ukb-topmed-phewas-skill

Fetch UKB-TOPMed PheWAS association summaries for single genetic variants.

5.3k|765|Updated Mar 4, 2026
One-click install
npx skills add https://github.com/openai/plugins --skill ukb-topmed-phewas-skill
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ukb-topmed-phewas-skill
Source: https://github.com/openai/plugins/tree/main/plugins/life-science-research/skills/ukb-topmed-phewas-skill
Command: npx skills add https://github.com/openai/plugins --skill ukb-topmed-phewas-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) components.

What problem does it solve?

Looking up phenome-wide association study (PheWAS) results for a genetic variant requires resolving rsIDs or GRCh37 coordinates into the GRCh38 format that the UKB-TOPMed API expects, then parsing large JSON payloads. This Skill automates that resolution and returns concise, truncated summaries instead of raw data dumps.

Core Features & Use Cases

  • Flexible Variant Input: Accepts exactly one of rsID, GRCh37, GRCh38, or generic variant strings and resolves them to the canonical GRCh38 chr:pos-ref-alt query via Ensembl.
  • Compact PheWAS Summaries: Queries the UKB-TOPMed PheWeb API and returns a bounded list of associations with total counts and truncation flags.
  • Raw Payload Export: Optionally saves the full association JSON to a file with save_raw for downstream analysis.
  • Use Case: A researcher asks for associations of rs7903146; the Skill resolves the rsID through Ensembl, queries UKB-TOPMed, and returns the top 10 phenotype associations with a link to the variant page.

Quick Start

Ask the assistant to fetch UKB-TOPMed PheWAS associations for rs7903146 with a maximum of 10 results.

Frequently Asked Questions about ukb-topmed-phewas-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I look up PheWAS associations for a genetic variant?

Provide one variant identifier as JSON on stdin, such as {"rsid":"rs7903146"} or {"grch38":"10:112998590-C-T"}, and the script queries the UKB-TOPMed PheWeb API. It returns a bounded list of phenotype associations with total counts and a variant URL.

How do I convert GRCh37 coordinates to GRCh38 for UKB-TOPMed queries?

Pass the GRCh37 coordinate under the grch37 key, for example {"grch37":"10:114758349-C-T"}. The script uses Ensembl GRCh37 and GRCh38 REST endpoints to resolve the position to an rsID and then to the canonical GRCh38 variant before querying UKB-TOPMed.

What input formats does the UKB-TOPMed PheWAS lookup accept?

It accepts exactly one of rsid, grch37, grch38, or variant as a JSON object, or a plain JSON string treated as GRCh38. Variant strings use flexible separators like 10:112998590-C-T or 10-112998590-C-T.

Can I get the full UKB-TOPMed association payload instead of a truncated list?

Yes, set save_raw to true and optionally provide raw_output_path. The full JSON response is written to that file (or a default path under /tmp), and the output reports raw_output_path instead of pasting large arrays into chat.

Why does the variant lookup return a not_found error?

A not_found error occurs when no rsID exists at the given chromosome and position in the Ensembl overlap endpoint for that build. Verify the coordinate and build are correct, or try querying by rsID directly.