Fine-tuning-based Transfer Learning for Characterization of Adeno-Associated Virus.
Fine-tuning-based Transfer Learning for Characterization of Adeno-Associated Virus.
复制标题
DOI：
10.1007/s11265-022-01758-3
复制
发表时间：
2022-12
影响因子：
1.8
通讯作者：
Dutta, Prashanta
中科院分区：
文献类型：
--
作者：
Khan, Aminul Islam;Kim, Min Jun;Dutta, Prashanta
关键词：
腺相关病毒（AAV）载体的准确鉴定在剂量依赖性基因治疗中起着重要作用。虽然固态纳米孔技术可以潜在地用于通过捕获离子电流来表征AAV载体，但是现有的数据分析技术不能从其离子电流分布中识别它们。最近推出的机器学习方法，如深度卷积神经网络（CNN），开发用于图像识别任务，可以应用于这种分类。然而，由于手头问题的数据集较小，因此不可能从头开始训练深度神经网络来准确分类AAV载体。为了规避这一点，我们应用了一个预先训练的深度CNN（GoogleNet）模型来从离子电流信号中捕获基本特征，随后使用基于微调的迁移学习来对AAV载体进行分类。所提出的方法是非常通用的，因为它需要最少的预处理，不需要任何手工制作的功能。我们的研究结果表明，基于微调的迁移学习可以在三种实现中实现90%至99%的平均分类准确率，并且标准差非常小。结果还表明，分类精度取决于所施加的电场（跨纳米孔）和用于数据分割的时间范围。我们还发现，对于电阻性脉冲数据集，深度网络的微调优于基于特征提取的分类。为了扩展基于微调的迁移学习的有用性，我们测试了另外两个预训练的深度网络（ResNet50和InceptionV3）用于AAV的分类。总的来说，来自预训练深度网络的基于微调的迁移学习对于分类非常有效，尽管ResNet50和InceptionV3等深度网络的训练时间比GoogleNet长得多。
Accurate and precise identification of adeno-associated virus (AAV) vectors play an important role in dose-dependent gene therapy. Although solid-state nanopore techniques can potentially be used to characterize AAV vectors by capturing ionic current, the existing data analysis techniques fall short of identifying them from their ionic current profiles. Recently introduced machine learning methods such as deep convolutional neural network (CNN), developed for image identification tasks, can be applied for such classification. However, with smaller data set for the problem in hand, it is not possible to train a deep neural network from scratch for accurate classification of AAV vectors. To circumvent this, we applied a pre-trained deep CNN (GoogleNet) model to capture the basic features from ionic current signals and subsequently used fine-tuning-based transfer learning to classify AAV vectors. The proposed method is very generic as it requires minimal preprocessing and does not require any handcrafted features. Our results indicate that fine-tuning-based transfer learning can achieve an average classification accuracy between 90 and 99% in three realizations with a very small standard deviation. Results also indicate that the classification accuracy depends on the applied electric field (across nanopore) and the time frame used for data segmentation. We also found that the fine-tuning of the deep network outperforms feature extraction-based classification for the resistive pulse dataset. To expand the usefulness of the fine-tuning-based transfer learning, we have tested two other pre-trained deep networks (ResNet50 and InceptionV3) for the classification of AAVs. Overall, the fine-tuning-based transfer learning from pre-trained deep networks is very effective for classification, though deep networks such as ResNet50 and InceptionV3 take significantly longer training time than GoogleNet.
登录
查看更多内容
DOI：
10.1007/s11265-020-01520-7
发表时间：
2020-01-30
影响因子：
1.8
作者：
Hur, Cheonghwan;Kang, Sanggil
通讯作者：
Kang, Sanggil
影响因子：
--
作者：
Hsu, CW;Lin, CJ
通讯作者：
Lin, CJ
DOI：
10.1073/pnas.90.22.10613
发表时间：
1993-11-15
影响因子：
11.1
作者：
FLOTTE, TR;AFIONE, SA;CARTER, BJ
通讯作者：
CARTER, BJ
影响因子：
3.1
作者：
Kensert, Alexander;Harrison, Philip J.;Spjuth, Ola
通讯作者：
Spjuth, Ola
DOI：
10.1016/j.omtm.2021.02.010
发表时间：
2021-03-12
期刊：
Molecular therapy. Methods & clinical development
影响因子：
--
作者：
Gimpel AL;Katsikis G;Sha S;Maloney AJ;Hong MS;Nguyen TNT;Wolfrum J;Springs SL;Sinskey AJ;Manalis SR;Barone PW;Braatz RD
通讯作者：
Braatz RD