Yongtao Shan

LucaVirus predicts viral evolution and function using a unified nucleotide-protein language model, achieving state-of-the-art results in key virology tasks.

LucaPhylo infers phylogenetic trees from unaligned protein sequences using hyperbolic geometry and protein language models, achieving accuracy comparable to alignment-based methods for divergent RNA viruses.

SegFinder identifies RNA virus genome segments by analyzing co-occurrence across samples, discovering novel segments and expanding known segmented virus families.

This paper introduces LucaOne, a foundation model trained on nucleic acid and protein sequences, demonstrating understanding of biological principles and performing well on related tasks.

The paper identifies 162 viral species in small mammals from Yunnan, China, including 102 novel species and 24 with potential human health risks.

VirID improves RNA virus discovery and characterization from metagenomic data by reducing false positives, accurately estimating diversity, and identifying virus-host associations.