Antiviral Peptides Research Articles

Antiviral Peptide-Generative Pre-Trained Transformer (AVP-GPT): A Deep Learning-Powered Model for Antiviral Peptide Design with High-Throughput Discovery and Exceptional Potency

Traditional antiviral peptide (AVP) discovery is a time-consuming and expensive process. This study introduces AVP-GPT, a novel deep learning method utilizing transformer-based language models and multimodal architectures specifically designed for AVP design. AVP-GPT demonstrated exceptional efficiency, generating 10,000 unique peptides and identifying potential AVPs within two days on a GPU system. Pre-trained on a respiratory syncytial virus (RSV) dataset, AVP-GPT successfully adapted to influenza A virus (INFVA) and other respiratory viruses. Compared to state-of-the-art models like LSTM and SVM, AVP-GPT achieved significantly lower perplexity (2.09 vs. 16.13) and higher AUC (0.90 vs. 0.82), indicating superior peptide sequence prediction and AVP classification. AVP-GPT generated a diverse set of peptides with excellent novelty and identified candidates with remarkably higher antiviral success rates than conventional design methods. Notably, AVP-GPT generated novel peptides against RSV and INFVA with exceptional potency, including four peptides exhibiting EC50 values around 0.02 uM—the strongest anti-RSV activity reported to date. These findings highlight AVP-GPT’s potential to revolutionize AVP discovery and development, accelerating the creation of novel antiviral drugs. Future studies could explore the application of AVP-GPT to other viral targets and investigate alternative AVP design strategies.

Virtual screening of antiviral peptides as novel blockers of human papillomavirus 16

Human papillomaviruses (HPVs) contribute to 5% of cancers, yet there is a lack of specific antiviral agents targeting HPV infection. Antiviral peptides (AVPs) present a promising alternative to conventional therapeutics. This study aims to explore the use of AVPs against the HPV16 E6 oncoprotein through virtual screening. The potential binding pocket of the E6 oncoprotein was determined, and using the antimicrobial CAMPR4 database 18 AVPs were shortlisted. These AVPs were then docked to the E6 oncoprotein using the HawkDock server, followed by dynamic simulation. Among the AVPs tested, AVP18, AVP10, and AVP7 demon­strated the highest inhibitory potential against the E6 oncoprotein. AVP18 exhibited more non-bonded contacts, hydrogen bonds, and electrostatic forces. Dynamics simulation confirmed the stability of the complexes formed by these top AVPs with E6. This research suggests that AVP7, AVP10, and AVP18 are promising lead candidates for blocking HPV16 by inhibiting the E6 oncoprotein. Keywords: antiviral peptides, docking, dynamics simulation, E6 oncoprotein, human papillomavirus

Global Antiviral Peptide Research: A Bibliometric Analysis from 1951 to 2022

Antiviral peptides (AVPs) are small molecules that inhibit the replication of viruses in living cells. AVPs are being investigated as potential alternatives to traditional antiviral drugs. The development of novel antiviral agents is of the highest concern because some traditional antiviral medications can be ineffective and lead to resistant viruses emergence. We conducted a bibliometric study on the global distribution of AVP research to comprehend the trends and patterns in the field. For this analysis, we retrieved data from the Scopus database on AVP-related publications from 1951 to 2022, including the number of publications, citations, and authors. Overall, 10,279 papers were published, with an annual average of 146 publications. The United States released the most documents, followed by China, Germany, and the United Kingdom. Since 2001, there has been a substantial increase in global publications on AVPs, with prominent themes including virology, genetics, protease inhibitors, polypeptide antimicrobial agents, and viral entry. This bibliometric analysis can be used to guide future research in this field.

Synthesis, Anti-TMV Activities, and Action Mechanisms of a Novel Cytidine Peptide Compound.

