Phage Virions Research Articles

PredPVP: A Stacking Model for Predicting Phage Virion Proteins Based on Feature Selection Methods

Background: Phage therapy has a broad application prospect as a novel therapeutic method, and Phage Virion Proteins (PVP) can recognize the host and bind to surface receptors, which is of great significance for the development of antimicrobial drugs for the treatment of infectious diseases caused by bacteria. In recent years, several PVP predictors based on machine learning have been developed, which usually use a single feature to train the learner. In contrast, higher dimensional feature representations tend to contain more potential sequence information. Methods: In this work, we construct a stacking model PredPVP for PVP prediction by combining multiple features and using feature selection methods. Specifically, the sequence is first encoded using seven features. For this high-dimensional feature representation, three feature selection methods wereutilized to remove redundant features, then integrated with eight machine learning algorithms. Finally, probability features and class features (PCFs) generated by 24 base models were put into logistic regression (LR) to train the model. Results: The results of the independent test set indicate that PredPVP has higher performance compared to other existing predictors, with an AUC of 93.4%. Conclusion: We expect PredPVP to be used as a tool for large-scale PVP recognition, providing a new way for the development of novel antimicrobials and accelerating its application in actual treatment. The datasets and source codes used in this study are available at https://github.com/caoqian23/PredPVP.

PhageScanner: a reconfigurable machine learning framework for bacteriophage genomic and metagenomic feature annotation.

Bacteriophages are the most prolific organisms on Earth, yet many of their genomes and assemblies from metagenomic sources lack protein sequences with identified functions. While most bacteriophage proteins are structural proteins, categorized as Phage Virion Proteins (PVPs), a considerable number remain unclassified. Complicating matters further, traditional lab-based methods for PVP identification can be tedious. To expedite the process of identifying PVPs, machine-learning models are increasingly being employed. Existing tools have developed models for predicting PVPs from protein sequences as input. However, none of these efforts have built software allowing for both genomic and metagenomic data as input. In addition, there is currently no framework available for easily curating data and creating new types of machine learning models. In response, we introduce PhageScanner, an open-source platform that streamlines data collection for genomic and metagenomic datasets, model training and testing, and includes a prediction pipeline for annotating genomic and metagenomic data. PhageScanner also features a graphical user interface (GUI) for visualizing annotations on genomic and metagenomic data. We further introduce a BLAST-based classifier that outperforms ML-based models and an efficient Long Short-Term Memory (LSTM) classifier. We then showcase the capabilities of PhageScanner by predicting PVPs in six previously uncharacterized bacteriophage genomes. In addition, we create a new model that predicts phage-encoded toxins within bacteriophage genomes, thus displaying the utility of the framework.

A large-scale type I CBASS antiphage screen identifies the phage prohead protease as a key determinant of immune activation and evasion

Cyclic oligonucleotide-based signaling system (CBASS) is an antiviral system that protects bacteria from phage infection and is evolutionarily related to human cGAS-STING immunity. cGAS-STING signaling is initiated by the recognition of viral DNA, but the molecular cues activating CBASS are incompletely understood. Using a screen of 975 type I CBASS operon-phage challenges, we show that operons with distinct cGAS/DncV-like nucleotidyltransferases (CD-NTases) and CD-NTase-associated protein (Cap) effectors exhibit marked patterns of phage restriction. We find that some type I CD-NTase enzymes require a C-terminal AGS-C immunoglobulin (Ig)-like fold domain for defense against select phages. Escaper phages evade CBASS via protein-coding mutations in virion assembly proteins, and acquired resistance is largely operon specific. We demonstrate that the phage Bas13 prohead protease interacts with the CD-NTase EcCdnD12 and can induce CBASS-dependent growth arrest in cells. Our results define phage virion assembly as a determinant of type I CBASS immune evasion and support viral protein recognition as a putative mechanism of cGAS-like enzyme activation.

Isolation, Characterization, and Complete Genome Sequence of Escherichia Phage KIT06 Which Infects Nalidixic Acid-Resistant Escherichia coli.

