The meeting focused on Professor Yiliang Ding’s research on RNA structures and the integration of AI, particularly foundation models, in advancing plant science and genetic variation studies.

Paul Shaw introduced Professor Yiliang Ding, highlighting her focus on RNA structure and functionality in cells.
Yiliang Ding discussed developing tools for studying RNA structures over the past eleven years.
She emphasized the importance of RNA structures in regulating transcription, splicing, and translation efficiency.
The presentation included findings on a specific RNA tertiary structure, the gcodial plax, and its role under stress conditions.
Research indicated that gcodial plax formation stabilizes RNA during cold stress in plants.
AI adoption in research, particularly using foundation models like GPT, is becoming widespread.
Foundation models enable self-learning from large datasets without extensive labeling.
Pre-training allows for the identification of important sequences and motifs affecting translation efficiency.
The model can predict gene expression impacts based on structural and sequence features.
Continuous updates to knowledge graphs enhance research capabilities in plant science.
Open-source platforms facilitate collaborative contributions and ongoing learning in the scientific community.
Foundation models tolerate data noise better than deep learning, requiring less labeled data for effective learning.
The team explores genetic variation in crops, aiming to address limitations in current population-based research methods.