• 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

SpliceAI 预测变异剪接的性能评估。

Performance Evaluation of SpliceAI for the Prediction of Splicing of Variants.

机构信息

Department of Laboratory Medicine and Genetics, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul 06351, Korea.

出版信息

Genes (Basel). 2021 Aug 25;12(9):1308. doi: 10.3390/genes12091308.

DOI:10.3390/genes12091308
PMID:34573290
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8472818/
Abstract

Neurofibromatosis type 1, characterized by neurofibromas and café-au-lait macules, is one of the most common genetic disorders caused by pathogenic variants. Because of the high proportion of splicing mutations in , identifying variants that alter splicing may be an essential issue for laboratories. Here, we investigated the sensitivity and specificity of SpliceAI, a recently introduced splicing prediction algorithm in conjunction with other tools. We evaluated 285 variants identified from 653 patients. The effect on variants on splicing alteration was confirmed by complementary DNA sequencing followed by genomic DNA sequencing. For prediction of splicing effects, we used SpliceAI, MaxEntScan (MES), and Splice Site Finder-like (SSF). The sensitivity and specificity of SpliceAI were 94.5% and 94.3%, respectively, with a cut-off value of Δ Score > 0.22. The area under the curve of SpliceAI was 0.975 ( < 0.0001). Combined analysis of MES/SSF showed a sensitivity of 83.6% and specificity of 82.5%. The concordance rate between SpliceAI and MES/SSF was 84.2%. SpliceAI showed better performance for the prediction of splicing alteration for variants compared with MES/SSF. As a convenient web-based tool, SpliceAI may be helpful in clinical laboratories conducting DNA-based sequencing.

摘要

神经纤维瘤病 1 型,其特征为神经纤维瘤和咖啡牛奶斑,是由致病性变异引起的最常见的遗传疾病之一。由于剪接突变在 中所占比例较高,因此鉴定改变剪接的变异可能是实验室的一个重要问题。在这里,我们研究了 SpliceAI 的灵敏度和特异性,SpliceAI 是一种最近引入的剪接预测算法,并结合了其他工具。我们评估了从 653 名患者中鉴定出的 285 个变体。通过互补 DNA 测序和基因组 DNA 测序确认了变体对剪接改变的影响。为了预测剪接效应,我们使用了 SpliceAI、MaxEntScan (MES) 和 Splice Site Finder-like (SSF)。SpliceAI 的灵敏度和特异性分别为 94.5%和 94.3%,截断值为ΔScore>0.22。SpliceAI 的曲线下面积为 0.975(<0.0001)。MES/SSF 的联合分析显示灵敏度为 83.6%,特异性为 82.5%。SpliceAI 与 MES/SSF 的一致性率为 84.2%。与 MES/SSF 相比,SpliceAI 对 变体剪接改变的预测性能更好。作为一种方便的基于网络的工具,SpliceAI 可能有助于进行基于 DNA 的 测序的临床实验室。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/8948edaf2408/genes-12-01308-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/3ec1fee83eed/genes-12-01308-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/74eb1c70c0a7/genes-12-01308-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/8948edaf2408/genes-12-01308-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/3ec1fee83eed/genes-12-01308-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/74eb1c70c0a7/genes-12-01308-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/1d55/8472818/8948edaf2408/genes-12-01308-g003.jpg

