This review explores machine learning's role in energy chemistry, spanning organic photovoltaics, perovskites, catalysis, and batteries, highlighting its potential to accelerate eco-friendly, sustainable energy development.

The rapid progression of machine learning, especially deep learning (DL), has catalyzed a new era in drug discovery, introducing innovative approaches for predicting molecular properties. Despite the many methods available for feature representation, efficiently utilizing rich, high-dimensional information remains a significant challenge. Our work introduces ChemXTree, a novel graph-based model that integrates a Gate Modulation Feature Unit (GMFU) and neural decision tree (NDT) in the output layer to address this challenge. Extensive evaluations on benchmark data sets, including MoleculeNet and eight additional drug databases, have demonstrated ChemXTree's superior performance, surpassing or matching the current state-of-the-art models. Visualization techniques clearly demonstrate that ChemXTree significantly improves the separation between substrates and nonsubstrates in the latent space. In summary, ChemXTree demonstrates a promising approach for integrating advanced feature extraction with neural decision trees, offering significant improvements in predictive accuracy for drug discovery tasks and opening new avenues for optimizing molecular properties.

Designing organic fluorescent molecules with tailored optical properties has been a long-standing challenge. Recently, statistical models have opened new avenues for tackling this problem. Inverse design has attracted considerable attention in organic materials science; however, most existing approaches focus on arbitrary design or theoretical properties. Here, we introduce a strategy that enables the direct optimization of specific experimental properties during the inverse design process. Our method employs an adaptive β-variational autoencoder (adaptive β-VAE) combined with a latent vector-based prediction model. By dynamically tuning the Kullback–Leibler divergence scaling factor (β) and employing a separate training strategy, we enhance both the robustness of the generator and the diversity of the generated molecules. We demonstrate that latent vectors from the adaptive β-VAE serve as powerful inputs for downstream prediction models of experimental properties, such as fluorescence energy and quantum yield. Our optimized search framework for organic fluorescent materialsguided by gradients in latent space and validated by newly synthesized molecules sampled from optimal regions in the high-dimensional spaceshows strong potential for broader applications in the design of diverse organic materials.