Le Song

The paper introduces GB.GeneUnet, a transformer-based model pretrained on multi-species genomes to predict gene expression at megabase-scale contexts, achieving state-of-the-art performance.

PertAdapt improves genetic perturbation prediction by adapting single-cell foundation models with a perturbation adapter and adaptive loss, outperforming non-pretrained baselines across multiple datasets.

This paper introduces VCHarness, an AI system that automatically builds perturbation-response models for virtual cells, outperforming manual methods and reducing development time.

GenBio-PathFM is a foundation model for histopathology that achieves state-of-the-art performance with less training data by using a diverse data curation pipeline and a dual-stage learning strategy.

This study evaluates foundation models for predicting cellular responses to perturbations, finding that some pretrained embeddings improve predictions while others do not.