Can Biomni analyze my own local datasets?

Yes, Biomni can generate and execute code to process local files such as .h5ad files for RNA-seq, GWAS summary statistics, or SMILES strings for drug analysis.

Is it safe to run the code Biomni generates?

Biomni executes code with system privileges. It is recommended to run it in isolated environments like Docker or VMs when processing sensitive data or experimental code.

Biomni is an autonomous biomedical AI framework developed by Stanford's SNAP lab, designed to execute complex research tasks across genomics, drug discovery, and clinical analysis.

What databases does the 11GB data lake include?

The framework integrates major sources including Ensembl, NCBI Gene, UniProt, PDB, AlphaFold, ClinVar, OMIM, and indexed PubMed literature.

Does Biomni require specific LLM models?

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

Biomni Biomedical Research Agent

Name: Biomni Biomedical Research Agent
Author: Activer007

byActiver007

数据科学与机器学习

Executes autonomous biomedical research tasks across genomics, drug discovery, and molecular biology using integrated databases and code execution.

关于

Biomni is a specialized Claude Code skill that integrates Stanford's SNAP lab framework for autonomous biomedical research. It empowers users to handle complex, multi-step tasks such as CRISPR screening design, single-cell RNA-seq analysis, and ADMET prediction by combining LLM reasoning with an 11GB integrated biomedical database. This skill is ideal for researchers and bioinformaticians who need to automate data analysis pipelines, interpret GWAS results, or optimize lab protocols through an intelligent, code-executing agent interface that bridges the gap between biological knowledge and computational execution.

主要功能

Access to an 11GB integrated biomedical data lake (Ensembl, PDB, PubMed)
Advanced drug discovery tools for ADMET prediction and target identification
Dynamic analysis pipeline creation with automated code execution
Cross-domain support for genomics, proteomics, and clinical analysis
0 GitHub stars
Autonomous multi-step biological reasoning and task planning

使用场景

Automating single-cell RNA-seq clustering and cell type annotation
Designing genome-wide CRISPR screens and prioritizing hit genes
Predicting ADMET properties and toxicity liabilities for drug candidates

关于

主要功能

Access to an 11GB integrated biomedical data lake (Ensembl, PDB, PubMed)
Advanced drug discovery tools for ADMET prediction and target identification
Dynamic analysis pipeline creation with automated code execution
Cross-domain support for genomics, proteomics, and clinical analysis
0 GitHub stars
Autonomous multi-step biological reasoning and task planning

使用场景

Automating single-cell RNA-seq clustering and cell type annotation
Designing genome-wide CRISPR screens and prioritizing hit genes
Predicting ADMET properties and toxicity liabilities for drug candidates