VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910468969332736 |
|---|---|
| author | Li, Siyuan Wang, Zedong Liu, Zicheng Wu, Di Tan, Cheng Zheng, Jiangbin Huang, Yufei Li, Stan Z. |
| author_facet | Li, Siyuan Wang, Zedong Liu, Zicheng Wu, Di Tan, Cheng Zheng, Jiangbin Huang, Yufei Li, Stan Z. |
| contents | Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners in biology. However, the hand-crafted tokenization policies used in these models may not encode the most discriminative patterns from the limited vocabulary of genomic data. In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning. By leveraging vector-quantized codebooks as learnable vocabulary, VQDNA can adaptively tokenize genomes into pattern-aware embeddings in an end-to-end manner. To further push its limits, we propose Hierarchical Residual Quantization (HRQ), where varying scales of codebooks are designed in a hierarchy to enrich the genome vocabulary in a coarse-to-fine manner. Extensive experiments on 32 genome datasets demonstrate VQDNA's superiority and favorable parameter efficiency compared to existing genome language models. Notably, empirical analysis of SARS-CoV-2 mutations reveals the fine-grained pattern awareness and biological significance of learned HRQ vocabulary, highlighting its untapped potential for broader applications in genomics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10812 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling Li, Siyuan Wang, Zedong Liu, Zicheng Wu, Di Tan, Cheng Zheng, Jiangbin Huang, Yufei Li, Stan Z. Genomics Artificial Intelligence Similar to natural language models, pre-trained genome language models are proposed to capture the underlying intricacies within genomes with unsupervised sequence modeling. They have become essential tools for researchers and practitioners in biology. However, the hand-crafted tokenization policies used in these models may not encode the most discriminative patterns from the limited vocabulary of genomic data. In this paper, we introduce VQDNA, a general-purpose framework that renovates genome tokenization from the perspective of genome vocabulary learning. By leveraging vector-quantized codebooks as learnable vocabulary, VQDNA can adaptively tokenize genomes into pattern-aware embeddings in an end-to-end manner. To further push its limits, we propose Hierarchical Residual Quantization (HRQ), where varying scales of codebooks are designed in a hierarchy to enrich the genome vocabulary in a coarse-to-fine manner. Extensive experiments on 32 genome datasets demonstrate VQDNA's superiority and favorable parameter efficiency compared to existing genome language models. Notably, empirical analysis of SARS-CoV-2 mutations reveals the fine-grained pattern awareness and biological significance of learned HRQ vocabulary, highlighting its untapped potential for broader applications in genomics. |
| title | VQDNA: Unleashing the Power of Vector Quantization for Multi-Species Genomic Sequence Modeling |
| topic | Genomics Artificial Intelligence |
| url | https://arxiv.org/abs/2405.10812 |