Sense the moment: A highly sensitive antimicrobial activity predictor based on hydrophobic moment

Investigating molecular descriptors in cell-penetrating peptides prediction with deep learning: Employing N, O, and hydrophobicity according to the Eisenberg scale

Cell-penetrating peptides comprise a group of molecules that can naturally cross the lipid bilayer membrane that protects cells, sharing physicochemical and structural properties, and having several pharmaceutical applications, particularly in drug delivery. Investigations of molecular descriptors have provided not only an improvement in the performance of classifiers but also less computational complexity and an enhanced understanding of membrane permeability. Furthermore, the employment of new technologies, such as the construction of deep learning models using overfitting treatment, promotes advantages in tackling this problem. In this study, the descriptors nitrogen, oxygen, and hydrophobicity on the Eisenberg scale were investigated, using the proposed ConvBoost-CPP composed of an improved convolutional neural network with overfitting treatment and an XGBoost model with adjusted hyperparameters. The results revealed favorable to the use of ConvBoost-CPP, having as input nitrogen, oxygen, and hydrophobicity together with ten other descriptors previously investigated in this research line, showing an increase in accuracy from 88% to 91.2% in cross-validation and 82.6% to 91.3% in independent test.

Accelerating the Discovery and Design of Antimicrobial Peptides with Artificial Intelligence

Peptides modulate many processes of human physiology targeting ion channels, protein receptors, or enzymes. They represent valuable starting points for the development of new biologics against communicable and non-communicable disorders. However, turning native peptide ligands into druggable materials requires high selectivity and efficacy, predictable metabolism, and good safety profiles. Machine learning models have gradually emerged as cost-effective and time-saving solutions to predict and generate new proteins with optimal properties. In this chapter, we will discuss the evolution and applications of predictive modeling and generative modeling to discover and design safe and effective antimicrobial peptides. We will also present their current limitations and suggest future research directions, applicable to peptide drug design campaigns.

Artificial intelligence-driven antimicrobial peptide discovery

Antimicrobial peptides (AMPs) emerge as promising agents against antimicrobial resistance, providing an alternative to conventional antibiotics. Artificial intelligence (AI) revolutionized AMP discovery through both discrimination and generation approaches. The discriminators aid in the identification of promising candidates by predicting key peptide properties such as activity and toxicity, while the generators learn the distribution of peptides and enable sampling novel AMP candidates, either de novo or as analogs of a prototype peptide. Moreover, the controlled generation of AMPs with desired properties is achieved by discriminator-guided filtering, positive-only learning, latent space sampling, as well as conditional and optimized generation. Here we review recent achievements in AI-driven AMP discovery, highlighting the most exciting directions.

SIGANEO: Similarity network with GAN enhancement for immunogenic neoepitope prediction

Target selection of the personalized cancer neoantigen vaccine, which is highly dependent on computational prediction algorithms, is crucial for its clinical efficacy. Due to the limited number of experimentally validated immunogenic neoepitopes as well as the complexity of neoantigens in eliciting T cell response, the accuracy of neoepitope immunogenicity prediction methods requires persistent efforts for improvement. We present a deep learning framework for neoepitope immunogenicity prediction - SIGANEO by integrating GAN-like network with similarity network to address issues of missing values and limited data concerning neoantigen prediction. This framework exhibits superior performance over competing machine-learning-based neoantigen prediction algorithms over an independent test dataset from TESLA consortium. Particularly for the clinical setting of neoantigen vaccine where only the top 10 and 20 predictions are selected for vaccine production, SIGANEO achieves significantly better accuracy for predicting experimentally validated neoepitopes. Our work demonstrates that deep learning techniques can greatly boost the accuracy of target identification for cancer neoantigen vaccine.

iASMP: An interpretable in-silico predictive tool focusing on species-specific antimicrobial peptides

Antimicrobial peptides (AMPs), a crucial part of the innate immune system, have been exploited as promising candidates for antibacterial agents. Many researchers have been devoting their efforts to develop novel AMPs in recent decades. In this term, many computational approaches have been developed to identify potential AMPs accurately. However, finding peptides specific to a particular bacterial species is challenging. Streptococcus mutans is a pathogen with an apparent cariogenic effect, and it is of great significance to study AMP that inhibit S. mutans for the prevention and treatment of caries. In this study, we proposed a sequence-based machine learning model, namely iASMP, to exactly identify potential anti-S. mutans peptides (ASMPs). After collecting ASMPs, the performances of models were compared by utilizing multiple feature descriptors and different classification algorithms. Among the baseline predictors, the model integrating the extra trees (ET) algorithm and the hybrid features exhibited optimal results. The feature selection method was utilized to remove redundant feature information to improve the model performance further. Finally, the proposed model achieved the maximum accuracy (ACC) of 0.962 on the training dataset and performed on the testing dataset with an ACC of 0.750. The results demonstrated that iASMP had an excellent predictive performance and was suitable for identifying potential ASMP. Furthermore, we also visualized the selected features and rationally explained the impact of individual features on the model output.

Discovering highly potent antimicrobial peptides with deep generative model HydrAMP

Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.

