PROTA: A Robust Tool for Protamine Prediction Using a Hybrid Approach of Machine Learning and Deep Learning.

Protamines play a critical role in DNA compaction and stabilization in sperm cells, significantly influencing male fertility and various biotechnological applications. Traditionally, identifying these proteins is a challenging and time-consuming process due to their species-specific variability and complexity. Leveraging advancements in computational biology, we present PROTA, a novel tool that combines machine learning (ML) and deep learning (DL) techniques to predict protamines with high accuracy. For the first time, we integrate Generative Adversarial Networks (GANs) with supervised learning methods to enhance the accuracy and generalizability of protamine prediction. Our methodology evaluated multiple ML models, including Light Gradient-Boosting Machine (LIGHTGBM), Multilayer Perceptron (MLP), Random Forest (RF), eXtreme Gradient Boosting (XGBOOST), k-Nearest Neighbors (KNN), Logistic Regression (LR), Naive Bayes (NB), and Radial Basis Function-Support Vector Machine (RBF-SVM). During ten-fold cross-validation on our training dataset, the MLP model with GAN-augmented data demonstrated superior performance metrics: 0.997 accuracy, 0.997 F1 score, 0.998 precision, 0.997 sensitivity, and 1.0 AUC. In the independent testing phase, this model achieved 0.999 accuracy, 0.999 F1 score, 1.0 precision, 0.999 sensitivity, and 1.0 AUC. These results establish PROTA, accessible via a user-friendly web application. We anticipate that PROTA will be a crucial resource for researchers, enabling the rapid and reliable prediction of protamines, thereby advancing our understanding of their roles in reproductive biology, biotechnology, and medicine.

MultiToxPred 1.0: a novel comprehensive tool for predicting 27 classes of protein toxins using an ensemble machine learning approach.

Protein toxins are defense mechanisms and adaptations found in various organisms and microorganisms, and their use in scientific research as therapeutic candidates is gaining relevance due to their effectiveness and specificity against cellular targets. However, discovering these toxins is time-consuming and expensive. In silico tools, particularly those based on machine learning and deep learning, have emerged as valuable resources to address this challenge. Existing tools primarily focus on binary classification, determining whether a protein is a toxin or not, and occasionally identifying specific types of toxins. For the first time, we propose a novel approach capable of classifying protein toxins into 27 distinct categories based on their mode of action within cells. To accomplish this, we assessed multiple machine learning techniques and found that an ensemble model incorporating the Light Gradient Boosting Machine and Quadratic Discriminant Analysis algorithms exhibited the best performance. During the tenfold cross-validation on the training dataset, our model exhibited notable metrics: 0.840 accuracy, 0.827 F1 score, 0.836 precision, 0.840 sensitivity, and 0.989 AUC. In the testing stage, using an independent dataset, the model achieved 0.846 accuracy, 0.838 F1 score, 0.847 precision, 0.849 sensitivity, and 0.991 AUC. These results present a powerful next-generation tool called MultiToxPred 1.0, accessible through a web application. We believe that MultiToxPred 1.0 has the potential to become an indispensable resource for researchers, facilitating the efficient identification of protein toxins. By leveraging this tool, scientists can accelerate their search for these toxins and advance their understanding of their therapeutic potential.

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.

Antibiotic discovery against Piscirickettsia salmonis using a combined in silico and in vitro approach.

Piscirickettsia salmonis is one of the main pathogens causing considerable economic losses in salmonid farming. The DNA gyrase of several pathogenic bacteria has been the target of choice for antibiotic design and discovery for years, due to its key function during DNA replication. In this study, we carried out a combined in silico and in vitro approach to antibiotic discovery targeting the GyrA subunit of Piscirickettsia salmonis. The in silico results of this work showed that flumequine (-6.6 kcal/mol), finafloxacin (-7.2 kcal/mol), rosoxacin (-6.6 kcal/mol), elvitegravir (-6.4 kcal/mol), sarafloxacin (-8.3 kcal/mol), orbifloxacin (-7.9 kcal/mol), and sparfloxacin (-7.2 kcal/mol) are docked with good affinities in the DNA binding domain of the Piscirickettsia salmonis GyrA subunit. In the in vitro inhibition assay, it was observed that most of these molecules inhibit the growth of Piscirickettsia salmonis, except for elvitegravir. We believe that this methodology could help to significantly reduce the time and cost of antibiotic discovery trials to combat Piscirickettsia salmonis within the salmonid farming industry.

In Silico Design of a Chimeric Humanized L-asparaginase.

