Energy Gaps and Bacteriochlorophyll Molecular Graph Representation Based on Machine Learning Algorithm.

Abstract

Light harvesting applications have proven to be highly valuable in various fields such as photovoltaics, photo catalysis, and photo polymerization. When bacteriochlorophyll is manipulated at the molecular level, it opens up numerous possibilities for improving its physical and chemical properties for harvesting light. . In their research study, the authors suggest using molecular graph representations from the Computational Material Repository (CMR) dataset to forecast the energy gaps of bacteriochlorophyll. The electro-topological-state index is the description for the molecular network that the authors choose expressly. The physical configuration of carbon in methane bonds associated to the attached group, as found by the authors, has a considerable impact on the energy gaps of bacteriochlorophyll. This observation is consistent with the three-dimensional diffusion patterns of the molecule's leading-edge molecular orbitals, as predicted by quantum mechanical calculations.