Speaker：Ziyu Chen（陈子玉）Junhan Chang（昌珺涵）Yichen Wang（王依琛）

Time：10:00 - 13:00

Abstract

With the boosting development of deep learning method, traditional computational methods in learning protein-molecule interaction(like predicting dynamic docking behavior around the meeting face) is being revolutionized. As an important building block of nowadays deep learning techniques, generative model is well-known for its probable explanatory power. Just as Feynman said,” “What I cannot create, I do not understand”. In the last few years, a variety of deep generative models have been proposed for modeling molecules, which differ in both their model structure and choice of input features. These models have been applied to numerous classes of materials: rational design of prospective drugs, synthetic routes to organic compounds, and optimization of photovoltaics and redox flow batteries, as well as a variety of other solid-state materials.

Guest information:

1. Dr. Jianfeng Pei (PKU)

http://cqb.pku.edu.cn/kxdw/zxjs/pjf/253431.shtml

1. Xu, Youjun, et al. "Deep learning for molecular generation." Future medicinal chemistry 0 (2019).

Link: https://doi.org/10.4155/fmc-2018-0358

1. Jin, Wengong, Regina Barzilay, and Tommi Jaakkola. "Junction tree variational autoencoder for molecular graph generation." arXiv preprint arXiv:1802.04364 (2018).

Link: https://arxiv.org/abs/1802.04364

2. Sanchez-Lengeling, Benjamin, et al. "Optimizing distributions over molecular space. An objective-reinforced generative adversarial network for inverse-design chemistry (ORGANIC)." Harvard University, Chem Rxiv (2017).

DOI: 10.26434/chemrxiv.5309668