Cytidine has a broad range of applications in the pharmaceutical field as an intermediate of antitumor or antiviral agent. Here, a series of new cytidine peptide compounds were synthesized using cytidine and Boc group-protected amino acids and analyzed for their antiviral activities against tobacco mosaic virus (TMV). Among these compounds, the structure of an effective antiviral cytidine peptide SN11 was characterized by 1H NMR, 13C NMR, and high-resolution mass spectrometer. The compound SN11 has a molecular formula of C15H22N6O8 and is named 2-amino-N-(2- ((1- (3,4-dihydroxy-5-(hydroxymethyl) tetrahydrofuran-2-yl) -2-oxo-1,2-dihydropyrimidin-4-yl) amino) -2-oxyethyl) amino). The protection, inactivation, and curation activities of SN11 at a concentration of 500 μg/mL against TMV in Nicotiana glutinosa were 82.6%, 84.2%, and 72.8%, respectively. SN11 also effectively suppressed the systemic transportation of a recombinant TMV carrying GFP reporter gene (p35S-30B:GFP) in Nicotiana benthamiana by reducing viral accumulation to 71.3% in the upper uninoculated leaves and inhibited the systemic infection of TMV in Nicotiana tabacum plants. Furthermore, the results of RNA-seq showed that compound SN11 induced differential expression of genes involved in the biogenesis and function of ribosome, plant hormone signal transduction, plant pathogen interaction, and chromatin. These results validate the antiviral mechanisms of the cytidine peptide compound and provide a theoretical basis for their potential application in the management of plant virus diseases.

HybAVPnet: A Novel Hybrid Network Architecture for Antiviral Peptides Prediction.

Viruses pose a great threat to human production and life, thus the research and development of antiviral drugs is urgently needed. Antiviral peptides play an important role in drug design and development. Compared with the time-consuming and laborious wet chemical experiment methods, it is critical to use computational methods to predict antiviral peptides accurately and rapidly. However, due to limited data, accurate prediction of antiviral peptides is still challenging and extracting effective feature representations from sequences is crucial for creating accurate models. This study introduces a novel two-step approach, named HybAVPnet, to predict antiviral peptides with a hybrid network architecture based on neural networks and traditional machine learning methods. We adopted a stacking-like structure to capture both the long-term dependencies and local evolution information to achieve a comprehensive and diverse prediction using the predicted labels and probabilities. Using an ensemble technique with the different kinds of features can reduce the variance without increasing the bias. The experimental result shows HybAVPnet can achieve better and more robust performance compared with the state-of-the-art methods, which makes it useful for the research and development of antiviral drugs. Meanwhile, it can also be extended to other peptide recognition problems because of its generalization ability.

Innovative Alignment-Based Method for Antiviral Peptide Prediction.

Antiviral peptides (AVPs) represent a promising strategy for addressing the global challenges of viral infections and their growing resistances to traditional drugs. Lab-based AVP discovery methods are resource-intensive, highlighting the need for efficient computational alternatives. In this study, we developed five non-trained but supervised multi-query similarity search models (MQSSMs) integrated into the StarPep toolbox. Rigorous testing and validation across diverse AVP datasets confirmed the models' robustness and reliability. The top-performing model, M13+, demonstrated impressive results, with an accuracy of 0.969 and a Matthew's correlation coefficient of 0.71. To assess their competitiveness, the top five models were benchmarked against 14 publicly available machine-learning and deep-learning AVP predictors. The MQSSMs outperformed these predictors, highlighting their efficiency in terms of resource demand and public accessibility. Another significant achievement of this study is the creation of the most comprehensive dataset of antiviral sequences to date. In general, these results suggest that MQSSMs are promissory tools to develop good alignment-based models that can be successfully applied in the screening of large datasets for new AVP discovery.

A computational approach to identifying peptide inhibitors againstWhite Spot Syndrome Virus: Targeting the virus envelope protein