相似文献

1
Performance Evaluation of SpliceAI for the Prediction of Splicing of Variants.SpliceAI 预测变异剪接的性能评估。
Genes (Basel). 2021 Aug 25;12(9):1308. doi: 10.3390/genes12091308.
2
Diagnostic value of multiple café-au-lait macules for neurofibromatosis 1 in Chinese children.多发性咖啡牛奶斑对中国儿童1型神经纤维瘤病的诊断价值
J Dermatol. 2016 May;43(5):537-42. doi: 10.1111/1346-8138.13169. Epub 2015 Oct 13.
3
Comparison of Tools for Splice-Altering Variant Prediction Using Established Spliceogenic Variants: An End-User's Point of View.使用已确定的剪接变异体进行剪接改变变异预测工具的比较:终端用户视角
Int J Genomics. 2022 Oct 13;2022:5265686. doi: 10.1155/2022/5265686. eCollection 2022.
4
Comprehensive RNA Analysis of the NF1 Gene in Classically Affected NF1 Affected Individuals Meeting NIH Criteria has High Sensitivity and Mutation Negative Testing is Reassuring in Isolated Cases With Pigmentary Features Only.对符合美国国立卫生研究院标准的典型受累神经纤维瘤病1型(NF1)患者的NF1基因进行全面RNA分析具有高灵敏度,且在仅具有色素沉着特征的孤立病例中,突变阴性检测结果令人安心。
EBioMedicine. 2016 May;7:212-20. doi: 10.1016/j.ebiom.2016.04.005. Epub 2016 Apr 13.
5
Phenotypic expression of a spectrum of Neurofibromatosis Type 1 (NF1) mutations identified through NGS and MLPA.通过 NGS 和 MLPA 鉴定的一系列神经纤维瘤病 1 型 (NF1) 突变的表型表达。
J Neurol Sci. 2018 Dec 15;395:95-105. doi: 10.1016/j.jns.2018.10.006. Epub 2018 Oct 4.
6
Novel and Recurring Disease-Causing NF1 Variants in Two Chinese Families with Neurofibromatosis Type 1.两例中国神经纤维瘤病 1 型家系中新型和重现的 NF1 致病变异。
J Mol Neurosci. 2018 Aug;65(4):557-563. doi: 10.1007/s12031-018-1128-9. Epub 2018 Jul 25.
7
High-yield identification of pathogenic NF1 variants by skin fibroblast transcriptome screening after apparently normal diagnostic DNA testing.通过明显正常的诊断 DNA 测试后,对皮肤成纤维细胞转录组进行筛选,可高效鉴定致病性 NF1 变异。
Hum Mutat. 2022 Dec;43(12):2130-2140. doi: 10.1002/humu.24487. Epub 2022 Nov 8.
8
Genotype-phenotype associations in neurofibromatosis type 1 (NF1): an increased risk of tumor complications in patients with NF1 splice-site mutations?神经纤维瘤病 1 型(NF1)的基因型-表型关联:NF1 剪接位点突变患者的肿瘤并发症风险增加?
Hum Genomics. 2012 Aug 13;6(1):12. doi: 10.1186/1479-7364-6-12.
9
Five novel NF1 gene pathogenic variants in 10 different Chinese families with neurofibromatosis type 1.10 个不同中国 NF1 家系中发现 5 种 NF1 基因致病性变异。
Mol Genet Genomic Med. 2019 Sep;7(9):e904. doi: 10.1002/mgg3.904. Epub 2019 Jul 25.
10
Jaffe-Campanacci syndrome, revisited: detailed clinical and molecular analyses determine whether patients have neurofibromatosis type 1, coincidental manifestations, or a distinct disorder.再探贾菲-坎帕纳奇综合征:详细的临床和分子分析确定患者是否患有1型神经纤维瘤病、巧合的表现或一种独特的疾病。
Genet Med. 2014 Jun;16(6):448-59. doi: 10.1038/gim.2013.163. Epub 2013 Nov 14.

引用本文的文献

1
Reassessment of variants of uncertain significance in tumor suppressor genes using new ClinGen PP1/PP4 criteria guidance.使用新的临床基因组资源(ClinGen)PP1/PP4标准指南重新评估肿瘤抑制基因中意义未明的变异体。
Eur J Hum Genet. 2025 Jul 23. doi: 10.1038/s41431-025-01911-z.
2
The Role of Artificial Intelligence in Identifying Gene Variants and Improving Diagnosis.人工智能在识别基因变异和改善诊断方面的作用。
Genes (Basel). 2025 May 7;16(5):560. doi: 10.3390/genes16050560.
3
A novel synonymous variant in the NF1 gene disrupting splicing contributes to neurofibromatosis pathogenesis.

