Background: Phage therapy shows promise for treating antibiotic-resistant Klebsiella infections. Identifying phage depolymerases that target Klebsiella capsular polysaccharides is crucial, as these capsules contribute to biofilm formation and virulence. However, homology-based searches have limitations in novel depolymerase discovery. Objective: To develop a machine learning model for identifying and ranking potential phage depolymerases targeting Klebsiella. Methods: We developed DepoRanker, a machine learning algorithm to rank proteins by their likelihood of being depolymerases. The model was experimentally validated on 5 newly characterized proteins and compared to BLAST. Results: DepoRanker demonstrated superior performance to BLAST in identifying potential depolymerases. Experimental validation confirmed its predictive ability on novel proteins. Conclusions: DepoRanker provides an accurate and functional tool to expedite depolymerase discovery for phage therapy against Klebsiella. It is available as a webserver and open-source software. Availability: Webserver: https://deporanker.dcs.warwick.ac.uk/ Source code: https://github.com/wgrgwrght/deporanker

Prior work on Self-supervised large language models have in-context MT has focused on prompt-engineering, treating demonstrated the ability to perform Machine GPT models as black boxes by focusing on which examples Translation (MT) via in-context learning, but little to provide in-context (Moslem et al., 2023). Agrawal et al. is known about where the model performs (2022) apply similarity-based retrieval to select in-context the task with respect to prompt instructions and examples, while Sia & Duh (2023) suggest a coherencebased demonstration examples. In this work, we attempt approach. However, these works apply surface level to characterize the region where large language interventions leaving the internal mechanism of MT in GPT models transition from in-context learners to translation models largely not understood.

Prokaryotic viruses, which infect bacteria and archaea, are key players in microbial communities. Predicting the hosts of prokaryotic viruses helps decipher the dynamic relationship between microbes. Experimental methods for host prediction cannot keep pace with the fast accumulation of sequenced phages. Thus, there is a need for computational host prediction. Despite some promising results, computational host prediction remains a challenge because of the limited known interactions and the sheer amount of sequenced phages by high-throughput sequencing technologies. The state-of-the-art methods can only achieve 43\% accuracy at the species level. In this work, we formulate host prediction as link prediction in a knowledge graph that integrates multiple protein and DNA-based sequence features. Our implementation named CHERRY can be applied to predict hosts for newly discovered viruses and to identify viruses infecting targeted bacteria. We demonstrated the utility of CHERRY for both applications and compared its performance with 11 popular host prediction methods. To our best knowledge, CHERRY has the highest accuracy in identifying virus-prokaryote interactions. It outperforms all the existing methods at the species level with an accuracy increase of 37\%. In addition, CHERRY's performance on short contigs is more stable than other tools.

To answer the question, "Where's Waldo?" readers need to look for a number of distinguishing features. Several characters may be spotted with a striped scarf, striped hat, round-rimmed glasses, or a cane, but only Waldo will have all of these features. As described July 22, 2019, in Nature Microbiology, a team led by scientists at the U.S. Department of Energy (DOE) Joint Genome Institute (JGI), a DOE Office of Science User Facility, developed an algorithm that a computer could use to conduct a similar type of search in microbial and metagenomic databases. In this case, the machine "learned" to identify a certain type of bacterial viruses or phages called inoviruses, which are filamentous viruses with small, single-stranded DNA genomes and a unique chronic infection cycle. "We're not sure why we systematically manage to miss them; maybe it's due to the way we currently isolate and extract viruses," said the study's lead author Simon Roux, a JGI research scientist in the Environmental Genomics group.

Patients in danger of dying from uncontrollable bacterial infections could find new allies: killer viruses known as phages. Armed with advances in DNA sequencing and artificial intelligence, a few startups are turning these natural enemies of bacteria into promising alternatives to antibiotics. Alternatives are desperately needed as more and more bacteria evolve resistance to the drugs we use today. Each year in the US, about two million people become infected with resistant bacteria, and at least 23,000 of those die from their infections. Resistance is much less likely to develop with phages, because each type of phage infects a specific type of bacteria.