The white spot syndrome virus (WSSV), a rapidly replicating and highly lethal pathogen that targets Penaeid shrimp, has emerged as one of the most widespread viruses globally due to its high virulence. With effective chemotherapeutics still unavailable, the pursuit of novel and viable strategies against WSSV remains a crucial focus in the field of shrimp farming. The envelope proteins of WSSV are essential for virus entry, serving as excellent targets for the development of antiviral therapeutics. Novel strategies in the design of inhibitory peptides, especially those targeting envelope protein (VP28) located on the surface of the virus particle, play a critical role as a significant virulence factor during the early stages of inherent WSSV infection in shrimp. In this direction, the current computational study focused on identifying self-inhibitory peptides from the hydrophobic membrane regions of the VP28 protein, employing peptide docking and molecular dynamics simulation (MDS) approaches. Such inhibitory peptides could be useful building blocks for the rational engineering of inhibitory therapeutics since they imitate the mechanism of binding to homologous partners used by their origin domain to interact with other molecules. The N-terminal sequence of VP28 has been reported as the potential site for membrane interactions during the virus entry. Moreover, drug delivery systems mediated by chitosan and gold nanoparticles are being developed to enhance the therapeutic efficacy of anti-viral peptides. These systems can increase the solubility, stability, and selectivity of peptides, possessing better qualities than conventional delivery methods. This computational study on self-inhibitory peptides could be a valuable resource for further in vitro and in vivo studies on anti-viral therapeutics in the aquaculture industry.

Discovery of potential antidiabetic peptides using deep learning

Antidiabetic peptides (ADPs), peptides with potential antidiabetic activity, hold significant importance in the treatment and control of diabetes. Despite their therapeutic potential, the discovery and prediction of ADPs remain challenging due to limited data, the complex nature of peptide functions, and the expensive and time-consuming nature of traditional wet lab experiments. This study aims to address these challenges by exploring methods for the discovery and prediction of ADPs using advanced deep learning techniques. Specifically, we developed two models: a single-channel CNN and a three-channel neural network (CNN + RNN + Bi-LSTM). ADPs were primarily gathered from the BioDADPep database, alongside thousands of non-ADPs sourced from anticancer, antibacterial, and antiviral peptide datasets. Subsequently, data preprocessing was performed with the evolutionary scale model (ESM-2), followed by model training and evaluation through 10-fold cross-validation. Furthermore, this work collected a series of newly published ADPs as an independent test set through literature review, and found that the CNN model achieved the highest accuracy (90.48 %) in predicting the independent test set, surpassing existing ADP prediction tools. Finally, the application of the model was considered. SeqGAN was used to generate new candidate ADPs, followed by screening with the constructed CNN model. Selected peptides were then evaluated using physicochemical property prediction and structural forecasts for pharmaceutical potential. In summary, this study not only established robust ADP prediction models but also employed these models to screen a batch of potential ADPs, addressing a critical need in the field of peptide-based antidiabetic research.

In silico screening and evaluation of antiviral peptides as inhibitors against ORF9b protein of SARS-CoV-2.

The online version contains supplementary material available at 10.1007/s13205-024-04032-4.

Structure-Guided Antiviral Peptides Identification Targeting the HIV-1 Integrase.

HIV-1 integrase (IN), a major protein in the HIV life cycle responsible for integrating viral cDNA into the host DNA, represents a promising drug target. Small peptides have emerged as antiviral therapeutics for HIV because of their facile synthesis, highly selective nature, and fewer side effects. However, selecting the best candidates from a vast pool of peptides is a daunting task. In this study, multistep virtual screening was employed to identify potential peptides from a list of 280 HIV inhibitory peptides. Initially, 80 peptides were selected based on their minimum inhibitory concentrations (MIC). Then, molecular docking was performed to evaluate their binding scores compared to HIP000 and HIP00N which are experimentally validated HIV-1 integrase binding peptides that were used as a positive and negative control, respectively. The top-scoring docked complexes, namely, IN-HIP1113, IN-HIP1140, IN-HIP1142, IN-HIP678, IN-HIP776, and IN-HIP777, were subjected to initial 500 ns molecular dynamics (MD) simulations. Subsequently, HIP776, HIP777, and HIP1142 were selected for an in-depth mechanistic study of peptide interactions, with multiple simulations conducted for each complex spanning one microsecond. Independent simulations of the peptides, along with comparisons to the bound state, were performed to elucidate the conformational dynamics of the peptides. These peptides exhibit strong interactions with specific residues, as revealed by snapshot interaction analysis. Notably, LYS159, LYS156, VAL150, and GLU69 residues are prominently involved in these interactions. Additionally, residue-based binding free energy (BFE) calculations highlight the significance of HIS67, GLN148, GLN146, and SER147 residues within the binding pocket. Furthermore, the structure-activity relationship (SAR) analysis demonstrated that aromatic amino acids and the overall volume of peptides are the two major contributors to the docking scores. The best peptides will be validated experimentally by incorporating SAR properties, aiming to develop them as therapeutic agents and structural models for future peptide-based HIV-1 drug design, addressing the urgent need for effective HIV treatments.

