Which LLM models work best with Biomni?

While it supports various providers, Anthropic Claude (Sonnet 3.5 or Opus) is recommended for the best balance of scientific reasoning and code generation quality.

Does Biomni require a local database?

Yes, Biomni automatically downloads an approximately 11GB biomedical data lake on its first use to support its reasoning and analysis functions.

Can Biomni help with clinical genomics?

Yes, it can perform tasks like rare disease diagnosis, variant pathogenicity prediction, and phenotype-genotype mapping by leveraging integrated clinical datasets.

Is it safe to run Biomni locally?

Biomni executes LLM-generated code with system privileges to perform analysis. It is highly recommended to run the agent in isolated environments like Docker or virtual machines.

Biomni is an autonomous agent framework from Stanford SNAP lab designed for executing complex biomedical research tasks across various scientific domains using LLMs.

Biomni Biomedical Research Agent

Name: Biomni Biomedical Research Agent
Author: Microck

byMicrock

•

Data Science & ML

Automates complex biomedical research tasks including genomics, drug discovery, and clinical data analysis using an autonomous AI agent framework.

About

Biomni is an open-source autonomous agent framework developed by Stanford's SNAP lab, designed specifically to bridge the gap between high-level biological reasoning and technical data execution. It enables Claude to perform multi-step planning, generate and run analysis code, and retrieve insights from an integrated 11GB biomedical knowledge base encompassing gene databases, protein structures, and clinical literature. This skill is indispensable for researchers and bioinformaticians working on CRISPR design, single-cell RNA-seq, drug ADMET prediction, and GWAS interpretation, providing a unified interface for sophisticated scientific discovery.

Key Features

Autonomous multi-step biological reasoning and task decomposition
Dynamic Python code generation and execution for data pipelines
Integrated access to 11GB of curated biomedical databases
Cross-domain support for genomics, proteomics, and drug discovery
Built-in evaluation framework for benchmarking research outputs
81 GitHub stars

Use Cases

Predicting drug ADMET properties and performing target identification
Analyzing single-cell RNA-seq datasets for cell type annotation and trajectory analysis
Designing genome-wide CRISPR screens and prioritizing gene targets

About

Key Features

Autonomous multi-step biological reasoning and task decomposition
Dynamic Python code generation and execution for data pipelines
Integrated access to 11GB of curated biomedical databases
Cross-domain support for genomics, proteomics, and drug discovery
Built-in evaluation framework for benchmarking research outputs
81 GitHub stars

Use Cases

Predicting drug ADMET properties and performing target identification
Analyzing single-cell RNA-seq datasets for cell type annotation and trajectory analysis
Designing genome-wide CRISPR screens and prioritizing gene targets