报告人：Wengong Jin
时 间：2022/10/13 上午10:00
主持人：周冰心 博士
Abstract
Molecules and proteins are geometric objects, and their function relies on their structure (e.g., graph or 3D point cloud). The challenge of AI-driven molecular design includes prediction and generation. The prediction task (forward problem) aims to predict the property of a molecule/protein automatically based on its structure. The generation task (inverse problem) aims to generate molecules/proteins that have specific properties of interest.
In this talk, I will present how to use geometric/graph deep learning to accelerate molecular design. The first half of the talk will focus on small molecule drug discovery, i.e., how to build graph convolutional networks for property prediction and fragment-based generative models for the de novo drug design. The second half of the talk will focus on antibody engineering, i.e., how to build equivariant geometric deep learning models to dock antibodies onto an antigen epitope and generate CDR sequences that bind to the epitope.
Biography
Wengong Jin is a Postdoctoral Associate at Eric and Wendy Schmidt Center of Broad Institute. He finished his Ph.D. in MIT CSAIL, advised by Regina Barzilay and Tommi Jaakkola . His research seeks to develop novel machine learning algorithms for biology, including drug discovery, immunology, genetic engineering, and synthetic biology. He is particularly interested in deep generative models and graph neural networks.
PSJAS（PKU-SJTU Joint AI Seminar）
PSJAS由必赢71886网址登录必赢626net入口与上海交通大学自然科学研究院联合组织，是汇聚顶尖科学家的杰出系列讲座项目，旨在为人工智能的建模、理论与应用提供更有深度及广度的交流平台。本学期的主题方向是图神经网络和几何深度学习。
图神经网络和几何深度学习是近几年发展起来的深度学习方法，用于解决传统图片卷积神经网络无法有效学习的结构数据预测问题，例如药物分子设计、蛋白质结构预测、社交网络分析。2021 年，基于几何深度学习的AlphaFold 实现了对蛋白质结构的准确预测，准确率可以达到 95% 以上的实验室水平，一举破解了困扰学界长达五十年之久的“蛋白质折叠”难题。这项工作被 Science 评为 2021 年十大科学进展之最并获2023年的科学突破奖。图神经网络广泛应用于其他领域，例如它对一些数学定理的证明或发现起到了很好的作用，特别是去年发表在 Nature 上的一个用 GNN 辅助数学证明的算法，由 DeepMind 与几位科学家合作完成，引起了数学圈很大的轰动。几何深度学习作为人工智能国际前沿领域，已有诸多模型积累，然而理论基础仍很薄弱，而工业界的新挑战需要我们发展更具解释性、符合特殊应用的结构学习模型。本论坛邀请相关领域的国际知名学者、学术新星介绍几何深度学习的模型设计、数学理论和工业应用的最新进展。
PSJAS讲座项目亦纳入必赢71886网址登录必赢626net入口经纬论坛系列。