Acute lymphoblastic leukemia (ALL) is the most common cancer among children worldwide, characterized by an overproduction of undifferentiated lymphoblasts in the bone marrow. The treatment of choice for this disease is the enzyme L-asparaginase (ASNase) from bacterial sources. ASNase hydrolyzes circulating L-asparagine in plasma, leading to starvation of leukemic cells. The ASNase formulations of E. coli and E. chrysanthemi present notorious adverse effects, especially the immunogenicity they generate, which undermine both their effectiveness as drugs and patient safety. In this study, we developed a humanized chimeric enzyme from E. coli L-asparaginase which would reduce the immunological problems associated with current L-asparaginase therapy. For these, the immunogenic epitopes of E. coli L-asparaginase (PDB: 3ECA) were determined and replaced with those of the less immunogenic Homo sapiens asparaginase (PDB:4O0H). The structures were modeled using the Pymol software and the chimeric enzyme was modeled using the SWISS-MODEL service. A humanized chimeric enzyme with four subunits similar to the template structure was obtained, and the presence of asparaginase enzymatic activity was predicted by protein-ligand docking.

L-Asparaginase as the gold standard in the treatment of acute lymphoblastic leukemia: a comprehensive review.

L-Asparaginase is an antileukemic drug long approved for clinical use to treat childhood acute lymphoblastic leukemia, the most common cancer in this population worldwide. However, the efficacy and its use as a drug have been subject to debate due to the variety of adverse effects that patients treated with it present, as well as the prompt elimination in plasma, the need for multiple administrations, and high rates of allergic reactions. For this reason, the search for new, less immunogenic variants has long been the subject of study. This review presents the main aspects of the L-asparaginase enzyme from a structural, pharmacological, and clinical point of view, from the perspective of its use in chemotherapy protocols in conjunction with other drugs in the different treatment phases.

PEP-PREDNa+: A web server for prediction of highly specific peptides targeting voltage-gated Na+ channels using machine learning techniques.

Voltage-gated sodium channel activity has long been associated with several diseases including epilepsy, chronic pain, cardiovascular diseases, cancers, immune system, neuromuscular and respiratory disorders. The strong participation of these channels in the development of diseases makes them excellent promising therapeutic targets. Voltage-gated Na+ channel blocking peptides come from a wide source of organisms such as venoms. However, the in vitro and in vivo identification and validation of these peptides are time-consuming and resource-intensive. In this work, we developed a bioinformatics tool called PEP-PREDNa + for the highly specific prediction of voltage-gated Na+ channel blocking peptides. PEP-PREDNa+ is based on the random forest algorithm, which presented excellent performance measures during the cross-validation (sensitivity = 0.81, accuracy = 0.83, precision = 0.85, F-score = 0.83, specificity = 0.86, and Matthew's correlation coefficient = 0.67) and testing (sensitivity = 0.88, accuracy = 0.92, precision = 0.96, F-score = 0.91, specificity = 0.96, and Matthew's correlation coefficient = 0.84) phases. The PEP-PREDNa + tool could be very useful in accelerating and reducing the costs of the discovery of new voltage-gated Na+ channel blocking peptides with therapeutic potential.

VirVACPRED: A Web Server for Prediction of Protective Viral Antigens.

Viral antigens are key in the development of vaccines that prevent or eradicate infections caused by these pathogens. Bioinformatics tools are modern alternatives that facilitate the discovery of viral antigens, reducing the costs of experimental assays. We developed a bioinformatics tool called VirVACPRED, which is highly efficient in predicting viral antigens. In this study, we obtained a model based on the gradient boosting classifier, which showed high performance during the training, leave-one-out cross-validation (accuracy = 0.7402, sensitivity = 0.7319, precision = 0.7503, F1 = 0.7251, kappa = 0.4774, Matthews correlation coefficient = 0.4981) and testing (accuracy = 0.8889, sensitivity = 1.0, precision = 0.8276, F1 = 0.9057, kappa = 0.7734, Matthews correlation coefficient = 0.7941). VirVACPRED is a robust tool that can be of great help in the search and proposal of new viral antigens, which can be considered in the development of future vaccines against infections caused by viruses.

Workflow optimization in a clinical laboratory using Lean management principles in the pre-analytical phase.

