Machine-learning assisted design principle search for singlet fission: an example study of cibalackrot
Machine-learning assisted design principle search for singlet fission: an example study of cibalackrot
复制标题
DOI：
10.1038/s41524-022-00860-1
复制
发表时间：
2022-08
影响因子：
9.7
通讯作者：
Fabian Weber;H. Mori
中科院分区：
文献类型：
--
作者：
Fabian Weber;H. Mori
这项工作使用量子化学计算和机器学习来探索400万靛蓝衍生物的化学空间中单线态裂变的设计规则。我们确定了约400，000种2，2 ′-二乙烯基cibalackrot的衍生物，它们在理论上满足硅带隙能量以上的放能单线态裂变的能量条件。探索这个数据库与随机森林分类器，我们观察到，小取代基与积极的内消旋效应和弱的负诱导效应加强所需的能量条件时，放置在特定的位置。最后，一个子集的分子，反映了随机森林分类器的规则进行了调查，他们的量子化学性质的理想的结构图案转换成波函数为基础的设计规则。在这里，单重态裂变，双自由基字符和电荷和三重态自旋密度在突出的分子区域的能量条件之间的直接相关性被确定，提供的见解，可以作为指导单重态裂变核结构的发展。
This work uses quantum chemistry calculations and machine learning to explore design rules for singlet fission in a chemical space of four million indigoid derivatives. We identify ~400,000 derivatives of 2,2′-diethenyl cibalackrot, which theoretically fulfil the energy conditions for exoergic singlet fission above the silicon band gap energy. Probing this database with a random forest classifier, we observe that small substituents with positive mesomeric effects and weak negative inductive effects reinforce the desired energetic conditions when placed at specific positions. Finally, a subset of molecules that reflects the random forest classifier’s rules are investigated for their quantum chemical properties to translate the desirable structural motifs into wavefunction-based design rules. Here, direct correlations between the energetic condition for singlet fission, the biradical character and the charge and triplet spin density in prominent molecular regions are identified, providing insights that may serve as a guide for singlet fission core structure development.