FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4214887800> ?p ?o ?g. }

• W4214887800 endingPage "148" @default.
• W4214887800 startingPage "139" @default.
• W4214887800 abstract "O 6-carboxymethyl guanine(O 6-CMG) is a highly mutagenic alkylation product of DNA that causes gastrointestinal cancer in organisms. Existing studies used mutant Mycobacteriumsmegmatis porin A (MspA) nanopore assisted by Phi29 DNA polymerase to localize it. Recently, machine learning technology has been widely used in the analysis of nanopore sequencing data. But the machine learning always need a large number of data labels that have brought extra work burden to researchers, which greatly affects its practicability. Accordingly, this paper proposes a nano-Unsupervised-Deep-Learning method (nano-UDL) based on an unsupervised clustering algorithm to identify methylation events in nanopore data automatically. Specially, nano-UDL first uses the deep AutoEncoder to extract features from the nanopore dataset and then applies the MeanShift clustering algorithm to classify data. Besides, nano-UDL can extract the optimal features for clustering by joint optimizing the clustering loss and reconstruction loss. Experimental results demonstrate that nano-UDL has relatively accurate recognition accuracy on the O 6-CMG dataset and can accurately identify all sequence segments containing O 6-CMG. In order to further verify the robustness of nano-UDL, hyperparameter sensitivity verification and ablation experiments were carried out in this paper. Using machine learning to analyze nanopore data can effectively reduce the additional cost of manual data analysis, which is significant for many biological studies, including genome sequencing.O 6-甲基鸟嘌呤（O 6-CMG）是DNA中的一种高致突变烷基化产物，它会导致生命体罹患胃肠道肿瘤。现有的研究主要是利用耻垢分枝杆菌膜蛋白（MspA）纳米孔技术，借助枯草芽孢杆菌噬菌体Phi29 DNA多聚酶（Phi29 DNA polymerase）对突变进行精确定位。近年来，机器学习技术被广泛应用于纳米孔测序数据的分析，但是机器学习往往需要大量的数据标记，这给研究者们带来了额外的工作负担，大大影响了其实用性。因此，本文提出了一种纳米无监督深度学习（nano-UDL）方法，该方法能自动识别含有突变段的纳米孔数据。nano-UDL方法利用深度自动编码器从纳米孔数据中提取特征，然后通过均值漂移（MeanShift）聚类算法对特征数据进行分类。此外，该方法还联合优化了聚类损失和重构损失，从而提取最优的特征用于聚类。实验结果表明，nano-UDL方法在O 6-CMG数据集上具有较高的识别精度，能准确识别出所有包含O 6-CMG的序列段。为了进一步验证nano-UDL方法的鲁棒性，本文进行了超参数敏感性验证和消融实验。利用nano-UDL方法分析纳米孔数据不但可以有效降低人工分析数据带来的额外成本，而且对包括基因组测序在内的诸多生物研究具有重要意义。." @default.
• W4214887800 created "2022-03-05" @default.
• W4214887800 creator A5005990956 @default.
• W4214887800 creator A5007229671 @default.
• W4214887800 creator A5010394567 @default.
• W4214887800 creator A5018821033 @default.
• W4214887800 creator A5070284401 @default.
• W4214887800 creator A5080050125 @default.
• W4214887800 date "2022-02-25" @default.
• W4214887800 modified "2023-09-28" @default.
• W4214887800 title "[Unsupervised deep learning for identifying the O 6-carboxymethyl guanine by nanopore sequencing]." @default.
• W4214887800 cites W1541777207 @default.
• W4214887800 cites W1992436825 @default.
• W4214887800 cites W2006255103 @default.
• W4214887800 cites W2100495367 @default.
• W4214887800 cites W2100810979 @default.
• W4214887800 cites W2127407003 @default.
• W4214887800 cites W2148332776 @default.
• W4214887800 cites W2174491615 @default.
• W4214887800 cites W2255568136 @default.
• W4214887800 cites W2591367881 @default.
• W4214887800 cites W2767629553 @default.
