Rapid discovery of novel prophages using biological feature engineering and machine learning

Abstract

Prophages are phages that are integrated into bacterial genomes and which are key to understanding many aspects of bacterial biology. Their extreme diversity means they are challenging to detect using sequence similarity, yet this remains the paradigm and thus many phages remain unidentified. We present a novel, fast and generalizing machine learning method based on feature space to facilitate novel prophage discovery. To validate the approach, we reanalyzed publicly available marine viromes and single-cell genomes using our feature-based approaches and found consistently more phages than were detected using current state-of-the-art tools while being notably faster. This demonstrates that our approach significantly enhances bacteriophage discovery and thus provides a new starting point for exploring new biologies.

Philympics 2021: Prophage Predictions Perplex Programs

“…Two—ProphET (Reis-Cunha et al, 2019) and LysoPhD (Niu et al, 2019) —could not be successfully installed and were not included in the current framework (see below). The remaining eight PhiSpy (Akhter et al, 2012), Phage Finder (Fouts, 2006), VIBRANT (Kieft et al, 2020), VirSorter (Roux et al, 2015), Virsorter2 (Guo et al, 2021), Phigaro (Starikova et al, 2020), PhageBoost (Sirén et al, 2021), and DBSCAN-SWA (Gan et al, 2020) were each used to predict the prophages in 49 different manually curated microbial genomes.…”

Genetic determinants of host tropism in Klebsiella phages

“… 81 https://github.com/iqtree/iqtree2 PhageBoost Sirén et al. 82 https://github.com/ku-cbd/PhageBoost CRISPRCasTyper Russel et al. 83 https://crisprcas.i2bc.paris-saclay.fr/Home/Download defense-finder Tesson et al.…”

Bacteriophages playing nice: Lysogenic bacteriophage replication stable in the human gut microbiota

“…2020 67 github.com/AnantharamanLab/VIBRANT PhageBoost V.0.1.7 Sirén et al. 2020 68 github.com/ku-cbd/PhageBoost mVIR V.1.0.0 Zund et al. 2021 69 github.com/SushiLab/mVIRs PropagAtE V.1.0.0 Kieft et al.…”

“…An overview of the analytical pipeline for the detection of phage contigs and active prophages is provided in Figure S1 B. Prophages were detected within bacterial bins by combining various tools: PHASTER, 66 VIRSorter (V.1.0.6), 49 VIBRANT (V.1.2.1), 67 PhageBoost (V.0.1.7), 68 and mVIR (V.1.0.0). 69 We also used a custom alignment method, where we aligned the viral reads to each bacterial bin using bowtie2 (V.2.3.5.1), then used samtools mpileup to calculate coverage per base (with default perimeters).…”