Structure-based models in the molecular sciences can be highly sensitive to input geometries and give predictions with large variance under subtle coordinate perturbations. We present an approach to mitigate this failure mode by generating conformations that explicitly minimize uncertainty in a predictive model. To achieve this, we compute differentiable estimates of aleatoric \textit{and} epistemic uncertainties directly from learned embeddings. We then train an optimizer that iteratively samples embeddings to reduce these uncertainties according to their gradients. As our predictive model is constructed as a variational autoencoder, the new embeddings can be decoded to their corresponding inputs, which we call \textit{MoleCLUEs}, or (molecular) counterfactual latent uncertainty explanations \citep{antoran2020getting}. We provide results of our algorithm for the task of predicting drug properties with maximum confidence as well as analysis of the differentiable structure simulations.

翻译：基于结构的分子科学模型对输入几何形状高度敏感，且在轻微坐标扰动下会产生较大方差预测。我们提出一种方法，通过生成显式最小化预测模型不确定性的构象来缓解这一失效模式。为实现该目标，我们直接从学习到的嵌入中计算偶然不确定性和认知不确定性的可微估计，随后训练一个优化器，根据梯度迭代采样嵌入以降低这些不确定性。由于预测模型被构建为变分自编码器，新的嵌入可解码为对应输入——我们称之为MoleCLUEs（分子反事实潜在不确定性解释）\citep{antoran2020getting}。我们提供了该算法在最大置信度预测药物性质任务中的结果，并对可微结构模拟进行了分析。