Evaluation of a Novel Synthetic Peptide Derived from Cytolytic Mycotoxin Candidalysin

The importance of neuroinflammation in neurology is becoming increasingly apparent. In addition to neuroinflammatory diseases such as multiple sclerosis, the role of neuroinflammation has been identified in many non-inflammatory neurological disorders such as stroke, epilepsy, and cancer. The immune response within the brain involves the presence of CNS resident cells; mainly glial cells, such as microglia, the CNS resident macrophages. We evaluated the peptide Ca-MAP1 bioinspired on the C. albicans immature cytolytic toxin candidalysin to develop a less hemolytic peptide with anti-neuroinflammatory, antibacterial, and cytotoxic activity against tumor cells. In silico and in vitro studies were performed at various concentrations. Ca-MAP1 exhibits low hemolytic activity at lower concentrations and was not cytotoxic to MRC-5 and BV-2 cells. Ca-MAP1 showed activity against Acinetobacter baumannii, Escherichia coli ATCC, E. coli KPC, Klebsiella pneumoniae ATCC, Pseudomonas aeruginosa, and Staphylococcus aureus ATCC. Furthermore, Ca-MAP1 exhibits anti-neuroinflammatory activity in the BV-2 microglia model, with 93.78% inhibition of nitrate production at 18.1 µM. Ca-MAP1 presents cytotoxic activity against tumor cell line NCI-H292 at 36.3 μM, with an IC₅₀ of 38.4 µM. Ca-MAP1 demonstrates results that qualify it to be evaluated in the next steps to promote the control of infections and provide an alternative antitumor therapy.

Synthetic Amphipathic β-Sheet Temporin-Derived Peptide with Dual Antibacterial and Anti-Inflammatory Activities

Temporin family is one of the largest among antimicrobial peptides (AMPs), which act mainly by penetrating and disrupting the bacterial membranes. To further understand the relationship between the physical-chemical properties and their antimicrobial activity and selectivity, an analogue of Temporin L, [Nle¹, dLeu⁹, dLys¹⁰]TL (Nle-Phe-Val-Pro-Trp-Phe-Lys-Phe-dLeu-dLys-Arg-Ile-Leu-CONH₂) has been developed in the present work. The design strategy consisted of the addition of a norleucine residue at the N-terminus of the lead peptide sequence, [dLeu⁹, dLys¹⁰]TL, previously developed by our group. This modification promoted an increase of peptide hydrophobicity and, interestingly, more efficient activity against both Gram-positive and Gram-negative strains, without affecting human keratinocytes and red blood cells survival compared to the lead peptide. Thus, this novel compound was subjected to biophysical studies, which showed that the peptide [Nle¹, dLeu⁹, dLys¹⁰]TL is unstructured in water, while it adopts β-type conformation in liposomes mimicking bacterial membranes, in contrast to its lead peptide forming α-helical aggregates. After its aggregation in the bacterial membrane, [Nle¹, dLeu⁹, dLys¹⁰]TL induced membrane destabilization and deformation. In addition, the increase of peptide hydrophobicity did not cause a loss of anti-inflammatory activity of the peptide [Nle¹, dLeu⁹, dLys¹⁰]TL in comparison with its lead peptide. In this study, our results demonstrated that positive net charge, optimum hydrophobic−hydrophilic balance, and chain length remain the most important parameters to be addressed while designing small cationic AMPs.

Legume Plant Peptides as Sources of Novel Antimicrobial Molecules Against Human Pathogens

Antimicrobial peptides are prominent components of the plant immune system acting against a wide variety of pathogens. Legume plants from the inverted repeat lacking clade (IRLC) have evolved a unique gene family encoding nodule-specific cysteine-rich NCR peptides acting in the symbiotic cells of root nodules, where they convert their bacterial endosymbionts into non-cultivable, polyploid nitrogen-fixing cells. NCRs are usually 30–50 amino acids long peptides having a characteristic pattern of 4 or 6 cysteines and highly divergent amino acid composition. While the function of NCRs is largely unknown, antimicrobial activity has been demonstrated for a few cationic Medicago truncatula NCR peptides against bacterial and fungal pathogens. The advantages of these plant peptides are their broad antimicrobial spectrum, fast killing modes of actions, multiple bacterial targets, and low propensity to develop resistance to them and no or low cytotoxicity to human cells. In the IRLC legumes, the number of NCR genes varies from a few to several hundred and it is possible that altogether hundreds of thousands of different NCR peptides exist. Due to the need for new antimicrobial agents, we investigated the antimicrobial potential of 104 synthetic NCR peptides from M. truncatula, M. sativa, Pisum sativum, Galega orientalis and Cicer arietinum against eight human pathogens, including ESKAPE bacteria. 50 NCRs showed antimicrobial activity with differences in the antimicrobial spectrum and effectivity. The most active peptides eliminated bacteria at concentrations from 0.8 to 3.1 μM. High isoelectric point and positive net charge were important but not the only determinants of their antimicrobial activity. Testing the activity of shorter peptide derivatives against Acinetobacter baumannii and Candida albicans led to identification of regions responsible for the antimicrobial activity and provided insight into their potential modes of action. This work provides highly potent lead molecules without hemolytic activity on human blood cells for novel antimicrobial drugs to fight against pathogens.

Improved Database Filtering Technology Enables More Efficient Ab Initio Design of Potent Peptides against Ebola Viruses

The rapid mutations of viruses such as SARS-CoV-2 require vaccine updates and the development of novel antiviral drugs. This article presents an improved database filtering technology for a more effective design of novel antiviral agents. Different from the previous approach, where the most probable parameters were obtained stepwise from the antimicrobial peptide database, we found it possible to accelerate the design process by deriving multiple parameters in a single step during the peptide amino acid analysis. The resulting peptide DFTavP1 displays the ability to inhibit Ebola virus. A deviation from the most probable peptide parameters reduces antiviral activity. The designed peptides appear to block viral entry. In addition, the amino acid signature provides a clue to peptide engineering to gain cell selectivity. Like human cathelicidin LL-37, our engineered peptide DDIP1 inhibits both Ebola and SARS-CoV-2 viruses. These peptides, with broad antiviral activity, may selectively disrupt viral envelopes and offer the lasting efficacy required to treat various RNA viruses, including their emerging mutants.