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.

Despite decades of intensive search for compounds that modulate the activity of particular protein targets, a large proportion of the human kinome remains as yet undrugged. Effective approaches are therefore required to map the massive space of unexplored compound–kinase interactions for novel and potent activities. Here, we carry out a crowdsourced benchmarking of predictive algorithms for kinase inhibitor potencies across multiple kinase families tested on unpublished bioactivity data. We find the top-performing predictions are based on various models, including kernel learning, gradient boosting and deep learning, and their ensemble leads to a predictive accuracy exceeding that of single-dose kinase activity assays. We design experiments based on the model predictions and identify unexpected activities even for under-studied kinases, thereby accelerating experimental mapping efforts. The open-source prediction algorithms together with the bioactivities between 95 compounds and 295 kinases provide a resource for benchmarking prediction algorithms and for extending the druggable kinome.

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%.

No abstract

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 β-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.