Computational prediction of inter-species relationships through omics data analysis and machine learning

Prediction of Klebsiella phage-host specificity at the strain level

Phages are increasingly considered promising alternatives to target drug-resistant bacterial pathogens. However, their often-narrow host range can make it challenging to find matching phages against bacteria of interest. Current computational tools do not accurately predict interactions at the strain level in a way that is relevant and properly evaluated for practical use. We present PhageHostLearn, a machine learning system that predicts strain-level interactions between receptor-binding proteins and bacterial receptors for Klebsiella phage-bacteria pairs. We evaluate this system both in silico and in the laboratory, in the clinically relevant setting of finding matching phages against bacterial strains. PhageHostLearn reaches a cross-validated ROC AUC of up to 81.8% in silico and maintains this performance in laboratory validation. Our approach provides a framework for developing and evaluating phage-host prediction methods that are useful in practice, which we believe to be a meaningful contribution to the machine-learning-guided development of phage therapeutics and diagnostics.

Advances in phage-host interaction prediction: in silico method enhances the development of phage therapies

Phages can specifically recognize and kill bacteria, which lead to important application value of bacteriophage in bacterial identification and typing, livestock aquaculture and treatment of human bacterial infection. Considering the variety of human-infected bacteria and the continuous discovery of numerous pathogenic bacteria, screening suitable therapeutic phages that are capable of infecting pathogens from massive phage databases has been a principal step in phage therapy design. Experimental methods to identify phage-host interaction (PHI) are time-consuming and expensive; high-throughput computational method to predict PHI is therefore a potential substitute. Here, we systemically review bioinformatic methods for predicting PHI, introduce reference databases and in silico models applied in these methods and highlight the strengths and challenges of current tools. Finally, we discuss the application scope and future research direction of computational prediction methods, which contribute to the performance improvement of prediction models and the development of personalized phage therapy.

Antimicrobial resistance crisis: could artificial intelligence be the solution?

Antimicrobial resistance is a global public health threat, and the World Health Organization (WHO) has announced a priority list of the most threatening pathogens against which novel antibiotics need to be developed. The discovery and introduction of novel antibiotics are time-consuming and expensive. According to WHO's report of antibacterial agents in clinical development, only 18 novel antibiotics have been approved since 2014. Therefore, novel antibiotics are critically needed. Artificial intelligence (AI) has been rapidly applied to drug development since its recent technical breakthrough and has dramatically improved the efficiency of the discovery of novel antibiotics. Here, we first summarized recently marketed novel antibiotics, and antibiotic candidates in clinical development. In addition, we systematically reviewed the involvement of AI in antibacterial drug development and utilization, including small molecules, antimicrobial peptides, phage therapy, essential oils, as well as resistance mechanism prediction, and antibiotic stewardship.

Differences in the microbiome of the small intestine of Leghorn lines divergently selected for antibody titer to sheep erythrocytes suggest roles for commensals in host humoral response

For forty generations, two lines of White Leghorn chickens have been selected for high (HAS) or low (LAS) antibody response to a low dose injection of sheep red blood cells (SRBCs). Their gut is home to billons of microorganisms and the largest number of immune cells in the body; therefore, the objective of this experiment was to gain understanding of the ways the microbiome may influence the differential antibody response observed in these lines. We achieved this by characterizing the small intestinal microbiome of HAS and LAS chickens, determining their functional microbiome profiles, and by using machine learning to identify microbes which best differentiate HAS from LAS and associating the abundance of those microbes with host gene expression. Microbiome sequencing revealed greater diversity in LAS but statistically higher abundance of several strains, particularly those of Lactobacillus, in HAS. Enrichment of microbial metabolites implicated in immune response such as lactic acid, short chain fatty acids, amino acids, and vitamins were different between HAS and LAS. The abundance of several microbial strains corresponds to enriched host gene expression pathways related to immune response. These data provide a compelling argument that the microbiome is both likely affected by host divergent genetic selection and that it exerts influence on host antibody response by various mechanisms.

PTBGRP: predicting phage-bacteria interactions with graph representation learning on microbial heterogeneous information network

Identifying the potential bacteriophages (phage) candidate to treat bacterial infections plays an essential role in the research of human pathogens. Computational approaches are recognized as a valid way to predict bacteria and target phages. However, most of the current methods only utilize lower-order biological information without considering the higher-order connectivity patterns, which helps to improve the predictive accuracy. Therefore, we developed a novel microbial heterogeneous interaction network (MHIN)-based model called PTBGRP to predict new phages for bacterial hosts. Specifically, PTBGRP first constructs an MHIN by integrating phage-bacteria interaction (PBI) and six bacteria-bacteria interaction networks with their biological attributes. Then, different representation learning methods are deployed to extract higher-level biological features and lower-level topological features from MHIN. Finally, PTBGRP employs a deep neural network as the classifier to predict unknown PBI pairs based on the fused biological information. Experiment results demonstrated that PTBGRP achieves the best performance on the corresponding ESKAPE pathogens and PBI dataset when compared with state-of-art methods. In addition, case studies of Klebsiella pneumoniae and Staphylococcus aureus further indicate that the consideration of rich heterogeneous information enables PTBGRP to accurately predict PBI from a more comprehensive perspective. The webserver of the PTBGRP predictor is freely available at http://120.77.11.78/PTBGRP/.

