Skip to content
biomni logo

Biomni

biomni

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction,...

SKILL.md

Full skill instructions

Biomni

Overview

Biomni is an open-source biomedical AI agent framework from Stanford's SNAP lab that autonomously executes complex research tasks across biomedical domains. Use this skill when working on multi-step biological reasoning tasks, analyzing biomedical data, or conducting research spanning genomics, drug discovery, molecular biology, and clinical analysis.

Core Capabilities

Biomni excels at:

  1. Multi-step biological reasoning - Autonomous task decomposition and planning for complex biomedical queries
  2. Code generation and execution - Dynamic analysis pipeline creation for data processing
  3. Knowledge retrieval - Access to ~11GB of integrated biomedical databases and literature
  4. Cross-domain problem solving - Unified interface for genomics, proteomics, drug discovery, and clinical tasks

When to Use This Skill

Use biomni for:

  • CRISPR screening - Design screens, prioritize genes, analyze knockout effects
  • Single-cell RNA-seq - Cell type annotation, differential expression, trajectory analysis
  • Drug discovery - ADMET prediction, target identification, compound optimization
  • GWAS analysis - Variant interpretation, causal gene identification, pathway enrichment
  • Clinical genomics - Rare disease diagnosis, variant pathogenicity, phenotype-genotype mapping
  • Lab protocols - Protocol optimization, literature synthesis, experimental design

Quick Start

Installation and Setup

Install Biomni and configure API keys for LLM providers:

uv pip install biomni --upgrade

Configure API keys (store in .env file or environment variables):

export ANTHROPIC_API_KEY="your-key-here"
# Optional: OpenAI, Azure, Google, Groq, AWS Bedrock keys

Use scripts/​setup_environment.py for interactive setup assistance.

Basic Usage Pattern

from biomni.agent import A1

# Initialize agent with data path and LLM choice
agent = A1(path='./​data', llm='claude-sonnet-4-20250514')

# Execute biomedical task autonomously
agent.go("Your biomedical research question or task")

# Save conversation history and results
agent.save_conversation_history("report.pdf")

Working with Biomni

1. Agent Initialization

The A1 class is the primary interface for biomni:

from biomni.agent import A1
from biomni.config import default_config

# Basic initialization
agent = A1(
    path='./​data',  # Path to data lake (~11GB downloaded on first use)
    llm='claude-sonnet-4-20250514'  # LLM model selection
)

# Advanced configuration
default_config.llm = "gpt-4"
default_config.timeout_seconds = 1200
default_config.max_iterations = 50

Supported LLM Providers:

  • Anthropic Claude (recommended): claude-sonnet-4-20250514, claude-opus-4-20250514
  • OpenAI: gpt-4, gpt-4-turbo
  • Azure OpenAI: via Azure configuration
  • Google Gemini: gemini-2.0-flash-exp
  • Groq: llama-3.3-70b-versatile
  • AWS Bedrock: Various models via Bedrock API

See references/​llm_providers.md for detailed LLM configuration instructions.

2. Task Execution Workflow

Biomni follows an autonomous agent workflow:

# Step 1: Initialize agent
agent = A1(path='./​data', llm='claude-sonnet-4-20250514')

# Step 2: Execute task with natural language query
result = agent.go("""
Design a CRISPR screen to identify genes regulating autophagy in
HEK293 cells. Prioritize genes based on essentiality and pathway
relevance.
""")

# Step 3: Review generated code and analysis
# Agent autonomously:
# - Decomposes task into sub-steps
# - Retrieves relevant biological knowledge
# - Generates and executes analysis code
# - Interprets results and provides insights

