Message passing neural networks have demonstrated significant efficacy in predicting molecular interactions. Introducing equivariant vectorial representations augments expressivity by capturing geometric data symmetries, thereby improving model accuracy. However, two-body bond vectors in opposition may cancel each other out during message passing, leading to the loss of directional information on their shared node. In this study, we develop Equivariant N-body Interaction Networks (ENINet) that explicitly integrates l = 1 equivariant many-body interactions to enhance directional symmetric information in the message passing scheme. We provided a mathematical analysis demonstrating the necessity of incorporating many-body equivariant interactions and generalized the formulation to N-body interactions. Experiments indicate that integrating many-body equivariant representations enhances prediction accuracy across diverse scalar and tensorial quantum chemical properties.

Self‐learning entropic population annealing (SLEPA) is a recently developed method used for achieving interpretable black‐box optimization via density‐of‐states estimation. Applying SLEPA to a chemical space is not straightforward, however, because of its dependence on Markov chain Monte Carlo sampling in the space of generated entities. Herein, SLEPA is applied to optimal molecule generation by combining an irreducible Markov chain in the space of fragment multisets and a probabilistic fragment assembler such as MoLeR. The weighted samples from SLEPA are used to identify salient fragments for the highest occupied molecular orbitals‐lowest unoccupied molecular orbitals (HOMO‐LUMO) gap maximization and minimization, and the relationship between the identified fragments and the electronic structures is elucidated. This approach offers a viable platform to reconcile the incompatible goals of optimization and interpretation during molecular design.

Self-learning entropic population annealing (SLEPA) is an interpretable method for materials design. It achieves efficient optimization without losing statistical consistency.

We report development of a new polymer electret CTX-A/APDEA based on Cyclic Transparent Optical Polymer (CYTOP, AGC Chemicals). With a 15-μm-thick film, the surface potential of the synthesized electret kept at -3 kV for more than 800 hours and the peak temperature under thermally stimulated discharge (TSD) measurement of it was 187 °C, which both outperformed all commercialized CYTOP polymer electrets. In our study, deep reinforcement learning is employed, where density functional theory (DFT) is used to characterize the material property and ChemTS is employed for exploring the unknown chemical space. Besides, functional group enrichment of the generated molecules is analyzed statistically for incorporating interpretable knowledge while solid-state quantum chemical analysis based on PCM-DFT is conducted for studying CTX-A/APDEA. Our results are the first to demonstrate the successful application of machine learning in polymer electret design and the combination of expert knowledge with artificial intelligence.

We designed a high-performance polymer electret material using a deep-learning-based de novo molecule generator. By statistically analyzing the enrichment of the functional groups of the generated molecules, the hydroxyl group was determined to be crucial for enhancing the electron gain energy. Incorporating such acquired knowledge, we designed a molecule using cyclic transparent optical polymer (CYTOP; perfluoro-3-butenyl-vinyl ether). The molecule was synthesized, and its surface potential for a 15-μm-thick film is kept at −3 kV for more than 800 h. Its performance was significantly better than all commercialized CYTOP polymer electrets, indicating great potential for its application in vibration-based energy harvesting. Our results demonstrate the application of machine learning in polymer electret design and confirm the combination of molecule generation and functional group enrichment analysis to be a promising chemical discovery method achieved via human–artificial intelligence collaboration.