Deep learning for nanopore ionic current blockades

被引:30
作者
Carral, Angel Diaz [1 ]
Ostertag, Magnus [1 ]
Fyta, Maria [1 ]
机构
[1] Univ Stuttgart, Inst Computat Phys, Allmandring 3, D-70569 Stuttgart, Germany
关键词
DNA-MOLECULES;
D O I
10.1063/5.0037938
中图分类号
O64 [物理化学(理论化学)、化学物理学];
学科分类号
070304 ; 081704 ;
摘要
DNA molecules can electrophoretically be driven through a nanoscale opening in a material, giving rise to rich and measurable ionic current blockades. In this work, we train machine learning models on experimental ionic blockade data from DNA nucleotide translocation through 2D pores of different diameters. The aim of the resulting classification is to enhance the read-out efficiency of the nucleotide identity providing pathways toward error-free sequencing. We propose a novel method that at the same time reduces the current traces to a few physical descriptors and trains low-complexity models, thus reducing the dimensionality of the data. We describe each translocation event by four features including the height of the ionic current blockade. Training on these lower dimensional data and utilizing deep neural networks and convolutional neural networks, we can reach a high accuracy of up to 94% in average. Compared to more complex baseline models trained on the full ionic current traces, our model outperforms. Our findings clearly reveal that the use of the ionic blockade height as a feature together with a proper combination of neural networks, feature extraction, and representation provides a strong enhancement in the detection. Our work points to a possible step toward guiding the experiments to the number of events necessary for sequencing an unknown biopolymer in view of improving the biosensitivity of novel nanopore sequencers.
引用
收藏
页数:10
相关论文
共 43 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]   Convolutional neural networks for classification of alignments of non-coding RNA sequences [J].
Aoki, Genta ;
Sakakibara, Yasubumi .
BIOINFORMATICS, 2018, 34 (13) :237-244
[3]   MinION nanopore sequencing identifies the position and structure of a bacterial antibiotic resistance island [J].
Ashton, Philip M. ;
Nair, Satheesh ;
Dallman, Tim ;
Rubino, Salvatore ;
Rabsch, Wolfgang ;
Mwaigwisya, Solomon ;
Wain, John ;
O'Grady, Justin .
NATURE BIOTECHNOLOGY, 2015, 33 (03) :296-+
[4]   Sequence-specific detection of individual DNA polymerase complexes in real time using a nanopore [J].
Benner, Seico ;
Chen, Roger J. A. ;
Wilson, Noah A. ;
Abu-Shumays, Robin ;
Hurt, Nicholas ;
Lieberman, Kate R. ;
Deamer, David W. ;
Dunbar, William B. ;
Akeson, Mark .
NATURE NANOTECHNOLOGY, 2007, 2 (11) :718-724
[5]   DeepNano: Deep recurrent neural networks for base calling in MinION nanopore reads [J].
Boza, Vladimir ;
Brejova, Brona ;
Vinar, Tomas .
PLOS ONE, 2017, 12 (06)
[6]   2D MoS2 nanopores: ionic current blockade height for clustering DNA events [J].
Carral, Angel Diaz ;
Sarap, Chandra Shekar ;
Liu, Ke ;
Radenovic, Aleksandra ;
Fyta, Maria .
2D MATERIALS, 2019, 6 (04)
[7]  
Chen Tianqi., 2016, KDD 16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, P785
[8]  
Chollet F., 2015, Keras
[9]   Clustering ionic flow blockade toggles with a Mixture of HMMs [J].
Churbanov, Alexander ;
Winters-Hilt, Stephen .
BMC BIOINFORMATICS, 2008, 9 (Suppl 9)
[10]   Constant size descriptors for accurate machine learning models of molecular properties [J].
Collins, Christopher R. ;
Gordon, Geoffrey J. ;
von Lilienfeld, O. Anatole ;
Yaron, David J. .
JOURNAL OF CHEMICAL PHYSICS, 2018, 148 (24)