论文标题
使用自动编码器对单分子数据的无监督分类和转移学习
Unsupervised Classification of Single-Molecule Data with Autoencoders and Transfer Learning
论文作者
论文摘要
来自单分子实验的数据集通常反映出各种各样的分子行为。探索此类数据集可能具有挑战性，特别是如果有关数据的知识有限，并且应避免有关预期数据特征的先验假设。实际上，搜索预定义的信号特征有时很有用，但它也可能导致信息丢失和引入期望偏差。在这里，我们演示了如何使用无监督的方式来识别和量化单分子电荷传输数据中的隐藏特征，以识别和量化隐藏的特征。利用经过数百万看似无关的图像数据培训的开放访问神经网络，我们的结果还显示了如何轻易使用深度学习方法，即使特定于问题的“自身”数据受到限制。
Datasets from single-molecule experiments often reflect a large variety of molecular behaviour. The exploration of such datasets can be challenging, especially if knowledge about the data is limited and a priori assumptions about expected data characteristics are to be avoided. Indeed, searching for pre-defined signal characteristics is sometimes useful, but it can also lead to information loss and the introduction of expectation bias. Here, we demonstrate how Transfer Learning-enhanced dimensionality reduction can be employed to identify and quantify hidden features in single-molecule charge transport data, in an unsupervised manner. Taking advantage of open-access neural networks trained on millions of seemingly unrelated image data, our results also show how Deep Learning methodologies can readily be employed, even if the amount of problem-specific, 'own' data is limited.
