GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
Chence Shi*1, Minkai Xu*2, Zhaocheng Zhu3,4, Weinan Zhang2, Ming Zhang1, Jian Tang3,5,6 1Department of Computer Science, Peking University, China 2Shanghai Jiao Tong University, China 3Mila - Québec AI Institute, Canada 4Université de Montréal, Canada 5HEC Montréal, Canada 6CIFAR AI Research Chair
Abstract
Molecular graph generation is a fundamental problem for drug discovery and has been attracting growing attention. The problem is challenging since it requires not only generating chemically valid molecular structures but also optimizing their chemical properties in the meantime. Inspired by the recent progress in deep generative models, in this paper we propose a flow-based autoregressive model for graph generation called GraphAF. GraphAF combines the advantages of both autoregressive and flow-based approaches and enjoys: (1) high model flexibility for data density estimation; (2) efficient parallel computation for training; (3) an iterative sampling process, which allows leveraging chemical domain knowledge for valency checking. Experimental results show that GraphAF is able to generate 68% chemically valid molecules even without chemical knowledge rules and 100% valid molecules with chemical rules. The training process of GraphAF is two times faster than the existing state-of-the-art approach GCPN. After fine-tuning the model for goal-directed property optimization with reinforcement learning, GraphAF achieves state-of-the-art performance on both chemical property optimization an
中文速览
药物分子的从头设计需要在庞大的化学空间里同时保证结构合法性和优化分子性质，现有自回归模型训练慢、流模型又难以逐步校验化学规则。GraphAF把自回归模型与标准化流（normalizing flow）结合起来：采样时像自回归模型一样逐步生成原子和化学键，每步都能检查化合价规则；训练时利用流模型的可逆映射把整张图一次性并行投影到高斯隐空间，从而精确计算数据似然。在ZINC数据集上，GraphAF训练速度是当时最优模型GCPN的两倍，加入化学规则后生成分子100%合法，即便不加规则合法率也高达68%；进一步用强化学习微调后，在分子性质优化和约束性质优化两项任务上均超越了此前所有方法。这项工作为分子生成提供了一个既高效又灵活、还能融入领域知识的新框架，对计算机辅助药物设计具有实际意义。
原文 arXiv:2001.09382;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2001.09382v2