Hyperdimensional computing: A fast, robust, and interpretable paradigm for biological data.

Advances in bioinformatics are primarily due to new algorithms for processing diverse biological data sources. While sophisticated alignment algorithms have been pivotal in analyzing biological sequences, deep learning has substantially transformed bioinformatics, addressing sequence, structure, and functional analyses. However, these methods are incredibly data-hungry, compute-intensive, and hard to interpret. Hyperdimensional computing (HDC) has recently emerged as an exciting alternative. The key idea is that random vectors of high dimensionality can represent concepts such as sequence identity or phylogeny. These vectors can then be combined using simple operators for learning, reasoning, or querying by exploiting the peculiar properties of high-dimensional spaces. Our work reviews and explores HDC's potential for bioinformatics, emphasizing its efficiency, interpretability, and adeptness in handling multimodal and structured data. HDC holds great potential for various omics data searching, biosignal analysis, and health applications.

DepoScope: Accurate phage depolymerase annotation and domain delineation using large language models.

Bacteriophages (phages) are viruses that infect bacteria. Many of them produce specific enzymes called depolymerases to break down external polysaccharide structures. Accurate annotation and domain identification of these depolymerases are challenging due to their inherent sequence diversity. Hence, we present DepoScope, a machine learning tool that combines a fine-tuned ESM-2 model with a convolutional neural network to identify depolymerase sequences and their enzymatic domains precisely. To accomplish this, we curated a dataset from the INPHARED phage genome database, created a polysaccharide-degrading domain database, and applied sequential filters to construct a high-quality dataset, which is subsequently used to train DepoScope. Our work is the first approach that combines sequence-level predictions with amino-acid-level predictions for accurate depolymerase detection and functional domain identification. In that way, we believe that DepoScope can greatly enhance our understanding of phage-host interactions at the level of depolymerases.

CkP1 bacteriophage, a S16-like myovirus that recognizes Citrobacter koseri lipopolysaccharide through its long tail fibers.

Citrobacter koseri is an emerging Gram-negative bacterial pathogen, which causes urinary tract infections. We isolated and characterized a novel S16-like myovirus CKP1 (vB_CkoM_CkP1), infecting C. koseri. CkP1 has a host range covering the whole C. koseri species, i.e., all strains that were tested, but does not infect other species. Its linear 168,463-bp genome contains 291 coding sequences, sharing sequence similarity with the Salmonella phage S16. Based on surface plasmon resonance and recombinant green florescence protein fusions, the tail fiber (gp267) was shown to decorate C. koseri cells, binding with a nanomolar affinity, without the need of accessory proteins. Both phage and the tail fiber specifically bind to bacterial cells by the lipopolysaccharide polymer. We further demonstrate that CkP1 is highly stable towards different environmental conditions of pH and temperatures and is able to control C. koseri cells in urine samples. Altogether, CkP1 features optimal in vitro characteristics to be used both as a control and detection agent towards drug-resistant C. koseri infections. KEY POINTS: • CkP1 infects all C. koseri strains tested • CkP1 recognizes C. koseri lipopolysaccharide through its long tail fiber • Both phage CkP1 and its tail fiber can be used to treat or detect C. koseri pathogens.

Machine Learning to Assist in Large-Scale, Activity-Based Synthetic Cannabinoid Receptor Agonist Screening of Serum Samples.

BACKGROUND: Synthetic cannabinoid receptor agonists (SCRAs) are amongst the largest groups of new psychoactive substances (NPS). Their often high activity at the CB1 cannabinoid receptor frequently results in intoxication, imposing serious health risks. Hence, continuous monitoring of these compounds is important, but challenged by the rapid emergence of novel analogues that are missed by traditional targeted detection strategies. We addressed this need by performing an activity-based, universal screening on a large set (n = 968) of serum samples from patients presenting to the emergency department with acute recreational drug or NPS toxicity. METHODS: We assessed the performance of an activity-based method in detecting newly circulating SCRAs compared with liquid chromatography coupled to high-resolution mass spectrometry. Additionally, we developed and evaluated machine learning models to reduce the screening workload by automating interpretation of the activity-based screening output. RESULTS: Activity-based screening delivered outstanding performance, with a sensitivity of 94.6% and a specificity of 98.5%. Furthermore, the developed machine learning models allowed accurate distinction between positive and negative patient samples in an automatic manner, closely matching the manual scoring of samples. The performance of the model depended on the predefined threshold, e.g., at a threshold of 0.055, sensitivity and specificity were both 94.0%. CONCLUSION: The activity-based bioassay is an ideal candidate for untargeted screening of novel SCRAs. The combination of this universal screening assay and a machine learning approach for automated sample scoring is a promising complement to conventional analytical methods in clinical practice.

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.

Foundation of the Belgian Society for Viruses of Microbes and Meeting Report of Its Inaugural Symposium.

