DNABERT-H-2M is a DNA language model based on DNABERT-S (1) and trained using Hierarchical Multi-label Contrastive Learning from Use All The Labels [2]. [1] https://github.com/MAGICS-LAB/D
This work proposes a Markovian memoryless model for the DNA that simplifies enormously the complexity of it. We encode nucleotide sequences into symbolic sequences, called words, from which we establi