GROVER

🚀 DNA Language Model GROVER

This is an official pre - trained model that learns sequence context in the human genome, offering valuable insights in the fields of biology, DNA, and genomics.

🚀 Quick Start

This is the official pre - trained model introduced in DNA language model GROVER learns sequence context in the human genome.

# Import the tokenizer and the model
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("PoetschLab/GROVER")
model = AutoModelForMaskedLM.from_pretrained("PoetschLab/GROVER")

✨ Features

Some preliminary analysis shows that sequence re - tokenization using Byte Pair Encoding (BPE) changes significantly if the sequence is less than 50 nucleotides long. Longer than 50 nucleotides, you should still be careful with sequence edges. We advice to add 100 nucleotides at the beginning and end of every sequence in order to guarantee that your sequence is represented with the same tokens as the original tokenization. We also provide the tokenized chromosomes with their respective nucleotide mappers (They are available in the folder tokenized chromosomes).

📚 Documentation

BibTeX entry and citation info

@article{sanabria2024dna,
  title={DNA language model GROVER learns sequence context in the human genome},
  author={Sanabria, Melissa and Hirsch, Jonas and Joubert, Pierre M and Poetsch, Anna R},
  journal={Nature Machine Intelligence},
  pages={1--13},
  year={2024},
  publisher={Nature Publishing Group UK London}
}

💡 Usage Tip

Add 100 nucleotides at the beginning and end of every sequence to ensure that your sequence is represented with the same tokens as the original tokenization.