Does Biomni require external data?

Yes, it downloads approximately 11GB of integrated biomedical databases (including NCBI and UniProt) on its first use to provide grounded reasoning and knowledge retrieval.

Can Biomni help with clinical genomics?

Yes, it is designed to handle rare disease diagnosis, variant pathogenicity interpretation, and phenotype-genotype mapping using integrated clinical databases.

Which LLM providers are supported by Biomni?

Biomni supports Anthropic Claude (recommended), OpenAI, Azure OpenAI, Google Gemini, Groq, and AWS Bedrock for its reasoning engine.

Biomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously performs complex research tasks in biology and medicine.

Is Biomni safe for executing research code?

Biomni executes LLM-generated code with full system privileges to process data. It is highly recommended to run the tool in isolated environments like Docker or VMs for security.

Biomni: Biomedical AI Agent

Name: Biomni: Biomedical AI Agent
Author: x-cmd

byx-cmd

•

数据科学与机器学习

Executes autonomous multi-step biomedical research tasks across genomics, drug discovery, and clinical analysis using integrated databases and code execution.

关于

Biomni is a specialized agentic framework developed by Stanford's SNAP lab, designed to automate complex biomedical research workflows. By combining large language model reasoning with a curated 11GB biomedical knowledge base and autonomous code execution, it assists researchers in tasks like CRISPR screening design, single-cell RNA-seq analysis, and ADMET prediction. It serves as a comprehensive tool for molecular biology and drug discovery, enabling a seamless transition from high-level research questions to detailed data analysis, variant interpretation, and protocol generation.

主要功能

Dynamic Python code generation and execution for data analysis pipelines
Automated result interpretation and comprehensive PDF report generation
8 GitHub stars
Multi-step autonomous reasoning and planning for complex biological queries
Cross-domain capabilities spanning genomics, proteomics, and drug discovery
Integrated access to 11GB of biomedical databases including Ensembl, UniProt, and PDB

使用场景

Performing end-to-end single-cell RNA-seq analysis and cell type annotation
Designing CRISPR screens and prioritizing genes based on pathway relevance
Predicting ADMET properties and identifying targets for drug discovery candidates

关于

主要功能

Dynamic Python code generation and execution for data analysis pipelines
Automated result interpretation and comprehensive PDF report generation
8 GitHub stars
Multi-step autonomous reasoning and planning for complex biological queries
Cross-domain capabilities spanning genomics, proteomics, and drug discovery
Integrated access to 11GB of biomedical databases including Ensembl, UniProt, and PDB

使用场景

Performing end-to-end single-cell RNA-seq analysis and cell type annotation
Designing CRISPR screens and prioritizing genes based on pathway relevance
Predicting ADMET properties and identifying targets for drug discovery candidates