Phage design and directed evolution to evolve phage for therapy

Phage therapy or Phage treatment is the use of bacteriolysing phage in treating bacterial infections by using the viruses that infects and kills bacteria. This technique has been studied and practiced very long ago, but with the advent of antibiotics, it has been neglected. This foregone technique is now witnessing a revival due to development of bacterial resistance. Nowadays, with the awareness of genetic sequence of organisms, it is required that informed choices of phages have to be made for the most efficacious results. Furthermore, phages with the evolving genes are taken into consideration for the subsequent improvement in treating the patients for bacterial diseases. In addition, direct evolution methods are increasingly developing, since these are capable of creating new biological molecules having changed or unique activities, such as, improved target specificity, evolution of novel proteins with new catalytic properties or creation of nucleic acids that are capable of recognizing required pathogenic bacteria. This system is incorporates continuous evolution such as protein or genes are put under continuous evolution by providing continuous mutagenesis with least human intervention. Although, this system providing continuous directed evolution is very effective, it imposes some challenges due to requirement of heavy investment of time and resources. This chapter focuses on development of phage as a therapeutic agent against various bacteria causing diseases and it improvement using direct evolution of proteins and nucleic acids such that they target specific organisms.

Bioinformatics approaches for unveiling virus-host interactions

The coronavirus disease-2019 (COVID-19) pandemic has elucidated major limitations in the capacity of medical and research institutions to appropriately manage emerging infectious diseases. We can improve our understanding of infectious diseases by unveiling virus-host interactions through host range prediction and protein-protein interaction prediction. Although many algorithms have been developed to predict virus-host interactions, numerous issues remain to be solved, and the entire network remains veiled. In this review, we comprehensively surveyed algorithms used to predict virus-host interactions. We also discuss the current challenges, such as dataset biases toward highly pathogenic viruses, and the potential solutions. The complete prediction of virus-host interactions remains difficult; however, bioinformatics can contribute to progress in research on infectious diseases and human health.

Phage Therapy for Crops: Concepts, Experimental and Bioinformatics Approaches to Direct Its Application

Phage therapy consists of applying bacteriophages, whose natural function is to kill specific bacteria. Bacteriophages are safe, evolve together with their host, and are environmentally friendly. At present, the indiscriminate use of antibiotics and salt minerals (Zn²⁺ or Cu²⁺) has caused the emergence of resistant strains that infect crops, causing difficulties and loss of food production. Phage therapy is an alternative that has shown positive results and can improve the treatments available for agriculture. However, the success of phage therapy depends on finding effective bacteriophages. This review focused on describing the potential, up to now, of applying phage therapy as an alternative treatment against bacterial diseases, with sustainable improvement in food production. We described the current isolation techniques, characterization, detection, and selection of lytic phages, highlighting the importance of complementary studies using genome analysis of the phage and its host. Finally, among these studies, we concentrated on the most relevant bacteriophages used for biocontrol of Pseudomonas spp., Xanthomonas spp., Pectobacterium spp., Ralstonia spp., Burkholderia spp., Dickeya spp., Clavibacter michiganensis, and Agrobacterium tumefaciens as agents that cause damage to crops, and affect food production around the world.

