• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

用于RNA剪接预测与设计的生成式建模

Generative modeling for RNA splicing predictions and design.

作者信息

Wu Di, Maus Natalie, Jha Anupama, Yang Kevin, Wales-McGrath Benjamin D, Jewell San, Tangiyan Anna, Choi Peter, Gardner Jacob R, Barash Yoseph

机构信息

Department of Computer and Information Science, School of Engineering, University of Pennsylvania.

Department of Genome Sciences, University of Washington.

出版信息

bioRxiv. 2025 Jan 24:2025.01.20.633986. doi: 10.1101/2025.01.20.633986.

DOI:10.1101/2025.01.20.633986
PMID:39896553
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11785043/
Abstract

Alternative splicing (AS) of pre-mRNA plays a crucial role in tissue-specific gene regulation, with disease implications due to splicing defects. Predicting and manipulating AS can therefore uncover new regulatory mechanisms and aid in therapeutics design. We introduce TrASPr+BOS, a generative AI model with Bayesian Optimization for predicting and designing RNA for tissue-specific splicing outcomes. TrASPr is a multi-transformer model that can handle different types of AS events and generalize to unseen cellular conditions. It then serves as an oracle, generating labeled data to train a Bayesian Optimization for Splicing (BOS) algorithm to design RNA for condition-specific splicing outcomes. We show TrASPr+BOS outperforms existing methods, enhancing tissue-specific AUPRC by up to 2.4 fold and capturing tissue-specific regulatory elements. We validate hundreds of predicted novel tissue-specific splicing variations and confirm new regulatory elements using dCas13. We envision TrASPr+BOS as a light yet accurate method researchers can probe or adopt for specific tasks.

摘要

前体信使核糖核酸（pre-mRNA）的可变剪接（AS）在组织特异性基因调控中起着关键作用，剪接缺陷会引发疾病。因此，预测和操控可变剪接能够揭示新的调控机制，并有助于治疗方案的设计。我们引入了TrASPr+BOS，这是一种结合贝叶斯优化的生成式人工智能模型，用于预测和设计具有组织特异性剪接结果的RNA。TrASPr是一个多变压器模型，能够处理不同类型的可变剪接事件，并推广到未见过的细胞条件。然后，它作为一个神谕，生成标记数据来训练剪接贝叶斯优化（BOS）算法，以设计具有条件特异性剪接结果的RNA。我们表明，TrASPr+BOS优于现有方法，将组织特异性精确召回率（AUPRC）提高了2.4倍，并捕捉到组织特异性调控元件。我们验证了数百个预测的新型组织特异性剪接变异，并使用dCas13确认了新的调控元件。我们设想TrASPr+BOS是一种轻量级但准确的方法，研究人员可以针对特定任务进行探索或采用。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/92dd0d456ca9/nihpp-2025.01.20.633986v1-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/fbbc9b054e5e/nihpp-2025.01.20.633986v1-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/6fd52611e4f0/nihpp-2025.01.20.633986v1-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/0fb5cb8cceca/nihpp-2025.01.20.633986v1-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/ed60898542b8/nihpp-2025.01.20.633986v1-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/32335ba1809f/nihpp-2025.01.20.633986v1-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/5df8aeae3776/nihpp-2025.01.20.633986v1-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/67305ad20f2e/nihpp-2025.01.20.633986v1-f0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/41b6b7df3096/nihpp-2025.01.20.633986v1-f0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/b516de0f244e/nihpp-2025.01.20.633986v1-f0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/605332f73bf8/nihpp-2025.01.20.633986v1-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/88be03bde7ee/nihpp-2025.01.20.633986v1-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/e5f38135bdac/nihpp-2025.01.20.633986v1-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/9cdb45c94532/nihpp-2025.01.20.633986v1-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/44c7b924e5a6/nihpp-2025.01.20.633986v1-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/92dd0d456ca9/nihpp-2025.01.20.633986v1-f0006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/fbbc9b054e5e/nihpp-2025.01.20.633986v1-f0007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/6fd52611e4f0/nihpp-2025.01.20.633986v1-f0008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/0fb5cb8cceca/nihpp-2025.01.20.633986v1-f0009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/ed60898542b8/nihpp-2025.01.20.633986v1-f0010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/32335ba1809f/nihpp-2025.01.20.633986v1-f0011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/5df8aeae3776/nihpp-2025.01.20.633986v1-f0012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/67305ad20f2e/nihpp-2025.01.20.633986v1-f0013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/41b6b7df3096/nihpp-2025.01.20.633986v1-f0014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/b516de0f244e/nihpp-2025.01.20.633986v1-f0015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/605332f73bf8/nihpp-2025.01.20.633986v1-f0001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/88be03bde7ee/nihpp-2025.01.20.633986v1-f0002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/e5f38135bdac/nihpp-2025.01.20.633986v1-f0003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/9cdb45c94532/nihpp-2025.01.20.633986v1-f0004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/44c7b924e5a6/nihpp-2025.01.20.633986v1-f0005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/a97d/11785043/92dd0d456ca9/nihpp-2025.01.20.633986v1-f0006.jpg

