Zhaorong Li

Contrasting a pretrained genomic language model's attention between case and control haplotypes ranked HBB first on chromosome 11 and recovered more known β-thalassemia variants than GWAS, without per-variant tests.

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.

OneGenome-Rice (OGR) is a genomic foundation model for rice pre-trained on 422 genomes, outperforming existing models in 11 tasks and enabling downstream applications like trait analysis and gene expression prediction.

Genos-m is a foundation model for human-associated microbial genomes that outperforms existing models in gene-fitness prediction and community structure analysis.

This paper introduces fluProfiler, a framework using viral sequences to predict antigenic relationships and improve vaccine strain selection by reducing reliance on time-consuming HI assays.

This paper benchmarks the Evo2 genomic AI model in cancer genomics, showing FP8 precision on H800 GPUs improves inference speed and accuracy, while larger models perform worse on non-FP8 hardware.

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.

This paper introduces FluAdaX, a deep learning framework to predict influenza A virus cross-species transmission potential using genomic data, identifying key genes and variants associated with host adaptation.

This study uses a protein language model to discover new phosphorus-cycling protein families in deep-sea cold seep sediments, revealing novel microbial processes and ecological roles.

This study identifies 742 RNA virus species in Lake Nam Co, revealing novel viral groups and evolutionary adaptations in an extreme high-altitude environment.

This paper introduces BIA, an intelligent agent using LLMs to automate bioinformatics tasks, demonstrating its effectiveness with scRNA-seq data and outlining strategies for improvement.

AnnoPRO improves protein function annotation by using image-like representations and multimodal deep learning, showing better performance for rare protein families.