AMAISE: a machine learning approach to index-free sequence enrichment.

AMAISE: a machine learning approach to index-free sequence enrichment.
复制标题

DOI:
10.1038/s42003-022-03498-3
复制
发表时间:
2022-06-09
影响因子:
5.9
通讯作者:
--
中科院分区:
生物学2区
文献类型:
--
作者:

文献摘要

参考文献

相似文献

宏基因组学具有改善传染病临床诊断的潜力,但来自临床标本的DNA通常由宿主衍生的序列主导。为了解决这个问题,研究人员采用了主机耗尽方法。然而,基于实验室的主机耗尽方法在时间和精力方面都是昂贵的,而计算主机耗尽方法依赖于内存密集型参考索引数据库,并且难以准确分类有噪声的序列数据。为了解决这些挑战,我们提出了一个无索引工具,AMAISE(一种无索引序列富集的机器学习方法)。应用于从微生物reads中分离宿主的任务,AMAISE达到98%以上的准确率。在宏基因组分类之前应用AMAISE,与单独使用宏基因组分类相比,内存使用减少了14-18%。我们的研究结果表明,一种与参考无关的主机耗尽机器学习方法可以准确有效地检测序列。基于机器学习的工具AMAISE可以在元基因组学数据中分离微生物和宿主序列,而无需依赖参考基因组来去除宿主序列。
Metagenomics holds potential to improve clinical diagnostics of infectious diseases, but DNA from clinical specimens is often dominated by host-derived sequences. To address this, researchers employ host-depletion methods. Laboratory-based host-depletion methods, however, are costly in terms of time and effort, while computational host-depletion methods rely on memory-intensive reference index databases and struggle to accurately classify noisy sequence data. To solve these challenges, we propose an index-free tool, AMAISE (A Machine Learning Approach to Index-Free Sequence Enrichment). Applied to the task of separating host from microbial reads, AMAISE achieves over 98% accuracy. Applied prior to metagenomic classification, AMAISE results in a 14–18% decrease in memory usage compared to using metagenomic classification alone. Our results show that a reference-independent machine learning approach to host depletion allows for accurate and efficient sequence detection. A machine learning-based tool, AMAISE, separates microbial and host sequences in metagenomics data without relying on reference genomes to remove host sequences.
DOI: 10.1038/s41576-020-0236-x
发表时间: 2020-10
期刊: Nature reviews. Genetics
影响因子: --
作者:
Logsdon GA;Vollger MR;Eichler EE
通讯作者: Eichler EE
DOI: 10.1093/bioinformatics/bty191
发表时间: 2018-09-15
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Li, Heng
通讯作者: Li, Heng
DOI: 10.4103/0301-4738.37595
发表时间: 2008-01
影响因子: 3.1
作者:
Parikh, Rajul;Mathai, Annie;Parikh, Shefali;Sekhar, G. Chandra;Thomas, Ravi
通讯作者: Thomas, Ravi
DOI: 10.1038/nbt.4060
发表时间: 2018-04
影响因子: 46.9
作者:
Jain M;Koren S;Miga KH;Quick J;Rand AC;Sasani TA;Tyson JR;Beggs AD;Dilthey AT;Fiddes IT;Malla S;Marriott H;Nieto T;O'Grady J;Olsen HE;Pedersen BS;Rhie A;Richardson H;Quinlan AR;Snutch TP;Tee L;Paten B;Phillippy AM;Simpson JT;Loman NJ;Loose M
通讯作者: Loose M
DOI: 10.1101/gr.210641.116
发表时间: 2016-12
期刊: Genome research
影响因子: 7
作者:
Kim D;Song L;Breitwieser FP;Salzberg SL
通讯作者: Salzberg SL