Le Song

EpiBinder predicts cell-type-specific TF binding by integrating DNA sequence and epigenetic data, improving prediction accuracy and providing interpretability.

AIDO.ModelGenerator enables rapid, reproducible multimodal foundation model development by integrating datasets, pre-trained models, and experiment recipes to improve biological predictions.

This paper introduces AIDO.DNA, a DNA language model that improves representation of DNA sequences across multiple tasks by scaling model size and training data.

This paper introduces AIDO.RNA, a large-scale foundation model for RNA function and structure prediction, achieving state-of-the-art performance on multiple tasks.

AttentionPert predicts gene expression under multiplexed genetic perturbations and generalizes to unseen conditions, outperforming existing methods in accuracy and handling diverse perturbations.