We investigate the impact of choosing regressors and molecular representations for the construction of fast machine learning (ML) models of thirteen electronic ground-state properties of organic molecules. The performance of each regressor/representation/property combination is assessed using learning curves which report out-of-sample errors as a function of training set size with up to $\sim$117k distinct molecules. Molecular structures and properties at hybrid density functional theory (DFT) level of theory used for training and testing come from the QM9 database [Ramakrishnan et al, {\em Scientific Data} {\bf 1} 140022 (2014)] and include dipole moment, polarizability, HOMO/LUMO energies and gap, electronic spatial extent, zero point vibrational energy, enthalpies and free energies of atomization, heat capacity and the highest fundamental vibrational frequency. Various representations from the literature have been studied (Coulomb matrix, bag of bonds, BAML and ECFP4, molecular graphs (MG)), as well as newly developed distribution based variants including histograms of distances (HD), and angles (HDA/MARAD), and dihedrals (HDAD). Regressors include linear models (Bayesian ridge regression (BR) and linear regression with elastic net regularization (EN)), random forest (RF), kernel ridge regression (KRR) and two types of neural net works, graph convolutions (GC) and gated graph networks (GG). We present numerical evidence that ML model predictions deviate from DFT less than DFT deviates from experiment for all properties. Furthermore, our out-of-sample prediction errors with respect to hybrid DFT reference are on par with, or close to, chemical accuracy. Our findings suggest that ML models could be more accurate than hybrid DFT if explicitly electron correlated quantum (or experimental) data was available.
翻译:我们调查了在构建13个有机分子电子地面状态特性的快速机器学习模型时选择递增器和分子表示法的影响。每个递减/代表/财产组合的性能都使用学习曲线进行评估,该曲线报告出样错误,作为培训设置规模的函数,最高为$sim 117k不同的分子。在混合密度功能理论(DFT)水平上,分子结构和特性用于培训和测试的理论来自QM9数据库[Ramakrishnan, Excial Data}, bf scial data 1} 140022(2014)],其中包括dipoole 时刻、极易变、HOM/LUMOO能量和差距、电子空间范围、零点振动能量、热容量和最基本振动频率。研究了各种文献表达法(Coulombmetrom、债券袋、BAML和ECF4分子图(MG),以及两个新开发的以内部货币递增量(Oral-ral-ral oral),包括OD-ral 直径直径直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直径、直、直、直、直、直方、直径、直径、直方、直、直、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、直方、