Can Biomni help with clinical data analysis?

Yes, it is designed for tasks including rare disease diagnosis, variant interpretation, and mapping phenotypes to genotypes.

What is the Biomni Claude Code skill?

Biomni is an open-source framework from Stanford SNAP lab that enables Claude to act as an autonomous agent for complex biomedical research tasks.

Which LLM models work best with Biomni?

While it supports various providers, Claude 3.5 Sonnet is highly recommended for the best balance of speed and biological reasoning accuracy.

Is the code executed by Biomni secure?

Biomni executes LLM-generated code with system privileges. For security, it is recommended to run the skill in isolated environments like Docker or virtual machines.

Does Biomni require a large data download?

Yes, on its first use, Biomni downloads an integrated ~11GB biomedical data lake to support its reasoning and analysis capabilities.

Biomni Biomedical AI Research Agent

Name: Biomni Biomedical AI Research Agent
Author: Activer007

byActiver007

•

Data Science & ML

Automates complex biomedical research tasks including genomics, drug discovery, and clinical analysis through autonomous AI reasoning and code execution.

About

Biomni is a specialized biomedical AI framework designed to function as an autonomous research assistant within Claude Code. Developed by Stanford's SNAP lab, it empowers researchers to execute multi-step biological queries by decomposing tasks into executable code and data analysis pipelines. By leveraging an integrated 11GB data lake containing genomics, proteomics, and clinical literature, Biomni bridges the gap between high-level biological hypotheses and technical implementation, making it an indispensable tool for bioinformaticians and life science developers working on CRISPR design, single-cell analysis, or drug property prediction.

Key Features

Cross-domain support for genomics, proteomics, and clinical diagnostics
Access to a built-in 11GB biomedical knowledge base and data lake
1 GitHub stars
Multi-step biological reasoning and autonomous task planning
Dynamic code generation and execution for data processing pipelines
Standardized evaluation framework for benchmarking research outputs

Use Cases

Designing genome-wide CRISPR screens and prioritizing gene targets based on pathway relevance
Predicting ADMET properties and identifying therapeutic targets for drug discovery candidates
Processing single-cell RNA-seq data for cell type annotation and differential expression analysis

About

Key Features

Cross-domain support for genomics, proteomics, and clinical diagnostics
Access to a built-in 11GB biomedical knowledge base and data lake
1 GitHub stars
Multi-step biological reasoning and autonomous task planning
Dynamic code generation and execution for data processing pipelines
Standardized evaluation framework for benchmarking research outputs

Use Cases

Designing genome-wide CRISPR screens and prioritizing gene targets based on pathway relevance
Predicting ADMET properties and identifying therapeutic targets for drug discovery candidates
Processing single-cell RNA-seq data for cell type annotation and differential expression analysis