Bacteriophage Genetic Edition Using LSTM

Bacteriophages are gaining increasing interest as antimicrobial tools, largely due to the emergence of multi-antibiotic-resistant bacteria. Although their huge diversity and virulence make them particularly attractive for targeting a wide range of bacterial pathogens, it is difficult to select suitable phages due to their high specificity which limits their host range. In addition, other challenges remain such as structural fragility under certain environmental conditions, immunogenicity of phage therapy, or development of bacterial resistance. The use of genetically engineered phages may reduce characteristics that hinder prophylactic and therapeutic applications of phages. Nowadays, there is no systematic method to modify a given phage genome conferring its sought characteristics. We explore the use of artificial intelligence for this purpose as it has the potential to both guide and accelerate genome modification to generate phage variants with unique properties that overcome the limitations of natural phages. We propose an original architecture composed of two deep learning-driven components: a phage-bacterium interaction predictor and a phage genome-sequence generator. The former is a multi-branch 1-D convolutional neural network (1D-CNN) that analyses phage and bacterial genomes to predict interactions. The latter is a recurrent neural network, more particularly a long short-term memory (LSTM), that performs genomic modifications to a phage to offer substantial host range improvement. For this component, we developed two different architectures composed of one or two stacked LSTM layers with 256 neurons each. These generators are used to modify, more precisely to rewrite, the genome sequence of 42 selected phages, while the predictor is used to estimate the host range of the modified bacteriophages across 46 strains of Pseudomonas aeruginosa. The proposed generators, trained with an average accuracy of 96.1%, are able to improve the host range for an average of 18 phages among the 42 under study, increasing both their average host range, by 73.0 and 103.7%, and the maximum host ranges from 21 to 24 and 29, respectively. These promising results showed that the use of deep learning methodologies allows genetic modification of phages to extend, for instance, their host range, confirming the potential of these approaches to guide bacteriophage engineering.

Advances and challenges in cataloging the human gut virome

The human gut virome, which is often referred to as the "dark matter" of the gut microbiome, remains understudied. A better understanding of the composition and variations of the gut virome across populations is critical for exploring its impact on diseases and health. A series of advances in the characterization of human gut virome have unveiled high genetic diversity and various functional potentials of gut viruses. Here, we summarize the recently available human gut virome databases and discuss their features, procedures, and challenges with the intention to provide a reference to researchers to use while choosing a profiling database. We also propose a "best practice" for cataloging the viral population.

PHISDetector: A Tool to Detect Diverse In Silico Phage-host Interaction Signals for Virome Studies

Phage-microbe interactions are appealing systems to study coevolution, and have also been increasingly emphasized due to their roles in human health, disease, and the development of novel therapeutics. Phage-microbe interactions leave diverse signals in bacterial and phage genomic sequences, defined as phage-host interaction signals (PHISs), which include clustered regularly interspaced short palindromic repeats (CRISPR) targeting, prophage, and protein-protein interaction signals. In the present study, we developed a novel tool phage-host interaction signal detector (PHISDetector) to predict phage-host interactions by detecting and integrating diverse in silico PHISs, and scoring the probability of phage-host interactions using machine learning models based on PHIS features. We evaluated the performance of PHISDetector on multiple benchmark datasets and application cases. When tested on a dataset of 758 annotated phage-host pairs, PHISDetector yields the prediction accuracies of 0.51 and 0.73 at the species and genus levels, respectively, outperforming other phage-host prediction tools. When applied to on 125,842 metagenomic viral contigs (mVCs) derived from 3042 geographically diverse samples, a detection rate of 54.54% could be achieved. Furthermore, PHISDetector could predict infecting phages for 85.6% of 368 multidrug-resistant (MDR) bacteria and 30% of 454 human gut bacteria obtained from the National Institutes of Health (NIH) Human Microbiome Project (HMP). The PHISDetector can be run either as a web server (http://www.microbiome-bigdata.com/PHISDetector/) for general users to study individual inputs or as a stand-alone version (https://github.com/HIT-ImmunologyLab/PHISDetector) to process massive phage contigs from virome studies.

Machine Learning Advances in Microbiology: A Review of Methods and Applications

Microorganisms play an important role in natural material and elemental cycles. Many common and general biology research techniques rely on microorganisms. Machine learning has been gradually integrated with multiple fields of study. Machine learning, including deep learning, aims to use mathematical insights to optimize variational functions to aid microbiology using various types of available data to help humans organize and apply collective knowledge of various research objects in a systematic and scaled manner. Classification and prediction have become the main achievements in the development of microbial community research in the direction of computational biology. This review summarizes the application and development of machine learning and deep learning in the field of microbiology and shows and compares the advantages and disadvantages of different algorithm tools in four fields: microbiome and taxonomy, microbial ecology, pathogen and epidemiology, and drug discovery.

Computational Network Inference for Bacterial Interactomics

Since the large-scale experimental characterization of protein–protein interactions (PPIs) is not possible for all species, several computational PPI prediction methods have been developed that harness existing data from other species. While PPI network prediction has been extensively used in eukaryotes, microbial network inference has lagged behind. However, bacterial interactomes can be built using the same principles and techniques; in fact, several methods are better suited to bacterial genomes. These predicted networks allow systems-level analyses in species that lack experimental interaction data. This review describes the current network inference and analysis techniques and summarizes the use of computationally-predicted microbial interactomes to date.

