: The ongoing Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) pandemic has been proven to be more severe than the previous coronavirus outbreaks due to the virus’ high transmissibility. With the emergence of new variants, this global phenomenon took on a more dramatic turn with many countries recently experiencing higher surges of confirmed cases and deaths. On top of this, the inadequacy of effective treatment options for COVID-19 aggravated the problem. As a way to address the unavailability of target-specific viral therapeutics, computational strategies have been employed to hasten and systematize the search. The objective of this review is to provide initial data highlighting the utility of polyphenols as potential prophylaxis or treatment for COVID-19. In particular, presented here are virtually screened polyphenolic compounds which showed potential as either antagonists to viral entry and host cell recognition through binding with various receptor-binding regions of SARS-CoV-2 spike protein or as inhibitors of viral replication and post-translational modifications through binding with essential SARS-CoV-2 non-structural proteins.

Background: The early and accurate detection of colorectal cancer (CRC) significantly affects its prognosis and clinical management. However, current standard diagnostic procedures for CRC often lack sensitivity and specificity since most rely on visual examination. Hence, there is a need to develop more accurate methods for its diagnosis. Methods: Support vector machine (SVM) and feedforward neural network (FNN) models were designed using the Fourier-transform infrared (FTIR) spectral data of several colorectal tissues that were unanimously identified as either benign or malignant by different unrelated pathologists. The set of samples wherein the pathologists had discordant readings were then analyzed using the AI models described above. Results: Between the SVM and NN models, the NN model was able to outperform the SVM model based on their prediction confidence scores. Using the spectral data of the concordant samples as training set, the FNN was able to predict the histologically diagnosed malignant tissues (n=118) at 59.9% to 99.9% confidence (average=93.5%). Of the 118 samples, 84 (71.18%) were classified with an above average confidence score; 34 (28.81%) classified below the average confidence score; and none was misclassified. Moreover, it was able to correctly identify the histologically confirmed benign samples (n=83) at 51.5% to 99.7% confidence (average=91.64%). Of the 83 samples, 60 (72.29%) were classified with an above average confidence score; 22 (26.51%) classified below the average confidence score, and only one sample (1.20%) was misclassified. Conclusion: The study provides additional proof of the ability of ATR-FTIR enhanced by AI tools to predict the likelihood of CRC without dependence on morphological changes in tissues.