Ensembl Sequence Tools#

Configuration File: ensembl_sequence_tools.json Tool Type: Local Tools Count: 2

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

Available Tools#

EnsemblSeq_get_id_sequence (Type: EnsemblSequenceTool)#

Get the amino acid or nucleotide sequence for an Ensembl protein, transcript, or gene ID with rec…

EnsemblSeq_get_id_sequence tool specification

Tool Information:

  • Name: EnsemblSeq_get_id_sequence

  • Type: EnsemblSequenceTool

  • Description: Get the amino acid or nucleotide sequence for an Ensembl protein, transcript, or gene ID with recoverable paging. Type auto-selects protein for ENSP, cDNA for ENST, and genomic for other IDs when omitted. The default page is 10,000 characters; continue with next_sequence_offset while has_more is true.

Parameters:

  • ensembl_id (string) (required) Ensembl stable ID. Examples: ‘ENSP00000269305’ (TP53 protein, 393 aa), ‘ENST00000269305’ (TP53-201 transcript), ‘ENSG00000141510’ (TP53 gene). Protein IDs start with ENSP, transcript with ENST, gene with ENSG.

  • type (string) (optional) Sequence type. If omitted: protein for ENSP, cDNA for ENST, genomic for ENSG/other IDs.

  • max_length (integer) (optional) Maximum sequence characters in this page.

  • sequence_offset (integer) (optional) Zero-based sequence characters to skip. Continue with next_sequence_offset.

Example Usage:

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

EnsemblSeq_get_region_sequence (Type: EnsemblSequenceTool)#

Get the DNA nucleotide sequence for a genomic region from Ensembl with recoverable sequence pagin…

EnsemblSeq_get_region_sequence tool specification

Tool Information:

  • Name: EnsemblSeq_get_region_sequence

  • Type: EnsemblSequenceTool

  • Description: Get the DNA nucleotide sequence for a genomic region from Ensembl with recoverable sequence paging. The default page is 10,000 bp; continue with next_sequence_offset while has_more is true. Returns the full sequence_length separately from sequence_returned_length. Supports any Ensembl species and coordinate strand.

Parameters:

  • region (string) (required) Genomic region in format ‘chr:start-end’ or ‘chr:start..end:strand’. Examples: ‘17:7668421-7668520’ (TP53 locus, 100bp), ‘7:140424943-140425043’ (BRAF locus, 100bp), ‘X:15560138-15602945’ (MECP2 gene). Strand: 1 for forward, -1 for reverse.

  • species (string) (optional) Ensembl species name. Default: ‘homo_sapiens’. Examples: ‘mus_musculus’, ‘danio_rerio’, ‘drosophila_melanogaster’.

  • max_length (integer) (optional) Maximum sequence characters in this page.

  • sequence_offset (integer) (optional) Zero-based sequence characters to skip. Continue with next_sequence_offset.

Example Usage:

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