Escherichia coli (E. coli) is one of the most common sources of infection in humans and animals. The emergence of E. coli which acquires resistance to various antibiotics has made treatment difficult. Bacteriophages can be considered promising agents to expand the options for the treatment of antibiotic-resistant bacteria. This study describes the isolation and characterization of Escherichia phage KIT06, which can infect E. coli resistant to the quinolone antibiotic nalidixic acid. Phage virions possess an icosahedral head that is 93 ± 8 nm in diameter and a contractile tail (116 ± 12 nm × 13 ± 5 nm). The phage was found to be stable under various thermal and pH conditions. A one-step growth curve showed that the latent time of the phage was 20 min, with a burst size of 28 particles per infected cell. Phage KIT06 infected 7 of 12 E. coli strains. It inhibited the growth of the host bacterium and nalidixic acid-resistant E. coli. The lipopolysaccharide and outer membrane proteins of E. coli, tsx and btuB, are phage receptors. Phage KIT06 is a new species of the genus Tequatrovirus with a genome of 167,059 bp consisting of 264 open reading frames (ORFs) that encode gene products related to morphogenesis, replication, regulation, and host lysis. The lack of genes encoding integrase or excisionase indicated that this phage was lytic. Thus, KIT06 could potentially be used to treat antibiotic-resistant E. coli using phage therapy. However, further studies are essential to understand its use in combination with other antimicrobial agents and its safe use in such applications.

Microfluidic Ecology Unravels the Genetic and Ecological Drivers of T4r Bacteriophage Resistance in E. coli: Insights into Biofilm-Mediated Evolution.

We use a microfluidic ecology which generates non-uniform phage concentration gradients and micro-ecological niches to reveal the importance of time, spatial population structure and collective population dynamics in the de novo evolution of T4r bacteriophage resistant motile E. coli. An insensitive bacterial population against T4r phage occurs within 20 hours in small interconnected population niches created by a gradient of phage virions, driven by evolution in transient biofilm patches. Sequencing of the resistant bacteria reveals mutations at the receptor site of bacteriophage T4r as expected but also in genes associated with biofilm formation and surface adhesion, supporting the hypothesis that evolution within transient biofilms drives de novo phage resistance.

An autonomous plasmid as an inovirus phage satellite.

Bacterial viruses (phages) are potent agents of lateral gene transfer and thus are important drivers of evolution. A group of mobile genetic elements, referred to as phage satellites, exploits phages to disseminate their own genetic material. Here, we isolated a novel member of the family Inoviridae, Shewanella phage Dolos, along with an autonomously replicating plasmid, pDolos. Dolos causes a chronic infection in its host Shewanella oneidensis by phage production with only minor effects on the host cell proliferation. When present, plasmid pDolos hijacks Dolos functions to be predominantly packaged into phage virions and released into the environment and, thus, acts as a phage satellite. pDolos can disseminate further genetic material encoding, e.g., resistances or fluorophores to host cells sensitive to Dolos infection. Given the rather simple requirements of a plasmid for takeover of an inovirus and the wide distribution of phages of this group, we speculate that similar phage-satellite systems are common among bacteria.IMPORTANCEPhage satellites are mobile genetic elements, which hijack phages to be transferred to other host cells. The vast majority of these phage satellites integrate within the host's chromosome, and they all carry remaining phage genes. Here, we identified a novel phage satellite, pDolos, which uses an inovirus for dissemination. pDolos (i) remains as an autonomously replicating plasmid within its host, (ii) does not carry recognizable phage genes, and (iii) is smaller than any other phage satellites identified so far. Thus, pDolos is the first member of a new class of phage satellites, which resemble natural versions of phagemids.

Bacillus phage phi18-2 is a novel temperate virus with an unintegrated genome present in the cytoplasm of lysogenic cells as a linear phage-plasmid.

Bacillus subtilis is a Gram-positive bacterium that is widely used in fermentation and in the pharmaceutical industry. Phage contamination occasionally occurs in various fermentation processes and causes significant economic loss. Here, we report the isolation and characterization of a temperate B. subtilis phage, termed phi18-2, from spore powder manufactured in a fermentation plant. Transmission electron microscopy showed that phi18-2 has a symmetrical polyhedral head and a long noncontractile tail. Receptor analysis showed that phi18-2 recognizes wall teichoic acid (WTA) for infection. The phage virions have a linear double-stranded DNA genome of 64,467 bp with identical direct repeat sequences of 309 bp at each end of the genome. In lysogenic cells, the phage genome was found to be present in the cytoplasm without integration into the host cell chromosome, and possibly as a linear phage-plasmid with unmodified ends. Our data may provide some insight into the molecular basis of the unique lysogenic cycle of phage phi18-2.

