Donghui Li

The paper introduces TranscriptFormer, a generative model trained on 112 million cells across 12 species, demonstrating cross-species cell type classification and disease state prediction.

VariantFormer predicts gene expression from diploid genomes, outperforming existing models and improving eQTL effect size estimation across ancestries and tissues.

This paper introduces rbio1, a biology reasoning model trained using soft verification via biological world models, achieving state-of-the-art performance on perturbation prediction.

The paper shows that combining language-based gene representations with experimental data improves perturbation prediction in single-cell data.

The paper describes a crowdsourcing initiative, CACAO, where undergraduates contribute gene function annotations to the Gene Ontology, enhancing coverage and enabling community-driven curation.