Predicting glass transition temperature and melting point of organic compounds via machine learning and molecular embeddings
Predicting glass transition temperature and melting point of organic compounds via machine learning and molecular embeddings
复制标题
DOI：
10.1039/d1ea00090j
复制
发表时间：
2022-05-01
期刊：
影响因子：
--
通讯作者：
Shiraiwa, Manabu
中科院分区：
文献类型：
--
作者：
Galeazzo, Tommaso;Shiraiwa, Manabu
二次有机气溶胶的气-粒分配受颗粒相态和粘度的影响，这可以从组成有机化合物的玻璃化转变温度（T-g）推断。开发了几种参数化方法来预测基于分子性质和元素组成的有机化合物的Tg，但它们受到相对较大的不确定性，因为它们不考虑分子结构和功能。在这里，我们开发了一种新的T-g预测方法，该方法由机器学习和“分子嵌入”提供支持，这是化学化合物的独特数值表示，保留了有关其结构，原子间连接性和功能的信息。我们已经在有机化合物的实验T-g及其相应的分子嵌入数据库上训练了多个最先进的机器学习模型。最佳预测模型是使用通过嵌套交叉验证方法训练的极端梯度提升（XGBoost）回归器构建的tgBoost模型，该模型非常好地再现了实验数据，平均绝对误差为18.3 K。它还可以量化官能团的数量和位置对有机分子的T-g的影响，同时考虑原子连接性并预测组成异构体的不同T-g。tgBoost模型表明，T-g对官能团添加的敏感性有以下趋势：-COOH（羧酸）> -C（=O）OR（酯）接近-OH（醇）> -C（=O）R（酮）接近-COR（醚）接近-C（=O）H（醛）。我们还开发了一个模型，通过在实验T-m的大数据集上训练深度神经网络来预测有机化合物的熔点（T-m）。该模型对可用数据集的平均绝对误差为31.0 K。这些新的机器学习动力模型可以应用于现场和实验室测量以及大气气溶胶模型，以预测SOA化合物的T-g和T-m，用于评估SOA的相态和粘度。
Gas-particle partitioning of secondary organic aerosols is impacted by particle phase state and viscosity, which can be inferred from the glass transition temperature (T-g) of the constituting organic compounds. Several parametrizations were developed to predict T-g of organic compounds based on molecular properties and elemental composition, but they are subject to relatively large uncertainties as they do not account for molecular structure and functionality. Here we develop a new T-g prediction method powered by machine learning and "molecular embeddings", which are unique numerical representations of chemical compounds that retain information on their structure, inter atomic connectivity and functionality. We have trained multiple state-of-the-art machine learning models on databases of experimental T-g of organic compounds and their corresponding molecular embeddings. The best prediction model is the tgBoost model built with an Extreme Gradient Boosting (XGBoost) regressor trained via a nested cross-validation method, reproducing experimental data very well with a mean absolute error of 18.3 K. It can also quantify the influence of number and location of functional groups on the T-g of organic molecules, while accounting for atom connectivity and predicting different T-g for compositional isomers. The tgBoost model suggests the following trend for sensitivity of T-g to functional group addition: -COOH(carboxylic acid) > -C(=O)OR (ester) approximate to -OH (alcohol) > -C(=O)R (ketone) approximate to -COR (ether) approximate to -C(=O)H (aldehyde). We also developed a model to predict the melting point (T-m) of organic compounds by training a deep neural network on a large dataset of experimental T-m. The model performs reasonably well against the available dataset with a mean absolute error of 31.0 K. These new machine learning powered models can be applied to field and laboratory measurements as well as atmospheric aerosol models to predict the T-g and T-m of SOA compounds for evaluation of the phase state and viscosity of SOA.