Prospects of Coffee Leaf against SARS-CoV-2 Infection

In the current climate, many countries are in dire need of effective preventive methods to curb the Severe Acute Respiratory Syndrome Coronavirus Type 2 (SARS-CoV-2) pandemic. The purpose of this research is to screen and explore natural plant extracts that have the potential to against SARS-CoV-2 and provide alternative options for SARS-CoV-2 prevention and hand sanitizer or spray-like disinfectants. We first used Spike-ACE2 ELISA and TMPRSS2 fluorescence resonance energy transfer (FRET) assays to screen extracts from agricultural by-products from Taiwan with the potential to impede SARS-CoV-2 infection. Next, the SARS-CoV-2 pseudo-particles (Vpp) infection assay was tested to validate the effectiveness. We identified an extract from coffee leaf (Coffea Arabica), a natural plant that effectively inhibited wild-type SARS-CoV-2, and five Variants of Concern (Alpha, Beta, Gamma, Delta, and Omicron strain) from entering host cells. In an attempt to apply coffee leaf extract for hand sanitizer or spray-like disinfectants, we designed a skin-like gelatin membrane experiment. We showed that the high concentration of coffee leaf extract on the skin surface could block SARS-CoV-2 into cells more potently than 75% Ethanol, a standard disinfectant to inactivate SARS-CoV-2. Finally, LC-HRMS analysis was used to identify compounds such as caffeine, chlorogenic acid (CGA), quinic acid, and mangiferin that are associated with an anti-SARS-CoV-2 activity. Our results demonstrated that coffee leaf extract, an agricultural by-product effectively inhibits SARS-CoV-2 Vpp infection through an ACE2-dependent mechanism and may be utilized to develop products against SARS-CoV-2 infection.

Machine Learning for Image Analysis: Leaf Disease Segmentation

Plant phenomics field has seen a great increase in scalability in the last decade mainly due to technological advances in remote sensors and phenotyping platforms. These are capable of screening thousands of plants many times throughout the day, generating massive amounts of data, which require an automated analysis to extract meaningful information. Deep learning is a branch of machine learning that has revolutionized many fields of research. Deep learning models are able to extract autonomously the underlying features within the dataset, providing a multi-level representation of the data. Our intention is to show the feasibility and effectiveness of using deep learning and low-cost technology for automated phenotyping. In this methods chapter, we describe how to train a deep neural network to segment leaf images and extract the pixels related to the disease.