本文引用的文献

1
Identification of Deep-Intronic Splice Mutations in a Large Cohort of Patients With Inherited Retinal Diseases.一大群遗传性视网膜疾病患者中深度内含子剪接突变的鉴定
Front Genet. 2021 Mar 2;12:647400. doi: 10.3389/fgene.2021.647400. eCollection 2021.
2
Prediction of Alzheimer's disease-specific phospholipase c gamma-1 SNV by deep learning-based approach for high-throughput screening.基于深度学习的高通量筛选阿尔茨海默病特异性磷酯酶 Cγ-1 SNV 的预测。
Proc Natl Acad Sci U S A. 2021 Jan 19;118(3). doi: 10.1073/pnas.2011250118.
3
GENCODE 2021.
NF1基因中一个破坏剪接的新型同义变异体促成了神经纤维瘤病的发病机制。
Front Genet. 2025 May 9;16:1572487. doi: 10.3389/fgene.2025.1572487. eCollection 2025.
4
An Update on Reported Variants in the Skeletal Muscle -Actin () Gene.骨骼肌α-肌动蛋白(α-actinin)基因中报道的变异体最新情况。
Hum Mutat. 2024 Oct 28;2024:6496088. doi: 10.1155/2024/6496088. eCollection 2024.
5
RNA Panel Sequencing Is an Effective Tool to Help Classify Splice Variants for Clinical Oncogenetic Diagnosis.RNA 基因panel测序是一种有效的工具,有助于对剪接变体进行分类以用于临床肿瘤遗传学诊断。
Hum Mutat. 2024 Apr 2;2024:4830045. doi: 10.1155/2024/4830045. eCollection 2024.
6
Phenotypic Characteristics of a Patient Cohort With Recessive Dystrophic Epidermolysis Bullosa and the Pathogenic Variant c.7485+5G>A in Intron 98 of COL7A1.患有隐性营养不良性大疱性表皮松解症且COL7A1基因第98内含子存在致病性变异c.7485+5G>A的患者队列的表型特征
Am J Med Genet A. 2025 Jul;197(7):e64032. doi: 10.1002/ajmg.a.64032. Epub 2025 Feb 27.
7
Functional evaluation of rare variants in complement factor I using a minigene assay.利用微基因检测方法对补体因子 I 中的稀有变异进行功能评估。
Front Immunol. 2024 Aug 22;15:1446081. doi: 10.3389/fimmu.2024.1446081. eCollection 2024.
8
Overcoming challenges associated with identifying FBN1 deep intronic variants through whole-genome sequencing.通过全基因组测序克服与鉴定 FBN1 深内含子变异相关的挑战。
J Clin Lab Anal. 2024 Jan;38(1-2):e25009. doi: 10.1002/jcla.25009. Epub 2024 Jan 17.
9
Predicting the impact of rare variants on RNA splicing in CAGI6.预测CAGI6中罕见变异对RNA剪接的影响。
Hum Genet. 2025 Mar;144(2-3):243-251. doi: 10.1007/s00439-023-02624-3. Epub 2024 Jan 3.
10
Benchmarking splice variant prediction algorithms using massively parallel splicing assays.基于大规模并行拼接分析的剪接变异预测算法的基准测试。
Genome Biol. 2023 Dec 21;24(1):294. doi: 10.1186/s13059-023-03144-z.
GENCODE 2021.
Nucleic Acids Res. 2021 Jan 8;49(D1):D916-D923. doi: 10.1093/nar/gkaa1087.
4
Evaluation of both exonic and intronic variants for effects on RNA splicing allows for accurate assessment of the effectiveness of precision therapies.评估外显子和内含子变异对 RNA 剪接的影响,可以准确评估精准治疗的效果。
PLoS Genet. 2020 Oct 21;16(10):e1009100. doi: 10.1371/journal.pgen.1009100. eCollection 2020 Oct.
5
The Experimentally Obtained Functional Impact Assessments of 5' Splice Site GT'GC Variants Differ Markedly from Those Predicted.实验获得的5'剪接位点GT'GC变体的功能影响评估与预测结果明显不同。
Curr Genomics. 2020 Jan;21(1):56-66. doi: 10.2174/1389202921666200210141701.
6
Blood RNA analysis can increase clinical diagnostic rate and resolve variants of uncertain significance.血液 RNA 分析可以提高临床诊断率,并解决意义不确定的变异。
Genet Med. 2020 Jun;22(6):1005-1014. doi: 10.1038/s41436-020-0766-9. Epub 2020 Mar 3.
7
Predicting Splicing from Primary Sequence with Deep Learning.深度学习预测剪接。
Cell. 2019 Jan 24;176(3):535-548.e24. doi: 10.1016/j.cell.2018.12.015. Epub 2019 Jan 17.
8
Computational Tools for Splicing Defect Prediction in Breast/Ovarian Cancer Genes: How Efficient Are They at Predicting RNA Alterations?用于预测乳腺癌/卵巢癌基因剪接缺陷的计算工具:它们在预测RNA改变方面的效率如何?
Front Genet. 2018 Sep 5;9:366. doi: 10.3389/fgene.2018.00366. eCollection 2018.
9
Novel diagnostic tool for prediction of variant spliceogenicity derived from a set of 395 combined in silico/in vitro studies: an international collaborative effort.一组 395 项联合计算机模拟/体外研究衍生的新型可变剪接预测诊断工具:一项国际合作研究。
Nucleic Acids Res. 2018 Sep 6;46(15):7913-7923. doi: 10.1093/nar/gky372.
10
Accurate Classification of Gene Variants in 84 Italian Patients with Neurofibromatosis Type 1.84例意大利1型神经纤维瘤病患者基因变异的准确分类
Genes (Basel). 2018 Apr 17;9(4):216. doi: 10.3390/genes9040216.