Computational Approach for Molecular Design of Small Organic Molecules with High Hole Mobilities in Amorphous Phase using Random Forest Technique and Computer Simulation Method

The molecular design system of small organic molecules was developed to realize high hole mobility in the amorphous phase by using the random forest technique and the computer simulation method. Since there was no accessible datasets of the hole mobilities in the amorphous phase, we have constructed a datasets of experimental hole mobilities for 321 organic molecules with calculated MO energies to utilize machine learning techniques for molecular generation procedures. Random forest (RF) was applied to the machine learning technique using the constructed datasets. The optimized RF with 69 structure-based descriptors exhibited correlation coefficients of 0.885 and 0.764 for the training and testing datasets, respectively. RF confirmed that molecules with two triphenylamine (TPA) and/or carbazole groups are likely to display high hole mobilities according to the topological polar surface area (TPSA). The modified ChemTS to use optimized RF was adapted to design molecules with high hole mobilities. The SC model that uses ab initio molecular orbital (MO) calculations and the Marcus theory was adapted to ensure the predicted mobilities. The generated molecules were verified to have high calculated hole mobility (the order of \({10}^{-2} \text{c}{\text{m}}^{2}/\text{V}\text{s})\) owing to the high transfer integral and low reorganization energy by the successive conduction (SC) model. The datasets and programs used to design molecules in this manuscript were publicity released on GitHub.