Understanding the evolution of a de novo molecule generator via characteristic functional group monitoring

Abstract

Recently, artificial intelligence (AI)-enabled de novo molecular generators (DNMGs) have automated molecular design based on data-driven or simulation-based property estimates. In some domains like the game of Go where AI surpassed human intelligence, humans are trying to learn from AI about the best strategy of the game. To understand DNMG’s strategy of molecule optimization, we propose an algorithm called characteristic functional group monitoring (CFGM). Given a time series of generated molecules, CFGM monitors statistically enriched functional groups in comparison to the training data. In the task of absorption wavelength maximization of pure organic molecules (consisting of H, C, N, and O), we successfully identified a strategic change from diketone and aniline derivatives to quinone derivatives. In addition, CFGM led us to a hypothesis that 1,2-quinone is an unconventional chromophore, which was verified with chemical synthesis. This study shows the possibility that human experts can learn from DNMGs to expand their ability to discover functional molecules.

Koopmans’ Theorem-Compliant Long-Range Corrected (KTLC) Density Functional Mediated by Black-Box Optimization and Data-Driven Prediction for Organic Molecules

“…Because the theories in quantum chemistry are not perfect, quantum chemistry is in a constant state of development, because of its predictive role. DFT is also not an exception, although it has successfully designed real-world compounds de novo with the aid of artificial intelligence. − In the case of DFT, the exact functional that is effective across universal problems has not yet been found. Hence, we use the approximately parametrized functionals whose parameters are usually fixed to constant values.…”

QCforever: Quantum chemistry for everyone

“…Combining QCforever with the black-box optimization algorithm, we can remove this restriction and bias and expand the search space. [27][28][29][30][31][32]…”

“…Combining a deep learning based de novo molecule generator (DNMG) 26 with machine learning and QCforever, we have successfully demonstrated that molecules designed in silico for optical absorption/emission can be realized experimentally. [27][28][29] In addition, the DNMG proposed to use an material that had never received attention as an electret material. 30 The DNMG becomes a molecular identifier by setting the computed property by QCforever NMR spectrum.…”

QCforever: A Quantum Chemistry Wrapper for Everyone to Use in Black-Box Optimization

“…Using QCforever combined the black-box optimization algorithms for discovering and designing materials, we have already reported several results. Combining a deep learning-based de novo molecule generator (DNMG) with QCforever, we have successfully demonstrated that molecules designed in silico for optical absorption/emission can be realized experimentally. − In addition, the DNMG proposed to use a material that had never received attention as an electret material . The DNMG becomes a molecular identifier by setting the computed property by QCforever NMR spectrum .…”