Subtypes of tail spike proteins predicts the host range of Ackermannviridae phages

Phages belonging to the Ackermannviridae family encode up to four tail spike proteins (TSPs), each recognizing a specific receptor of their bacterial hosts. Here, we determined the TSPs diversity of 99 Ackermannviridae phages by performing a comprehensive in silico analysis. Based on sequence diversity, we assigned all TSPs into distinctive subtypes of TSP1, TSP2, TSP3 and TSP4, and found each TSP subtype to be specifically associated with the genera (Kuttervirus, Agtrevirus, Limestonevirus, Taipeivirus) of the Ackermannviridae family. Further analysis showed that the N-terminal XD1 and XD2 domains in TSP2 and TSP4, hinging the four TSPs together, are preserved. In contrast, the C-terminal receptor binding modules were only conserved within TSP subtypes, except for some Kuttervirus TSP1s and TSP3s that were similar to specific TSP4s. A conserved motif in TSP1, TSP3 and TSP4 of Kuttervirus phages may allow recombination between receptor binding modules, thus altering host recognition. The receptors for numerous uncharacterized phages expressing TSPs in the same subtypes were predicted using previous host range data. To validate our predictions, we experimentally determined the host recognition of three of the four TSPs expressed by kuttervirus S117. We confirmed that S117 TSP1 and TSP2 bind to their predicted host receptors, and identified the receptor for TSP3, which is shared by 51 other Kuttervirus phages. Kuttervirus phages were thus shown encode a vast genetic diversity of potentially exchangeable TSPs influencing host recognition. Overall, our study demonstrates that comprehensive in silico and host range analysis of TSPs can predict host recognition of Ackermannviridae phages.

A Deep Learning-Based Method for Identification of Bacteriophage-Host Interaction

Multi-drug resistance (MDR) has become one of the greatest threats to human health worldwide, and novel treatment methods of infections caused by MDR bacteria are urgently needed. Phage therapy is a promising alternative to solve this problem, to which the key is correctly matching target pathogenic bacteria with the corresponding therapeutic phage. Deep learning is powerful for mining complex patterns to generate accurate predictions. In this study, we develop PredPHI (Predicting Phage-Host Interactions), a deep learning-based tool capable of predicting the host of phages from sequence data. We collect >3000 phage-host pairs along with their protein sequences from PhagesDB and GenBank databases and extract a set of features. Then we select high-quality negative samples based on the K-Means clustering method and construct a balanced training set. Finally, we employ a deep convolutional neural network to build the predictive model. The results indicate that PredPHI can achieve a predictive performance of 81 percent in terms of the area under the receiver operating characteristic curve on the test set, and the clustering-based method is significantly more robust than that based on randomly selecting negative samples. These results highlight that PredPHI is a useful and accurate tool for identifying phage-host interactions from sequence data.

PHIAF: prediction of phage-host interactions with GAN-based data augmentation and sequence-based feature fusion

Phage therapy has become one of the most promising alternatives to antibiotics in the treatment of bacterial diseases, and identifying phage-host interactions (PHIs) helps to understand the possible mechanism through which a phage infects bacteria to guide the development of phage therapy. Compared with wet experiments, computational methods of identifying PHIs can reduce costs and save time and are more effective and economic. In this paper, we propose a PHI prediction method with a generative adversarial network (GAN)-based data augmentation and sequence-based feature fusion (PHIAF). First, PHIAF applies a GAN-based data augmentation module, which generates pseudo PHIs to alleviate the data scarcity. Second, PHIAF fuses the features originated from DNA and protein sequences for better performance. Third, PHIAF utilizes an attention mechanism to consider different contributions of DNA/protein sequence-derived features, which also provides interpretability of the prediction model. In computational experiments, PHIAF outperforms other state-of-the-art PHI prediction methods when evaluated via 5-fold cross-validation (AUC and AUPR are 0.88 and 0.86, respectively). An ablation study shows that data augmentation, feature fusion and an attention mechanism are all beneficial to improve the prediction performance of PHIAF. Additionally, four new PHIs with the highest PHIAF score in the case study were verified by recent literature. In conclusion, PHIAF is a promising tool to accelerate the exploration of phage therapy.

RaFAH: Host prediction for viruses of Bacteria and Archaea based on protein content

Culture-independent approaches have recently shed light on the genomic diversity of viruses of prokaryotes. One fundamental question when trying to understand their ecological roles is: which host do they infect? To tackle this issue we developed a machine-learning approach named Random Forest Assignment of Hosts (RaFAH), that uses scores to 43,644 protein clusters to assign hosts to complete or fragmented genomes of viruses of Archaea and Bacteria. RaFAH displayed performance comparable with that of other methods for virus-host prediction in three different benchmarks encompassing viruses from RefSeq, single amplified genomes, and metagenomes. RaFAH was applied to assembled metagenomic datasets of uncultured viruses from eight different biomes of medical, biotechnological, and environmental relevance. Our analyses led to the identification of 537 sequences of archaeal viruses representing unknown lineages, whose genomes encode novel auxiliary metabolic genes, shedding light on how these viruses interfere with the host molecular machinery. RaFAH is available at https://sourceforge.net/projects/rafah/.

