Search

A web-based tool for identifying and annotating prophage sequences within bacterial genomes; Web server for identification and annotation of prophages in bacterial genomes and metagenomes

Phage prediction by Hidden Markov Model annotation and smoothing window algorithm mand GC content to predict prophage regions.

Uses several interaction signals, including CRISPR and protein–protein interaction, to predict novel phage–host pairings

A 3-class classifier that allows identification of phages from metagenomic assemblies with enhanced performance for short fragments Deep learning CNN approach to identify both phages and plasmids

Allows simultaneous extraction of high-quality DNA and RNA from biological material

Represents a complete set of orthologous gene families shared across multiple complete genomes of bacterial or archaeal viruses

Deep learning framework that uses Long Short -Term Memory models (LSTM) which does not depend on sequence motifs.

A public webserver that provides information about the virus orthologous groups

An automated tool that uses a hybrid machine-learning and protein-similarity approach to recover and annotate viruses of microbes Deep learning neural network based on protein signatures which also highlights auxiliary metabolic genes and

Pipeline for virus identification by nucleotide and remote amino acid comparisons; multiple k-mer de novo assembly; and phylogeny.

Extension of DeepVirFinder that is trained to identify any virus that may colonise human samples.

A novel k-mer-based tool that identifies viral sequences from assembled metagenomic data; K-mer based machine learning method for identification of viral contigs.

Uses similar oligonucleotide frequency patterns between phages and bacteria to predict host range for phages on a genus level

Uses a combination of nucleotide and protein signals to taxonomically classify viral sequences independently of genome coverage or read overlap; Creates “super-scaffolds” from de novo assembly and a mapping assembly and taxonomically class

Can identify viral genomes from collective raw reads within metagenomes of different environments; Iterative pipeline that relies on the abundance of non-viral sequences in databases to strictly filter out unwanted contigs. Pipeline accept

Web-based pipeline that handles genome assembly, functional annotation using a variety of databases and identification of phage contigs via a random forest algorithm

Deep learning neural network using an attentional neural model trained on nucleotide viral fragments.

Web-based pipeline that classifies viral sequences based on homology to databases and functional annotates them.

Screens metagenomic reads against complete viral genome database before being filtered and then screen against the same database again. Provides viral hit counts and relative abundance.