Melissa Sanabria

The paper uses GROVER to analyze how DNA sequence, chromatin, and regulatory features influence genome stability by predicting DSB locations and identifying sequence tokens associated with DSB sensitivity.

The paper evaluates DNA language models by assessing their ability to distinguish sequence context from token identity, finding that overlapping k-mer tokenization limits context learning.

This paper introduces GROVER, a DNA language model trained on the human genome to generate a dictionary of tokens and analyze genomic sequence context and functional annotations.