Biologic and genomic characterization of a novel virulent Aeromonas hydrophila phage phiA051, with high homology to prophages.

Aeromonas hydrophila is particularly harmful to freshwater aquaculture, and the search for phage is an effective biological control method, but reports of possible temperate phages and their mutants are rare in this field. In this study, a virulent phage highly homologous to prophage in the genomes of A. hydrophila was collected and preliminary biological characterization was carried out to understand its nature. Water samples taken from eel ponds in Fujian, China were combined with the strain. Spot test method and double-layer agar plate assay was used for confirmation and purification. Phage virions were observed using transmission electron microscope. A total of 68 strains of Aeromonas spp. were used to determine the host range. MOI groups of 1,000, 100, 10, 1, 0.1, 0.01, 0.001, 0.0001, 0.00001 were prepared to detect the optimal MOI. The conditions of thermal stability assay were set as 30, 40, 50, 60, 70 and 80°C for 1 h, respectively, and conditions of acid and alkali stability assay were set as 2.0, 4.0, 6.0, 8.0, 10.0 and 12.0 of pH. MOI of 0.01 and 0.1, respectively, are set to determine the inhibitory capacity of phage. A novel virulent A. hydrophila phage designated phiA051 has been isolated from aquaculture water. Electron microscopic observation showed that the phage phiA051 was composed of an icosahedral capsid. The phage phiA051 possesses an optimal multiplicity of infection (MOI) of 0.01, and its burst size was 108 PFU/cell. The phage maintained a high viability at temperatures of 30-50°C or pH 6.0-10.0 for 1 h. Phage phiA051 has certain potentials in rapidly inhibiting the spread of pathogen early in the outbreak, and it has a linear dsDNA with GC content of 60.55% and a total length of 32,212 bp, including 46 ORFs. The phage phiA051 behaved as a virulent phage. However, the BLASTN result showed that 23 of the top 25 hits were genomes of Aeromonas strains. It was suggested that phiA051 was probably derived from some prophage in the chromosome of Aeromonas. Further investigation of the mechanism how phage phiA051 transforms from a temperate phage to a virulent phage will provide a unique perspective and idea to explore the potential of prophages.

Visualization of Engineered M13 Phages Bound to Bacterial Targets by Transmission Electron Microscopy.

The filamentous phage M13 is one of the most well-studied and characterized phages, particularly since it was introduced as a scaffold for phage display, a technique to express and evolve fusion proteins on the M13 phage's coat to study protein or peptide binding interactions. Since phages can be engineered or evolved to specifically bind to a variety of targets, engineered M13 phages have been explored for applications such as drug delivery, biosensing, and cancer therapy, among others. Specifically, with the rising challenge of antimicrobial resistance among bacteria, chimeric M13 phages have been explored both as detection and therapeutic agents due to the flexibility in tuning target specificity. Transmission electron microscopy (TEM) is a powerful tool enabling researchers to directly visualize and characterize binding of phages to bacterial surfaces. However, the filamentous phage structure poses a challenge for this technique, as the phages have similar morphology to bacterial structures such as pili. In order to differentiate between bacterial structures and the filamentous phages, here we describe a protocol to prepare TEM samples of engineered M13 phages bound to bacterial cells, in which the phage virions have been specifically labeled by decoration of the major capsid proteins with gold nanoparticles. This protocol enables clear visualization and unambiguous identification of attached filamentous phages within the context of bacterial cells expressing numerous pili.

Integrating Low-Order and High-Order Correlation Information for Identifying Phage Virion Proteins.

Phage virion proteins (PVPs) play an important role in the host cell. Fast and accurate identification of PVPs is beneficial for the discovery and development of related drugs. Although wet experimental approaches are the first choice to identify PVPs, they are costly and time-consuming. Thus, researchers have turned their attention to computational models, which can speed up related studies. Therefore, we proposed a novel machine-learning model to identify PVPs in the current study. First, 50 different types of physicochemical properties were used to denote protein sequences. Next, two different approaches, including Pearson's correlation coefficient (PCC) and maximal information coefficient (MIC), were employed to extract discriminative information. Further, to capture the high-order correlation information, we used PCC and MIC once again. After that, we adopted the least absolute shrinkage and selection operator algorithm to select the optimal feature subset. Finally, these chosen features were fed into a support vector machine to discriminate PVPs from phage non-virion proteins. We performed experiments on two different datasets to validate the effectiveness of our proposed method. Experimental results showed a significant improvement in performance compared with state-of-the-art approaches. It indicates that the proposed computational model may become a powerful predictor in identifying PVPs.

