Machine learning-based analysis of the impact of 5' untranslated region on protein expression.

IF 13.1 2区生物学 Q1 BIOCHEMISTRY & MOLECULAR BIOLOGY

Nucleic Acids Research Pub Date : 2025-09-05 DOI:10.1093/nar/gkaf861

Linfeng Wang,Sujia Liu,Jia-Xin Huang,Haifeng Zhu,Shuyu Li,Yannan Li,Sen Chen,Jianying Han,Yin Zhu,Jiahao Wu,Wentao Liao,Hongmei Zhang,Haiyan Zeng,Shaoting Li,Shuping Zhao,Bingwei Wang,Jiaqi Lin,Ji Zeng

{"title":"Machine learning-based analysis of the impact of 5' untranslated region on protein expression.","authors":"Linfeng Wang,Sujia Liu,Jia-Xin Huang,Haifeng Zhu,Shuyu Li,Yannan Li,Sen Chen,Jianying Han,Yin Zhu,Jiahao Wu,Wentao Liao,Hongmei Zhang,Haiyan Zeng,Shaoting Li,Shuping Zhao,Bingwei Wang,Jiaqi Lin,Ji Zeng","doi":"10.1093/nar/gkaf861","DOIUrl":null,"url":null,"abstract":"The 5' untranslated region (5'UTR) plays a crucial regulatory role in messenger RNA (mRNA), with modified 5'UTRs extensively utilized in vaccine production, gene therapy, etc. Nevertheless, manually optimizing 5'UTRs may encounter difficulties in balancing the effects of various cis-elements. Consequently, multiple 5'UTR libraries have been created, and machine learning models have been employed to analyze and predict translation efficiency (TE) and protein expression, providing insights into critical regulatory features. On the one hand, these screening libraries, based on TE and mean ribosome load, struggle to accurately quantify protein expression; on the other hand, a precise method for quantifying 5'UTRs necessitates a significantly costlier library. To resolve this dilemma, we constructed a library utilizing firefly luciferase as the reporter to measure accurate protein expression. In addition, we optimized the library construction method by clustering mRNA sequences to reduce redundant data and minimize the size of the dataset. This dual strategy by increasing accuracy and reducing dataset size was found to be effective in predicting the 5'UTRs from the PC3 cell line.","PeriodicalId":19471,"journal":{"name":"Nucleic Acids Research","volume":"307 1","pages":""},"PeriodicalIF":13.1000,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nucleic Acids Research","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1093/nar/gkaf861","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

The 5' untranslated region (5'UTR) plays a crucial regulatory role in messenger RNA (mRNA), with modified 5'UTRs extensively utilized in vaccine production, gene therapy, etc. Nevertheless, manually optimizing 5'UTRs may encounter difficulties in balancing the effects of various cis-elements. Consequently, multiple 5'UTR libraries have been created, and machine learning models have been employed to analyze and predict translation efficiency (TE) and protein expression, providing insights into critical regulatory features. On the one hand, these screening libraries, based on TE and mean ribosome load, struggle to accurately quantify protein expression; on the other hand, a precise method for quantifying 5'UTRs necessitates a significantly costlier library. To resolve this dilemma, we constructed a library utilizing firefly luciferase as the reporter to measure accurate protein expression. In addition, we optimized the library construction method by clustering mRNA sequences to reduce redundant data and minimize the size of the dataset. This dual strategy by increasing accuracy and reducing dataset size was found to be effective in predicting the 5'UTRs from the PC3 cell line.

查看原文本刊更多论文

基于机器学习的5'非翻译区对蛋白表达影响分析。

5‘非翻译区（5’ utr）对信使RNA （mRNA）起着至关重要的调控作用，修饰后的5' utr广泛应用于疫苗生产、基因治疗等领域。然而，手动优化5' utr可能会在平衡各种顺式元素的影响方面遇到困难。因此，研究人员创建了多个5'UTR库，并使用机器学习模型来分析和预测翻译效率（TE）和蛋白质表达，从而深入了解关键的调控特征。一方面，这些基于TE和平均核糖体负荷的筛选文库难以准确量化蛋白质表达；另一方面，量化5' utr的精确方法需要一个非常昂贵的库。为了解决这一难题，我们利用萤火虫荧光素酶作为报告基因构建了一个文库，以测量准确的蛋白表达。此外，我们通过mRNA序列聚类优化了文库构建方法，以减少冗余数据，使数据集的大小最小化。这种通过提高准确性和减少数据集大小的双重策略被发现可以有效地预测来自PC3细胞系的5' utr。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Nucleic Acids Research 生物-生化与分子生物学

CiteScore

27.10

自引率

4.70%

发文量

1057

审稿时长

2 months

期刊介绍： Nucleic Acids Research (NAR) is a scientific journal that publishes research on various aspects of nucleic acids and proteins involved in nucleic acid metabolism and interactions. It covers areas such as chemistry and synthetic biology, computational biology, gene regulation, chromatin and epigenetics, genome integrity, repair and replication, genomics, molecular biology, nucleic acid enzymes, RNA, and structural biology. The journal also includes a Survey and Summary section for brief reviews. Additionally, each year, the first issue is dedicated to biological databases, and an issue in July focuses on web-based software resources for the biological community. Nucleic Acids Research is indexed by several services including Abstracts on Hygiene and Communicable Diseases, Animal Breeding Abstracts, Agricultural Engineering Abstracts, Agbiotech News and Information, BIOSIS Previews, CAB Abstracts, and EMBASE.