Kaiwen Deng

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.

GRASP improves gene network inference using LLMs by adapting prompts to gene pairs, outperforming other strategies and recovering unannotated interactions.

The paper identifies a lipid metabolism defect as a contributor to variable anemia in Diamond Blackfan anemia syndrome using a murine model and transcriptomic analysis.

A NeurIPS 2021 benchmarking competition evaluated over 2600 submissions from 280 competitors across three multimodal single-cell integration tasks using a purpose-built benchmarking dataset and cloud evaluation pipeline.