发表机构
Umeå University; Science for Life Laboratory (SciLifeLab)（于默奥大学; 生命科学实验室（SciLifeLab））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究结合智能体AI与静态分析，将生物信息学遗留代码翻译为Rust，在Bascet软件上实现规模、构建时间、性能的显著优化，且支持原生Windows运行，为生物信息学软件大规模重构提供了低成本方案。
AI 中文摘要
生物信息学领域面临遗留代码问题：这类代码虽被广泛使用，但可能已无维护人员，或由如今不熟悉的语言（如Perl、Fortran）编写，这会产生维护成本（技术债务）；同时，动态类型语言会对环境产生负面影响，且无法利用现代硬件的优势，遗留代码还可能存在安全或可靠性问题，不适合在临床环境中使用。本文展示，智能体AI结合静态分析可用于将遗留代码翻译为现代语言Rust；我们提供提示词和辅助软件以支持系统化翻译，并在NGS和成像领域的常用软件上进行了评估；我们在自研软件Bascet上展示了成果：代码规模缩减约80倍，构建时间缩短约10倍，关键步骤性能提升超3倍，还移除了Unix依赖，使Bascet成为唯一可在原生Windows上运行且无需容器的单细胞分析流程。因此，如今可在有限预算下对生物信息学软件进行大规模重构，从而能开发更复杂的工具。
英文摘要
The field of bioinformatics struggles with legacy code - old code that is commonly used but may no longer have a maintainer, or may be written in an now-unfamiliar language (e.g. Perl, Fortran). This incurs maintenance cost (technical debt), but dynamically typed languages also negatively impacts the environment and fail to make use of modern hardware. Legacy code may also have security or safety problems that make it unsuited for use in clinical settings. Here we show that agentic AI, combined with static analysis, can be used to translate legacy code to the modern language Rust. We provide prompts and supporting software to aid systematic translation, and evaluate it on common software for NGS and imaging. We showcase the result on our software Bascet: Size was reduced by ~80x, build time decreased by ~10x, and performance of key steps improved >3x. Unix dependencies were also removed, making Bascet the only single-cell pipeline able to run on native Windows, without a container. Large-scale refactoring of bioinformatics software is thus now possible at a limited budget, enabling more complex tools to be developed.