相似文献

1
Generative modeling for RNA splicing predictions and design.用于RNA剪接预测与设计的生成式建模
bioRxiv. 2025 Jan 24:2025.01.20.633986. doi: 10.1101/2025.01.20.633986.
2
Genome-wide prediction of cis-acting RNA elements regulating tissue-specific pre-mRNA alternative splicing.调控组织特异性前体mRNA可变剪接的顺式作用RNA元件的全基因组预测
BMC Genomics. 2009 Jul 7;10 Suppl 1(Suppl 1):S4. doi: 10.1186/1471-2164-10-S1-S4.
3
A CRISPR-dCas13 RNA-editing tool to study alternative splicing.一种用于研究可变剪接的 CRISPR-dCas13 RNA 编辑工具。
Nucleic Acids Res. 2024 Oct 28;52(19):11926-11939. doi: 10.1093/nar/gkae682.
4
mRNA-Seq of testis and liver tissues reveals a testis-specific gene and alternative splicing associated with hybrid male sterility in dzo.睾丸和肝脏组织的 mRNA-Seq 分析揭示了一个与 dzo 杂种雄性不育相关的睾丸特异性基因和可变剪接。
J Anim Sci. 2024 Jan 3;102. doi: 10.1093/jas/skae091.
5
Bayesian prediction of tissue-regulated splicing using RNA sequence and cellular context.基于 RNA 序列和细胞环境的组织调控剪接的贝叶斯预测。
Bioinformatics. 2011 Sep 15;27(18):2554-62. doi: 10.1093/bioinformatics/btr444. Epub 2011 Jul 29.
6
Robust and annotation-free analysis of alternative splicing across diverse cell types in mice.在不同小鼠细胞类型中进行稳健且无需注释的选择性剪接分析。
Elife. 2022 Mar 1;11:e73520. doi: 10.7554/eLife.73520.
7
Inferring global levels of alternative splicing isoforms using a generative model of microarray data.使用微阵列数据生成模型推断可变剪接异构体的全局水平。
Bioinformatics. 2006 Mar 1;22(5):606-13. doi: 10.1093/bioinformatics/btk028. Epub 2006 Jan 10.
8
From computational models of the splicing code to regulatory mechanisms and therapeutic implications.从剪接密码的计算模型到调控机制及治疗意义
Nat Rev Genet. 2025 Mar;26(3):171-190. doi: 10.1038/s41576-024-00774-2. Epub 2024 Oct 2.
9
Linking transcriptome and morphology in bone cells at cellular resolution with generative AI.利用生成式人工智能在细胞分辨率下将骨细胞中的转录组与形态学联系起来。
J Bone Miner Res. 2024 Dec 31;40(1):20-26. doi: 10.1093/jbmr/zjae151.
10
Unannotated splicing regulatory elements in deep intron space.深内含子空间中的无注释剪接调控元件。
Wiley Interdiscip Rev RNA. 2021 Sep;12(5):e1656. doi: 10.1002/wrna.1656. Epub 2021 Apr 22.

本文引用的文献

1
Machine learning-optimized targeted detection of alternative splicing.机器学习优化的可变剪接靶向检测
Nucleic Acids Res. 2025 Jan 24;53(3). doi: 10.1093/nar/gkae1260.
2
SpliceTransformer predicts tissue-specific splicing linked to human diseases.SpliceTransformer 预测与人类疾病相关的组织特异性剪接。
Nat Commun. 2024 Oct 23;15(1):9129. doi: 10.1038/s41467-024-53088-6.
3
Self-supervised learning on millions of primary RNA sequences from 72 vertebrates improves sequence-based RNA splicing prediction.对来自 72 种脊椎动物的数百万个原始 RNA 序列进行自监督学习，可提高基于序列的 RNA 剪接预测。
Brief Bioinform. 2024 Mar 27;25(3). doi: 10.1093/bib/bbae163.
4
Ptpn23 Controls Cardiac T-Tubule Patterning by Promoting the Assembly of Dystrophin-Glycoprotein Complex.Ptpn23通过促进肌营养不良蛋白-糖蛋白复合物的组装来控制心脏T小管的形态。
Circulation. 2024 Apr 23;149(17):1375-1390. doi: 10.1161/CIRCULATIONAHA.123.065767. Epub 2024 Jan 12.
5
RBFOX2 deregulation promotes pancreatic cancer progression and metastasis through alternative splicing.RBFOX2 失调通过选择性剪接促进胰腺癌的进展和转移。
Nat Commun. 2023 Dec 19;14(1):8444. doi: 10.1038/s41467-023-44126-w.
6
PTPN23 ubiquitination by WDR4 suppresses EGFR and c-MET degradation to define a lung cancer therapeutic target.WDR4 介导的 PTPN23 泛素化抑制 EGFR 和 c-MET 的降解，为定义肺癌治疗靶点提供了依据。
Cell Death Dis. 2023 Oct 11;14(10):671. doi: 10.1038/s41419-023-06201-4.
7
LegNet: a best-in-class deep learning model for short DNA regulatory regions.LegNet：用于短 DNA 调控区域的一流深度学习模型。
Bioinformatics. 2023 Aug 1;39(8). doi: 10.1093/bioinformatics/btad457.
8
Aberrant splicing prediction across human tissues.跨人类组织的异常剪接预测
Nat Genet. 2023 May;55(5):861-870. doi: 10.1038/s41588-023-01373-3. Epub 2023 May 4.
9
RNA splicing analysis using heterogeneous and large RNA-seq datasets.使用异质和大型 RNA-seq 数据集进行 RNA 剪接分析。
Nat Commun. 2023 Mar 3;14(1):1230. doi: 10.1038/s41467-023-36585-y.
10
High-throughput mutagenesis identifies mutations and RNA-binding proteins controlling CD19 splicing and CART-19 therapy resistance.高通量诱变鉴定控制 CD19 剪接和 CART-19 治疗耐药性的突变和 RNA 结合蛋白。
Nat Commun. 2022 Sep 22;13(1):5570. doi: 10.1038/s41467-022-31818-y.