Evolution of the T4 phage virion is driven by selection pressure from non-bacterial factors.

Bacteriophages colonize animal and human bodies, propagating on sensitive bacteria that are symbionts, commensals, or pathogens of animals and humans. T4-like phages are dependent on abundant symbionts such as Escherichia coli, commonly present in animal and human gastrointestinal (GI) tracts. Bacteriophage T4 is one of the most complex viruses, and its intricate structure, particularly the capsid head protecting the phage genome, likely contributes substantially to the overall phage fitness in diverse environments. We investigated how individual head proteins-gp24, Hoc, and Soc-affect T4 phage survival under pressure from non-bacterial factors. We constructed a panel of T4 phage variants defective in these structural proteins: T4∆Soc, T4∆24byp24, T4∆Hoc∆Soc, T4∆Hoc∆24byp24, T4∆Soc∆24byp24, and T4∆Hoc∆Soc∆24byp24 (byp = bypass). These variants were investigated for their sensitivity to selected environmental conditions relevant to the microenvironment of the GI tract, including pH, temperature, and digestive enzymes. The simple and "primitive" structure of the phage capsid (∆24byp24) was significantly less stable at low pH and more sensitive to inactivation by digestive enzymes, and the simultaneous lack of gp24 and Soc resulted in a notable decrease in phage activity at 37°C. Gp24 was also found to be highly resistant to thermal and chemical denaturation. Thus, gp24, which was acquired relatively late in evolution, seems to play a key role in T4 withstanding environmental conditions, including those related to the animal/human GI tract, and Soc is a molecular glue that enhances this protective effect. IMPORTANCE Bacteriophages are important components of animal and human microbiota, particularly in the gastrointestinal tract, where they dominate the viral community and contribute to shaping microbial balance. However, interactions with bacterial hosts are not the only element of the equation in phage survival-phages inhabiting the GI tract are constantly exposed to increased temperature, pH fluctuations, or digestive enzymes, which raises the question of whether and how the complex structure of phage capsids contributes to their persistence in the specific microenvironment of human/animal bodies. Here we address this phage-centric perspective, identifying the role of individual head proteins in T4 phage survival in GI tract conditions. The selection pressure driving the evolution of T4-like phages could have come from the external environment that affects phage virions with increased temperature and variable pH; it is possible that in the local microenvironment along the GI tract, the phage benefits from stability-protecting proteins.

Phage-microbe dynamics after sterile faecal filtrate transplantation in individuals with metabolic syndrome: a double-blind, randomised, placebo-controlled clinical trial assessing efficacy and safety

Bacteriophages (phages) are bacterial viruses that have been shown to shape microbial communities. Previous studies have shown that faecal virome transplantation can decrease weight gain and normalize blood glucose tolerance in diet-induced obese mice. Therefore, we performed a double-blind, randomised, placebo-controlled pilot study in which 24 individuals with metabolic syndrome were randomised to a faecal filtrate transplantation (FFT) from a lean healthy donor (n = 12) or placebo (n = 12). The primary outcome, change in glucose metabolism, and secondary outcomes, safety and longitudinal changes within the intestinal bacteriome and phageome, were assessed from baseline up to 28 days. All 24 included subjects completed the study and are included in the analyses. While the overall changes in glucose metabolism are not significantly different between both groups, the FFT is well-tolerated and without any serious adverse events. The phage virion composition is significantly altered two days after FFT as compared to placebo, which coincides with more virulent phage-microbe interactions. In conclusion, we provide evidence that gut phages can be safely administered to transiently alter the gut microbiota of recipients.

Replication cycle timing determines phage sensitivity to a cytidine deaminase toxin/antitoxin bacterial defense system.