The Belgian Society for Viruses of Microbes (BSVoM) was founded on 9 June 2022 to capture and enhance the collaborative spirit among the expanding community of microbial virus researchers in Belgium. The sixteen founders are affiliated to fourteen different research entities across academia, industry and government. Its inaugural symposium was held on 23 September 2022 in the Thermotechnical Institute at KU Leuven. The meeting program covered three thematic sessions launched by international keynote speakers: (1) virus-host interactions, (2) viral ecology, evolution and diversity and (3) present and future applications. During the one-day symposium, four invited keynote lectures, ten selected talks and eight student pitches were given along with 41 presented posters. The meeting hosted 155 participants from twelve countries.

Identification of Phage Receptor-Binding Protein Sequences with Hidden Markov Models and an Extreme Gradient Boosting Classifier.

Receptor-binding proteins (RBPs) of bacteriophages initiate the infection of their corresponding bacterial host and act as the primary determinant for host specificity. The ever-increasing amount of sequence data enables the development of predictive models for the automated identification of RBP sequences. However, the development of such models is challenged by the inconsistent or missing annotation of many phage proteins. Recently developed tools have started to bridge this gap but are not specifically focused on RBP sequences, for which many different annotations are available. We have developed two parallel approaches to alleviate the complex identification of RBP sequences in phage genomic data. The first combines known RBP-related hidden Markov models (HMMs) from the Pfam database with custom-built HMMs to identify phage RBPs based on protein domains. The second approach consists of training an extreme gradient boosting classifier that can accurately discriminate between RBPs and other phage proteins. We explained how these complementary approaches can reinforce each other in identifying RBP sequences. In addition, we benchmarked our methods against the recently developed PhANNs tool. Our best performing model reached a precision-recall area-under-the-curve of 93.8% and outperformed PhANNs on an independent test set, reaching an F1-score of 84.0% compared to 69.8%.

Digital phagograms: predicting phage infectivity through a multilayer machine learning approach.

Machine learning has been broadly implemented to investigate biological systems. In this regard, the field of phage biology has embraced machine learning to elucidate and predict phage-host interactions, based on receptor-binding proteins, (anti-)defense systems, prophage detection, and life cycle recognition. Here, we highlight the enormous potential of integrating information from omics data with insights from systems biology to better understand phage-host interactions. We conceptualize and discuss the potential of a multilayer model that mirrors the phage infection process, integrating adsorption, bacterial pan-immune components and hijacking of the bacterial metabolism to predict phage infectivity. In the future, this model can offer insights into the underlying mechanisms of the infection process, and digital phagograms can support phage cocktail design and phage engineering.

The Specific Capsule Depolymerase of Phage PMK34 Sensitizes Acinetobacter baumannii to Serum Killing.

The rising antimicrobial resistance is particularly alarming for Acinetobacter baumannii, calling for the discovery and evaluation of alternatives to treat A. baumannii infections. Some bacteriophages produce a structural protein that depolymerizes capsular exopolysaccharide. Such purified depolymerases are considered as novel antivirulence compounds. We identified and characterized a depolymerase (DpoMK34) from Acinetobacter phage vB_AbaP_PMK34 active against the clinical isolate A. baumannii MK34. In silico analysis reveals a modular protein displaying a conserved N-terminal domain for anchoring to the phage tail, and variable central and C-terminal domains for enzymatic activity and specificity. AlphaFold-Multimer predicts a trimeric protein adopting an elongated structure due to a long α-helix, an enzymatic ß-helix domain and a hypervariable 4 amino acid hotspot in the most ultimate loop of the C-terminal domain. In contrast to the tail fiber of phage T3, this hypervariable hotspot appears unrelated with the primary receptor. The functional characterization of DpoMK34 revealed a mesophilic enzyme active up to 50 °C across a wide pH range (4 to 11) and specific for the capsule of A. baumannii MK34. Enzymatic degradation of the A. baumannii MK34 capsule causes a significant drop in phage adsorption from 95% to 9% after 5 min. Although lacking intrinsic antibacterial activity, DpoMK34 renders A. baumannii MK34 fully susceptible to serum killing in a serum concentration dependent manner. Unlike phage PMK34, DpoMK34 does not easily select for resistant mutants either against PMK34 or itself. In sum, DpoMK34 is a potential antivirulence compound that can be included in a depolymerase cocktail to control difficult to treat A. baumannii infections.

The International Virus Bioinformatics Meeting 2022.

The International Virus Bioinformatics Meeting 2022 took place online, on 23-25 March 2022, and has attracted about 380 participants from all over the world. The goal of the meeting was to provide a meaningful and interactive scientific environment to promote discussion and collaboration and to inspire and suggest new research directions and questions. The participants created a highly interactive scientific environment even without physical face-to-face interactions. This meeting is a focal point to gain an insight into the state-of-the-art of the virus bioinformatics research landscape and to interact with researchers in the forefront as well as aspiring young scientists. The meeting featured eight invited and 18 contributed talks in eight sessions on three days, as well as 52 posters, which were presented during three virtual poster sessions. The main topics were: SARS-CoV-2, viral emergence and surveillance, virus-host interactions, viral sequence analysis, virus identification and annotation, phages, and viral diversity. This report summarizes the main research findings and highlights presented at the meeting.

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.