Researchers have introduced GP-GPT, a large language model specifically designed for mapping gene-phenotype associations. This model has been fine-tuned with over 3 million genomics and medical genetics terms, excelling at analyzing complex gene-phenotype relationships. Additionally, a new paper discusses pangenome-informed language models for privacy-preserving synthetic genome sequence generation. The paper introduces two novel tokenization schemes: Pangenome-based Node Tokenization (PNT) and Pangenome-based k-mer tokenization. These methods utilize pangenome graphs to enhance the generation of synthetic DNA data. The research also highlights the use of Pretrained-Language Models for improved privacy-preserving measures.