• W4214887800 cites W2919115771 @default.
• W4214887800 cites W2942010261 @default.
• W4214887800 cites W2951434717 @default.
• W4214887800 cites W2953562574 @default.
• W4214887800 cites W2971454256 @default.
• W4214887800 doi "https://doi.org/10.7507/1001-5515.202104068" @default.
• W4214887800 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35231975" @default.
• W4214887800 hasPublicationYear "2022" @default.
• W4214887800 type Work @default.
• W4214887800 citedByCount "0" @default.
• W4214887800 crossrefType "journal-article" @default.
• W4214887800 hasAuthorship W4214887800A5005990956 @default.
• W4214887800 hasAuthorship W4214887800A5007229671 @default.
• W4214887800 hasAuthorship W4214887800A5010394567 @default.
• W4214887800 hasAuthorship W4214887800A5018821033 @default.
• W4214887800 hasAuthorship W4214887800A5070284401 @default.
• W4214887800 hasAuthorship W4214887800A5080050125 @default.
• W4214887800 hasConcept C108583219 @default.
• W4214887800 hasConcept C119857082 @default.
• W4214887800 hasConcept C126513998 @default.
• W4214887800 hasConcept C141795571 @default.
• W4214887800 hasConcept C153180895 @default.
• W4214887800 hasConcept C154945302 @default.
• W4214887800 hasConcept C171250308 @default.
• W4214887800 hasConcept C192562407 @default.
• W4214887800 hasConcept C41008148 @default.
• W4214887800 hasConcept C51679486 @default.
• W4214887800 hasConcept C54355233 @default.
• W4214887800 hasConcept C552990157 @default.
• W4214887800 hasConcept C70721500 @default.
• W4214887800 hasConcept C73555534 @default.
• W4214887800 hasConcept C8038995 @default.
• W4214887800 hasConcept C86803240 @default.
• W4214887800 hasConceptScore W4214887800C108583219 @default.
• W4214887800 hasConceptScore W4214887800C119857082 @default.
• W4214887800 hasConceptScore W4214887800C126513998 @default.
• W4214887800 hasConceptScore W4214887800C141795571 @default.
• W4214887800 hasConceptScore W4214887800C153180895 @default.
• W4214887800 hasConceptScore W4214887800C154945302 @default.
• W4214887800 hasConceptScore W4214887800C171250308 @default.
• W4214887800 hasConceptScore W4214887800C192562407 @default.
• W4214887800 hasConceptScore W4214887800C41008148 @default.
• W4214887800 hasConceptScore W4214887800C51679486 @default.
• W4214887800 hasConceptScore W4214887800C54355233 @default.
• W4214887800 hasConceptScore W4214887800C552990157 @default.
• W4214887800 hasConceptScore W4214887800C70721500 @default.
• W4214887800 hasConceptScore W4214887800C73555534 @default.
• W4214887800 hasConceptScore W4214887800C8038995 @default.
• W4214887800 hasConceptScore W4214887800C86803240 @default.
• W4214887800 hasIssue "1" @default.
• W4214887800 hasLocation W42148878001 @default.
• W4214887800 hasOpenAccess W4214887800 @default.
• W4214887800 hasPrimaryLocation W42148878001 @default.
• W4214887800 hasRelatedWork W2032711662 @default.
• W4214887800 hasRelatedWork W2086290527 @default.
• W4214887800 hasRelatedWork W2942826041 @default.
• W4214887800 hasRelatedWork W2964187307 @default.
• W4214887800 hasRelatedWork W3118981907 @default.
• W4214887800 hasRelatedWork W3123344745 @default.
• W4214887800 hasRelatedWork W3149795039 @default.
• W4214887800 hasRelatedWork W4211044943 @default.
• W4214887800 hasRelatedWork W4221136938 @default.
• W4214887800 hasRelatedWork W3108696707 @default.
• W4214887800 hasVolume "39" @default.
• W4214887800 isParatext "false" @default.
• W4214887800 isRetracted "false" @default.
• W4214887800 workType "article" @default.