Revealing Structure-Property Relationships in Polybenzenoid Hydrocarbons with Interpretable Machine-Learning

Abstract

The structure-property relationships of polybenzenoid hydrocarbons (PBHs) were investigated with interpretable machine learning, for which two new tools were developed and applied. First, a novel textual molecular representation, based on the annulation sequence of PBHs was defined and developed. This representation can be used either in its textual form or as a basis for a curated feature-vector; both forms show improved interpretability over the standard SMILES representation, and the former also has increased predictive accuracy. Second, the recently-developed model, CUSTODI, was applied for the first time as an interpretable model and identified important structural features that impact various electronic molecular properties. The resulting insights not only validate several well-known “rules of thumb” of organic chemistry but also reveal new behaviors and influential structural motifs, thus providing guiding principles for rational design and fine-tuning of PBHs.

The COMPAS Project: A Computational Database of Polycyclic Aromatic Systems. Phase 1: cata-Condensed Polybenzenoid Hydrocarbons

“…Our group has performed additional investigations of the data contained in the COMPAS-1x and COMPAS-1D data sets to probe the structure−property relationships of these molecules using both interpretable ML 59 and interpretable DL techniques. 60 In addition, we are currently analyzing the aromatic character of these molecules using a wide variety of aromaticity indices.…”

Excited‐state aromaticity and antiaromaticity special issue

“…Looking at the dication and dianion of corannulene, Aleksić et al [ 7 ] find that the dianion in its triplet state has a Baird‐aromatic rim. Fite et al [ 8 ] report on a text‐based machine‐learning approach for polybenzenoid hydrocarbons and reveal new interesting structure–property relationships.…”