Department of Chemistry, Indian Institute of Technology (IIT) Indore, Indore, Madhya Pradesh 453552, India.
Nano Lett. 2023 Apr 12;23(7):2511-2521. doi: 10.1021/acs.nanolett.2c04062. Epub 2023 Feb 17.
Solid-state nanopore-based single-molecule DNA sequencing with quantum tunneling technology poses formidable challenges to achieve long-read sequencing and high-throughput analysis. Here, we propose a method for developing an artificially intelligent (AI) nanopore that does not require extraction of the signature transmission function for each nucleotide of the whole DNA strand by integrating supervised machine learning (ML) and transverse quantum transport technology with a graphene nanopore. The optimized ML model can predict the transmission function of all other nucleotides after training with data sets of all the orientations of any nucleotide inside the nanopore with a root-mean-square error (RMSE) of as low as 0.062. Further, up to 96.01% accuracy is achieved in classifying the unlabeled nucleotides with their transmission readouts. We envision that an AI nanopore can alleviate the experimental challenges of the quantum-tunneling method and pave the way for rapid and high-precision DNA sequencing by predicting their signature transmission functions.
基于固态纳米孔的单分子 DNA 测序结合量子隧穿技术，实现长读测序和高通量分析面临巨大挑战。在这里，我们提出了一种开发人工智能（AI）纳米孔的方法，该方法不需要通过提取整个 DNA 链中每个核苷酸的特征传输函数来实现，而是将监督机器学习（ML）和横向量子输运技术与石墨烯纳米孔相结合。经过对纳米孔内任意核苷酸所有取向的数据进行训练，优化后的 ML 模型可以预测所有其他核苷酸的传输函数，均方根误差（RMSE）低至 0.062。此外，通过其传输读出结果对未标记核苷酸进行分类的准确率高达 96.01%。我们设想，人工智能纳米孔可以缓解量子隧穿方法的实验挑战，通过预测其特征传输函数，为快速、高精度的 DNA 测序铺平道路。
