Computer aided molecular design coupled to deep learning techniques as a less-expensive approach to design organic photoredox catalysts

To date, the prediction of electronic absorption spectra of organic molecules by computational chemistry methods is still limited, with differences of even 100 nm between the theoretical and experimental values, often at relatively high computational cost. In this work, we present a computationally cheaper approach for the design of new molecules that may be candidates for organic photoredox catalysts based on the prediction of their absorbance in the visible region of the electromagnetic spectrum. This problem is important to promote the development and use of solar energy in chemical processes, as an exemplary application. The design of new chromophoric molecules is approached as a two-step procedure. In the first step, a Mixed-Integer Nonlinear Programming (MINLP) model was formulated for the In-silico design of organic chromophores. A quantitative structure–activity relationship model was developed for the prediction of the difference in energy from the HOMO to the LUMO orbitals of organic dyes. This molecular design approach produced 4 molecules, where 3 have not been previously reported. In the second step, a large chemical compound database was leveraged to develop a deep learning model aimed at forecasting the absorption of visible light by such and related compounds. We have taken advantage of the deep learning model to verify that the light absorption between this model and the results of the MINLP formulation match with reasonable accuracy. For 3 of the 4 molecules, both results appear similar, allowing to verify that the molecules could in fact offer the desired absorbance at the target wavelength. •A novel way to integrate traditional MINLP and Machine Learning tools is provided.•The proposed methodology can be used for the initial design of new materials.•Our methodology identifies 3 new molecules for their intended purposes.•Large data bases comprising QM were used to screening analysis of promising molecules•The methodology can incorporate Bayesian optimization for new materials design.