•

RaFAH was developed to predict the hosts of viruses of Bacteria and Archaea

•

RaFAH displayed comparable or superior performance to other host-prediction tools

•

RaFAH performed well across viromes from eight different ecosystems

•

RaFAH identified hundreds of genomic sequences as derived from viruses of Archaea

Viruses that infect Bacteria and Archaea are ubiquitous and extremely abundant. Recent advances have led to the discovery of many thousands of complete and partial genomes of these biological entities. Understanding the biology of these viruses and how they influence their ecosystems depends on knowing which hosts they infect. We developed a tool that uses data from complete or fragmented genomes to predict the hosts of viruses using a machine-learning approach. Our tool, RaFAH, displayed performance comparable with or superior to that of other host-prediction tools. In addition, it identified hundreds of sequences as derived from the genomes of viruses of Archaea, which are one of the least characterized fractions of the global virosphere.

Global overview and major challenges of host prediction methods for uncultivated phages

Bacterial communities play critical roles across all of Earth's biomes, affecting human health and global ecosystem functioning. They do so under strong constraints exerted by viruses, that is, bacteriophages or 'phages'. Phages can reshape bacterial communities' structure, influence long-term evolution of bacterial populations, and alter host cell metabolism during infection. Metagenomics approaches, that is, shotgun sequencing of environmental DNA or RNA, recently enabled large-scale exploration of phage genomic diversity, yielding several millions of phage genomes now to be further analyzed and characterized. One major challenge however is the lack of direct host information for these phages. Several methods and tools have been proposed to bioinformatically predict the potential host(s) of uncultivated phages based only on genome sequence information. Here we review these different approaches and highlight their distinct strengths and limitations. We also outline complementary experimental assays which are being proposed to validate and refine these bioinformatic predictions.

Computational Biology and Machine Learning Approaches to Understand Mechanistic Microbiome-Host Interactions

The microbiome, by virtue of its interactions with the host, is implicated in various host functions including its influence on nutrition and homeostasis. Many chronic diseases such as diabetes, cancer, inflammatory bowel diseases are characterized by a disruption of microbial communities in at least one biological niche/organ system. Various molecular mechanisms between microbial and host components such as proteins, RNAs, metabolites have recently been identified, thus filling many gaps in our understanding of how the microbiome modulates host processes. Concurrently, high-throughput technologies have enabled the profiling of heterogeneous datasets capturing community level changes in the microbiome as well as the host responses. However, due to limitations in parallel sampling and analytical procedures, big gaps still exist in terms of how the microbiome mechanistically influences host functions at a system and community level. In the past decade, computational biology and machine learning methodologies have been developed with the aim of filling the existing gaps. Due to the agnostic nature of the tools, they have been applied in diverse disease contexts to analyze and infer the interactions between the microbiome and host molecular components. Some of these approaches allow the identification and analysis of affected downstream host processes. Most of the tools statistically or mechanistically integrate different types of -omic and meta -omic datasets followed by functional/biological interpretation. In this review, we provide an overview of the landscape of computational approaches for investigating mechanistic interactions between individual microbes/microbiome and the host and the opportunities for basic and clinical research. These could include but are not limited to the development of activity- and mechanism-based biomarkers, uncovering mechanisms for therapeutic interventions and generating integrated signatures to stratify patients.

Learning chemistry: exploring the suitability of machine learning for the task of structure-based chemical ontology classification

Chemical data is increasingly openly available in databases such as PubChem, which contains approximately 110 million compound entries as of February 2021. With the availability of data at such scale, the burden has shifted to organisation, analysis and interpretation. Chemical ontologies provide structured classifications of chemical entities that can be used for navigation and filtering of the large chemical space. ChEBI is a prominent example of a chemical ontology, widely used in life science contexts. However, ChEBI is manually maintained and as such cannot easily scale to the full scope of public chemical data. There is a need for tools that are able to automatically classify chemical data into chemical ontologies, which can be framed as a hierarchical multi-class classification problem. In this paper we evaluate machine learning approaches for this task, comparing different learning frameworks including logistic regression, decision trees and long short-term memory artificial neural networks, and different encoding approaches for the chemical structures, including cheminformatics fingerprints and character-based encoding from chemical line notation representations. We find that classical learning approaches such as logistic regression perform well with sets of relatively specific, disjoint chemical classes, while the neural network is able to handle larger sets of overlapping classes but needs more examples per class to learn from, and is not able to make a class prediction for every molecule. Future work will explore hybrid and ensemble approaches, as well as alternative network architectures including neuro-symbolic approaches.