# Step 4: Save results
agent.save_conversation_history("autophagy_screen_report.pdf")

3. Common Task Patterns

CRISPR Screening Design
agent.go("""
Design a genome-wide CRISPR knockout screen for identifying genes
affecting [phenotype] in [cell type]. Include:
1. sgRNA library design
2. Gene prioritization criteria
3. Expected hit genes based on pathway analysis
""")
Single-Cell RNA-seq Analysis
agent.go("""
Analyze this single-cell RNA-seq dataset:
- Perform quality control and filtering
- Identify cell populations via clustering
- Annotate cell types using marker genes
- Conduct differential expression between conditions
File path: [path/​to/​data.h5ad]
""")
Drug ADMET Prediction
agent.go("""
Predict ADMET properties for these drug candidates:
[SMILES strings or compound IDs]
Focus on:
- Absorption (Caco-2 permeability, HIA)
- Distribution (plasma protein binding, BBB penetration)
- Metabolism (CYP450 interaction)
- Excretion (clearance)
- Toxicity (hERG liability, hepatotoxicity)
""")
GWAS Variant Interpretation
agent.go("""
Interpret GWAS results for [trait/​disease]:
- Identify genome-wide significant variants
- Map variants to causal genes
- Perform pathway enrichment analysis
- Predict functional consequences
Summary statistics file: [path/​to/​gwas_summary.txt]
""")

See references/​use_cases.md for comprehensive task examples across all biomedical domains.

4. Data Integration

Biomni integrates ~11GB of biomedical knowledge sources:

  • Gene databases - Ensembl, NCBI Gene, UniProt
  • Protein structures - PDB, AlphaFold
  • Clinical datasets - ClinVar, OMIM, HPO
  • Literature indices - PubMed abstracts, biomedical ontologies
  • Pathway databases - KEGG, Reactome, GO

Data is automatically downloaded to the specified path on first use.

5. MCP Server Integration

Extend biomni with external tools via Model Context Protocol:

# MCP servers can provide:
# - FDA drug databases
# - Web search for literature
# - Custom biomedical APIs
# - Laboratory equipment interfaces

# Configure MCP servers in .biomni/​mcp_config.json

6. Evaluation Framework

Benchmark agent performance on biomedical tasks:

from biomni.eval import BiomniEval1

evaluator = BiomniEval1()

# Evaluate on specific task types
score = evaluator.evaluate(
    task_type='crispr_design',
    instance_id='test_001',
    answer=agent_output
)

# Access evaluation dataset
dataset = evaluator.load_dataset()

Best Practices

Task Formulation

  • Be specific - Include biological context, organism, cell type, conditions
  • Specify outputs - Clearly state desired analysis outputs and formats
  • Provide data paths - Include file paths for datasets to analyze
  • Set constraints - Mention time/​computational limits if relevant

Security Considerations

⚠️ Important: Biomni executes LLM-generated code with full system privileges. For production use:

  • Run in isolated environments (Docker, VMs)
  • Avoid exposing sensitive credentials
  • Review generated code before execution in sensitive contexts
  • Use sandboxed execution environments when possible

Performance Optimization

  • Choose appropriate LLMs - Claude Sonnet 4 recommended for balance of speed/​quality
  • Set reasonable timeouts - Adjust default_config.timeout_seconds for complex tasks
  • Monitor iterations - Track max_iterations to prevent runaway loops
  • Cache data - Reuse downloaded data lake across sessions

Result Documentation

# Always save conversation history for reproducibility
agent.save_conversation_history("results/​project_name_YYYYMMDD.pdf")

# Include in reports:
# - Original task description
# - Generated analysis code
# - Results and interpretations
# - Data sources used

Resources

References

Detailed documentation available in the references/ directory:

  • api_reference.md - Complete API documentation for A1 class, configuration, and evaluation
  • llm_providers.md - LLM provider setup (Anthropic, OpenAI, Azure, Google, Groq, AWS)
  • use_cases.md - Comprehensive task examples for all biomedical domains

Scripts

Helper scripts in the scripts/ directory:

  • setup_environment.py - Interactive environment and API key configuration
  • generate_report.py - Enhanced PDF report generation with custom formatting

External Resources

Troubleshooting

Common Issues

Data download fails

# Manually trigger data lake download
agent = A1(path='./​data', llm='your-llm')
# First .go() call will download data

API key errors

# Verify environment variables
echo $ANTHROPIC_API_KEY
# Or check .env file in working directory

Timeout on complex tasks

from biomni.config import default_config
default_config.timeout_seconds = 3600  # 1 hour

Memory issues with large datasets

  • Use streaming for large files
  • Process data in chunks
  • Increase system memory allocation

Getting Help

For issues or questions:

More skills from BbgnsurfTech

performing-visual-regression-testing logo
BbgnsurfTech/claude-skills-collection

performing-visual-regression-testing

This skill enables Claude to execute visual regression tests using tools like Percy, Chromatic, and BackstopJS. It captures screenshots, compares them against baselines, and analyzes visual differences to identify unintended UI changes. Use this skill when the user requests visual testing, UI cha...

