berdl

Query KBase BERDL Data Lakehouse for microbial genomic and biochemical data via SQL.

14|11|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/kbaseincubator/BERIL-research-observatory --skill berdl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: berdl
Source: https://github.com/kbaseincubator/BERIL-research-observatory/tree/main/.claude/skills/berdl
Command: npx skills add https://github.com/kbaseincubator/BERIL-research-observatory --skill berdl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and scripts (resource) components.

What problem does it solve?

This Skill provides programmatic access to the KBase BER Data Lakehouse (BERDL), enabling users to query vast microbial genomic and biochemical datasets that would otherwise be inaccessible.

Core Features & Use Cases

  • Query BERDL Databases: Access and query specific databases within BERDL, such as pangenome data, biochemistry models, and fitness data.
  • Data Exploration: Retrieve genome statistics, analyze gene clusters, access functional annotations, and query biochemical reaction data.
  • Use Case: A researcher wants to find all genes associated with a specific metabolic pathway (e.g., glycolysis) across all Escherichia coli strains in the pangenome database and then retrieve the thermodynamic properties of the reactions involved from the biochemistry database.

Quick Start

Use the berdl skill to list all available databases.

Frequently Asked Questions about berdl

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

FAQPage Schema
How do I query microbial genomic data from the KBase BERDL Data Lakehouse?

You can query microbial genomic data from the KBase BERDL Data Lakehouse by executing SQL queries through the Skill's API endpoints. It requires a KBASE_AUTH_TOKEN for authentication to access pangenome data, genome statistics, and functional annotations.

Can I retrieve thermodynamic properties for biochemical reactions using a SQL query?

Yes, you can retrieve thermodynamic properties and biochemical reaction data by executing SQL queries against the biochemistry database within the BERDL Data Lakehouse. The Skill facilitates exploration of biochemistry models and functional annotations.

What data types are available for microbial discovery in the BERDL Data Lakehouse?

Available data types for microbial discovery in the BERDL Data Lakehouse include pangenome data, species information, genome statistics, gene clusters, functional annotations, fitness data, and biochemistry models. You can explore these through database listing and sampling endpoints.

Do I need a KBASE_AUTH_TOKEN to access genome statistics and species information?

Yes, a KBASE_AUTH_TOKEN is required for authentication to access genome statistics and species information. The token ensures secure programmatic access to the BERDL Data Lakehouse via its API interactions and SQL query endpoints.

How do I list available databases and table schemas before running a SQL query?

You can list available databases and retrieve table schemas by using the Skill's dedicated endpoints for listing databases, tables, and schemas. This allows you to inspect the structure of pangenome and biochemistry data before executing your SQL queries.

How does the BERDL Skill integrate biochemistry data with pangenome analysis?

The Skill integrates biochemistry data with pangenome analysis by allowing cross-database SQL queries. You can find genes associated with a metabolic pathway across microbial strains in the pangenome database and retrieve corresponding reaction thermodynamics from the biochemistry database.