亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Penguin: A tool for predicting pseudouridine sites in direct RNA nanopore sequencing data

假尿苷 核糖核酸 计算生物学 纳米孔测序 纳米孔 生物 遗传学 纳米技术 基因 转移RNA DNA测序 材料科学
作者
Doaa Hassan,Daniel Acevedo,Swapna Vidhur Daulatabad,Quoseena Mir,Sarath Chandra Janga
出处
期刊:Methods [Elsevier BV]
卷期号:203: 478-487 被引量:40
标识
DOI:10.1016/j.ymeth.2022.02.005
摘要

Pseudouridine is one of the most abundant RNA modifications, occurring when uridines are catalyzed by Pseudouridine synthase proteins. It plays an important role in many biological processes and has been reported to have application in drug development. Recently, the single-molecule sequencing techniques such as the direct RNA sequencing platform offered by Oxford Nanopore technologies have enabled direct detection of RNA modifications on the molecule being sequenced. In this study, we introduce a tool called Penguin that integrates several machine learning (ML) models to identify RNA Pseudouridine sites on Nanopore direct RNA sequencing reads. Pseudouridine sites were identified on single molecule sequencing data collected from direct RNA sequencing resulting in 723 K reads in Hek293 and 500 K reads in Hela cell lines. Penguin extracts a set of features from the raw signal measured by the Oxford Nanopore and the corresponding basecalled k-mer. Those features are used to train the predictors included in Penguin, which in turn, can predict whether the signal is modified by the presence of Pseudouridine sites in the testing phase. We have included various predictors in Penguin, including Support vector machines (SVM), Random Forest (RF), and Neural network (NN). The results on the two benchmark data sets for Hek293 and Hela cell lines show outstanding performance of Penguin either in random split testing or in independent validation testing. In random split testing, Penguin has been able to identify Pseudouridine sites with a high accuracy of 93.38% by applying SVM to Hek293 benchmark dataset. In independent validation testing, Penguin achieves an accuracy of 92.61% by training SVM with Hek293 benchmark dataset and testing it for identifying Pseudouridine sites on Hela benchmark dataset. Thus, Penguin outperforms the existing Pseudouridine predictors in the literature by 16 % higher accuracy than those predictors using independent validation testing. Employing penguin to predict Pseudouridine sites revealed a significant enrichment of “regulation of mRNA 3'-end processing” in Hek293 cell line and 'positive regulation of transcription from RNA polymerase II promoter involved in cellular response to chemical stimulus' in Hela cell line. Penguin software and models are available on GitHub at https://github.com/Janga-Lab/Penguin and can be readily employed for predicting Ψ sites from Nanopore direct RNA-sequencing datasets.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
执着绮兰完成签到,获得积分10
8秒前
lovelife完成签到,获得积分10
48秒前
酷炫绮琴完成签到,获得积分10
54秒前
强健的绿蕊完成签到,获得积分10
1分钟前
呆萌访琴完成签到,获得积分10
1分钟前
null的应助被科研通管家采纳,获得10
1分钟前
Owen的应助被科研通管家采纳,获得10
1分钟前
1分钟前
null的应助被科研通管家采纳,获得10
1分钟前
科研通AI6.2的应助被juaner采纳,获得10
1分钟前
高兴战斗机完成签到,获得积分10
1分钟前
1分钟前
Jamal发布了新的文献求助10
1分钟前
大气翠风完成签到,获得积分10
1分钟前
顾矜的应助被Jamal采纳,获得10
1分钟前
CodeCraft的应助被酥酥采纳,获得10
2分钟前
和谐如彤完成签到,获得积分10
2分钟前
2分钟前
酥酥发布了新的文献求助10
2分钟前
甜蜜语堂完成签到,获得积分10
2分钟前
111哩完成签到,获得积分10
2分钟前
2分钟前
zeng发布了新的文献求助10
2分钟前
irene完成签到,获得积分10
2分钟前
酥酥完成签到,获得积分10
2分钟前
杨佳佳完成签到,获得积分10
2分钟前
Noob_saibot完成签到,获得积分10
2分钟前
彭于晏的应助被zeng采纳,获得10
2分钟前
儒雅语雪完成签到,获得积分10
2分钟前
3分钟前
Shicheng完成签到,获得积分10
3分钟前
小李老博发布了新的文献求助10
3分钟前
ZZzz完成签到 ,获得积分10
3分钟前
酷波er的应助被科研通管家采纳,获得10
3分钟前
fantasy的应助被科研通管家采纳,获得10
3分钟前
小李老博完成签到,获得积分10
3分钟前
3分钟前
Noob_saibot关注了科研通微信公众号
3分钟前
忐忑的烤鸡完成签到,获得积分10
3分钟前
复杂曼荷完成签到,获得积分10
3分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Hidden Empire of Finance: How Wall Street Profits from Our Cities and Fuels Global Inequality 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8166132
求助须知:如何正确求助?哪些是违规求助? 9559433
关于积分的说明 21750361
捐赠科研通 7756990
什么是DOI,文献DOI怎么找? 3429119
关于科研通互助平台的介绍 2553436
邀请新用户注册赠送积分活动 2473781