Reorganization Energy Predictions with Graph Neural Networks Informed by Low-Cost Conformers
Reorganization Energy Predictions with Graph Neural Networks Informed by Low-Cost Conformers
复制标题
DOI：
10.1021/acs.jpca.2c09030
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Cheng-Han Li;Daniel P. Tabor
中科院分区：
文献类型：
--
作者：
Cheng-Han Li;Daniel P. Tabor
设计高导电性有机材料的一个关键瓶颈是找到具有低重组能的分子。为了对多种类型的有机电子材料开展高通量虚拟筛选活动，需要一种相较于密度泛函理论更快的重组能预测方法。然而，开发用于计算重组能的低成本基于机器学习的模型已被证明具有挑战性。在本文中，我们将一种最近在药物设计应用中经过基准测试的基于3D图的神经网络（GNN）——ChIRo，与用于重组能预测的低成本构象特征相结合。通过将ChIRo与另一种3D GNN——SchNet的性能进行比较，我们发现有证据表明ChIRo的键不变特性使该模型能够更有效地从低成本构象特征中学习。通过对一种2D GNN进行消融研究，我们发现，在2D特征的基础上使用低成本构象特征可以为模型提供更准确预测的信息。我们的结果证明了在基准QM9数据集上进行重组能预测的可行性，且无需密度泛函理论（DFT）优化的几何结构，并展示了在不同化学空间中有效工作的稳健模型所需的特征类型。此外，我们表明，结合低成本构象特征的ChIRo在π -共轭烃分子上取得了与先前报道的基于结构的模型相当的性能。我们期望这类方法能够应用于高导电性有机电子候选材料的高通量筛选。
A critical bottleneck for the design of high-conductivity organic materials is finding molecules with low reorganization energy. To enable high-throughput virtual screening campaigns for many types of organic electronic materials, a fast reorganization energy prediction method compared to density functional theory is needed. However, the development of low-cost machine-learning-based models for calculating the reorganization energy has proven to be challenging. In this paper, we combine a 3D graph-based neural network (GNN) recently benchmarked for drug design applications, ChIRo, with low-cost conformational features for reorganization energy predictions. By comparing the performance of ChIRo to another 3D GNN, SchNet, we find evidence that the bond-invariant property of ChIRo enables the model to learn from low-cost conformational features more efficiently. Through an ablation study with a 2D GNN, we find that using low-cost conformational features on top of 2D features informs the model for making more accurate predictions. Our results demonstrate the feasibility of reorganization energy predictions on the benchmark QM9 data set without needing DFT-optimized geometries and demonstrate the types of features needed for robust models that work on diverse chemical spaces. Furthermore, we show that ChIRo informed with low-cost conformational features achieves comparable performance with the previously reported structure-based model on π-conjugated hydrocarbon molecules. We expect this class of methods can be applied to the high-throughput screening of high-conductivity organic electronics candidates.