Progress and Pitfalls of Bacteriophage Therapy in Critical Care: A Concise Definitive Review

Supplemental Digital Content is available in the text.

Objective:

Bacterial infections caused by antibiotic-resistant pathogens are a major problem for patients requiring critical care. An approach to combat resistance is the use of bacterial viruses known as “phage therapy.” This review provides a brief “clinicians guide” to phage biology and discusses recent applications in the context of common infections encountered in ICUs.

Data Sources:

Research articles were sourced from PubMed using search term combinations of “bacteriophages” or “phage therapy” with either “lung,” “pneumonia,” “bloodstream,” “abdominal,” “urinary tract,” or “burn wound.”

Study Selection:

Preclinical trials using animal models, case studies detailing compassionate use of phage therapy in humans, and randomized controlled trials were included.

Data Extraction:

We systematically extracted: 1) the infection setting, 2) the causative bacterial pathogen and its antibiotic resistance profile, 3) the nature of the phage therapeutic and how it was administered, 4) outcomes of the therapy, and 5) adverse events.

Data Synthesis:

Phage therapy for the treatment of experimental infections in animal models and in cases of compassionate use in humans has been associated with largely positive outcomes. These findings, however, have failed to translate into positive patient outcomes in the limited number of randomized controlled trails that have been performed to date.

Conclusions:

Widespread clinical implementation of phage therapy depends on success in randomized controlled trials. Additional translational and reverse translational studies aimed at overcoming phage resistance, exploiting phage-antibiotic synergies, and optimizing phage administration will likely improve the design and outcome of future trials.

Viral Host Range database, an online tool for recording, analyzing and disseminating virus-host interactions

Motivation

Viruses are ubiquitous in the living world, and their ability to infect more than one host defines their host range. However, information about which virus infects which host, and about which host is infected by which virus, is not readily available.

Results

We developed a web-based tool called the Viral Host Range database to record, analyze and disseminate experimental host range data for viruses infecting archaea, bacteria and eukaryotes.

Availability and implementation

The ViralHostRangeDB application is available from https://viralhostrangedb.pasteur.cloud. Its source code is freely available from the Gitlab instance of Institut Pasteur (https://gitlab.pasteur.fr/hub/viralhostrangedb).

Predicting bacteriophage hosts based on sequences of annotated receptor-binding proteins

Nowadays, bacteriophages are increasingly considered as an alternative treatment for a variety of bacterial infections in cases where classical antibiotics have become ineffective. However, characterizing the host specificity of phages remains a labor- and time-intensive process. In order to alleviate this burden, we have developed a new machine-learning-based pipeline to predict bacteriophage hosts based on annotated receptor-binding protein (RBP) sequence data. We focus on predicting bacterial hosts from the ESKAPE group, Escherichia coli, Salmonella enterica and Clostridium difficile. We compare the performance of our predictive model with that of the widely used Basic Local Alignment Search Tool (BLAST). Our best-performing predictive model reaches Precision-Recall Area Under the Curve (PR-AUC) scores between 73.6 and 93.8% for different levels of sequence similarity in the collected data. Our model reaches a performance comparable to that of BLASTp when sequence similarity in the data is high and starts outperforming BLASTp when sequence similarity drops below 75%. Therefore, our machine learning methods can be especially useful in settings in which sequence similarity to other known sequences is low. Predicting the hosts of novel metagenomic RBP sequences could extend our toolbox to tune the host spectrum of phages or phage tail-like bacteriocins by swapping RBPs.

The Rationale for Using Bacteriophage to Treat and Prevent Periprosthetic Joint Infections

Prosthetic joint infection (PJI) is a devastating complication after a joint replacement. PJI and its treatment have a high monetary cost, morbidity, and mortality. The lack of success treating PJI with conventional antibiotics alone is related to the presence of bacterial biofilm on medical implants. Consequently, surgical removal of the implant and prolonged intravenous antibiotics to eradicate the infection are necessary prior to re-implanting a new prosthetic joint. Growing clinical data shows that bacterial predators, called bacteriophages (phages), could be an alternative treatment strategy or prophylactic approach for PJI. Phages could further be exploited to degrade biofilms, making bacteria more susceptible to antibiotics and enabling potential combinatorial therapies. Emerging research suggests that phages may also directly interact with the innate immune response. Phage therapy may play an important, and currently understudied, role in the clearance of PJI, and has the potential to treat thousands of patients who would either have to undergo revision surgery to attempt to clear an infections, take antibiotics for a prolonged period to try and suppress the re-emerging infection, or potentially risk losing a limb.

