A Comparison of Tokenization Impact in AttentionBased and State Space Genomic Language Models

Genomic language models have recently emerged as a new method to decode, interpret, and generate genetic sequences. Existing genomic language models have utilized various tokenization methods, including character tokenization, overlapping and non-overlapping k-mer tokenization, and byte-pair encoding, a method widely used in natural language models. Genomic sequences differ from natural language because of their low character variability, complex and overlapping features, and inconsistent directionality. These features make sub-word tokenization in genomic language models significantly different from both traditional language models and protein language models. This study explores the impact of tokenization in genomic language models by evaluating their downstream performance on forty-four classification fine-tuning tasks. We also perform a direct comparison of byte pair encoding and character tokenization in Mamba, a state-space model. Our results indicate that character tokenization outperforms sub-word tokenization methods on tasks that rely on nucleotide level resolution, such as splice site prediction and promoter detection. While byte-pair tokenization had stronger performance on the SARS-CoV-2 variant classification task, we observed limited statistically significant differences between tokenization methods on the remaining downstream tasks.