Toxin-antitoxin (TA) systems are ubiquitous two-gene loci that bacteria use to regulate cellular processes such as phage defense. Here, we demonstrate the mechanism by which a novel type III TA system, avcID, is activated and confers resistance to phage infection. The toxin of the system (AvcD) is a deoxycytidylate deaminase that converts deoxycytidines (dC) to dexoyuridines (dU), while the RNA antitoxin (AvcI) inhibits AvcD activity. We have shown that AvcD deaminated dC nucleotides upon phage infection, but the molecular mechanism that activated AvcD was unknown. Here we show that the activation of AvcD arises from phage-induced inhibition of host transcription, leading to degradation of the labile AvcI. AvcD activation and nucleotide depletion not only decreases phage replication but also increases the formation of defective phage virions. Surprisingly, infection of phages such as T7 that are not inhibited by AvcID also lead to AvcI RNA antitoxin degradation and AvcD activation, suggesting that depletion of AvcI is not sufficient to confer protection against some phage. Rather, our results support that phage with a longer replication cycle like T5 are sensitive to AvcID-mediated protection while those with a shorter replication cycle like T7 are resistant.

Cell Free Bacteriophage Synthesis from Engineered Strains Improves Yield.

Phage therapy to treat life-threatening drug-resistant infections has been hampered by technical challenges in phage production. Cell-free bacteriophage synthesis (CFBS) can overcome the limitations of standard phage production methods by manufacturing phage virions in vitro. CFBS mimics intracellular phage assembly using transcription/translation machinery (TXTL) harvested from bacterial lysates and combined with reagents to synthesize proteins encoded by a phage genomic DNA template. These systems may enable rapid phage production and engineering to accelerate phages from bench-to-bedside. TXTL harvested from wild type or commonly used bacterial strains was not optimized for bacteriophage production. Here, we demonstrate that TXTL from genetically modified E. coli BL21 can be used to enhance phage T7 yields in vitro by CFBS. Expression of 18 E. coli BL21 genes was manipulated by inducible CRISPR interference (CRISPRi) mediated by nuclease deficient Cas12a from F. novicida (dFnCas12a) to identify genes implicated in T7 propagation as positive or negative effectors. Genes shown to have a significant effect were overexpressed (positive effectors) or repressed (negative effectors) to modify the genetic background of TXTL harvested for CFBS. Phage T7 CFBS yields were improved by up to 10-fold in vitro through overexpression of translation initiation factor IF-3 (infC) and small RNAs OxyS and CyaR and by repression of RecC subunit exonuclease RecBCD. Continued improvement of CFBS will mitigate phage manufacturing bottlenecks and lower hurdles to widespread adoption of phage therapy.

Determination of the Dissociation Constant for Polyvalent Receptors Using ELISA: A Case of M13 Phages Displaying Troponin T-Specific Peptides.

Phage-derived affinity peptides have become widespread thanks to their easy selection via phage display. Interactions between a target protein and its specific peptide are similar to those between antibodies and antigens. The strength of these non-covalent complexes may be described by the dissociation constant (Kd). In this paper, protein-specific peptides are exposed on the pIII protein present in the M13 bacteriophage virion with up to five copies. Therefore, one phage particle can bind from one to five ligands. Here, we discuss the dependences between phage-displayed peptides and their ligands in solution using a model system based on troponin T (TnT) binding phages. Moreover, a method of calculating Kd values from ELISA experiments was developed and is presented. The determined Kd values are in the picomolar range.

PhaVIP: Phage VIrion Protein classification based on chaos game representation and Vision Transformer.

As viruses that mainly infect bacteria, phages are key players across a wide range of ecosystems. Analyzing phage proteins is indispensable for understanding phages' functions and roles in microbiomes. High-throughput sequencing enables us to obtain phages in different microbiomes with low cost. However, compared to the fast accumulation of newly identified phages, phage protein classification remains difficult. In particular, a fundamental need is to annotate virion proteins, the structural proteins, such as major tail, baseplate, etc. Although there are experimental methods for virion protein identification, they are too expensive or time-consuming, leaving a large number of proteins unclassified. Thus, there is a great demand to develop a computational method for fast and accurate phage virion protein (PVP) classification. In this work, we adapted the state-of-the-art image classification model, Vision Transformer, to conduct virion protein classification. By encoding protein sequences into unique images using chaos game representation, we can leverage Vision Transformer to learn both local and global features from sequence "images". Our method, PhaVIP, has two main functions: classifying PVP and non-PVP sequences and annotating the types of PVP, such as capsid and tail. We tested PhaVIP on several datasets with increasing difficulty and benchmarked it against alternative tools. The experimental results show that PhaVIP has superior performance. After validating the performance of PhaVIP, we investigated two applications that can use the output of PhaVIP: phage taxonomy classification and phage host prediction. The results showed the benefit of using classified proteins over all proteins. The web server of PhaVIP is available via: https://phage.ee.cityu.edu.hk/phavip. The source code of PhaVIP is available via: https://github.com/KennthShang/PhaVIP.