BACKGROUND: The application of the Lean methodology in clinical laboratories can improve workflow and user satisfaction through the efficient delivery of analytical results. The purpose of this study was to optimise delivery times of the test results at a clinical laboratory, using Lean management principles in the pre-analytical phase. METHODS: A prospective study with a quasi-experimental design was implemented. Staff functions were restructured and sample flows were modified. Delivery times of clinical results (glucose and haematocrit; 6648 data) from the Medicine and Adult Emergency services for years 2017 and 2018 were compared. RESULTS: A reduction (p < 0.05) in turnaround times in the delivery of glucose test results at the adult emergency service was observed (84 to 73 min, 13%, pre and post). In addition, there was a non-significant reduction in the turnaround times for glucose (Medicine) and haematocrit in both services. In the analytical and post-analytical phase (not intervened), an increase in turnaround times was observed in some cases. CONCLUSIONS: Other studies have indicated that the application of the Lean methodology in clinical laboratories improves workflow, increasing effectiveness and efficiency. This study showed an improvement in the delivery time of test results (glucose - Emergency), giving rise to a culture of cooperation and continuous improvement. It would, however, be essential to address the management model integrating the analytical and post-analytical phases.

TAP 1.0: A robust immunoinformatic tool for the prediction of tumor T-cell antigens based on AAindex properties.

Immunotherapy is a research area with great potential in drug discovery for cancer treatment. Because of the capacity of tumor antigens to activate the immune response and promote the destruction of tumor cells, they are considered excellent immunotherapeutic drugs. In this work, we evaluated fifteen machine learning algorithms for the classification of tumor antigens. For this purpose, we build robust datasets, carefully selected from the TANTIGEN and IEDB databases. The feature computation of all antigens in this study was performed by developing a script written in Python 3.8, which allowed the calculation of 544 physicochemical and biochemical properties extracted from the AAindex database. All classifiers were subjected to the training, 10-fold cross-validation, and testing on an independent dataset. The results of this study showed that the quadratic discriminant classifier presented the best performance measures over the independent dataset, accuracy = 0.7384, AUC = 0.817, recall = 0.676, precision = 0.7857, F1 = 0.713, kappa = 0.4764, and Matthews correlation coefficient = 0.4834, outperforming common machine learning classifiers used in the bioinformatics area. We believe that our prediction model could be of great importance in the field of cancer immunotherapy for the search of potential tumor antigens. Taking all aspects mentioned before, we developed an immunoinformatic tool called TAP 1.0 with a friendly interface for tumor antigens prediction, available at https://tapredictor.herokuapp.com/.

The CatSper channel is present and plays a key role in sperm motility of the Atlantic salmon (Salmo salar).

Among all the Ca2+ channels, CatSper channels have been one of the most studied in sperm of different species due to their demonstrated role in the fertilization process. In fish sperm, the calcium channel plays a key role in sperm activation. However, the functionality of the CatSper channels has not been studied in any of the fish species. For the first time, we studied the relationship of the CatSper channel with sperm motility in a fish, using Atlantic salmon (Salmo salar) as the model. The results of our study showed that the CatSper channel in Salmo salar has chemical-physical characteristics similar to those reported for mammalian CatSper channels. In this work, it was shown that Salmo salar CatSper 3 protein has a molecular weight of approximately 55-kDa similar to Homo sapiens CatSper 3. In silico analyses suggest that this channel forms a heterotetramer sensitive to the specific inhibitor HC-056456, with a binding site in the center of the pore of the CatSper channel, hindering or preventing the influx of Ca2+ ions. The in vitro assay of the sperm motility inhibition of Salmo salar with the inhibitor HC-056456 showed that sperm treated with this inhibitor significantly reduced the total and progressive motility (p < .0001), demonstrating the importance of this ionic channel for this cell. The complementation of the in silico and in vitro analyses of the present work demonstrates that the CatSper channel plays a key role in the regulation of sperm motility in Atlantic salmon.

TTAgP 1.0: A computational tool for the specific prediction of tumor T cell antigens.

Nowadays, cancer is considered a global pandemic and millions of people die every year because this disease remains a challenge for the world scientific community. Even with the efforts made to combat it, there is a growing need to discover and design new drugs and vaccines. Among these alternatives, antitumor peptides are a promising therapeutic solution to reduce the incidence of deaths caused by cancer. In the present study, we developed TTAgP, an accurate bioinformatic tool that uses the random forest algorithm for antitumor peptide predictions, which are presented in the context of MHC class I. The predictive model of TTAgP was trained and validated based on several features of 922 peptides. During the model validation we achieved sensitivity = 0.89, specificity = 0.92, accuracy = 0.90 and the Matthews correlation coefficient = 0.79 performance measures, which are indicative of a robust model. TTAgP is a fast, accurate and intuitive software focused on the prediction of tumor T cell antigens.