从文章到代码:从科学出版物中按需生成核心算法
Cameron S Movassaghi1, Amanda Momenzadeh1, Jesse G Meyer1
1Department of Computational Biomedicine, Cedars Sinai Medical Center, Los Angeles, CA 90048.
Bioinformatics (Oxford, England)
|January 11, 2026
概括
大型语言模型 (LLM) 可以直接从出版物中生成科学代码,与许多算法的现有库性能相匹配. 这种以文献为导向的方法显示了降低软件维护成本和提高可重复性的前景.
科学领域:
- 计算生物学是一种计算生物学.
- 生物信息学是一种生物信息学.
- 机器学习 机器学习
背景情况:
- 由于依赖性和错误,科学软件的维护成本很高.
- 发表的论文是正典记录,但将它们翻译成代码是很困难的.
- 大型语言模型 (LLM) 提供了从出版物中自动生成代码的潜力.
研究的目的:
- 评估利用LLMs从已发表的文章中生成科学代码的可行性.
- 评估LLM在复制既定计算算法的表现.
- 确定当前代码生成的出版标准中的局限性.
主要方法:
- 系统评估最先进的法学士课程.
- 让LLM执行核心算法,只使用科学出版物作为输入.
- 跨多种算法进行基准测试,包括随机森林,批量校正和基因组丰富分析.
主要成果:
- 对于许多算法来说,LLM成功地重现了包级功能.
- 通过LLM生成的代码性能往往无法与已建立的库区分开来.
- 差异主要源于低调的手稿细节,而不是LLM推理的限制.
结论:
- 基于文献的代码生成对于精确指定的算法是可行的.
- 通过LLM,可以减少对持续维护软件库的依赖.
- 目前的出版标准需要改进,以充分支持自动代码生成和可重复性.
相关概念视频
What is Genetic Engineering?
Overview
Genetic Screens
Genetic screens are tools used to identify genes and mutations responsible for phenotypes of interest. Genetic screens help identify individuals or a group of people at risk of developing genetic diseases and help them with early intervention, targeted therapy, and reproductive options.
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which result in visible changes...
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which result in visible changes...
Non-equilibrium in the Cell
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
Genome Size and the Evolution of New Genes
While every living organism has a genome of some kind (be it RNA, or DNA), there is considerable variation in the sizes of these blueprints. One major factor that impacts genome size is whether the organism is prokaryotic or eukaryotic. In prokaryotes, the genome contains little to no non-coding sequence, such that genes are tightly clustered in groups or operons sequentially along the chromosome. Conversely, the genes in eukaryotes are punctuated by long stretches of non-coding sequence.
DC Generator
An alternator converts mechanical energy into electrical energy that varies sinusoidally, resulting in AC current. Meanwhile, a DC generator converts mechanical energy into electrical energy, which are DC pulses with the same polarity. The construction of a DC generator is similar to that of an alternator, except that the pair of slip rings is replaced by a single split ring, also called a commutator. The commutator functions like a periodic rotary switch; it changes the contacts with the...
Behavioral Genetics and Its Designs
Behavior genetics explores how genetic inheritance influences human behavior. It focuses on how genes, passed from parents to offspring, contribute to the development of behavioral traits and tendencies. This branch of genetics seeks to understand the complex interplay between inherited genetic factors and environmental influences in shaping our behaviors.
The primary methodologies used in behavior genetics include family studies, twin studies, and adoption studies, each providing unique...
The primary methodologies used in behavior genetics include family studies, twin studies, and adoption studies, each providing unique...


