mRNABench:一个精心策划的成熟mRNA属性和功能预测基准
Ruian Ian Shi1,2,3, Taykhoom Dalal3, Philip Fradkin1,2
1Department of Computer Science, University of Toronto.
bioRxiv : the preprint server for biology
|July 17, 2025
概括
mRNABench提供了一个标准化的基准,用于评估成熟信使RNA (mRNA) 生物学中的自我监督模型. 它确定了最佳模型和训练策略,以了解mRNA调节和功能.
科学领域:
- 计算生物学 计算生物学
- 分子生物学分子生物学
- 机器学习 机器学习
背景情况:
- 使者RNA (mRNA) 在基因表达中起着至关重要的作用,通过其半衰期,局部化和翻译效率影响细胞表型.
- 自主监督基础模型为研究mRNA调控代码提供了先进的功能,超越了传统监督学习的局限性.
- 缺乏标准化的基准阻碍了对mRNA生物学中不同自我监督模型的评估和比较.
研究的目的:
- 介绍mRNABench,这是一个全面的基准测试套件,用于评估成熟mRNA生物学中自我监督的核酸基础模型的性能.
- 评估这些模型在各种生物任务中产生的mRNA嵌入的表示质量.
- 促进对mRNA研究的优秀模型和培训方法的识别.
主要方法:
- 策划了十个不同的数据集和59个预测任务,涵盖成熟mRNA的关键特性.
- 评估了18个家族核酸基模型的性能,共进行了135,000次实验.
- 研究了参数缩放,组合概括,以及序列可压缩性和模型性能之间的关系.
主要成果:
- 确定了特定的自我监督学习目标之间的协同效应.
- 开发了一种基于Mamba的新型模型,可以在显著减少参数 (700倍更少) 的情况下实现最先进的性能.
- 证明了mRNABench在评估和比较mRNA生物学基础模型中的有效性.
结论:
- mRNABench提供了一个强大的框架,用于在mRNA生物学中对自我监督模型进行基准测试.
- 该研究强调了高效的大型模型的潜力,例如新的基于Mamba的架构.
- 该资源将加速人工智能的开发和应用,以了解mRNA调节和功能.
相关概念视频
Nuclear Export of mRNA
7.9K
Before mRNAs are exported to the cytoplasm, it is crucial to check each mRNA for structural and functional integrity. Eukaryotic cells use several different mechanisms, collectively known as mRNA surveillance, to look for irregularities in mRNAs. Irregular or aberrant mRNA are rapidly degraded by various enzymes. If a defective mRNA escapes the surveillance, it would be translated into a protein which would either be non-functional or not function properly. One of the primary irregularities in...
7.9K
mRNA Stability and Gene Expression
5.7K
The structure and stability of mRNA molecules regulates gene expression, as mRNAs are a key step in the pathway from gene to protein. In eukaryotes, the half-life of mRNA varies from a few minutes up to several days. mRNA stability is essential in growth and development. The absence of the proteins regulating its stability, such as tristetraprolin in mice, can cause systemic issues, including bone marrow overgrowth, inflammation, and autoimmunity.
Cis-acting Elements involved in mRNA stability
Cis-acting Elements involved in mRNA stability
5.7K
Nonsense-mediated mRNA Decay
10.9K
The Upf proteins that carry out nonsense-mediated decay (NMD) are found in all eukaryotic organisms, including humans. Each protein has an individual role, but they need to work in collaboration. Upf1 is an ATP-dependent RNA helicase that unwinds the RNA helix. Because Upf1 can unwind any RNA, Upf2 and Upf3 are required to help Upf1 discriminate between nonsense and normal mRNAs.
Usually, Upf3 binds to an Exon Junction Complex (EJC) at mRNA splice sites. If a ribosome fully translates the mRNA,...
Usually, Upf3 binds to an Exon Junction Complex (EJC) at mRNA splice sites. If a ribosome fully translates the mRNA,...
10.9K
Regulation of Expression Occurs at Multiple Steps
23.5K
Gene expression can be regulated at almost every step from gene to protein. Transcription is the step that is most commonly regulated. This involves the binding of proteins to short regulatory sequences on the DNA. This association can either promote or inhibit the transcription of a gene associated with the respective sequence.
Transcription results in the generation of precursor (pre-mRNA) that consists of both exons and introns, which needs further processing before being translated to a...
Transcription results in the generation of precursor (pre-mRNA) that consists of both exons and introns, which needs further processing before being translated to a...
23.5K
MicroRNAs
3.1K
MicroRNA (miRNA) are short, regulatory RNA transcribed from introns (non-coding regions of a gene) or intergenic regions (stretches of DNA present between genes). Several processing steps are required to form biologically active, mature miRNA. The initial transcript, called primary miRNA (pri-mRNA), base-pairs with itself, forming a stem-loop structure. Within the nucleus, an endonuclease enzyme, called Drosha, shortens the stem-loop structure into hairpin-shaped pre-miRNA. After the pre-miRNA...
3.1K
Regulation of Expression at Multiple Steps
1.0K
The gene expression in cells is regulated at different stages: (i) transcription, (ii) RNA processing, (iii) RNA localization, and (iv) translation. Transcriptional regulation is mediated by regulatory proteins such as transcription factors, activators, or repressors—these control gene expression by initiating or inhibiting the transcription of genes. Once a precursor or pre-mRNA is produced, it undergoes post-transcriptional modification, including 5' capping, splicing, and the...
1.0K


