Visualization of a Machine Learning Framework toward Highly Sensitive Qualitative Analysis by SERS.

Surface-enhanced Raman spectroscopy (SERS), providing near-single-molecule-level fingerprint information, is a powerful tool for the trace analysis of a target in a complicated matrix and is especially facilitated by the development of modern machine learning algorithms. However, both the high demand of mass data and the low interpretability of the mysterious black-box operation significantly limit the well-trained model to real systems in practical applications. Aiming at these two issues, we constructed a novel machine learning algorithm-based framework (Vis-CAD), integrating visual random forest, characteristic amplifier, and data augmentation. The introduction of data augmentation significantly reduced the requirement of mass data, and the visualization of the random forest clearly presented the captured features, by which one was able to determine the reliability of the algorithm. Taking the trace analysis of individual polycyclic aromatic hydrocarbons in a mixture as an example, a trustworthy accuracy no less than 99% was realized under the optimized condition. The visualization of the algorithm framework distinctly demonstrated that the captured feature was well correlated to the characteristic Raman peaks of each individual. Furthermore, the sensitivity toward the trace individual could be improved by least 1 order of magnitude as compared to that with the naked eye. The proposed algorithm distinguished by the lesser demand of mass data and the visualization of the operation process offers a new way for the indestructible application of machine learning algorithms, which would bring push-to-the-limit sensitivity toward the qualitative and quantitative analysis of trace targets, not only in the field of SERS, but also in the much wider spectroscopy world. It is implemented in the Python programming language and is open-source at https://github.com/3331822w/Vis-CAD.

Developing a Peak Extraction and Retention (PEER) Algorithm for Improving the Temporal Resolution of Raman Spectroscopy.

In spectroscopic analysis, push-to-the-limit sensitivity is one of the important topics, particularly when facing the qualitative and quantitative analyses of the trace target. Normally, the effective recognition and extraction of weak signals are the first key steps, for which there has been considerable effort in developing various denoising algorithms for decades. Nevertheless, the lower the signal-to-noise ratio (SNR), the greater the deviation of the peak height and shape during the denoising process. Therefore, we propose a denoising algorithm along with peak extraction and retention (PEER). First, both the first and second derivatives of the Raman spectrum are used to determine Raman peaks with a high SNR whose peak information is kept away from the denoising process. Second, an optimized window smoothing algorithm is applied to the left part of the Raman spectrum, which is combined with the untreated Raman peaks to obtain the denoised Raman spectrum. The PEER algorithm is demonstrated with much better signal extraction and retention and successfully improves the temporal resolution of Raman imaging of a living cell by at least 1 order of magnitude higher than those by traditional algorithms.