A Machine Learning Framework for Detecting COVID-19 Infection Using Surface-Enhanced Raman Scattering.

In this study, we explored machine learning approaches for predictive diagnosis using surface-enhanced Raman scattering (SERS), applied to the detection of COVID-19 infection in biological samples. To do this, we utilized SERS data collected from 20 patients at the University of Maryland Baltimore School of Medicine. As a preprocessing step, the positive-negative labels are obtained using Polymerase Chain Reaction (PCR) testing. First, we compared the performance of linear and nonlinear dimensionality techniques for projecting the high-dimensional Raman spectra to a low-dimensional space where a smaller number of variables defines each sample. The appropriate number of reduced features used was obtained by comparing the mean accuracy from a 10-fold cross-validation. Finally, we employed Gaussian process (GP) classification, a probabilistic machine learning approach, to correctly predict the occurrence of a negative or positive sample as a function of the low-dimensional space variables. As opposed to providing rigid class labels, the GP classifier provides a probability (ranging from zero to one) that a given sample is positive or negative. In practice, the proposed framework can be used to provide high-throughput rapid testing, and a follow-up PCR can be used for confirmation in cases where the model's uncertainty is unacceptably high.

Probing the mutation independent interaction of DNA probes with SARS-CoV-2 variants through a combination of surface-enhanced Raman scattering and machine learning.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) evolution has been characterized by the emergence of sets of mutations impacting the virus characteristics, such as transmissibility and antigenicity, presumably in response to the changing immune profile of the human population. The presence of mutations in the SARS-CoV-2 virus can potentially impact therapeutic and diagnostic test performances. We design and develop here a unique set of DNA probes i.e., antisense oligonucleotides (ASOs) which can interact with genetic sequences of the virus irrespective of its ongoing mutations. The probes, developed herein, target a specific segment of the nucleocapsid phosphoprotein (N) gene of SARS-CoV-2 with high binding efficiency which do not mutate among the known variants. Further probing into the interaction profile of the ASOs reveals that the ASO-RNA hybridization remains unaltered even for a hypothetical single point mutation at the target RNA site and diminished only in case of the hypothetical double or triple point mutations. The mechanism of interaction among the ASOs and SARS-CoV-2 RNA is then explored with a combination of surface-enhanced Raman scattering (SERS) and machine learning techniques. It has been observed that the technique, described herein, could efficiently discriminate between clinically positive and negative samples with ∼100% sensitivity and ∼90% specificity up to 63 copies/mL of SARS-CoV-2 RNA concentration. Thus, this study establishes N gene targeted ASOs as the fundamental machinery to efficiently detect all the current SARS-CoV-2 variants regardless of their mutations.