Interpretable Deep-Learning Unveils Structure–Property Relationships in Polybenzenoid Hydrocarbons

Abstract

In this work, interpretable deep learning was used to identify structure−property relationships governing the HOMO− LUMO gap and the relative stability of polybenzenoid hydrocarbons (PBHs) using a ring-based graph representation. This representation was combined with a subunit-based perception of PBHs, allowing chemical insights to be presented in terms of intuitive and simple structural motifs. The resulting insights agree with conventional organic chemistry knowledge and electronic structure-based analyses and also reveal new behaviors and identify influential structural motifs. In particular, we evaluated and compared the effects of linear, angular, and branching motifs on these two molecular properties and explored the role of dispersion in mitigating the torsional strain inherent in nonplanar PBHs. Hence, the observed regularities and the proposed analysis contribute to a deeper understanding of the behavior of PBHs and form the foundation for design strategies for new functional PBHs.

COMPAS-3: a dataset of peri-condensed polybenzenoid hydrocarbons

“…73 We previously benchmarked methods for identification of diradical character and established a threshold of N FOD = 1.3 as the cutoff value (we refer the reader to the ESI of ref. 63). Thus, molecules with N FOD ≥ 1.3 were removed from the COMPAS-3 datasets, providing a final tally of 39 482 molecules.…”

“…The first installment, COMPAS-1, 60 focuses on ground-state cata -condensed polybenzenoid hydrocarbons; the second installment, COMPAS-2, 61 focuses on ground-state cata -condensed heterocyclic PASs. COMPAS-1 and COMPAS-2 have already been used to provide the first examples of interpretable machine and deep-learning models for PASs 62,63 and to demonstrate the first generative design of PASs with targeted properties. 64 Both datasets, as well as all future installments, are freely available for use, according to the FAIR 65 principles of data sharing.…”

Effect of Benzo‐Annelation on Triplet State Energies in Polycyclic Conjugated Hydrocarbons

“…Along these lines, it is worth mentioning the work of Gershoni-Poranne and her coworkers who significantly contributed to better understanding of the relationship between aromaticity and linear and angular topologies. [17,29,41,42] The benzo-annelation effect on the aromaticity in conjugated molecules was first examined for their ground singlet electronic states. However, there are several recent papers [26,29,[43][44][45] in which the benzo-annelation strategy was used as a tool to adjust aromaticity and other properties of the first excited triplet state of the so-called aromatic chameleons, [46] which are molecules able to adjust their πelectron distributions so to maximize their aromaticity in different electronic states.…”

“…However, the regularities obtained at the HMO level were corroborated at the level of ab initio calculations, by employing different aromaticity indices which measure electronic, [36] geometric [30,34,36] and magnetic [38–40] aspects of aromaticity. Along these lines, it is worth mentioning the work of Gershoni‐Poranne and her coworkers who significantly contributed to better understanding of the relationship between aromaticity and linear and angular topologies [17,29,41,42] …”

COMPAS-3: a Data Set of peri-Condensed Polybenzenoid Hydrocarbons

“…The first installment, COMPAS-1, 60 focuses on groundstate cata-condensed Polybenzenoid Hydrocarbons; the second installment, COMPAS-2, 61 focuses on ground-state cata-condensed heterocyclic PASs. COMPAS-1 and COMPAS-2 have already been used to provide the first examples of interpretable machine and deeplearning models for PASs 62,63 and to demonstrate the first generative design of PASs with targeted properties. 64 Both data, as well as all future installments, are freely available for use, according to the FAIR 65 principles of data sharing.…”