Principal component analysis for detection of NS1 molecules from Raman spectra of saliva

摘要

NS1 is an early biomarker for detection of flavivirus related diseases such as Japanese Encephalitis, Murray Valley Encephalitis, Tick-borne Encephalitis, West Nile Encephalitis, Dengue Fever and Yellow Fever. At present, it is detected in the infected blood serum through ELISA and immune-chromatographic lateral flow test. As a preliminary study, we are using PCA to extract NS1 feature from SERS spectra of NS1 adulterated saliva. NS1 characteristic peak at about 1000cm is extracted by the most significant principal component, PC1. Using PCA adhoc stopping rules, data dimension is significantly reduced to more than 90% without losing important features from the original data. Furthermore, PCA score plots of the dataset is also showing clear separation between NS1 adulterated saliva and healthy saliva. This encouraging finding is suggesting the possibility to develop a SERS based automatic classification algorithm for detection of NS1 in saliva. Being a salivary based technique, this will lead to a novel, rapid, non-invasive and non-infectious detection method, dispense of problem arising from blood sampling.