Virion glycosylation influences mycobacteriophage immune recognition

Glycosylation of eukaryotic virus particles is common and influences their uptake, trafficking, and immune recognition. In contrast, glycosylation of bacteriophage particles has not been reported; phage virions typically do not enter the cytoplasm upon infection, and they do not generally inhabit eukaryotic systems. We show here that several genomically distinct phages of Mycobacteria are modified with glycans attached to the C terminus of capsid and tail tube protein subunits. These O-linked glycans influence antibody production and recognition, shielding viral particles from antibody binding and reducing production of neutralizing antibodies. Glycosylation is mediated by phage-encoded glycosyltransferases, and genomic analysis suggests that they are relatively common among mycobacteriophages. Putative glycosyltransferases are also encoded by some Gordonia and Streptomyces phages, but there is little evidence of glycosylation among the broader phage population. The immune response to glycosylated phage virions in mice suggests that glycosylation may be an advantageous property for phage therapy of Mycobacterium infections.

An Edible Biopolymeric Microcapsular Wrapping Integrating Lytic Bacteriophage Particles for Salmonella enterica: Potential for Integration into Poultry Feed.

This research work aimed at developing an edible biopolymeric microcapsular wrapping (EBMW) integrating lytic bacteriophage particles for Salmonella enterica, with potential application in poultry feed for biocontrol of that pathogen. This pathogen is known as one of the main microorganisms responsible for contamination in the food industry and in foodstuff. The current techniques for decontamination and pathogen control in the food industry can be very expensive, not very selective, and even outdated, such as the use of broad-spectrum antibiotics that end up selecting resistant bacteria. Hence, there is a need for new technologies for pathogen biocontrol. In this context, bacteriophage-based biocontrol appears as a potential alternative. As a cocktail, both phages were able to significantly reduce the bacterial load after 12 h of treatment, at either multiplicity of infection (MOI) 1 and 10, by 84.3% and 87.6%, respectively. Entrapment of the phage virions within the EBMW matrix did not exert any deleterious effect upon their lytic activity. The results obtained showed high promise for integration in poultry feed aiming at controlling Salmonella enterica, since the edible biopolymeric microcapsular wrapping integrating lytic bacteriophage particles developed was successful in maintaining lytic phage viability while fully stabilizing the phage particles.

Prediction of Phage Virion Proteins Using Machine Learning Methods

Antimicrobial resistance (AMR) is a major problem and an immediate alternative to antibiotics is the need of the hour. Research on the possible alternative products to tackle bacterial infections is ongoing worldwide. One of the most promising alternatives to antibiotics is the use of bacteriophages (phage) or phage-driven antibacterial drugs to cure bacterial infections caused by AMR bacteria. Phage-driven proteins, including holins, endolysins, and exopolysaccharides, have shown great potential in the development of antibacterial drugs. Likewise, phage virion proteins (PVPs) might also play an important role in the development of antibacterial drugs. Here, we have developed a machine learning-based prediction method to predict PVPs using phage protein sequences. We have employed well-known basic and ensemble machine learning methods with protein sequence composition features for the prediction of PVPs. We found that the gradient boosting classifier (GBC) method achieved the best accuracy of 80% on the training dataset and an accuracy of 83% on the independent dataset. The performance on the independent dataset is better than other existing methods. A user-friendly web server developed by us is freely available to all users for the prediction of PVPs from phage protein sequences. The web server might facilitate the large-scale prediction of PVPs and hypothesis-driven experimental study design.

RF_phage virion: Classification of phage virion proteins with a random forest model.

Introduction: Phages play essential roles in biological procession, and the virion proteins encoded by the phage genome constitute critical elements of the assembled phage particle. Methods: This study uses machine learning methods to classify phage virion proteins. We proposed a novel approach, RF_phage virion, for the effective classification of the virion and non-virion proteins. The model uses four protein sequence coding methods as features, and the random forest algorithm was employed to solve the classification problem. Results: The performance of the RF_phage virion model was analyzed by comparing the performance of this algorithm with that of classical machine learning methods. The proposed method achieved a specificity (Sp) of 93.37%%, sensitivity (Sn) of 90.30%, accuracy (Acc) of 91.84%, Matthews correlation coefficient (MCC) of .8371, and an F1 score of .9196.