Plantcaduceus L32
PlantCaduceus is a DNA language model pre-trained on the genomes of 16 angiosperm species, utilizing Caduceus and Mamba architectures to learn evolutionary conservation and DNA sequence syntax through masked language modeling objectives.
Downloads 3,340
Release Time : 5/19/2024
Model Overview
PlantCaduceus is a DNA language model designed to learn evolutionary conservation and DNA sequence syntax from the genomes of 16 species, suitable for genome analysis and prediction tasks.
Model Features
Multi-species genome pre-training
Pre-trained on the genomes of 16 angiosperm species, covering 160 million years of evolutionary history.
Multiple parameter scales
Offers models ranging from 20 million to 225 million parameters to meet different computational needs.
Evolutionary conservation learning
Enhances genome analysis capabilities by learning evolutionary conservation and DNA sequence syntax.
Model Capabilities
DNA sequence analysis
Genome prediction
Evolutionary conservation learning
Use Cases
Genome research
Genome sequence analysis
Analyze the syntax and structural features of DNA sequences.
Evolutionary conservation prediction
Predict evolutionarily conserved regions in the genome.
Featured Recommended AI Models
Š 2025AIbase