A machine learning approach for accurate and real-time DNA sequence identification.
A machine learning approach for accurate and real-time DNA sequence identification.
复制标题
DOI：
10.1186/s12864-021-07841-6
复制
发表时间：
2021-07-09
期刊：
影响因子：
4.4
通讯作者：
Anantram MP
中科院分区：
文献类型：
--
作者：
Wang Y;Alangari M;Hihath J;Das AK;Anantram MP
全电子单分子断裂连接（SMBJ）方法是传统聚合酶链反应（PCR）技术的新兴替代方法，用于基因测序和鉴定。现有的工作表明，从SMBJ实验记录的当前光谱包含独特的签名，以识别来自数据集的已知序列。然而，由于基质、样品、环境和测量系统之间的随机和复杂的相互作用，光谱通常非常嘈杂，需要数百或数千次实验才能获得可靠和准确的结果。本文提出了一种基于十个短链序列的电流谱的DNA序列鉴定系统，其中包括一对差异为单个错配的序列。通过采用在电导直方图上训练的梯度提升树分类器模型，我们证明了极高的准确度，从大约96%的分子差异由一个单一的错配到99.5%，否则，是可能的。此外，这样的准确度度量可以仅用二十或三十个SMBJ测量而不是数百或数千个测量来近实时地实现。我们还证明了一个串联分类器架构，其中第一阶段是一个多类分类器和第二阶段是一个二元分类器，可以用来提高单个不匹配对的识别准确率为99.5%。单片分类器，或更一般地，具有依赖于实验电流谱的模型特定参数的多级分类器可以用于成功地识别DNA链。在线版本包含补充材料，可通过10.1186/s12864-021-07841-6获得。
The all-electronic Single Molecule Break Junction (SMBJ) method is an emerging alternative to traditional polymerase chain reaction (PCR) techniques for genetic sequencing and identification. Existing work indicates that the current spectra recorded from SMBJ experimentations contain unique signatures to identify known sequences from a dataset. However, the spectra are typically extremely noisy due to the stochastic and complex interactions between the substrate, sample, environment, and the measuring system, necessitating hundreds or thousands of experimentations to obtain reliable and accurate results. This article presents a DNA sequence identification system based on the current spectra of ten short strand sequences, including a pair that differs by a single mismatch. By employing a gradient boosted tree classifier model trained on conductance histograms, we demonstrate that extremely high accuracy, ranging from approximately 96 % for molecules differing by a single mismatch to 99.5 % otherwise, is possible. Further, such accuracy metrics are achievable in near real-time with just twenty or thirty SMBJ measurements instead of hundreds or thousands. We also demonstrate that a tandem classifier architecture, where the first stage is a multiclass classifier and the second stage is a binary classifier, can be employed to boost the single mismatched pair’s identification accuracy to 99.5 %. A monolithic classifier, or more generally, a multistage classifier with model specific parameters that depend on experimental current spectra can be used to successfully identify DNA strands. The online version contains supplementary material available at 10.1186/s12864-021-07841-6.
登录
查看更多内容
影响因子：
37.8
作者：
Dewey FE;Pan S;Wheeler MT;Quake SR;Ashley EA
通讯作者：
Ashley EA
影响因子：
3.3
作者：
Ribot, Josep Casarnada;Chatterjee, Anushree;Nagpal, Prashant
通讯作者：
Nagpal, Prashant
影响因子：
3.5
作者：
Pollard MO;Gurdasani D;Mentzer AJ;Porter T;Sandhu MS
通讯作者：
Sandhu MS
影响因子：
4.5
作者：
Friedman, JH
通讯作者：
Friedman, JH
影响因子：
4
作者：
Cabosart, Damien;El Abbassi, Maria;Perrin, Mickael L.
通讯作者：
Perrin, Mickael L.