Exploring Chemical Space with Score-based Out-of-distribution Generation
Seul Lee Jaehyeong Jo Sung Ju Hwang
Abstract
A well-known limitation of existing molecular generative models is that the generated molecules highly resemble those in the training set. To generate truly novel molecules that may have even better properties for de novo drug discovery, more powerful exploration in the chemical space is necessary. To this end, we propose Molecular Out-Of-distribution Diffusion (MOOD), a score-based diffusion scheme that incorporates out-of-distribution (OOD) control in the generative stochastic differential equation (SDE) with simple control of a hyperparameter, thus requires no additional costs. Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor that guides the reverse-time diffusion process to high-scoring regions according to target properties such as protein-ligand interactions, drug-likeness, and synthesizability. This allows MOOD to search for novel and meaningful molecules rather than generating unseen yet trivial ones. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones fou
中文速览
现有分子生成模型总是"抄近路"——生成的分子和训练集高度相似，难以发现真正新颖的药物候选结构。为此，研究者提出了MOOD（分子分布外扩散，Molecular Out-Of-distribution Diffusion），在基于分数的扩散生成框架中引入一个简单的超参数λ来控制生成分子偏离训练分布的程度，让模型主动探索化学空间中的"未知领域"，且无需额外计算开销。为避免偏离分布后产生化学上不合理或无药用价值的分子，MOOD同时利用性质预测网络的梯度引导采样过程，使生成分子在"新颖"的同时也满足蛋白质-配体结合亲和力、类药性和可合成性等多项约束。实验表明，MOOD在五个蛋白靶点的分子优化任务上全面超越现有最优方法，甚至能发现结合亲和力超过训练集前0.01%的全新分子——这对于从头药物设计（de novo drug discovery）具有重要意义，证明扩散模型结合分布外控制可以真正突破已知化学空间的边界。
原文 arXiv:2206.07632;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2206.07632v3