变压器显著改善了拼接部位预测
Benedikt A Jónsson1,2, Gísli H Halldórsson1, Steinþór Árdal1,2
1deCODE Genetics/Amgen Inc., Reykjavik, Iceland.
Communications biology
|December 5, 2024
概括
我们开发了一种新的机器学习方法,使用变压器准确检测长DNA序列的RNA拼接. 这种方法改进了现有的遗传研究工具和诊断接相关疾病的方法.
科学领域:
- 基因组学就是基因组学.
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
背景情况:
- 影响RNA拼接的突变对人类多样性和疾病至关重要.
- 精确检测拼接事件对于遗传研究和诊断至关重要.
研究的目的:
- 引入一种新的机器学习方法,用于检测从长核酸序列中RNA剪接.
- 评估这种新方法的性能与现有最先进的工具相比.
主要方法:
- 利用变压器,一种机器学习模型,用于拼接检测.
- 产生了与残余神经网络的嵌入,并对高效的长序列训练进行了严格的注意.
- 在GENCODE和ENSEMBL注释以及来自冰岛和GTEx队列的RNA测序数据上测试了该方法.
主要成果:
- 与领先的工具SpliceAI.相比,新方法在检测拼接部位方面表现优越.
- 在大型队列中实现更高精度回忆AUC (0.834对比0.820) 用于拼接连接检测.
- 在ClinVar中,在识别与疾病相关的拼接变体方面表现出更大的有效性 (PR-AUC = 0.997对比0.996).
结论:
- 开发的基于变压器的方法为RNA拼接检测提供了更高的准确性.
- 这一进步有很大的潜力改善遗传研究和临床诊断用于拼接相关疾病.
相关概念视频
Pre-mRNA Processing: RNA Splicing
5.2K
5.2K
Long-patch Base Excision Repair
7.0K
Since the discovery of the two BER pathways, there has been a debate about how a cell chooses one pathway over the other and the factors determining this selection. Numerous in vitro experiments have pointed out multiple determinants for the sub-pathway selection. These are:
7.0K
Fixing Double-strand Breaks
12.3K
The double-stranded structure of DNA has two major advantages. First, it serves as a safe repository of genetic information where one strand serves as the back-up in case the other strand is damaged. Second, the double-helical structure can be wrapped around proteins called histones to form nucleosomes, which can then be tightly wound to form chromosomes. This way, DNA chains up to 2 inches long can be contained within microscopic structures in a cell. A double-stranded break not only damages...
12.3K
RNA Splicing
56.0K
Splicing is the process by which eukaryotic RNA is edited before its translation into protein. The RNA strand transcribed from eukaryotic DNA is called the primary transcript. The primary transcripts that become mRNAs are called precursor messenger RNAs (pre-mRNAs). Eukaryotic pre-mRNA contains alternating sequences of exons and introns. Exons are nucleotide sequences that code for proteins, whereas introns are the non-coding regions. In RNA splicing, introns are removed and exons are bonded...
56.0K
Conservative Site-specific Recombination and Phase Variation
5.9K
Because the DNA segments are cut and reorganized in a direction-specific manner, site-specific recombination has emerged as an efficient genetic engineering technique. Flippase and Cyclization recombinases or Flp and Cre, respectively, are two members of the tyrosine recombinase family derived from bacteriophages, that are used to mediate site-specific DNA insertions, deletions, and targeted expression of proteins in mammalian cell lines.
The recognition sites for Cre recombinase called LoxP...
The recognition sites for Cre recombinase called LoxP...
5.9K
Alternative RNA Splicing
21.0K
Alternative RNA splicing is the regulated splicing of exons and introns to produce different mature mRNAs from a single pre-mRNA. Unlike in constitutive splicing where a single gene produces a single type of mRNA, alternative splicing allows an organism to produce multiple proteins from a single gene and plays an important role in protein diversity.
There are five types of alternative RNA splicing that vary in the ways the pre-mRNA segments are removed or retained in the mature mRNA. The first...
There are five types of alternative RNA splicing that vary in the ways the pre-mRNA segments are removed or retained in the mature mRNA. The first...
21.0K


