Automated Extraction of Principal Components of Non-Structural Protein 1 from SERS Spectrum

Abstract

In this paper, the SERS analysis technique for extracting principal components of non-structural protein 1 from its spectra is examined. The non-structural protein 1 is found a major role in the replication process of virus of flaviviridae, the cause for many viral diseases. SERS is a technique that can provide fingerprint spectral information of even a single molecule. However, the Raman spectra from SERS complicate the feature extraction process with redundant features. Principal Component Analysis is a signal processing technique, useful for filtering for the significant features while filtering off the redundant ones with minimal loss of information. Here, PCA adopting a 3-steps approach, i.e. Eigenvalue-One-Criterion, Scree test and Cumulative Percent Variance, is used to select significant principal components of NS1 from Raman spectra. It is found that principal components of NS1 from its spectra of [900x10] from SERS is found being trimmed to [9x10] by Scree test supplemented by EOC and [2x10] by CPV, with a corresponding reduction of 99% and 99.8% from the original spectral array. However, since the spectra of biological samples in actual is noisier, selection by the former of first nine components is found appropriate. So far, SERS analysis technique for detection of salivary NS1 has yet to be reported.