生物编码器:使用大型语言模型生成生物信息学代码的基准
Xiangru Tang1, Bill Qian1, Rick Gao1
1Department of Computer Science, Yale University, New Haven, CT 06520, United States.
Bioinformatics (Oxford, England)
|June 28, 2024
概括
一个新的基准BioCoder评估了生物信息学代码生成的大型语言模型 (LLM). 具有特定领域知识和长文本能力的模型表现最好.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 人工智能的人工智能
背景情况:
- 大型语言模型 (LLM) 在代码生成方面表现有前途,但对于复杂的任务需要域专业化.
- 生物信息学涉及复杂的算法,数据操作和领域知识,需要量身定制的LLM评估.
研究的目的:
- 介绍BioCoder,这是一个新的基准,旨在评估LLM在生成生物信息学特定代码方面的表现.
- 评估各种LLM在复杂的生物信息编码任务上的能力,包括交叉文件依赖和类声明.
主要方法:
- 使用 1026 个 Python 函数和 1243 个来自 GitHub 的 Java 方法开发 BioCoder,再加上 253 个 Rosalind 项目示例.
- 采用主题建模来确保基准代码对生物信息学计算的代表性.
- 利用一个模糊测试框架,在多个模型中进行严格的LLM评估.
主要成果:
- 评估了包括GPT-4,GPT-3.5,StarCoder等在内的模型,确定了关键性能因素.
- 证明了对特定域数据 (StarCoder) 的微调可以显著提高基准性能 (>15% Pass@K).
- 观察到具有长文本处理 (>2600令牌) 和生物信息学领域知识的模型优于一般模型.
结论:
- 在有效的生物信息代码生成中,LLM需要特定领域的知识和长时间的背景理解.
- 生物编码器是促进专业科学领域LLM能力的关键工具.
- 未来的LLM发展应优先考虑科学应用的专业知识和上下文意识的整合.
更多相关视频
03:37Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
Published on: March 1, 2024
686
09:34A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
Published on: September 25, 2021
3.9K
相关概念视频
Improving Translational Accuracy
10.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
10.0K
Synthetic Biology
4.7K
Synthetic biology is an interdisciplinary science that involves using principles from disciplines such as engineering, molecular biology, cell biology, and systems biology. It involves remodeling existing organisms from nature or constructing completely new synthetic organisms for applications such as protein or enzyme production, bioremediation, value-added macromolecule production, and the addition of desirable traits to crops, to name a few.
Golden rice
Golden rice is a genetically modified...
Golden rice
Golden rice is a genetically modified...
4.7K
Comparing Mitochondrial, Chloroplast, and Prokaryotic Genomes
12.3K
The present-day mitochondrial and chloroplast genomes have retained some of the characteristics of their ancestral prokaryotes and also have acquired new attributes during their evolution within eukaryotic cells. Like prokaryotic genomes, mitochondrial and chloroplast genomes neither bind with histone-like proteins nor show complex packaging into chromosome-like structures, as observed in eukaryotes. Unlike mitotic cell divisions observed in eukaryotic cells, mitochondria and chloroplasts...
12.3K
Genomics
36.3K
Genomics is the science of genomes: it is the study of all the genetic material of an organism. In humans, the genome consists of information carried in 23 pairs of chromosomes in the nucleus, as well as mitochondrial DNA. In genomics, both coding and non-coding DNA is sequenced and analyzed. Genomics allows a better understanding of all living things, their evolution, and their diversity. It has a myriad of uses: for example, to build phylogenetic trees, to improve productivity and...
36.3K
Biostatistics: Overview
233
Biostatistics plays a crucial role in understanding and analyzing data in healthcare and biology. Biostatisticians conduct experiments, gather evidence, and draw meaningful conclusions using statistical methods and techniques. Different variables form the foundation of biostatistical analysis, allowing researchers to understand and interpret data effectively. These variables are classified into different types, each serving a specific purpose in statistical analysis.
Discrete variables are...
Discrete variables are...
233
Per-Unit Sequence Models
73
An ideal Y-Y transformer, grounded through neutral impedances, displays per-unit sequence networks akin to those of a single-phase ideal transformer when subjected to balanced positive- or negative-sequence currents. These currents do not produce neutral currents, and their associated voltage drops.
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
Zero-sequence currents, which are identical in magnitude and phase, generate a neutral current, resulting in voltage drops across the neutral impedance and the low-voltage winding. If the...
73
