The component parts of bacteriophage virions accurately defined by a machine-learning approach built on evolutionary features

Abstract

Antimicrobial resistance (AMR) continues to evolve as a major threat to human health and new strategies are required for the treatment of AMR infections. Bacteriophages (phages) that kill bacterial pathogens are being identified for use in phage therapies, with the intention to apply these bactericidal viruses directly into the infection sites in bespoke phage cocktails. Despite the great unsampled phage diversity for this purpose, an issue hampering the roll out of phage therapy is the poor quality annotation of many of the phage genomes, particularly for those from infrequently sampled environmental sources. We developed a computational tool called STEP3 to use the “evolutionary features” that can be recognized in genome sequences of diverse phages. These features, when integrated into an ensemble framework, achieved a stable and robust prediction performance when benchmarked against other prediction tools using phages from diverse sources. Validation of the prediction accuracy of STEP3 was conducted with high-resolution mass spectrometry analysis of two novel phages, isolated from a watercourse in the Southern Hemisphere. STEP3 provides a robust computational approach to distinguish specific and universal features in phages to improve the quality of phage cocktails, and is available for use at http://step3.erc.monash.edu/.IMPORTANCEIn response to the global problem of antimicrobial resistance there are moves to use bacteriophages (phages) as therapeutic agents. Selecting which phages will be effective therapeutics relies on interpreting features contributing to shelf-life and applicability to diagnosed infections. However, the protein components of the phage virions that dictate these properties vary so much in sequence that best estimates suggest failure to recognize up to 90% of them. We have utilised this diversity in evolutionary features as an advantage, to apply machine learning for prediction accuracy for diverse components in phage virions. We benchmark this new tool showing the accurate recognition and evaluation of phage components parts using genome sequence data of phages from under-sampled environments, where the richest diversity of phage still lies.

Mechanistic Insights into the Capsule-Targeting Depolymerase from a Klebsiella pneumoniae Bacteriophage

“…S1 at the URL mentioned above). The STEP 3 ( 20 ) predictor identified 25 protein components that would be present in the virion, including a putative depolymerase DpK2 ( gp02 ) (see Table S1 at the URL mentioned above). gp02 encodes the 98-kDa DpK2 protein, which has domain features similar to those found in proteins annotated as tailspike or tail-fiber depolymerase proteins (see Tables S2 and S3, respectively, at the URL mentioned above).…”

“…Screening of virion-associated and nonvirion proteins made use of STEP 3 ( 20 ), and protein sequence and domain analysis of each predicted RAD2 ORF was performed using BLAST and HMMer 3.3, respectively. Structural predictions were performed using HHpred ( 68 ) using the default settings.…”

“…Within this overall framework, homology-based features of depolymerase RBPs are somewhat varied, with seven different structural scaffolds described ( 12 , 18 , 19 ). However, there are often limitations with sequence-informed predictions, especially given the overall lack of sequence homology in virion components ( 20 ).…”

Micromonospora tarapacensis sp. nov., a bacterium isolated from a hypersaline lake

“…PHAge Search Tool Enhanced (PHASTER) [38] and Prophage Hunter [39] (with similarity matching) were used to detect and annotate prophage sequences within the genome assembly. Identified intact prophage regions annotated as coding for hypothetical proteins were additionally classified with machine-learning algorithms using the ensemble predictor STEP3 [40]. VIRFAM [41] was used for additional homology detection of viral protein superfamilies, complementing the classification and viral proteomic tree generation for the top 200 related phages with VipTree [42].…”