Charting the virosphere: computational synergies of AI and bioinformatics in viral discovery and evolution

ABSTRACT The advancement of metagenomic sequencing has revealed a vast viral diversity while simultaneously exposing limitations of homology-based tools such as BLAST and HMMER, which often fail to detect highly divergent viral genomes. The integration of artificial intelligence (AI) into viromics has transformed this landscape, introducing machine learning and deep learning models—including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers—that extend viral discovery beyond sequence similarity constraints. Structure-based frameworks such as AlphaFold, ESMFold, and Foldseek further enable annotation of divergent viral proteins through conserved 3D folds, while graph neural networks (GNNs) model host-virus interaction and explainable AI enhances interpretability of prediction. Despite their high sensitivity and scalability, AI-driven approaches face notable challenges: computational burden, data set bias, limited explainability, and elevated false discovery rates. This review traces the evolution of computational virology from traditional methods to AI-based and hybrid frameworks. We examine landmark AI tools while underscoring the continuing importance of phylogenetics and functional annotation in contextualizing AI predictions. We propose an integrated workflow that combines AI pattern recognition with classical bioinformatics to enhance both scalability and interpretability. By addressing the limitations of solely AI-driven or traditional approaches, this review presents a unified computational strategy to accelerate viral discovery, enhance evolutionary insights, and strengthen global preparedness for emerging infectious diseases.

• Publication year

  2025

• Venue

  Journal of Virology

• Publication date

  2025-11-12

• Fields of study

  Biology, Medicine, Computer Science

• Identifiers
  DOI 10.1128/jvi.01554-25PMID 41222234PMCID 12724264
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Machine learning algorithms to predict the risk of admission to intensive care units in HIV-infected individuals: a single-centre study

  2025cited by this paper
• Overcoming diagnostic and data privacy challenges in viral disease detection: an integrated approach using generative AI, vision transformers, explainable AI, and federated learning

  2025cited by this paper
• Viromics approaches for the study of viral diversity and ecology in microbiomes

  2025cited by this paper
• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification

  2025cited by this paper
• AlphaFold 3: an unprecedent opportunity for fundamental research and drug development

  2025cited by this paper
• Interpreting Attention Mechanisms in Genomic Transformer Models: A Framework for Biological Insights

  2025cited by this paper
• The hidden Markov model and its applications in bioinformatics analysis

  2025cited by this paper
• Evaluating the Trade-offs Between Machine Learning and Deep Learning: A Multi-Dimensional Analysis

  2025cited by this paper
• Using artificial intelligence to document the hidden RNA virosphere

  2024cited by this paper
• Deep learning methods in metagenomics: a review

  2024cited by this paper
• Beyond traditional analytics: Exploring hybrid deep learning architectures for scalable data analysis

  2024cited by this paper
• The protein structurome of Orthornavirae and its dark matter

  2024cited by this paper
• GRAViTy-V2: a grounded viral taxonomy application

  2024cited by this paper
• Comparative Analyses of Bacteriophage Genomes.

  2024cited by this paper
• LSTM-based recurrent neural network provides effective short term flu forecasting

  2023cited by this paper
• HostNet: improved sequence representation in deep neural networks for virus-host prediction

  2023cited by this paper
• Virus-host interactions predictor (VHIP): Machine learning approach to resolve microbial virus-host interaction networks

  2023cited by this paper
• Transforming clinical virology with AI, machine learning and deep learning: a comprehensive review and outlook

  2023cited by this paper
• MetaTransformer: deep metagenomic sequencing read classification using self-attention models

  2023cited by this paper
• MArVD2: a machine learning enhanced tool to discriminate between archaeal and bacterial viruses in viral datasets

  2023cited by this paper
• Deep learning methods in metagenomics: a review

  2023cited by this paper
• Editorial: Predicting virus evolution: from genome evolution to epidemiological trends

  2023cited by this paper
• Using AlphaFold Predictions in Viral Research

  2023cited by this paper
• Environmental viromes reveal global virosphere of deep-sea sediment RNA viruses

  2023cited by this paper
• CGXplain: Rule-Based Deep Neural Network Explanations Using Dual Linear Programs

  2023cited by this paper
• Applications of transformer-based language models in bioinformatics: a survey

  2023cited by this paper
• HoCoRT: host contamination removal tool

  2023cited by this paper
• IMG/VR v4: an expanded database of uncultivated virus genomes within a framework of extensive functional, taxonomic, and ecological metadata

  2022cited by this paper
• Evolutionary-scale prediction of atomic level protein structure with a language model

  2022cited by this paper
• Expansion of the global RNA virome reveals diverse clades of bacteriophages.

  2022cited by this paper
• Unraveling the viral dark matter through viral metagenomics

  2022cited by this paper
• VIRify: An integrated detection, annotation and taxonomic classification pipeline using virus-specific protein profile hidden Markov models

  2022cited by this paper
• Virus finding tools: current solutions and limitations

  2022cited by this paper
• Performance of Five Metagenomic Classifiers for Virus Pathogen Detection Using Respiratory Samples from a Clinical Cohort

  2022cited by this paper
• A Glimpse on the Evolution of RNA Viruses: Implications and Lessons from SARS-CoV-2

  2022cited by this paper
• Fast and accurate protein structure search with Foldseek

  2022cited by this paper
• Sensitive protein alignments at tree-of-life scale using DIAMOND

  2021cited by this paper
• Transformer in Transformer

  2021cited by this paper
• vRhyme enables binning of viral genomes from metagenomes

  2021cited by this paper
• Bacteriophage classification for assembled contigs using graph convolutional network

  2021influential reference
• High Throughput Sequencing for the Detection and Characterization of RNA Viruses

  2021cited by this paper
• AlphaFold2 and the future of structural biology

  2021cited by this paper
• Highly accurate protein structure prediction with AlphaFold

  2021cited by this paper
• Benchmark of thirteen bioinformatic pipelines for metagenomic virus diagnostics using datasets from clinical samples.

