

Search NCBI Nucleotide database (GenBank/EMBL/RefSeq) by organism, gene name, or keywords. Return…

NCBI_search_nucleotide tool specification

Tool Information:

  • Name: NCBI_search_nucleotide

  • Type: NCBINucleotideSearchTool

  • Description: Search NCBI Nucleotide database (GenBank/EMBL/RefSeq) by organism, gene name, or keywords. Returns GenBank UIDs which can be used to fetch accession numbers. Supports filtering by organism, gene, strain, sequence type (complete genome, mRNA, RefSeq). Use this to discover DNA/RNA sequences for specific organisms or genes. Returns both EMBL/GenBank accessions (U00096, M15390) and RefSeq accessions (NC_*, NM_*). Follow up with NCBI_fetch_accessions to get actual accession numbers.

Parameters:

  • operation (unknown) (required) Operation type (fixed: search)

  • organism (string) (optional) Organism name to search (e.g., ‘Escherichia coli’, ‘Homo sapiens’). Searches in [Organism] field.

  • gene (string) (optional) Gene name to search (e.g., ‘BRCA1’, ‘TP53’). Searches in [Gene] field.

  • strain (string) (optional) Strain name to filter (e.g., ‘K-12’, ‘MG1655’). Searches in [Strain] field.

  • keywords (string) (optional) Keywords to search in titles (e.g., ‘complete genome’, ‘mitochondrial’). Searches in [Title] field.

  • seq_type (string) (optional) Sequence type filter: ‘complete_genome’ for complete genomes, ‘mrna’ for mRNA sequences, ‘refseq’ for RefSeq curated sequences

  • query (string) (optional) Free-form search query if not using structured filters. Use NCBI query syntax (e.g., ‘(Escherichia coli[Organism]) AND (K-12[Strain])’)

  • limit (integer) (optional) Maximum number of results to return (default: 20, max: 100)

  • sort (string) (optional) Sort order for results (default: relevance)

Example Usage:

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