Ucsc Genome Tools#

Configuration File: ucsc_genome_tools.json Tool Type: Local Tools Count: 4

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

Available Tools#

UCSC_get_sequence (Type: UCSCGenomeTool)#

Get DNA sequence from the UCSC Genome Browser for a genomic region. Pass ‘region’ as a written lo…

UCSC_get_sequence tool specification

Tool Information:

  • Name: UCSC_get_sequence

  • Type: UCSCGenomeTool

  • Description: Get DNA sequence from the UCSC Genome Browser for a genomic region. Pass ‘region’ as a written locus (e.g. ‘chr14:89000000-89000100’, 1-based inclusive, 101 bp) to paste coordinates verbatim, or give chrom/start/end with ‘coordinate_system’. Returns the nucleotide sequence plus the resolved region in both conventions. Useful for primer design, sequence analysis and regulatory element inspection.

Parameters:

  • genome (string) (required) UCSC genome assembly identifier. Examples: ‘hg38’ (human), ‘mm39’ (mouse), ‘dm6’ (fly), ‘sacCer3’ (yeast).

  • chrom (string) (optional) Chromosome name. Examples: ‘chr1’, ‘chr17’, ‘chrX’, ‘chrM’.

  • start (integer) (optional) Start position. Interpreted per ‘coordinate_system’ (default 0-based, inclusive). Example: 7668421.

  • end (integer) (optional) End position. Exclusive when coordinate_system is 0-based, inclusive when 1-based. Span must be <= 100000 bp. Example: 7668521.

  • region (string) (optional) Genomic region written the usual way, 1-based INCLUSIVE on both ends, e.g. ‘chr14:89000000-89000100’ (101 bp). This is the form shown by the UCSC browser, IGV and samtools, so you can paste a locus verbatim. PREFERRED over chrom/start/end: it removes the 0-based/1-based conversion that otherwise silently drops the first base.

  • coordinate_system (string) (optional) Which convention chrom/start/end are given in. ‘0-based’ (default) is half-open, matching the UCSC API: length = end - start. ‘1-based’ is inclusive, matching a written locus: length = end - start + 1. Ignored when ‘region’ is supplied.

Example Usage:

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

UCSC_get_track (Type: UCSCGenomeTool)#

Get annotation track data from the UCSC Genome Browser for a specified genomic region. Retrieves …

UCSC_get_track tool specification

Tool Information:

  • Name: UCSC_get_track

  • Type: UCSCGenomeTool

  • Description: Get annotation track data from the UCSC Genome Browser for a specified genomic region. Retrieves features like genes, regulatory elements, conservation scores, variants, or repeats from any of UCSC’s 370+ tracks. Use UCSC_search first to find the genomic coordinates of your gene of interest. Example: track ‘knownGene’ on hg38 chr17:7668421-7687490 returns GENCODE gene annotations for the TP53 region.

Parameters:

  • genome (string) (required) UCSC genome assembly. Examples: ‘hg38’, ‘hg19’, ‘mm39’.

  • track (string) (required) Track name. Common tracks: ‘knownGene’ (GENCODE genes), ‘ncbiRefSeq’ (RefSeq), ‘snp151’ (dbSNP), ‘encodeCcreCombined’ (ENCODE cCREs), ‘phastCons100way’ (conservation), ‘rmsk’ (repeats).

  • chrom (string) (required) Chromosome name. Examples: ‘chr1’, ‘chr17’, ‘chrX’.

  • start (integer) (required) 0-based start position (inclusive).

  • end (integer) (required) End position (exclusive). Must be > start.

  • maxItemsOutput ([‘integer’, ‘null’]) (optional) Maximum number of items to return. Default: 100. Set to limit large result sets.

Example Usage:

query = {
    "name": "UCSC_get_track",
    "arguments": {
        "genome": "example_value",
        "track": "example_value",
        "chrom": "example_value",
        "start": 10,
        "end": 10
    }
}
result = tu.run(query)

UCSC_list_tracks (Type: UCSCGenomeTool)#

Discover available UCSC Genome Browser annotation tracks for a genome assembly, and inspect a tra…

UCSC_list_tracks tool specification

Tool Information:

  • Name: UCSC_list_tracks

  • Type: UCSCGenomeTool

  • Description: Discover available UCSC Genome Browser annotation tracks for a genome assembly, and inspect a track’s column schema. With only ‘genome’ set, returns the list of leaf tracks (each with track name, type, shortLabel, longLabel, parent) so you can find valid track names to pass to UCSC_get_track (there are tens of thousands, e.g. dbSnp155, dbSnp155ClinVar, dbSnp155Common, knownGene, ncbiRefSeq, encodeCcreCombined). Use ‘name_filter’ to narrow the list by substring (matched against track name, shortLabel, longLabel). When ‘track’ is also provided, returns that track’s column schema instead (column name, sqlType, jsonType, description) from the list/schema endpoint. Example: genome ‘hg38’ returns 23000+ tracks; genome ‘hg38’ + track ‘knownGene’ returns its 27 columns (chrom, chromStart, …).

Parameters:

  • genome (string) (required) UCSC genome assembly identifier. Examples: ‘hg38’, ‘hg19’, ‘mm39’, ‘mm10’, ‘dm6’, ‘danRer11’.

  • track ([‘string’, ‘null’]) (optional) Optional. When set, return this track’s column schema instead of the track list. Example: ‘knownGene’, ‘dbSnp155’, ‘ncbiRefSeq’.

  • name_filter ([‘string’, ‘null’]) (optional) Optional substring filter (case-insensitive) applied to track name/shortLabel/longLabel when listing tracks. Example: ‘dbSnp’, ‘gencode’, ‘clinvar’.

  • max_tracks ([‘integer’, ‘null’]) (optional) Maximum number of tracks to return when listing (default 500). The total matched count is always reported in track_count.

Example Usage:

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

UCSC_search (Type: UCSCGenomeTool)#

Search the UCSC Genome Browser for genes, transcripts, or genomic features by name. Returns posit…

UCSC_search tool specification

Tool Information:

  • Name: UCSC_search

  • Type: UCSCGenomeTool

  • Description: Search the UCSC Genome Browser for genes, transcripts, or genomic features by name. Returns position matches across tracks (MANE, RefSeq, GENCODE, HGNC, etc.) for a given genome assembly. Supports searching for gene symbols, transcript IDs, SNP rsIDs, or chromosomal bands. Example: searching ‘TP53’ in hg38 returns chr17:7668421-7687490 from MANE Select and other tracks.

Parameters:

  • search_term (string) (required) Gene symbol, transcript ID, SNP rsID, or genomic feature to search. Examples: ‘TP53’, ‘BRCA1’, ‘rs429358’, ‘ENST00000269305’.

  • genome (string) (optional) UCSC genome assembly identifier. Default: ‘hg38’. Others: ‘hg19’, ‘mm10’, ‘mm39’, ‘dm6’, ‘ce11’, ‘danRer11’, ‘sacCer3’.

Example Usage:

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