  2021cited by this paper
• The Illumina Sequencing Protocol and the NovaSeq 6000 System.

  2021cited by this paper
• Machine learning and deep learning

  2021cited by this paper
• VirSorter2: a multi-classifier, expert-guided approach to detect diverse DNA and RNA viruses

  2021cited by this paper
• The Short- and Long-Range RNA-RNA Interactome of SARS-CoV-2

  2020cited by this paper
• Identifying viruses from metagenomic data using deep learning

  2020cited by this paper
• BERTology Meets Biology: Interpreting Attention in Protein Language Models

  2020cited by this paper
• VIRIDIC—A Novel Tool to Calculate the Intergenomic Similarities of Prokaryote-Infecting Viruses

  2020cited by this paper
• Predicting the animal hosts of coronaviruses from compositional biases of spike protein and whole genome sequences through machine learning

  2020cited by this paper
• RNN-VirSeeker: A Deep Learning Method for Identification of Short Viral Sequences From Metagenomes

  2020cited by this paper
• Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI

  2019cited by this paper
• MGnify: the microbiome analysis resource in 2020

  2019cited by this paper
• Recurrent Neural Networks (RNNs): A gentle Introduction and Overview

  2019cited by this paper
• Deep learning: new computational modelling techniques for genomics

  2019cited by this paper
• A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

  2019cited by this paper
• Advances in structure-assisted antiviral discovery for animal viral diseases

  2019cited by this paper
• HMMER web server: 2018 update

  2018cited by this paper
• RAxML-NG: a fast, scalable and user-friendly tool for maximum likelihood phylogenetic inference

  2018cited by this paper
• The diversity, evolution and origins of vertebrate RNA viruses

  2018cited by this paper
• Clustal Omega for making accurate alignments of many protein sequences

  2018cited by this paper
• VirFinder: a novel k-mer based tool for identifying viral sequences from assembled metagenomic data

  2017cited by this paper
• Origins and challenges of viral dark matter.

  2017cited by this paper
• Comprehensive benchmarking and ensemble approaches for metagenomic classifiers

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• Dilated Convolutions for Modeling Long-Distance Genomic Dependencies

  2017cited by this paper
• VICTOR: genome-based phylogeny and classification of prokaryotic viruses

  2017cited by this paper
• Axiomatic Attribution for Deep Networks

  2017cited by this paper
• Computational biology in the 21st century

  2016cited by this paper
• MEGAHIT v1.0: A fast and scalable metagenome assembler driven by advanced methodologies and community practices.

  2016cited by this paper
• Uncovering Earth’s virome

  2016cited by this paper
• DanQ: a hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences

  2015cited by this paper
• An Introduction to Convolutional Neural Networks

  2015cited by this paper
• The structure and functions of coronavirus genomic 3′ and 5′ ends

  2015cited by this paper
• Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning

  2015cited by this paper
• IQ-TREE: A Fast and Effective Stochastic Algorithm for Estimating Maximum-Likelihood Phylogenies

  2014cited by this paper
• SortMeRNA: fast and accurate filtering of ribosomal RNAs in metatranscriptomic data

  2012cited by this paper
• SPAdes: A New Genome Assembly Algorithm and Its Applications to Single-Cell Sequencing

  2012cited by this paper
• Field guide to next‐generation DNA sequencers

  2011cited by this paper
• ViPR: an open bioinformatics database and analysis resource for virology research

  2011cited by this paper
• New algorithms and methods to estimate maximum-likelihood phylogenies: assessing the performance of PhyML 3.0.

  2010cited by this paper
• FastTree 2 – Approximately Maximum-Likelihood Trees for Large Alignments

  2010cited by this paper
• The Graph Neural Network Model

  2009cited by this paper
• Multiple alignment of DNA sequences with MAFFT.

  2009cited by this paper
• Genetic Detection and Characterization of Lujo Virus, a New Hemorrhagic Fever–Associated Arenavirus from Southern Africa

  2009cited by this paper
• Modern Uses of Electron Microscopy for Detection of Viruses

  2009cited by this paper
• Viral metagenomics

  2007cited by this paper
• Assembling Genomic DNA Sequences with PHRAP

  2007cited by this paper
• A Metagenomic Survey of Microbes in Honey Bee Colony Collapse Disorder

  2007cited by this paper
• Characterization and Complete Genome Sequence of a Novel Coronavirus, Coronavirus HKU1, from Patients with Pneumonia

  2005cited by this paper
• RNA Viral Community in Human Feces: Prevalence of Plant Pathogenic Viruses

  2005cited by this paper
• Viral metagenomics

  2005cited by this paper
• Programmed ribosomal frameshifting in HIV-1 and the SARS–CoV

  2005cited by this paper
• The Pfam protein families database

  2004cited by this paper
• Multiple Sequence Alignment Using ClustalW and ClustalX

  2003cited by this paper
• InterProScan - an integration platform for the signature-recognition methods in InterPro

  2001cited by this paper
• Base-calling of automated sequencer traces using phred. I. Accuracy assessment.

  1998cited by this paper
• Structure and Classification of Viruses

  1996cited by this paper

• No citing papers are available for this paper.