25 0
View
uv logo
BbgnsurfTech/claude-skills-collection

uv

Expert guidance for Astral's uv - an extremely fast Python package and project manager. Use when working with Python projects, managing dependencies, creating scripts with PEP 723 metadata, installing tools, managing Python versions, or configuring package indexes. Covers project initialization, ...

25 0
View
ms365-tenant-manager logo
BbgnsurfTech/claude-skills-collection

ms365-tenant-manager

Comprehensive Microsoft 365 tenant administration skill for setup, configuration, user management, security policies, and organizational structure optimization for Global Administrators

25 0
View
finding-arbitrage-opportunities logo
BbgnsurfTech/claude-skills-collection

finding-arbitrage-opportunities

Identify profitable arbitrage opportunities across exchanges and DEXs in real-time. Use when discovering profitable arbitrage across exchanges. Trigger with phrases like "find arbitrage", "scan for arb opportunities", or "check arbitrage".

25 0
View
marketing-demand-acquisition logo
BbgnsurfTech/claude-skills-collection

marketing-demand-acquisition

Multi-channel demand generation, paid media optimization, SEO strategy, and partnership programs for Series A+ startups. Includes CAC calculator, channel playbooks, HubSpot integration, and international expansion tactics. Use when planning demand generation campaigns, optimizing paid media, buil...

25 0
View
web-artifacts-builder logo
BbgnsurfTech/claude-skills-collection

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

25 0
View
xdg-base-directory logo
BbgnsurfTech/claude-skills-collection

xdg-base-directory

When an application needs to store config, data, cache, or state files. When designing where user-specific files should live. When code writes to ~/.appname or hardcoded home paths. When implementing cross-platform file storage with platformdirs.

25 0
View
managing-database-testing logo
BbgnsurfTech/claude-skills-collection

managing-database-testing

This skill manages database testing by generating test data, wrapping tests in transactions, and validating database schemas. It is used to create robust and reliable database interactions. Claude uses this skill when the user requests database testing utilities, including test data generation, t...

25 0
View
processing-computer-vision-tasks logo
BbgnsurfTech/claude-skills-collection

processing-computer-vision-tasks

This skill enables Claude to process and analyze images using computer vision techniques. It's used to perform tasks such as object detection, image classification, and image segmentation. Use this skill when a user requests analysis of an image, asks for identification of objects within an image...

25 0
View
lead-research-assistant logo
BbgnsurfTech/claude-skills-collection

lead-research-assistant

Identifies high-quality leads for your product or service by analyzing your business, searching for target companies, and providing actionable contact strategies. Perfect for sales, business development, and marketing professionals.

25 0
View
pydeseq2 logo
BbgnsurfTech/claude-skills-collection

pydeseq2

Differential gene expression analysis (Python DESeq2). Identify DE genes from bulk RNA-seq counts, Wald tests, FDR correction, volcano/MA plots, for RNA-seq analysis.

25 0
View
generating-database-documentation logo
BbgnsurfTech/claude-skills-collection

generating-database-documentation

This skill enables Claude to automatically generate comprehensive documentation for existing database schemas using the database-documentation-gen plugin. It is triggered when the user requests database documentation, ERD diagrams, or a data dictionary. The plugin supports multiple database engin...

25 0
View

Popular AI tools

Kaiber logo
Video

Kaiber

Generate, edit, and beat-sync AI video with leading models in one workspace.

Paid
View
Vimcal logo
Productivity

Vimcal

The world's fastest calendar for remote work

Free
View

Transform Your Design with AI Designer by ImgCreator.ai

Freemium
View
Akool AI logo
Content & writing

Akool AI

Revolutionizing Video Production with AI-Powered Creativity

Paid
View

Extend an image past the frame and let AI fill the new aspect ratio.

Freemium
View
StarByFace logo
Security

StarByFace

Discover your celebrity doppelgänger with StarByFace!

Free
View
C

ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.

Freemium
View
Opus Clip logo
Coding & apps

Opus Clip

Opus.ai: Revolutionize Your Web Experience

Free
View