What databases can I access with this skill?

This skill provides access to the JGI Dremio Lakehouse, specifically the GOLD (Genomes OnLine Database) and IMG (Integrated Microbial Genomes) databases.

Can I perform complex data joins?

Yes, you can run standard SQL join operations across tables within the GOLD and IMG schemas using the --sql flag.

Do I need special credentials to use this skill?

Yes, you must have a JGI account and set your DREMIO_USER and DREMIO_PASSWORD environment variables to authenticate with the lakehouse.

How do I see the structure of a specific table?

You can use the 'describe' command on a specific collection or query the INFORMATION_SCHEMA to view column names and data types.

What formats are supported for data export?

The skill supports exporting query results in JSON, CSV, and YAML formats through the linkml-store interface.

JGI Lakehouse Query

Name: JGI Lakehouse Query
Author: cmungall

bycmungall

0•

Database Management

Facilitates querying and exploring the Joint Genome Institute (JGI) Dremio Lakehouse, including GOLD and IMG genomics databases.

This skill empowers Claude to interact directly with the JGI Dremio Lakehouse, providing seamless access to the Genomes OnLine Database (GOLD) and Integrated Microbial Genomes (IMG) datasets. It allows users to perform complex SQL queries, list collections, and export LinkML schemas using the linkml-store CLI. It is particularly useful for bioinformaticians and researchers needing to programmatically explore genome metadata, ecosystem statistics, and project-level genomic information directly from their development environment.

Key Features

01Collection-based querying with built-in filtering for genomic metadata

020 GitHub stars

03Support for multiple output formats including JSON, CSV, and YAML

04Automated LinkML schema export with foreign key relationship mapping

05Direct SQL querying of GOLD and IMG databases via Dremio REST CLI

06Discovery tools to list schemas, tables, and column metadata

Use Cases

01Analyzing genome project metadata and study ecosystem distributions from GOLD

02Querying microbial gene annotations, taxa, and experimental data in IMG

03Generating structured LinkML schemas for complex biological datasets

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add cmungall/lakehouse-skills jgi-lakehouse

For use in Claude.ai and ChatGPT

Download Skill