Discover omics metadata across GOLD, IMG, Mycocosm, and Phytozome via SQL.
npx skills add https://github.com/fmschulz/omics-skills --skill jgi-lakehouse
Please help me install this Agent Skill. Skill: jgi-lakehouse Source: https://github.com/fmschulz/omics-skills/tree/main/skills/jgi-lakehouse Command: npx skills add https://github.com/fmschulz/omics-skills --skill jgi-lakehouse
The JGI Lakehouse hosts centralized genomics metadata across GOLD, IMG, Mycocosm, and Phytozome, enabling researchers to discover projects, taxa, and provenance while avoiding scattered data sources.
Authenticate to the Lakehouse, run a sample query to discover GOLD/IMG taxa, and begin genome downloads.
High-intent search queries and answers about installing and using this skill.
To query JGI Lakehouse genomics metadata, you use SQL-based exploration through the Dremio Lakehouse, requiring a DREMIO_PAT token for authentication. This allows unified metadata discovery across GOLD, IMG, Mycocosm, and Phytozome.
Yes, a DREMIO_PAT token is required for token-based authentication to access the JGI Lakehouse. This safety mechanism ensures secure querying and guides file downloads from the JGI filesystem while maintaining provenance.
The best way to discover IMG genome packages is by running SQL queries to map projects and taxa, then coordinating file downloads directly from the JGI filesystem. The process prefers view-based queries to ensure safe exploration.
Yes, you can search for specific taxa and projects across Phytozome and Mycocosm using SQL. The JGI Lakehouse enables quick discovery of taxonomy and project mappings via Dremio, avoiding scattered data sources.
A key limitation is the strict requirement for a DREMIO_PAT token for authentication. Additionally, to maintain safety and provenance, the system prefers view-based queries and guides downloads specifically from the JGI filesystem.
openscientist-ioQuery JGI GOLD and IMG genomic metadata via the Dremio Lakehouse using SQL.
cultivariumRetrieve genomic, gene, and taxonomy data from NCBI Datasets.
Yezez9Retrieve nucleotide sequences, FASTQ reads, and genome assemblies from ENA via REST APIs.
Shakudo-ioQuery Dremio to retrieve CRM, billing, and business analytics data.