A Biochemical and Biophysical Analysis of the Interaction of nsp9 with nsp12 from SARS-CoV-2-Implications for Future Drug Discovery Efforts.

The ongoing global pandemic of the coronavirus 2019 (COVID-19) disease is caused by the virus SARS-CoV-2, with very few highly effective antiviral treatments currently available. The machinery responsible for the replication and transcription of viral RNA during infection is made up of several important proteins. Two of these are nsp12, the catalytic subunit of the viral polymerase, and nsp9, a cofactor of nsp12 involved in the capping and priming of viral RNA. While several recent studies have determined the structural details of the interaction of nsp9 with nsp12 in the context of RNA capping, very few biochemical or biophysical details are currently available. In this study, we have used a combination of surface plasmon resonance (SPR) experiments, size exclusion chromatography (SEC) experiments, and biochemical assays to identify specific nsp9 residues that are critical for nsp12 binding as well as RNAylation, both of which are essential for the RNA capping process. Our data indicate that nsp9 dimerization is unlikely to play a significant functional role in the virus. We confirm that a set of recently discovered antiviral peptides inhibit nsp9-nsp12 interaction by specifically binding to nsp9; however, we find that these peptides do not impact RNAylation. In summary, our results have important implications for future drug discovery efforts to combat SARS-CoV-2 and any newly emerging coronaviruses.

The antiherpetic and anti-inflammatory activity of the frog-derived peptide Hylin-a1.

The high incidence of virus-related infections and the large diffusion of drug-resistant pathogens stimulate the search and identification of new antiviral agents with a broad spectrum of action. Antivirals can be designed to act on a single target by interfering with a specific step in the viral lifecycle. On the contrary, antiviral peptides (AVPs) are known for acting on a wide range of viruses, with a diversified mechanism of action targeting virus and/or host cell. In the present study, we evaluated the antiviral potential of the peptide Hylin-a1 secreted by the frog Hypsiobas albopunctatus against members of the Herpesviridae family. The inhibitory capacity of the peptide was evaluated in vitro by plaque assays in order to understand the possible mechanism of action. The results were also confirmed by real-time PCR and Western blot evaluating the expression of viral genes. Hylin-a1 acts to block the herpetic infection interfering at the early stages of both herpes simplex virus type 1 (HSV-1) and type 2 infection. Its mechanism is mainly directed on the membrane, probably by damaging the viral envelope. The same effect was also observed against HSV-1 strains resistant to acyclovir. The data presented in this study, such as the increased activity of the peptide when combined to acyclovir, a weak hemolytic profile, an anti-inflammatory effect, and a tolerable half-life in serum, indicates Hylin-a1 as a novel antiherpetic molecule with promising potential in the clinical setting.

Nanobody peptide conjugate: a novel CD163 based broad neutralizing strategy against porcine reproductive and respiratory syndrome virus

