Deepvirusclassifier: a deep learning tool for classifying SARS-CoV-2 based on viral subtypes within the coronaviridae family.

PURPOSE: In this study, we present DeepVirusClassifier, a tool capable of accurately classifying Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) viral sequences among other subtypes of the coronaviridae family. This classification is achieved through a deep neural network model that relies on convolutional neural networks (CNNs). Since viruses within the same family share similar genetic and structural characteristics, the classification process becomes more challenging, necessitating more robust models. With the rapid evolution of viral genomes and the increasing need for timely classification, we aimed to provide a robust and efficient tool that could increase the accuracy of viral identification and classification processes. Contribute to advancing research in viral genomics and assist in surveilling emerging viral strains. METHODS: Based on a one-dimensional deep CNN, the proposed tool is capable of training and testing on the Coronaviridae family, including SARS-CoV-2. Our model's performance was assessed using various metrics, including F1-score and AUROC. Additionally, artificial mutation tests were conducted to evaluate the model's generalization ability across sequence variations. We also used the BLAST algorithm and conducted comprehensive processing time analyses for comparison. RESULTS: DeepVirusClassifier demonstrated exceptional performance across several evaluation metrics in the training and testing phases. Indicating its robust learning capacity. Notably, during testing on more than 10,000 viral sequences, the model exhibited a more than 99% sensitivity for sequences with fewer than 2000 mutations. The tool achieves superior accuracy and significantly reduced processing times compared to the Basic Local Alignment Search Tool algorithm. Furthermore, the results appear more reliable than the work discussed in the text, indicating that the tool has great potential to revolutionize viral genomic research. CONCLUSION: DeepVirusClassifier is a powerful tool for accurately classifying viral sequences, specifically focusing on SARS-CoV-2 and other subtypes within the Coronaviridae family. The superiority of our model becomes evident through rigorous evaluation and comparison with existing methods. Introducing artificial mutations into the sequences demonstrates the tool's ability to identify variations and significantly contributes to viral classification and genomic research. As viral surveillance becomes increasingly critical, our model holds promise in aiding rapid and accurate identification of emerging viral strains.

Solid Lipid Nanoparticles for Dibucaine Sustained Release.

Dibucaine (DBC) is among the more potent long-acting local anesthetics (LA), and it is also one of the most toxic. Over the last decades, solid lipid nanoparticles (SLN) have been developed as promising carriers for drug delivery. In this study, SLN formulations were prepared with the aim of prolonging DBC release and reducing its toxicity. To this end, SLN composed of two different lipid matrices and prepared by two different hot-emulsion techniques (high-pressure procedure and sonication) were compared. The colloidal stability of the SLN formulations was tracked in terms of particle size (nm), polydispersity index (PDI), and zeta potential (mV) for 240 days at 4 °C; the DBC encapsulation efficiency was determined by the ultrafiltration/centrifugation method. The formulations were characterized by differential scanning calorimetry (DSC), electron paramagnetic resonance (EPR), and release kinetic experiments. Finally, the in vitro cytotoxicity against 3T3 fibroblast and HaCaT cells was determined, and the in vivo analgesic action was assessed using the tail flick test in rats. Both of the homogenization procedures were found suitable to produce particles in the 200 nm range, with good shelf stability (240 days) and high DBC encapsulation efficiency (~72⁻89%). DSC results disclosed structural information on the nanoparticles, such as the lower crystallinity of the lipid core vs. the bulk lipid. EPR measurements provided evidence of DBC partitioning in both SLNs. In vitro (cytotoxicity) and in vivo (tail flick) experiments revealed that the encapsulation of DBC into nanoparticles reduces its intrinsic cytotoxicity and prolongs the anesthetic effect, respectively. These results show that the SLNs produced are safe and have great potential to extend the applications of dibucaine by enhancing its bioavailability.