Machine Learning-Aided Data Analysis in Single-Protein Conductance Measurement with Electron Tunneling Probes

The electrical tunneling sensors have excellent potential in the next generation of single-molecule measurement and sequencing technologies due to their high sensitivity and spatial resolution capabilities. Electrical tunneling signals that have been measured at a high sampling rate may provide detailed molecular information. Despite the extraordinarily large amount of data that has been gathered, it is still difficult to correlate signal transformations with molecular processes, which creates great obstacles for signal analysis. Machine learning is an effective tool for data analysis that is currently gaining more significance. It has demonstrated promising results when used to analyze data from single-molecule electrical measurements. In order to extract meaningful information from raw measurement data, we have combined intelligent machine learning with tunneling electrical signals. For the purpose of analyzing tunneling electrical signals, we investigated the clustering approach, which is a classic algorithm in machine learning. A clustering model was built that combines the advantages of hierarchical clustering and Gaussian mixture model clustering. Additionally, customized statistical algorithms were designed. It has been proven to efficiently gather molecular information and enhance the effectiveness of data analysis.