Skip to main content
🧬

Caduceus Genomics LLM

Open-source long-context LLM pre-trained on DNA and genomic sequences

Healthcare
Caduceus Genomics LLM logo

Caduceus Genomics LLM

Open-source long-context LLM pre-trained on DNA and genomic sequences

Caduceus is an open-source large language model developed by researchers at Carnegie Mellon and Princeton, pre-trained on the human genome and other DNA sequences using a bidirectional Mamba SSM architecture. Unlike standard LLMs, Caduceus processes DNA sequences as tokens and enables downstream tasks like variant effect prediction, gene expression modeling, and regulatory element classification. Supports sequences up to 131K base pairs.

Key Features

  • 131K DNA sequence context
  • Bidirectional Mamba
  • Variant effect prediction
  • Gene expression modeling
  • Open weights
  • Genomics research
#genomics#biomedical#dna#research#open-source

Get Started

Visit Caduceus Genomics LLM
🟢
Free
Completely free to use

Quick Info

Category
Healthcare
Pricing
Free

More Healthcare Tools