PHISDetector: a web tool to detect diverse in silico phage-host interaction signals
Zhang, F.; Zhou, F.; Gan, R.; Ren, C.; Jia, Y.; Yu, L.; Huang, Z.
Show abstract
Phage-microbe interactions not only are appealing systems to study coevolution but also have been increasingly emphasized due to their roles in human health, diseases, and novel therapeutic development. Meanwhile, their interactions leave diverse signals in bacterial and phage genomic sequences, defined as phage-host interaction signals (PHISs), such as sequence composition, CRISPR targeting, prophage, and protein-protein interaction signals. We infer that proper detection and integration of these diverse PHISs will allow us to predict phage-host interactions. Here, we developed PHISDetector, a novel tool to predict phage-host interactions by detecting and integrating diverse in silico PHISs and scoring the probability of phage-host interactions using machine-learning models based on PHIS features. PHISDetector is available as a one-stop web service version for general users to study individual inputs. A stand-alone software version is also provided to process massive phage contigs from virome studies. PHISDetector is freely available at http://www.microbiome-bigdata.com/PHISDetector/ and https://github.com/HIT-ImmunologyLab/PHISDector.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- VIBES: A Workflow for Annotating and Visualizing Viral Sequences Integrated into Bacterial Genomes 96%
- SYNTERUPTOR: mining genomic islands for non-classical specialised metabolite gene clusters 94%
- Estimating Assembly Base Errors Using K-mer Abundance Difference (KAD) Between Short Reads and Genome Assembled Sequences 94%
Similar papers in this journal
- Unveiling the Microbial Realm with VEBA 2.0: A modular bioinformatics suite for end-to-end genome-resolved prokaryotic, (micro)eukaryotic, and viral multi-omics from either short- or long-read sequencing 94%
- A new framework for SubtiWiki, the database for the model organism Bacillus subtilis 94%
- BGCFlow: Systematic pangenome workflow for the analysis of biosynthetic gene clusters across large genomic datasets 94%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
- Identifying Genomic Islands with Deep Neural Networks 96%
- OpenGenomeBrowser: A versatile, dataset-independent and scalable web platform for genome data management and comparative genomics 95%
- Isolation and Characterization of a Roseophage Representing a Novel Genus in the N4-like Rhodovirinae Subfamily Distributed in Estuarine Waters 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.