Benjamin Bolduc

CheckAMG identifies auxiliary viral genes by combining annotation-based prediction with a genome-language model, improving accuracy and uncovering novel genes with no sequence similarity to references.

This paper organizes a community challenge to develop automated virus taxonomy classification tools and evaluates their performance on a combined dataset of expert-curated and metagenomic sequences.

The paper introduces vConTACT3, a machine learning tool that improves virus taxonomy classification, scalability, and accuracy, and identifies taxonomic issues across the virosphere.

The paper uses remote sensing and machine learning to upscale methane emissions from Arctic wetlands and improves isotope estimates in global methane source partitioning.

The paper identifies and characterizes RNA viruses in permafrost soil over four years, showing their diversity is structured by habitat and linked to greenhouse gas emissions.

kb_DRAM integrates DRAM tools into KBase for microbial and viral genome annotation and metabolic modeling through a user-friendly interface.

MetaPop analyzes and visualizes microbial and viral metagenome-derived populations at macro- and micro-diversity levels, revealing lower viral nucleotide diversity in autistic children.

A human gut virome reference catalog compiled from 648 metagenomes identifies 13,203 viral populations across 702 previously uncharacterized genera, boosting viral detection nearly 60-fold over NCBI viral RefSeq.

This paper introduces vConTACT 2.0, a network-based tool for prokaryotic virus taxonomy that scales to large datasets and achieves high accuracy in taxonomic assignments.

iVirus provides a centralized resource with tools and datasets for viromics analysis to study viral ecology.