What is the Biomni Claude Code skill?

Biomni is an autonomous agent framework from Stanford's SNAP lab that helps researchers execute complex biomedical tasks like genomics analysis and drug discovery using natural language.

Can Biomni execute code on my local machine?

Yes, Biomni generates and executes Python code to process data. It is recommended to run these tasks in isolated environments like Docker for security.

Which biological domains does Biomni support?

It supports a wide range of domains including genomics, proteomics, molecular biology, clinical analysis, and laboratory protocol optimization.

Does Biomni require external databases?

Biomni comes with an integrated 11GB knowledge lake including Ensembl, UniProt, ClinVar, and PubMed, which it downloads automatically upon first use.

Biomni Biomedical Agent

Name: Biomni Biomedical Agent
Author: pur3v4d3r

bypur3v4d3r

•

Data Science & ML

Executes complex biomedical research tasks including genomics analysis, drug discovery, and clinical interpretation via autonomous AI agents.

About

Biomni is an open-source biomedical AI agent framework developed by Stanford's SNAP lab, designed to automate multi-step biological reasoning and data analysis. By integrating a massive 11GB biomedical knowledge base with autonomous code execution capabilities, it allows researchers to perform high-level tasks like CRISPR screen design, single-cell RNA-seq processing, and ADMET prediction. This skill is essential for scientists and bioinformaticians who need to bridge the gap between complex biological queries and technical implementation, providing a unified interface for genomics, proteomics, and clinical research.

Key Features

Integrated access to 11GB of curated biomedical databases and literature
Cross-domain support for genomics, drug discovery, and clinical tasks
1 GitHub stars
Autonomous multi-step biological task decomposition and planning
Dynamic Python code generation and execution for data pipelines
Comprehensive evaluation framework for benchmarking research outputs

Use Cases

Designing genome-wide CRISPR screens and prioritizing gene targets
Processing single-cell RNA-seq data for cell-type annotation and clustering
Predicting ADMET properties and performing target identification in drug discovery

About

Key Features

Integrated access to 11GB of curated biomedical databases and literature
Cross-domain support for genomics, drug discovery, and clinical tasks
1 GitHub stars
Autonomous multi-step biological task decomposition and planning
Dynamic Python code generation and execution for data pipelines
Comprehensive evaluation framework for benchmarking research outputs

Use Cases

Designing genome-wide CRISPR screens and prioritizing gene targets
Processing single-cell RNA-seq data for cell-type annotation and clustering
Predicting ADMET properties and performing target identification in drug discovery