Predicting Antimicrobial Peptides by Using Increment of Diversity with Quadratic Discriminant Analysis Method

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.

Partner of neuropeptide bursicon homodimer pburs mediates a novel antimicrobial peptide Ten3LP via Dif/Dorsal2 in Tribolium castaneum

Bursicon is a cystine knot family neuropeptide, composed of two subunits, bursicon (burs) and partner of burs (pburs). The subunits can form heterodimers to regulate cuticle tanning and wing maturation and homodimers to signal different biological functions in innate immunity, midgut stem cell proliferation and energy homeostasis, and reproductive physiology in the model insects Drosophila melanogaster or Tribolium castaneum. Here, we report on the role of the pburs homodimer in signaling innate immunity in T. castaneum larvae. Through transcriptome analysis we identified a set of immune-related genes that respond to pburs RNAi. Treating larvae with recombinant-pburs protein led to up-regulation of antimicrobial peptide (AMP) genes in vivo and in vitro. The upregulation of most AMP genes was dependent on the NF-κB transcription factor Relish. Most importantly, we identified a novel AMP, Tenecin 3-like peptide (Ten3LP), regulated by pburs via NF-κB transcription factor Dorsal-related immunity factor (Dif)/Dorsal2, but not Relish. We conducted Ten3LP RNAi, synthesized recombinant Ten3LP protein for microbial inhibition assays and functionally characterized Ten3LP as an AMP specific for fungi and Gram-positive bacteria. We demonstrate that expression of Ten3LP is activated by pburs via the Toll pathway. These findings identify new molecular targets for development of potential antibiotics for treating microbial infections and perhaps for RNAi based pest management technology.

Machine Learning Prediction of Antimicrobial Peptides

Antibiotic resistance constitutes a global threat and could lead to a future pandemic. One strategy is to develop a new generation of antimicrobials. Naturally occurring antimicrobial peptides (AMPs) are recognized templates and some are already in clinical use. To accelerate the discovery of new antibiotics, it is useful to predict novel AMPs from the sequenced genomes of various organisms. The antimicrobial peptide database (APD) provided the first empirical peptide prediction program. It also facilitated the testing of the first machine-learning algorithms. This chapter provides an overview of machine-learning predictions of AMPs. Most of the predictors, such as AntiBP, CAMP, and iAMPpred, involve a single-label prediction of antimicrobial activity. This type of prediction has been expanded to antifungal, antiviral, antibiofilm, anti-TB, hemolytic, and anti-inflammatory peptides. The multiple functional roles of AMPs annotated in the APD also enabled multi-label predictions (iAMP-2L, MLAMP, and AMAP), which include antibacterial, antiviral, antifungal, antiparasitic, antibiofilm, anticancer, anti-HIV, antimalarial, insecticidal, antioxidant, chemotactic, spermicidal activities, and protease inhibiting activities. Also considered in predictions are peptide posttranslational modification, 3D structure, and microbial species-specific information. We compare important amino acids of AMPs implied from machine learning with the frequently occurring residues of the major classes of natural peptides. Finally, we discuss advances, limitations, and future directions of machine-learning predictions of antimicrobial peptides. Ultimately, we may assemble a pipeline of such predictions beyond antimicrobial activity to accelerate the discovery of novel AMP-based antimicrobials.

Artificial Intelligence and Antibiotic Discovery

Over recent decades, a new antibiotic crisis has been unfolding due to a decreased research in this domain, a low return of investment for the companies that developed the drug, a lengthy and difficult research process, a low success rate for candidate molecules, an increased use of antibiotics in farms and an overall inappropriate use of antibiotics. This has led to a series of pathogens developing antibiotic resistance, which poses severe threats to public health systems while also driving up the costs of hospitalization and treatment. Moreover, without proper action and collaboration between academic and health institutions, a catastrophic trend might develop, with the possibility of returning to a pre-antibiotic era. Nevertheless, new emerging AI-based technologies have started to enter the field of antibiotic and drug development, offering a new perspective to an ever-growing problem. Cheaper and faster research can be achieved through algorithms that identify hit compounds, thereby further accelerating the development of new antibiotics, which represents a vital step in solving the current antibiotic crisis. The aim of this review is to provide an extended overview of the current artificial intelligence-based technologies that are used for antibiotic discovery, together with their technological and economic impact on the industrial sector.

Antimicrobial Peptides: An Update on Classifications and Databases

Antimicrobial peptides (AMPs) are distributed across all kingdoms of life and are an indispensable component of host defenses. They consist of predominantly short cationic peptides with a wide variety of structures and targets. Given the ever-emerging resistance of various pathogens to existing antimicrobial therapies, AMPs have recently attracted extensive interest as potential therapeutic agents. As the discovery of new AMPs has increased, many databases specializing in AMPs have been developed to collect both fundamental and pharmacological information. In this review, we summarize the sources, structures, modes of action, and classifications of AMPs. Additionally, we examine current AMP databases, compare valuable computational tools used to predict antimicrobial activity and mechanisms of action, and highlight new machine learning approaches that can be employed to improve AMP activity to combat global antimicrobial resistance.

The Development of Machine Learning Methods in discriminating Secretory Proteins of Malaria Parasite

Malaria caused by Plasmodium falciparum is one of the major infectious diseases in the world. It is essential to exploit an effective method to predict secretory proteins of malaria parasites to develop effective cures and treatment. Biochemical assays can provide details for accurate identification of the secretory proteins, but these methods are expensive and time-consuming. In this paper, we summarized the machine learning-based identification algorithms and compared the construction strategies between different computational methods. Also, we discussed the use of machine learning to improve the ability of algorithms to identify proteins secreted by malaria parasites.

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/.

Toward insights on determining factors for high activity in antimicrobial peptides via machine learning

The continued and general rise of antibiotic resistance in pathogenic microbes is a well-recognized global threat. Host defense peptides (HDPs), a component of the innate immune system have demonstrated promising potential to become a next generation antibiotic effective against a plethora of pathogens. While the effectiveness of antimicrobial HDPs has been extensively demonstrated in experimental studies, theoretical insights on the mechanism by which these peptides function is comparably limited. In particular, experimental studies of AMP mechanisms are limited in the number of different peptides investigated and the type of peptide parameters considered. This study makes use of the random forest algorithm for classifying the antimicrobial activity as well for identifying molecular descriptors underpinning the antimicrobial activity of investigated peptides. Subsequent manual interpretation of the identified important descriptors revealed that polarity-solubility are necessary for the membrane lytic antimicrobial activity of HDPs.