Machine learning discovery of high-temperature polymers.
Machine learning discovery of high-temperature polymers.
复制标题
DOI：
10.1016/j.patter.2021.100225
复制
发表时间：
2021-04-09
期刊：
影响因子：
--
通讯作者：
Li Y
中科院分区：
文献类型：
--
作者：
Tao L;Chen G;Li Y
为了建立一个机器学习(ML)模型来建立聚合物的玻璃化转变温度的结构-性能关联，我们从最大的聚合物数据库PoLyInfo收集了近13,000种真实均聚物的不同集合。我们使用这些聚合物的化学结构的摩根指纹表示来训练具有6923个实验值的深度神经网络(DNN)模型。有趣的是，与分子动力学模拟和实验结果相比，训练好的DNN模型可以合理地预测具有不同分子结构的聚合物的未知值。ML模型具有经过验证的可转移性和泛化能力，可用于对近一百万种假想聚合物进行高通量筛选。我们确定了65,000多个有希望的>；200°C候选聚合物，这是现有已知高温聚合物(来自PoLyInfo的∼2000)的30倍。这一大批有希望的候选材料的发现将对高温聚合物的开发和设计产生重大影响。收集了聚合物玻璃化转变温度的大数据集，ML模型的可转换性取决于特征表示。分子动力学模型和实验结果验证了所建立的ML模型的有效性，通过ML模型筛选出了具有广泛前景的高温聚合物候选者。高温聚合物的设计和开发一直是一个由经验、直觉和概念洞察力指导的实验驱动和反复尝试的过程。然而，这种爱迪生式的方法往往昂贵、缓慢、偏向于某些化学空间域，而且仅限于相对较小规模的研究，可能很容易错过有希望的化合物。为了克服这一挑战，我们提出了一种数据驱动的机器学习(ML)方法，与高保真分子动力学模拟相结合，用于根据聚合物的化学结构定量预测聚合物的玻璃化转变温度，并快速筛选出有希望的高温聚合物候选者。我们的工作表明，ML是一种预测和快速筛选高温聚合物的有效方法，特别是在聚合物材料的大量实验和计算数据不断增长的情况下。具有优异高温性能的聚合物已被认为是航空航天、电子和汽车应用的最有前途的材料。然而，目前高温聚合物的设计和开发一直是一个由经验、直觉和概念洞察力指导的实验驱动和反复尝试的过程。因此，我们建立了一个机器学习模型，可以根据聚合物的化学结构定量地预测其玻璃化转变温度，从而通过高通量筛选有效地筛选出更有前途的高温聚合物。
To formulate a machine learning (ML) model to establish the polymer's structure-property correlation for glass transition temperature , we collect a diverse set of nearly 13,000 real homopolymers from the largest polymer database, PoLyInfo. We train the deep neural network (DNN) model with 6,923 experimental values using Morgan fingerprint representations of chemical structures for these polymers. Interestingly, the trained DNN model can reasonably predict the unknown values of polymers with distinct molecular structures, in comparison with molecular dynamics simulations and experimental results. With the validated transferability and generalization ability, the ML model is utilized for high-throughput screening of nearly one million hypothetical polymers. We identify more than 65,000 promising candidates with > 200°C, which is 30 times more than existing known high-temperature polymers (∼2,000 from PoLyInfo). The discovery of this large number of promising candidates will be of significant interest in the development and design of high-temperature polymers. Large datasets for polymer's glass transition temperature are collected Transferability of ML models depends on feature representations Molecular dynamics models and experimental results validate the formulated ML model Extensive promising candidates for high-temperature polymers are screened by ML model The design and development of high-temperature polymers has been an experimentally driven and trial-and-error process guided by experience, intuition, and conceptual insights. However, such an Edisonian approach is often costly, slow, biased toward certain chemical space domains, and limited to relatively small-scale studies, which may easily miss promising compounds. To overcome this challenge, we formulate a data-driven machine learning (ML) approach, integrated with high-fidelity molecular dynamics simulations, for quantitatively predicting the glass transition temperature of a polymer from its chemical structure and rapid screening of promising candidates for high-temperature polymers. Our work demonstrates that ML is a powerful method for the prediction and rapid screening of high-temperature polymers, particularly with growing large sets of experimental and computational data for polymeric materials. Polymers with outstanding high-temperature properties have been identified as promising materials for aerospace, electronics, and automotive applications. However, the current design and development of high-temperature polymers has been an experimentally driven and trial-and-error process guided by experience, intuition, and conceptual insights. Therefore, we formulate a machine learning model that can quantitatively predict the glass transition temperature of a polymer from its chemical structure, such that more promising high-temperature polymers can be efficiently filtered out through high-throughput screening.
登录
查看更多内容
影响因子：
18.2
作者：
Gómez-Bombarelli R;Wei JN;Duvenaud D;Hernández-Lobato JM;Sánchez-Lengeling B;Sheberla D;Aguilera-Iparraguirre J;Hirzel TD;Adams RP;Aspuru-Guzik A
通讯作者：
Aspuru-Guzik A
影响因子：
3.2
作者：
FOX, TG;FLORY, PJ
通讯作者：
FLORY, PJ
影响因子：
13.6
作者：
Barnett, J. Wesley;Bilchak, Connor R.;Kumar, Sanat K.
通讯作者：
Kumar, Sanat K.
影响因子：
3.3
作者：
Dudowicz, J;Freed, KF;Douglas, JF
通讯作者：
Douglas, JF
DOI：
10.1007/978-3-030-40245-7_18
发表时间：
2020-01-01
期刊：
MACHINE LEARNING MEETS QUANTUM PHYSICS
影响因子：
--
作者：
Chandrasekaran, Anand;Kim, Chiho;Ramprasad, Rampi
通讯作者：
Ramprasad, Rampi