BackgroundPorcine reproductive and respiratory syndrome virus (PRRSV) is a prevalent swine pathogen, which has caused adverse impact on the global swine industry for almost 30 years. However, due to the immune suppression caused by the virus and the genetic diversity in PRRSV, no virus-targeting broad neutralizing strategy has been successfully developed yet. Antiviral peptide and nanobody have attracted extensive attention with the ease in production and the efficacy in practice. In this study, four new fusion proteins named nanobody peptide conjugates (NPCs) were developed by combining PRRSV specific non-neutralizing nanobodies with CD163-derived peptides targeting the receptor binding domain (RBD) of PRRSV proteins.ResultsFour NPCs were successfully constructed using two nanobodies against PRRSV N and nsp9 individually, recombining with two antiviral peptides 4H7 or 8H2 from porcine CD163 respectively. All four NPCs demonstrated specific capability of binding to PRRSV and broad inhibitory effect against various lineages of PRRSV in a dose-dependent manner. NPCs interfere with the binding of the RBD of PRRSV proteins to CD163 in the PRRSV pre-attachment stage by CD163 epitope peptides in the assistance of Nb components. NPCs also suppress viral replication during the stage of post-attachment, and the inhibitory effects depend on the antiviral functions of Nb parts in NPCs, including the interference in long viral RNA synthesis, NF-κB and IFN-β activation. Moreover, an interaction was predicted between aa K31 and T32 sites of neutralizing domain 4H7 of NPC-N/nsp9-4H7 and the motif 171NLRLTG176 of PRRSV GP2a. The motif 28SSS30 of neutralizing domain 8H2 of NPC-N/nsp9-8H2 could also form hydrogens to bind with the motif 152NAFLP156 of PRRSV GP3. The study provides valuable insights into the structural characteristics and potential functional implications of the RBD of PRRSV proteins. Finally, as indicated in a mouse model, NPC intranasally inoculated in vivo for 12–24 h sustains the significant neutralizing activity against PRRSV. These findings inspire the potential of NPC as a preventive measure to reduce the transmission risk in the host population against respiratory infectious agents like PRRSV.ConclusionThe aim of the current study was to develop a peptide based bioactive compound to neutralize various PRRSV strains. The new antiviral NPC (nanobody peptide conjugate) consists of a specific nanobody targeting the viral protein and a neutralizing CD163 epitope peptide for virus blocking and provides significant antiviral activity. The study will greatly promote the antiviral drug R&D against PRRSV and enlighten a new strategy against other viral diseases.Graphical abstract image

Scyllatoxin-based peptide design for E. coli expression and HIV gp120 binding

Targeting the hydrophobic Phe43 pocket of HIV's envelope glycoprotein gp120 is a critical strategy for antiviral interventions due to its role in interacting with the host cell's CD4. Previous inhibitors, including small molecules and CD4 mimetic peptides based on scyllatoxin, have demonstrated significant binding and neutralization capabilities but were often chemically synthesized or contained non-canonical amino acids. Microbial expression using natural amino acids offers advantages such as cost-effectiveness, scalability, and efficient production of fusion proteins. In this study, we enhanced the previous scyllatoxin-based synthetic peptide by substituting natural amino acids and successfully expressed it in E. coli. The peptide was optimized by mutating the C-terminal amidated valine to valine and glutamine, and by reducing the disulfide bonds from three to two. Circular dichroism confirmed proper secondary structure formation, and fluorescence polarization analysis revealed specific, concentration-dependent binding to HIV gp120, supported by molecular dynamics simulations. These findings indicate the potential for scalable microbial production of effective antiviral peptides, with significant applications in pharmaceutical development for HIV treatment.

Antiviral activity of temporin-1CEb analogues against gingival infection with herpes simplex virus type 1.

Oral herpes infections caused by herpes simplex virus type 1 (HSV-1) are one of the most common in the human population. Recently, they have been classified as an increasing problem in immunocompromised patients and those suffering from chronic inflammation of the oral mucosa and gums. Treatment mainly involves nucleoside analogues, such as acyclovir and its derivatives, which reduce virus replication and shedding. As drug-resistant strains of herpes emerge rapidly, there is a need for the development of novel anti-herpes agents. The aim of the study was to design an antiviral peptide, based on natural compounds, non-toxic to the host, and efficient against drug-resistant HSV-1. Here, we designed a lysine-rich derivative of amphibian temporin-1CEb conjugated to peptides penetrating the host cell membrane and examined their activity against HSV-1 infection of oral mucosa. We assessed the antiviral efficiency of the tested compound in simple 2D cell models (VeroE6 and TIGKs cells) and a 3D organotypic model of human gingiva (OTG) using titration assay, qPCR, and confocal imaging. To identify the molecular mechanism of antiviral activity, we applied the Azure A metachromatic test, and attachment assays techniques. Toxicity of the conjugates was examined using XTT and LDH assays. Our results showed that temporin-1CEb analogues significantly reduce viral replication in oral mucosa. The mechanism of peptide analogues is based on the interaction with heparan sulfate, leading to the reduce attachment of HSV-1 to the cell membrane. Moreover, temporin-1CEb conjugates effectively penetrate the gingival tissue being effective against acyclovir-resistant strains. Collectively, we showed that temporin-1CEb can be regarded as a novel, naturally derived antiviral compound for HSV-1 treatment.

