Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.16262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912168360804352 |
|---|---|
| author | Marathe, Vishwajeet Bajracharya, Deewan Yan, Changhui |
| author_facet | Marathe, Vishwajeet Bajracharya, Deewan Yan, Changhui |
| contents | During a virus's evolution,various regions of the genome are subjected to distinct levels of functional constraints.Combined with factors like codon bias and DNA repair efficiency,these constraints contribute to unique mutation patterns within the genome or a specific gene. In this project, we harnessed the power of Large Language Models(LLMs) to predict the evolution of SARS-CoV-2. By treating the mutation process from one generation to the next as a translation task, we trained a transformer model, called VirusT5, to capture the mutation patterns underlying SARS-CoV-2 evolution. We evaluated the VirusT5's ability to detect these mutation patterns including its ability to identify mutation hotspots and explored the potential of using VirusT5 to predict future virus variants. Our findings demonstrate the feasibility of using a large language model to model viral evolution as a translation process. This study establishes the groundbreaking concept of "mutation-as-translation," paving the way for new methodologies and tools for combating virus threats |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16262 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | VirusT5: Harnessing Large Language Models to Predicting SARS-CoV-2 Evolution Marathe, Vishwajeet Bajracharya, Deewan Yan, Changhui Quantitative Methods Artificial Intelligence During a virus's evolution,various regions of the genome are subjected to distinct levels of functional constraints.Combined with factors like codon bias and DNA repair efficiency,these constraints contribute to unique mutation patterns within the genome or a specific gene. In this project, we harnessed the power of Large Language Models(LLMs) to predict the evolution of SARS-CoV-2. By treating the mutation process from one generation to the next as a translation task, we trained a transformer model, called VirusT5, to capture the mutation patterns underlying SARS-CoV-2 evolution. We evaluated the VirusT5's ability to detect these mutation patterns including its ability to identify mutation hotspots and explored the potential of using VirusT5 to predict future virus variants. Our findings demonstrate the feasibility of using a large language model to model viral evolution as a translation process. This study establishes the groundbreaking concept of "mutation-as-translation," paving the way for new methodologies and tools for combating virus threats |
| title | VirusT5: Harnessing Large Language Models to Predicting SARS-CoV-2 Evolution |
| topic | Quantitative Methods Artificial Intelligence |
| url | https://arxiv.org/abs/2412.16262 |