CheckAMG: Accurate Identification of Auxiliary Viral Genes with Genome-Language Models
- 1University of Wisconsin-Madison
Abstract
Viruses shape microbial metabolism through auxiliary viral genes (AVGs) that reprogram host metabolism, physiology, and gene regulation during infection. Identifying AVGs is complicated by ambiguous viral versus cellular assignment, inconsistent curation, and reliance on sequence homology that misses divergent functions. Here we present CheckAMG, which pairs annotation-based AVG prediction, curated with a per-gene viral scoring system and ontological mapping of metabolic function, with a finetuned genome-language model for annotation-independent discovery. Benchmarked against DRAM-V and VIBRANT across three ecosystems, CheckAMG produced more strongly supported auxiliary metabolic gene (AMG) calls, and uniquely among AMG tools reports auxiliary physiological (APGs) and regulatory (AReGs) genes. Applied to 1,005,980 fragmented or complete soil and human-gut viral genomes, CheckAMG identified 541,199 AVGs tracking biome-specific protein clusters and functions, including 109,107 proteins with no detectable sequence similarity to any reference database. CheckAMG thus provides a reproducible, scalable framework for identifying the genes through which viruses reprogram host biology.
Related
- Informed forecasting: Leveraging auxiliary knowledge to boost large language model performance on time series forecasting
- SpaMOAL is a deep learning method that enables accurate spatial domain identification from multi-omics data
- T2G: fast and accurate transcriptome to genome BAM liftover for short and long read RNA sequencing
- EM3DFold: accurate de novo protein and nucleic acid model building for cryo-EM maps using language model-powered deep learning
- Accurate automated photo-identification of Near Eastern and European fire salamanders
BibTeX
@misc{kosmopoulos2026checkamg,
title = {{CheckAMG: Accurate Identification of Auxiliary Viral Genes with Genome-Language Models}},
author = {J. C. Kosmopoulos and C. Martin and J. M. Wainaina and B. Bolduc and M. Urvoy and M. B. Sullivan and K. Anantharaman},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.23.753886},
url = {https://www.biorxiv.org/content/10.64898/2026.09.23.753886v1},
note = {CC BY-NC},
}
RIS
TY - UNPB
TI - CheckAMG: Accurate Identification of Auxiliary Viral Genes with Genome-Language Models
AU - J. C. Kosmopoulos
AU - C. Martin
AU - J. M. Wainaina
AU - B. Bolduc
AU - M. Urvoy
AU - M. B. Sullivan
AU - K. Anantharaman
PY - 2026
DA - 2026/09/23
PB - bioRxiv
DO - 10.64898/2026.09.23.753886
UR - https://www.biorxiv.org/content/10.64898/2026.09.23.753886v1
AB - Viruses shape microbial metabolism through auxiliary viral genes (AVGs) that reprogram host metabolism, physiology, and gene regulation during infection. Identifying AVGs is complicated by ambiguous viral versus cellular assignment, inconsistent curation, and reliance on sequence homology that misses divergent functions. Here we present CheckAMG, which pairs annotation-based AVG prediction, curated with a per-gene viral scoring system and ontological mapping of metabolic function, with a finetuned genome-language model for annotation-independent discovery. Benchmarked against DRAM-V and VIBRANT across three ecosystems, CheckAMG produced more strongly supported auxiliary metabolic gene (AMG) calls, and uniquely among AMG tools reports auxiliary physiological (APGs) and regulatory (AReGs) genes. Applied to 1,005,980 fragmented or complete soil and human-gut viral genomes, CheckAMG identified 541,199 AVGs tracking biome-specific protein clusters and functions, including 109,107 proteins with no detectable sequence similarity to any reference database. CheckAMG thus provides a reproducible, scalable framework for identifying the genes through which viruses reprogram host biology.
ER -