Covering assisted intuitionistic fuzzy bi-selection technique for data reduction and its applications

The dimension and size of data is growing rapidly with the extensive applications of computer science and lab based engineering in daily life. Due to availability of vagueness, later uncertainty, redundancy, irrelevancy, and noise, which imposes concerns in building effective learning models. Fuzzy rough set and its extensions have been applied to deal with these issues by various data reduction approaches. However, construction of a model that can cope with all these issues simultaneously is always a challenging task. None of the studies till date has addressed all these issues simultaneously. This paper investigates a method based on the notions of intuitionistic fuzzy (IF) and rough sets to avoid these obstacles simultaneously by putting forward an interesting data reduction technique. To accomplish this task, firstly, a novel IF similarity relation is addressed. Secondly, we establish an IF rough set model on the basis of this similarity relation. Thirdly, an IF granular structure is presented by using the established similarity relation and the lower approximation. Next, the mathematical theorems are used to validate the proposed notions. Then, the importance-degree of the IF granules is employed for redundant size elimination. Further, significance-degree-preserved dimensionality reduction is discussed. Hence, simultaneous instance and feature selection for large volume of high-dimensional datasets can be performed to eliminate redundancy and irrelevancy in both dimension and size, where vagueness and later uncertainty are handled with rough and IF sets respectively, whilst noise is tackled with IF granular structure. Thereafter, a comprehensive experiment is carried out over the benchmark datasets to demonstrate the effectiveness of simultaneous feature and data point selection methods. Finally, our proposed methodology aided framework is discussed to enhance the regression performance for IC50 of Antiviral Peptides.

The antimicrobial peptide Sparamosin26–54 exhibits antiviral activity against three aquatic enveloped viruses through lipid-binding-mediated virus lysis

The aquaculture industry is faced with huge economic losses caused by various enveloped virus infections, such as white spot syndrome virus (WSSV), Rana grylio virus (RGV), and Anguillid Herpesvirus 1 (AngHV). The urgent need for readily available broad-spectrum antiviral agents has led to the exploration of antiviral peptides (AVPs), among which antimicrobial peptides (AMPs) with antiviral activity have attracted increasing attention. Sparamosin26–54 (derived from Scylla paramamosain) is a promising antimicrobial agent. In this study, we found that Sparamosin26–54 significantly inhibited WSSV transcription and replication (as indicated by VP28 gene and protein levels), irreversibly inactivated virions, and impeded viral entry before binding to the cell. Transmission electron microscopy observations showed that Sparamosin26–54 had a direct destructive effect on WSSV virions. Lipidomic analysis and ELISA assay highlighted that Sparamosin26–54 had a potent affinity for phosphatidic acid (PA) and phosphatidylserine (PS) of WSSV. Liposome leakage assays further revealed a pronounced effect of Sparamosin26–54 on membrane lipid compositions, emphasizing its efficacy against the other two enveloped viruses (RGV and AngHV), but not against the non-enveloped virus, American eel adomavirus (AEAdov). Notably, in three animal models of viral infection, Sparamosin26–54 reduced viral loads in tissues, increased survival, or decreased infection rates in a concentration-dependent manner. Importantly, Sparamosin26–54 showed no animal toxicity under different modes of administration and could maintain antiviral activity in the complex aquatic environment. Taken together, Sparamosin26–54 was proved to be effective against three enveloped viruses, possibly inducing viral lysis via lipid-binding, providing an alternative approach for combating enveloped virus infections.

TP-LMMSG: a peptide prediction graph neural network incorporating flexible amino acid property representation.