Enhancing phage therapy through synthetic biology and genome engineering

The antimicrobial and therapeutic efficacy of bacteriophages is currently limited, mostly due to rapid emergence of phage-resistance and the inability of most phage isolates to bind and infect a broad range of clinical strains. Here, we discuss how phage therapy can be improved through recent advances in genetic engineering. First, we outline how receptor-binding proteins and their relevant structural domains are engineered to redirect phage specificity and to avoid resistance. Next, we summarize how phages are reprogrammed as prokaryotic gene therapy vectors that deliver antimicrobial 'payload' proteins, such as sequence-specific nucleases, to target defined cells within complex microbiomes. Finally, we delineate big data- and novel artificial intelligence-driven approaches that may guide the design of improved synthetic phage in the future.

Alternatives to antibiotics in a One Health context and the role genomics can play in reducing antimicrobial use

BACKGROUND

This review follows on from the International Conference on One Health Antimicrobial Resistance (ICOHAR 2019), where strategies to improve the fundamental understanding and management of antimicrobial resistance at the interface between humans, animals and the environment were discussed.

OBJECTIVE

This review identifies alternatives to antimicrobials in a One Health context, noting how advances in genomic technologies are assisting their development and enabling more targeted use of antimicrobials.

SOURCES

Key articles on the use of microbiota modulation, livestock breeding and gene editing, vaccination, antivirulence strategies and bacteriophage therapy are discussed.

CONTENT

Antimicrobials are central for disease control, but reducing their use is paramount as a result of the rise of transmissible antimicrobial resistance. This review discusses antimicrobial alternatives in the context of improved understanding of fundamental host-pathogen and microbiota interactions using genomic tools.

IMPLICATIONS

Host and microbial genomics and other novel technologies play an important role in devising disease control strategies for healthier animals and humans that in turn reduce our reliance on antimicrobials.

Unlocking the next generation of phage therapy: the key is in the receptors

Phage therapy, the clinical use of viruses that kill bacteria, is a promising strategy in the fight against antimicrobial resistance. Before administration, phages undergo a careful examination of their safety and interactions with target bacteria. This characterization seldom includes identifying the receptor on the bacterial surface involved in phage adsorption. In this perspective article, we propose that understanding the function and location of these phage receptors can open the door to improved and innovative ways to use phage therapy. With knowledge of phage receptors, we can design intelligent phage cocktails, discover new phage-derived antimicrobials, and steer the evolution of phage-resistance towards clinically exploitable phenotypes. In an effort to jump-start this initiative, we recommend priority groups of hosts and phages. Finally, we review modern approaches for the identification of phage receptors, including molecular platforms for high-throughput mutagenesis, synthetic biology, and machine learning.

Application of artificial intelligence to the in silico assessment of antimicrobial resistance and risks to human and animal health presented by priority enteric bacterial pathogens

Each year, approximately one in eight Canadians are affected by foodborne illness, either through outbreaks or sporadic illness, with animals being the major reservoir for the pathogens. Whole genome sequence analyses are now routinely implemented by public and animal health laboratories to define epidemiological disease clusters and to identify potential sources of infection. Similarly, a number of bioinformatics tools can be used to identify virulence and antimicrobial resistance (AMR) determinants in the genomes of pathogenic strains. Many important clinical and phenotypic characteristics of these pathogens can now be predicted using machine learning algorithms applied to whole genome sequence data. In this overview, we compare the ability of support vector machines, gradient-boosted decision trees and artificial neural networks to predict the levels of AMR within Salmonella enterica and extended-spectrum β-lactamase (ESBL) producing Escherichia coli. We show that minimum inhibitory concentrations (MIC) for each of 13 antimicrobials for S. enterica strains can be accurately determined, and that ESBL-producing E. coli strains can be accurately classified as susceptible, intermediate or resistant for each of seven antimicrobials. In addition to AMR and bacterial populations of greatest risk to human health, artificial intelligence algorithms hold promise as tools to predict other clinically and epidemiologically important phenotypes of enteric pathogens.

Predicting host taxonomic information from viral genomes: A comparison of feature representations

The rise in metagenomics has led to an exponential growth in virus discovery. However, the majority of these new virus sequences have no assigned host. Current machine learning approaches to predicting virus host interactions have a tendency to focus on nucleotide features, ignoring other representations of genomic information. Here we investigate the predictive potential of features generated from four different ‘levels’ of viral genome representation: nucleotide, amino acid, amino acid properties and protein domains. This more fully exploits the biological information present in the virus genomes. Over a hundred and eighty binary datasets for infecting versus non-infecting viruses at all taxonomic ranks of both eukaryote and prokaryote hosts were compiled. The viral genomes were converted into the four different levels of genome representation and twenty feature sets were generated by extracting k-mer compositions and predicted protein domains. We trained and tested Support Vector Machine, SVM, classifiers to compare the predictive capacity of each of these feature sets for each dataset. Our results show that all levels of genome representation are consistently predictive of host taxonomy and that prediction k-mer composition improves with increasing k-mer length for all k-mer based features. Using a phylogenetically aware holdout method, we demonstrate that the predictive feature sets contain signals reflecting both the evolutionary relationship between the viruses infecting related hosts, and host-mimicry. Our results demonstrate that incorporating a range of complementary features, generated purely from virus genome sequences, leads to improved accuracy for a range of virus host prediction tasks enabling computational assignment of host taxonomic information.

