Article

vir2vec: A Viral Genome-Wide Viral Embedding

2025-12-13

Abstract excerpt

Genomic language models (gLMs) have recently emerged as powerful numerical surrogates for DNA, but existing architectures are largely focused on human DNA or trained on limited viral references, and no dedicated benchmark currently exists for viral genome understanding. Here we introduce vir2vec, a 422-million-parameter, decoder-only gLM obtained by continual pretraining of Mistral-DNA on a rigorously curated pan-...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 92812cbe-31de-5a70-9df8-3181c8603550
DOI: 10.64898/2025.12.12.693901

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

vir2vec: A Viral Genome-Wide Viral EmbeddingDOI 10.64898/2025.12.12.693901Read

HViLM: A Foundation Model for Viral Genomics Enables Multi-Task Prediction of Pathogenicity, Transmissibility, and Host TropismSemantic proximity Read

Illuminating the Virosphere’s Dark Matter using Hierarchical Deep LearningSemantic proximity Read

Fine-Tuning Protein Language Models Unlocks the Potential of Underrepresented Viral ProteomesSemantic proximity Read

Genomic Touchstone: Benchmarking Genomic Language Models in the Context of the Central DogmaSemantic proximity Read

Benchmarking DNA Foundation Models for Genomic and Genetic TasksSemantic proximity Read

LAMBDA: A Prophage Detection Benchmark for Genomic Language ModelsSemantic proximity Read

GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamicsSemantic proximity Read

Interpretable detection of novel human viruses from genome sequencing dataSemantic proximity Read

METAGENE-1: Metagenomic Foundation Model for Pandemic MonitoringSemantic proximity Read

Enhancing Recognition and Interpretation of Functional Phenotypic Sequences through Fine-Tuning Pre-Trained Genomic ModelsSemantic proximity Read

DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genomeSemantic proximity Read

Safeguarding open-weight genomic foundation models through weight lockingSemantic proximity Read