Bioactive peptide therapeutics has been a long-standing research topic. Notably, the antimicrobial peptides (AMPs) have been extensively studied for its therapeutic potential. Meanwhile, the demand for annotating other therapeutic peptides, such as antiviral peptides (AVPs) and anticancer peptides (ACPs), also witnessed an increase in recent years. However, we conceive that the structure of peptide chains and the intrinsic information between the amino acids is not fully investigated among the existing protocols. Therefore, we develop a new graph deep learning model, namely TP-LMMSG, which offers lightweight and easy-to-deploy advantages while improving the annotation performance in a generalizable manner. The results indicate that our model can accurately predict the properties of different peptides. The model surpasses the other state-of-the-art models on AMP, AVP and ACP prediction across multiple experimental validated datasets. Moreover, TP-LMMSG also addresses the challenges of time-consuming pre-processing in graph neural network frameworks. With its flexibility in integrating heterogeneous peptide features, our model can provide substantial impacts on the screening and discovery of therapeutic peptides. The source code is available at https://github.com/NanjunChen37/TP_LMMSG.

DeepAVP-TPPred: identification of antiviral peptides using transformed image-based localized descriptors and binary tree growth algorithm.

Despite the extensive manufacturing of antiviral drugs and vaccination, viral infections continue to be a major human ailment. Antiviral peptides (AVPs) have emerged as potential candidates in the pursuit of novel antiviral drugs. These peptides show vigorous antiviral activity against a diverse range of viruses by targeting different phases of the viral life cycle. Therefore, the accurate prediction of AVPs is an essential yet challenging task. Lately, many machine learning-based approaches have developed for this purpose; however, their limited capabilities in terms of feature engineering, accuracy, and generalization make these methods restricted. In the present study, we aim to develop an efficient machine learning-based approach for the identification of AVPs, referred to as DeepAVP-TPPred, to address the aforementioned problems. First, we extract two new transformed feature sets using our designed image-based feature extraction algorithms and integrate them with an evolutionary information-based feature. Next, these feature sets were optimized using a novel feature selection approach called binary tree growth Algorithm. Finally, the optimal feature space from the training dataset was fed to the deep neural network to build the final classification model. The proposed model DeepAVP-TPPred was tested using stringent 5-fold cross-validation and two independent dataset testing methods, which achieved the maximum performance and showed enhanced efficiency over existing predictors in terms of both accuracy and generalization capabilities. https://github.com/MateeullahKhan/DeepAVP-TPPred.

A Rationally Designed Synthetic Antiviral Peptide Binder Targeting the Receptor-Binding Domain of SARS-CoV-2.

The severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), a novel coronavirus, is the causative agent responsible for the spread of the COVID19 pandemic across the globe. The global impact of the COVID19 pandemic, the successful approval of vaccines for controlling the pandemic, and the further resurgence of COVID19 necessitate the exploration and validation of alternative therapeutic avenues targeting SARS-CoV-2. The initial entry and further invasion by SARS-CoV-2 require strong protein-protein interactions (PPIs) between the receptor-binding domain (RBD) of the SARS-CoV-2 spike protein and the human angiotensin-converting enzyme 2 (ACE2) receptors expressed on the cell surfaces of various tissues. In principle, disruption of the PPIs between the RBD of SARS-CoV-2 and the ACE2 receptor by designer peptides with optimized pharmacology appears to be an ideal choice for potentially preventing viral entry with minimal immunogenicity. In this context, the current study describes a short, synthetic designer peptide (codenamed SR16, ≤18 aa, molecular weight ≤2.5 kDa), which has a few noncoded amino acids, demonstrates a helical conformation in solution, and also engages the RBD of SARS-CoV-2 through a high-affinity interaction, as judged from a battery of biophysical studies. Further, the designer peptide demonstrates resistance to trypsin degradation, appears to be nontoxic to mammalian cells, and also does not induce hemolysis in freshly isolated human erythrocytes. In summary, SR16 appears to be an ideal peptide binder targeting the RBD of SARS-CoV-2, which has the potential for further optimization and development as an antiviral agent targeting SARS-CoV-2.