A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak.

Coronavirus disease 2019 (COVID-19) has spread globally for over three years, and chest computed tomography (CT) has been used to diagnose COVID-19 and identify lung damage in COVID-19 patients. Given its widespread, CT will remain a common diagnostic tool in future pandemics, but its effectiveness at the beginning of any pandemic will depend strongly on the ability to classify CT scans quickly and correctly when only limited resources are available, as it will happen inevitably again in future pandemics. Here, we resort into the transfer learning procedure and limited hyperparameters to use as few computing resources as possible for COVID-19 CT images classification. Advanced Normalisation Tools (ANTs) are used to synthesise images as augmented/independent data and trained on EfficientNet to investigate the effect of synthetic images. On the COVID-CT dataset, classification accuracy increases from 91.15% to 95.50% and Area Under the Receiver Operating Characteristic (AUC) from 96.40% to 98.54%. We also customise a small dataset to simulate data collected in the early stages of the outbreak and report an improvement in accuracy from 85.95% to 94.32% and AUC from 93.21% to 98.61%. This study provides a feasible Low-Threshold, Easy-To-Deploy and Ready-To-Use solution with a relatively low computational cost for medical image classification at an early stage of an outbreak in which scarce data are available and traditional data augmentation may fail. Hence, it would be most suitable for low-resource settings.

Evolutionary analysis of chloroplast tRNA of Gymnosperm revealed the novel structural variation and evolutionary aspect.

Gymnosperms such as ginkgo, conifers, cycads, and gnetophytes are vital components of land ecosystems, and they have significant economic and ecologic value, as well as important roles as forest vegetation. In this study, we investigated the structural variation and evolution of chloroplast transfer RNAs (tRNAs) in gymnosperms. Chloroplasts are important organelles in photosynthetic plants. tRNAs are key participants in translation where they act as adapter molecules between the information level of nucleic acids and functional level of proteins. The basic structures of gymnosperm chloroplast tRNAs were found to have family-specific conserved sequences. The tRNAΨ -loop was observed to contain a conforming sequence, i.e., U-U-C-N-A-N2. In gymnosperms, tRNAIle was found to encode a "CAU" anticodon, which is usually encoded by tRNAMet. Phylogenetic analysis suggested that plastid tRNAs have a common polyphyletic evolutionary pattern, i.e., rooted in abundant common ancestors. Analyses of duplication and loss events in chloroplast tRNAs showed that gymnosperm tRNAs have experienced little more gene loss than gene duplication. Transition and transversion analysis showed that the tRNAs are iso-acceptor specific and they have experienced unequal evolutionary rates. These results provide new insights into the structural variation and evolution of gymnosperm chloroplast tRNAs, which may improve our comprehensive understanding of the biological characteristics of the tRNA family.