High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV
Genome Research · 2026
DOI: 10.1101/gr.281341.125 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genome Research, 2026. Verfasst von Herui Liao und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Medical Engineering and Sciences, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA. Hauptthemen laut MEDLINE: Deep Learning, Polymorphism, Single Nucleotide, Genome, Bacterial, Bacteria. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIGMS NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Accurate detection of mutations within bacterial species is critical for fundamental studies of microbial evolution, reconstruction of transmission events, and identification of antimicrobial resistance mutations. Although many tools have been developed to identify single-nucleotide variants (SNVs) from whole-genome sequencing, they often suffer from high false-positive rates owing to the complexity of bacterial genomes and the need for different filtering cutoffs across sample types and sequencing depths. As data sets increase in size, the manual filtering required for high accuracy presents a significant obstacle. Here, we present AccuSNV, a novel deep learning–based tool for high-precision and automated bacterial SNV calling. Unlike traditional methods that process one sample at a time, AccuSNV leverages a convolutional neural network (CNN) that integrates alignment information across multiple samples, enhancing precision through learned across-sample patterns. We evaluate AccuSNV against seven popular SNV-calling tools using simulated data from six bacterial species with varied sequencing depths, numbers of isolates, mutations, and divergence levels. To further validate its real-world utility, we test AccuSNV on multiple curated bacterial data sets containing reported SNVs. In both simulated and real-world scenarios, AccuSNV consistently achieves the best performance. Moreover, AccuSNV provides comprehensive user-friendly downstream analysis modules and outputs, including mutation annotation information, phylogenetic inference, d N / d S calculations, and optional manual filtering. Together with the automated deep learning–based calling, these features make AccuSNV broadly accessible to users with different levels of computational expertise.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Institute for Medical Engineering and Sciences, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.
- Department of Civil and Environmental Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA.
- Max Planck Institute for Infection Biology, 10117 Berlin, Germany.
- Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany.
- Humboldt-Universität zu Berlin, Faculty of Life Sciences, 10099 Berlin, Germany.
- Institute for Medical Engineering and Sciences, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA; tami@mit.edu.
Förderung
- NIGMS NIH HHS
- National Institutes of Health
Zitieren
APA
Liao, H., Conwill, A., Light-Maka, I., Fenk, M., Mitchell, A. H., Qu, E. B., Torrillo, P., Baker, J. S., Bartsch, L. R., Key, F. M., & Lieberman, T. D. (2026). High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV. Genome Research. https://doi.org/10.1101/gr.281341.125
Vancouver
Liao H, Conwill A, Light-Maka I, Fenk M, Mitchell AH, Qu EB, et al. High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV. Genome Research. 2026. doi:10.1101/gr.281341.125
BibTeX
@article{Liao2026,
author = {Liao, Herui and Conwill, Arolyn and Light-Maka, Ian and Fenk, Martin and Mitchell, Alyssa H and Qu, Evan B and Torrillo, Paul and Baker, Jacob S and Bartsch, Lilly R and Key, Felix M and Lieberman, Tami D},
title = {High-accuracy SNV calling for bacterial isolates using deep learning with AccuSNV},
journal = {Genome Research},
year = {2026},
doi = {10.1101/gr.281341.125}
}
EUVIMED