Sequence-Only Prediction of Super-Enhancers in Human Cell Lines Using Transformer Models.

IF 3.6 3区 生物学 Q1 BIOLOGY Biology-Basel Pub Date : 2025-02-07 DOI:10.3390/biology14020172
Ekaterina V Kravchuk, German A Ashniev, Marina G Gladkova, Alexey V Orlov, Zoia G Zaitseva, Juri A Malkerov, Natalia N Orlova
{"title":"Sequence-Only Prediction of Super-Enhancers in Human Cell Lines Using Transformer Models.","authors":"Ekaterina V Kravchuk, German A Ashniev, Marina G Gladkova, Alexey V Orlov, Zoia G Zaitseva, Juri A Malkerov, Natalia N Orlova","doi":"10.3390/biology14020172","DOIUrl":null,"url":null,"abstract":"<p><p>The study discloses the application of transformer-based deep learning models for the task of super-enhancers prediction in human tumor cell lines with a specific focus on sequence-only features within studied entities of super-enhancer and enhancer elements in the human genome. The proposed SE-prediction method included the GENA-LM application at handling long DNA sequences with the classification task, distinguishing super-enhancers from enhancers using H3K36me, H3K4me1, H3K4me3 and H3K27ac landscape datasets from HeLa, HEK293, H2171, Jurkat, K562, MM1S and U87 cell lines. The model was fine-tuned on relevant sequence data, allowing for the analysis of extended genomic sequences without the need for epigenetic markers as proposed in early approaches. The study achieved balanced accuracy metrics, surpassing previous models like SENet, particularly in HEK293 and K562 cell lines. Also, it was shown that super-enhancers frequently co-localize with epigenetic marks such as H3K4me3 and H3K27ac. Therefore, the attention mechanism of the model provided insights into the sequence features contributing to SE classification, indicating a correlation between sequence-only features and mentioned epigenetic landscapes. These findings support the potential transformer models use in further genomic sequence analysis for bioinformatics applications in enhancer/super-enhancer characterization and gene regulation studies.</p>","PeriodicalId":48624,"journal":{"name":"Biology-Basel","volume":"14 2","pages":""},"PeriodicalIF":3.6000,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11852244/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biology-Basel","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3390/biology14020172","RegionNum":3,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

The study discloses the application of transformer-based deep learning models for the task of super-enhancers prediction in human tumor cell lines with a specific focus on sequence-only features within studied entities of super-enhancer and enhancer elements in the human genome. The proposed SE-prediction method included the GENA-LM application at handling long DNA sequences with the classification task, distinguishing super-enhancers from enhancers using H3K36me, H3K4me1, H3K4me3 and H3K27ac landscape datasets from HeLa, HEK293, H2171, Jurkat, K562, MM1S and U87 cell lines. The model was fine-tuned on relevant sequence data, allowing for the analysis of extended genomic sequences without the need for epigenetic markers as proposed in early approaches. The study achieved balanced accuracy metrics, surpassing previous models like SENet, particularly in HEK293 and K562 cell lines. Also, it was shown that super-enhancers frequently co-localize with epigenetic marks such as H3K4me3 and H3K27ac. Therefore, the attention mechanism of the model provided insights into the sequence features contributing to SE classification, indicating a correlation between sequence-only features and mentioned epigenetic landscapes. These findings support the potential transformer models use in further genomic sequence analysis for bioinformatics applications in enhancer/super-enhancer characterization and gene regulation studies.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
该研究披露了基于变换器的深度学习模型在人类肿瘤细胞系中超级增强子预测任务中的应用,特别关注人类基因组中超级增强子和增强子元件实体中的纯序列特征。所提出的 SE 预测方法包括 GENA-LM 应用程序,用于处理长 DNA 序列的分类任务,使用来自 HeLa、HEK293、H2171、Jurkat、K562、MM1S 和 U87 细胞系的 H3K36me、H3K4me1、H3K4me3 和 H3K27ac 景观数据集区分超级增强子和增强子。该模型在相关序列数据上进行了微调,从而可以分析扩展的基因组序列,而不需要早期方法中提出的表观遗传标记。该研究达到了均衡的准确度指标,超过了 SENet 等以前的模型,特别是在 HEK293 和 K562 细胞系中。研究还表明,超级增强子经常与 H3K4me3 和 H3K27ac 等表观遗传标记共定位。因此,该模型的注意机制有助于深入了解有助于SE分类的序列特征,表明纯序列特征与所提及的表观遗传景观之间存在相关性。这些研究结果支持将转化子模型用于进一步的基因组序列分析,以便在增强子/超级增强子特征描述和基因调控研究中进行生物信息学应用。
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 去求助
来源期刊
Biology-Basel
Biology-Basel Biological Science-Biological Science
CiteScore
5.70
自引率
4.80%
发文量
1618
审稿时长
11 weeks
期刊介绍: Biology (ISSN 2079-7737) is an international, peer-reviewed, quick-refereeing open access journal of Biological Science published by MDPI online. It publishes reviews, research papers and communications in all areas of biology and at the interface of related disciplines. Our aim is to encourage scientists to publish their experimental and theoretical results in as much detail as possible. There is no restriction on the length of the papers. The full experimental details must be provided so that the results can be reproduced. Electronic files regarding the full details of the experimental procedure, if unable to be published in a normal way, can be deposited as supplementary material.
期刊最新文献
The Role of tRNA-Derived Small RNAs (tsRNAs) in Regulating Cell Death of Cardiovascular Diseases. Effect of Fertilization on the Performance of Adult Pinus pinea Trees. Long-Term Engraftment of Cryopreserved Human Neurons for In Vivo Disease Modeling in Neurodegenerative Disease. CNPY2 in Solid Tumors: Mechanisms, Biomarker Potential, and Therapeutic Implications. Characterization of Exosome-like Nanoparticles from Saffron Tepals and Their Immunostimulatory Activity.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1