通过去噪体素网格生成3D分子

摘要

我们提出了一种基于评分的新方法，用于生成以原子密度在规则网格上表示的3D分子。首先，我们训练了一个去噪神经网络，该网络学习将具有噪声分子的平滑分布映射到真实分子的分布。然后，我们遵循神经经验贝叶斯框架[Saremi和Hyvarinen，2019]，并分两步生成分子：(i)通过欠阻尼朗之万格维金马尔可夫链蒙特卡洛从平滑分布中对噪声密度网格进行采样，(ii)通过一步去噪处理从噪声网格中恢复“干净”的分子。我们的方法VoxMol以一种基本不同于当前技术水平（即应用于原子点云的扩散模型）的方式生成分子。它在数据表示、噪声模型、网络架构和生成建模算法方面有所不同。VoxMol在无条件的3D分子生成方面取得了与技术水平相媲美的结果，同时训练更简单，生成速度更快。

English

We propose a new score-based approach to generate 3D molecules represented as atomic densities on regular grids. First, we train a denoising neural network that learns to map from a smooth distribution of noisy molecules to the distribution of real molecules. Then, we follow the neural empirical Bayes framework [Saremi and Hyvarinen, 2019] and generate molecules in two steps: (i) sample noisy density grids from a smooth distribution via underdamped Langevin Markov chain Monte Carlo, and (ii) recover the ``clean'' molecule by denoising the noisy grid with a single step. Our method, VoxMol, generates molecules in a fundamentally different way than the current state of the art (i.e., diffusion models applied to atom point clouds). It differs in terms of the data representation, the noise model, the network architecture and the generative modeling algorithm. VoxMol achieves comparable results to state of the art on unconditional 3D molecule generation while being simpler to train and faster to generate molecules.

通过去噪体素网格生成3D分子

3D molecule generation by denoising voxel grids

摘要

Support