arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.06017cond-mat.mtrl-sci
收藏

解析过渡金属化学空间:用于机器学习和结构-性质关系的特征选择

Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships

Jon Paul Janet, Heather J. Kulik

摘要:

量子力学性质的机器学习(ML)显示出加速化学发现的希望。对于过渡金属化学,精确计算的计算成本很高,可用的训练数据集很小,分子表示成为ML模型预测准确性的关键因素。我们引入了一系列修正的自相关函数(RAC),这些自相关函数对启发式原子属性(例如,大小、连接性和电负性)。我们改变了标准AC中评估的数量的起点、范围和性质,以使这些RAC适合无机化学。在有机分子集上,我们首先展示了优于ML模型训练的其他现有拓扑描述符的标准AC性能,其中搁置测试分子的原子化能量的平均无符号误差(MUE)低至6 kcal/mol。对于无机化学,我们的RAC在自旋态分裂中在搁置的测试分子上产生1 kcal/mol ML MUE,与编码全分子结构信息的特征集相比,误差高15- 20倍。系统特征选择方法包括单变量滤波、递归特征消除和直接优化(例如,随机森林和LASSO)进行比较。比RAC-155小4- 5倍的随机森林或LASSO选择的子集产生亚至1 kcal/mol的自旋分裂MUE,具有良好的可转移性,可用于金属配体键长预测(0.004-5 eV MUE)和较小数据集上的氧化还原电位(0.2-0.3 eV MUE)。跨属性集的特征选择结果的评估揭示了本地电子描述符(例如,电负性、原子序数)以及氧化还原电位和键长中的远端、空间效应。

英文摘要:

Machine learning (ML) of quantum mechanical properties shows promise for accelerating chemical discovery. For transition metal chemistry where accurate calculations are computationally costly and available training data sets are small, the molecular representation becomes a critical ingredient in ML model predictive accuracy. We introduce a series of revised autocorrelation functions (RACs) that encode relationships between the heuristic atomic properties (e.g., size, connectivity, and electronegativity) on a molecular graph. We alter the starting point, scope, and nature of the quantities evaluated in standard ACs to make these RACs amenable to inorganic chemistry. On an organic molecule set, we first demonstrate superior standard AC performance to other presently-available topological descriptors for ML model training, with mean unsigned errors (MUEs) for atomization energies on set-aside test molecules as low as 6 kcal/mol. For inorganic chemistry, our RACs yield 1 kcal/mol ML MUEs on set-aside test molecules in spin-state splitting in comparison to 15-20x higher errors from feature sets that encode whole-molecule structural information. Systematic feature selection methods including univariate filtering, recursive feature elimination, and direct optimization (e.g., random forest and LASSO) are compared. Random-forest- or LASSO-selected subsets 4-5x smaller than RAC-155 produce sub- to 1-kcal/mol spin-splitting MUEs, with good transferability to metal-ligand bond length prediction (0.004-5 Å MUE) and redox potential on a smaller data set (0.2-0.3 eV MUE). Evaluation of feature selection results across property sets reveals the relative importance of local, electronic descriptors (e.g., electronegativity, atomic number) in spin-splitting and distal, steric effects in redox potential and bond lengths.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