Speaker: Prof. Shirui Pan, Griffith University

Inviter: 周川副研究员

Title: Decoding Scientific Knowledge from Sequence Data: from GNNs to LLMs

Language: Chinese

Time & Venue: 2024.09.25 15：00-16：00 腾讯会议：838-740-338

Abstract: Sequence data is widely used across various scientific domains. This talk will explore how sequence data can be harnessed to gain valuable scientific insights, transforming fields such as drug discovery. It will introduce PSICHIC, a novel graph neural network (GNN) model that predicts protein interactions and binding affinity using only sequence data, eliminating the need for expensive structural information. The talk will also discuss the application of large language models (LLMs) to autonomously discover new scientific insights across different fields, such as biophysics and physiology. With advanced GNN and LLM methods, we can unlock the vast potential of sequence data for significant benefits.