VirusHound-I: prediction of viral proteins involved in the evasion of host adaptive immune response using the random forest algorithm and generative adversarial network for data augmentation.

Throughout evolution, pathogenic viruses have developed different strategies to evade the response of the adaptive immune system. To carry out successful replication, some pathogenic viruses encode different proteins that manipulate the molecular mechanisms of host cells. Currently, there are different bioinformatics tools for virus research; however, none of them focus on predicting viral proteins that evade the adaptive system. In this work, we have developed a novel tool based on machine and deep learning for predicting this type of viral protein named VirusHound-I. This tool is based on a model developed with the multilayer perceptron algorithm using the dipeptide composition molecular descriptor. In this study, we have also demonstrated the robustness of our strategy for data augmentation of the positive dataset based on generative antagonistic networks. During the 10-fold cross-validation step in the training dataset, the predictive model showed 0.947 accuracy, 0.994 precision, 0.943 F1 score, 0.995 specificity, 0.896 sensitivity, 0.894 kappa, 0.898 Matthew's correlation coefficient and 0.989 AUC. On the other hand, during the testing step, the model showed 0.964 accuracy, 1.0 precision, 0.967 F1 score, 1.0 specificity, 0.936 sensitivity, 0.929 kappa, 0.931 Matthew's correlation coefficient and 1.0 AUC. Taking this model into account, we have developed a tool called VirusHound-I that makes it possible to predict viral proteins that evade the host's adaptive immune system. We believe that VirusHound-I can be very useful in accelerating studies on the molecular mechanisms of evasion of pathogenic viruses, as well as in the discovery of therapeutic targets.

Enzyme Engineering Strategies for the Bioenhancement of L-Asparaginase Used as a Biopharmaceutical.

Over the past few years, there has been a surge in the industrial production of recombinant enzymes from microorganisms due to their catalytic characteristics being highly efficient, selective, and biocompatible. L-asparaginase (L-ASNase) is an enzyme belonging to the class of amidohydrolases that catalyzes the hydrolysis of L-asparagine into L-aspartic acid and ammonia. It has been widely investigated as a biologic agent for its antineoplastic properties in treating acute lymphoblastic leukemia. The demand for L-ASNase is mainly met by the production of recombinant type II L-ASNase from Escherichia coli and Erwinia chrysanthemi. However, the presence of immunogenic proteins in L-ASNase sourced from prokaryotes has been known to result in adverse reactions in patients undergoing treatment. As a result, efforts are being made to explore strategies that can help mitigate the immunogenicity of the drug. This review gives an overview of recent biotechnological breakthroughs in enzyme engineering techniques and technologies used to improve anti-leukemic L-ASNase, taking into account the pharmacological importance of L-ASNase.

Review and perspective on bioinformatics tools using machine learning and deep learning for predicting antiviral peptides.

Viruses constitute a constant threat to global health and have caused millions of human and animal deaths throughout human history. Despite advances in the discovery of antiviral compounds that help fight these pathogens, finding a solution to this problem continues to be a task that consumes time and financial resources. Currently, artificial intelligence (AI) has revolutionized many areas of the biological sciences, making it possible to decipher patterns in amino acid sequences that encode different functions and activities. Within the field of AI, machine learning, and deep learning algorithms have been used to discover antimicrobial peptides. Due to their effectiveness and specificity, antimicrobial peptides (AMPs) hold excellent promise for treating various infections caused by pathogens. Antiviral peptides (AVPs) are a specific type of AMPs that have activity against certain viruses. Unlike the research focused on the development of tools and methods for the prediction of antimicrobial peptides, those related to the prediction of AVPs are still scarce. Given the significance of AVPs as potential pharmaceutical options for human and animal health and the ongoing AI revolution, we have reviewed and summarized the current machine learning and deep learning-based tools and methods available for predicting these types of peptides.

Current state of molecular and metabolic strategies for the improvement of L-asparaginase expression in heterologous systems.

Heterologous expression of L-asparaginase (L-ASNase) has become an important area of research due to its clinical and food industry applications. This review provides a comprehensive overview of the molecular and metabolic strategies that can be used to optimize the expression of L-ASNase in heterologous systems. This article describes various approaches that have been employed to increase enzyme production, including the use of molecular tools, strain engineering, and in silico optimization. The review article highlights the critical role that rational design plays in achieving successful heterologous expression and underscores the challenges of large-scale production of L-ASNase, such as inadequate protein folding and the metabolic burden on host cells. Improved gene expression is shown to be achievable through the optimization of codon usage, synthetic promoters, transcription and translation regulation, and host strain improvement, among others. Additionally, this review provides a deep understanding of the enzymatic properties of L-ASNase and how this knowledge has been employed to enhance its properties and production. Finally, future trends in L-ASNase production, including the integration of CRISPR and machine learning tools are discussed. This work serves as a valuable resource for researchers looking to design effective heterologous expression systems for L-ASNase production as well as for enzymes production in general.

Current Status of Omics in Biological Quality Elements for Freshwater Biomonitoring.

Freshwater ecosystems have been experiencing various forms of threats, mainly since the last century. The severity of this adverse scenario presents unprecedented challenges to human health, water supply, agriculture, forestry, ecological systems, and biodiversity, among other areas. Despite the progress made in various biomonitoring techniques tailored to specific countries and biotic communities, significant constraints exist, particularly in assessing and quantifying biodiversity and its interplay with detrimental factors. Incorporating modern techniques into biomonitoring methodologies presents a challenging topic with multiple perspectives and assertions. This review aims to present a comprehensive overview of the contemporary advancements in freshwater biomonitoring, specifically by utilizing omics methodologies such as genomics, metagenomics, transcriptomics, proteomics, metabolomics, and multi-omics. The present study aims to elucidate the rationale behind the imperative need for modernization in this field. This will be achieved by presenting case studies, examining the diverse range of organisms that have been studied, and evaluating the potential benefits and drawbacks associated with the utilization of these methodologies. The utilization of advanced high-throughput bioinformatics techniques represents a sophisticated approach that necessitates a significant departure from the conventional practices of contemporary freshwater biomonitoring. The significant contributions of omics techniques in the context of biological quality elements (BQEs) and their interpretations in ecological problems are crucial for biomonitoring programs. Such contributions are primarily attributed to the previously overlooked identification of interactions between different levels of biological organization and their responses, isolated and combined, to specific critical conditions.