Transform your bioinformatics research with AI agents that understand your data and provide expert analysis insights.
- ✨ What is Lobster AI?
- 🚀 Quick Start
- 💡 Example Usage
- 🧬 Features
- 🔧 Configuration
- 📚 Documentation
- 🤝 Community & Support
- 📄 License
Lobster AI is a bioinformatics platform that combines specialized AI agents with open-source tools to analyze complex multi-omics data (starting with transcriptomics). Simply describe your analysis needs in natural language - no coding required.
Perfect for:
- Bioinformatics researchers analyzing RNA-seq data
- Computational biologists seeking intelligent analysis workflows
- Life science teams requiring reproducible, publication-ready results
- Students learning modern bioinformatics approaches
- Python 3.12 or higher
- An LLM API key (Claude or AWS Bedrock)
# 1. Clone the repository
git clone https://github.com/the-omics-os/lobster-local.git
cd lobster-local
# 2. Install with make (automatically creates .env file)
make install
# 3. Configure your API key
# The .env file is automatically created during installation
# Edit it with your preferred editor:
# macOS:
open .env
# Linux:
nano .env
# Windows (untested):
notepad .env
# Add your API key to the .env file:
# ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
# 4. Activate the virtual environment
source .venv/bin/activate
# 5. Start analyzing!
lobster chat
# or if you want to see the reasoning
lobster chat --reasoning
# Optional: Install globally to use 'lobster' from any directory
make install-global
Rate Limits
Anthropic's API has conservative rate limits for new accounts. If you encounter rate limit errors:
- Wait and retry - Limits reset after a short period (typically 60 seconds)
- Request increase - Visit Anthropic Rate Limits Documentation
- Use AWS Bedrock - Recommended for production use with higher limits
- Contact us - Email info@omics-os.com for assistance
Recommended Setup by Use Case:
Use Case | Recommended Provider | Notes |
---|---|---|
Quick Testing | Claude API | May encounter rate limits |
Development | Claude API + Rate Increase | Request higher limits from Anthropic |
Production | AWS Bedrock | Enterprise-grade limits |
Heavy Analysis | AWS Bedrock | Required for large datasets |
For AWS Bedrock setup, see the Configuration Guide.
🦞 lobster chat
Welcome to Lobster AI - Your bioinformatics analysis assistant
🦞 You: Download GSE109564 and perform single-cell clustering analysis
🦞 Lobster: I'll download and analyze this single-cell dataset for you...
✓ Downloaded 5,000 cells × 20,000 genes
✓ Quality control: filtered to 4,477 high-quality cells
✓ Identified 12 distinct cell clusters
✓ Generated UMAP visualization and marker gene analysis
Analysis complete! Results saved to workspace.
Command | Description |
---|---|
/help |
Show all available commands |
/files |
List workspace files |
/read <file> |
Load a dataset |
/data |
Show current dataset info |
/plots |
List generated visualizations |
/workspace |
Show workspace information |
/workspace list |
List available datasets |
/workspace load <name> |
Load specific dataset |
# Download and analyze GEO datasets
🦞 You: "Download GSE12345 and perform quality control"
# Analyze your own data
🦞 You: "Load my_data.csv and identify differentially expressed genes"
# Generate visualizations
🦞 You: "Create a UMAP plot colored by cell type"
# Perform complex analyses
🦞 You: "Run pseudobulk aggregation and differential expression between conditions"
- Quality control and filtering
- Normalization and scaling
- Clustering and UMAP visualization
- Cell type annotation
- Marker gene identification
- Pseudobulk aggregation
- Differential expression with pyDESeq2
- R-style formula-based statistics
- Complex experimental designs
- Batch effect correction
- Support for CSV, Excel, H5AD, 10X formats
- GEO dataset downloading
- Literature mining via PubMed
- Automatic visualization generation
- Mass spectrometry proteomics (DDA/DIA workflows)
- Affinity proteomics (Olink panels, antibody arrays)
- Missing value handling and normalization
- Pathway enrichment analysis
- Cross-platform data integration
- Multi-modal analysis workflows
- Scalable cloud computing
- No local hardware requirements
The .env
file is automatically created during installation (make install
calls setup-env
). You just need to edit it with your API credentials.
Edit the .env file:
# macOS - Opens in default text editor (TextEdit, etc.)
open .env
# Linux - Use nano or your preferred editor
nano .env
# Windows (⚠️ untested platform)
notepad .env
Choose ONE LLM provider:
Option 1: Claude API (Recommended for quick start)
# Get your key from https://console.anthropic.com/
ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
Option 2: AWS Bedrock (Recommended for production)
# Requires AWS account with Bedrock access
AWS_BEDROCK_ACCESS_KEY=AKIA...
AWS_BEDROCK_SECRET_ACCESS_KEY=your-secret-key
# Enhanced literature search (optional)
NCBI_API_KEY=your-ncbi-api-key # Get from NCBI
# Force specific provider (auto-detected by default)
LOBSTER_LLM_PROVIDER=anthropic # or "bedrock"
# Cloud mode (optional - contact info@omics-os.com for access)
LOBSTER_CLOUD_KEY=your-cloud-api-key
- ✅ macOS: Fully tested and supported
- ✅ Linux: Tested and supported
⚠️ Windows: Not currently tested (may work but no guarantees)
- Full Documentation - Guides and tutorials
- Example Analyses - Real-world use cases
- Architecture Overview - Technical details
- 🐛 Report Issues - Bug reports and feature requests
- 📧 Email Support - Direct help from our team
Need custom integrations or dedicated support? Contact us
Lobster AI is open source under the Apache License 2.0 (see LICENSE
). Documentation is licensed CC-BY-4.0.
Contributions are accepted under a Contributor License Agreement to preserve future licensing flexibility.