Elucidating the host of a newly identified virus species is an important challenge, with applications from knowing the source species of a newly emerged pathogen to understanding the bacteriophage-host relationships within the microbiome of any of earth’s ecosystems. Current high throughput methods used to identify viruses within biological or environmental samples have resulted in an unprecedented increase in virus discovery. However, for the majority of these virus genomes the host species/taxonomic classification remains unknown. To address this gap in our knowledge there is a need for fast, accurate computational methods for the assignment of putative host taxonomic information. Machine learning is an ideal approach but to maximise predictive accuracy the viral genomes need to be represented in a format (sets of features) that makes the discriminative information available to the machine learning algorithm. Here, we compare different types of features derived from the same viral genomes for their ability to predict host information. Our results demonstrate that all these feature sets are predictive of host taxonomy and when combined have the potential to improve accuracy over the use of individual feature sets across many virus host prediction applications.

Biological challenges of phage therapy and proposed solutions: a literature review

Introduction: In light of the emergence of antibiotic-resistant bacteria, phage (bacteriophage) therapy has been recognized as a potential alternative or addition to antibiotics in Western medicine for use in humans.Areas covered: This review assessed the scientific literature on phage therapy published between 1 January 2007 and 21 October 2019, with a focus on the successes and challenges of this prospective therapeutic.Expert opinion: Efficacy has been shown in animal models and experimental findings suggest promise for the safety of human phagotherapy. Significant challenges remain to be addressed prior to the standardization of phage therapy in the West, including the development of phage-resistant bacteria; the pharmacokinetic complexities of phage; and any potential human immune response incited by phagotherapy.

Computational Health Engineering Applied to Model Infectious Diseases and Antimicrobial Resistance Spread

Infectious diseases are the primary cause of mortality worldwide. The dangers of infectious disease are compounded with antimicrobial resistance, which remains the greatest concern for human health. Although novel approaches are under investigation, the World Health Organization predicts that by 2050, septicaemia caused by antimicrobial resistant bacteria could result in 10 million deaths per year. One of the main challenges in medical microbiology is to develop novel experimental approaches, which enable a better understanding of bacterial infections and antimicrobial resistance. After the introduction of whole genome sequencing, there was a great improvement in bacterial detection and identification, which also enabled the characterization of virulence factors and antimicrobial resistance genes. Today, the use of in silico experiments jointly with computational and machine learning offer an in depth understanding of systems biology, allowing us to use this knowledge for the prevention, prediction, and control of infectious disease. Herein, the aim of this review is to discuss the latest advances in human health engineering and their applicability in the control of infectious diseases. An in-depth knowledge of host–pathogen–protein interactions, combined with a better understanding of a host’s immune response and bacterial fitness, are key determinants for halting infectious diseases and antimicrobial resistance dissemination.

FLOating-Window Projective Separator (FloWPS): A Data Trimming Tool for Support Vector Machines (SVM) to Improve Robustness of the Classifier

Here, we propose a heuristic technique of data trimming for SVM termed FLOating Window Projective Separator (FloWPS), tailored for personalized predictions based on molecular data. This procedure can operate with high throughput genetic datasets like gene expression or mutation profiles. Its application prevents SVM from extrapolation by excluding non-informative features. FloWPS requires training on the data for the individuals with known clinical outcomes to create a clinically relevant classifier. The genetic profiles linked with the outcomes are broken as usual into the training and validation datasets. The unique property of FloWPS is that irrelevant features in validation dataset that don’t have significant number of neighboring hits in the training dataset are removed from further analyses. Next, similarly to the k nearest neighbors (kNN) method, for each point of a validation dataset, FloWPS takes into account only the proximal points of the training dataset. Thus, for every point of a validation dataset, the training dataset is adjusted to form a floating window. FloWPS performance was tested on ten gene expression datasets for 992 cancer patients either responding or not on the different types of chemotherapy. We experimentally confirmed by leave-one-out cross-validation that FloWPS enables to significantly increase quality of a classifier built based on the classical SVM in most of the applications, particularly for polynomial kernels.