主持人：吕晖 教授

报告时间：2026年10月22日（周四）下午 13：00

报告地点：闵行校区生物药学楼树华厅

个人简介：

Alex Bateman is Senior Team Leader for Protein Sequence Resources at EMBL's European Bioinformatics Institute (EMBL-EBI), where he leads the Pfam, InterPro, Rfam and RNAcentral databases, with the goal of completely and accurately classifying protein and non-coding RNA sequences. He joined the Pfam project in 1997 and led it for over two decades at the Wellcome Sanger Institute before moving to EMBL-EBI in 2012, and has pioneered the integration of AlphaFold structure predictions and deep learning methods into large-scale protein family classification. He is Vice President of the International Society for Computational Biology (ISCB) and Editor-in-Chief of its journal Bioinformatics Advances. He was elected a Fellow of ISCB in 2019 and a member of EMBO in 2021.

报告摘要：

We are living through a revolution in AI approaches that is transforming how we classify and annotate the protein universe. In this talk I will describe how we are using AI to transform proteins resources such as UniProt, Pfam and InterPro at EMBL-EBI. I will explore use cases of bespoke Deep Learning models for identifying protein domains and families. I will describe the ways we are using LLMs to extract knowledge from the scientific literature to write detailed annotation about proteins. We have also revisited the age old protein of sequence and structure alignment using Deep Learning and have begun to identify new distant evolutionary relationships between proteins. Finally, I will step back to consider foundation models in biology more broadly. Compared to frontier text LLMs, biological foundation models remain small, and I will discuss what the cost and compute needed to train them mean for the future of the field.

欢迎感兴趣的师生扫码报名（截止时间为9月21日中午12点前）