The ability of molecular property prediction is of great significance to drug discovery, human health, and environmental protection. Despite considerable efforts, quantitative prediction of various molecular properties remains a challenge. Although some machine learning models, such as bidirectional encoder from transformer, can incorporate massive unlabeled molecular data into molecular representations via a self-supervised learning strategy, it neglects three-dimensional (3D) stereochemical information. Algebraic graph, specifically, element-specific multiscale weighted colored algebraic graph, embeds complementary 3D molecular information into graph invariants. We propose an algebraic graph-assisted bidirectional transformer (AGBT) framework by fusing representations generated by algebraic graph and bidirectional transformer, as well as a variety of machine learning algorithms, including decision trees, multitask learning, and deep neural networks. We validate the proposed AGBT framework on eight molecular datasets, involving quantitative toxicity, physical chemistry, and physiology datasets. Extensive numerical experiments have shown that AGBT is a state-of-the-art framework for molecular property prediction.

Accurate theoretical predictions of desired properties of materials play an important role in materials research and development. Machine learning (ML) can accelerate the materials design by building a model from input data. For complex datasets, such as those of crystalline compounds, a vital issue is how to construct low-dimensional representations for input crystal structures with chemical insights. In this work, we introduce an algebraic topology-based method, called atom-specific persistent homology (ASPH), as a unique representation of crystal structures. The ASPH can capture both pairwise and many-body interactions and reveal the topology-property relationship of a group of atoms at various scales. Combined with composition-based attributes, ASPH-based ML model provides a highly accurate prediction of the formation energy calculated by density functional theory (DFT). After training with more than 30,000 different structure types and compositions, our model achieves a mean absolute error of 61 meV/atom in cross-validation, which outperforms previous work such as Voronoi tessellations and Coulomb matrix method using the same ML algorithm and datasets. Our results indicate that the proposed topology-based method provides a powerful computational tool for predicting materials properties compared to previous works.

In recent years, we have witnessed a widespread application of machine learning techniques in the field of materials science, owing to the increased availability of research data and sophisticated algorithms. At the core of this technology lies the ability to encode material structures into descriptors that are understandable for a computer. Although significant advances have been made in this area, there is a continued need to explore efficient structure‐encoding strategies so as to maximize the predictive power of the machine learning models. Here we present a revision of the exciting progress in four representative structural features that are capable of describing the structures of diverse materials: structure graph, Coulomb matrix, topological descriptor, and diffraction fingerprint. Particular attention is given to the studies of crystalline solids, which appear more challenging to be encoded than molecules. By summarizing previous works and presenting critical appraisals of these descriptors, this review could offer some guideline for the selection of structural features and stimulate inspiration for the design of powerful descriptors suited towards different tasks. This article is categorized under: Structure and Mechanism > Computational Materials Science Data Science > Artificial Intelligence/Machine Learning

In cluster physics, the determination of the ground-state structure of medium-sized and large-sized clusters is a challenge due to the number of local minimal values on the potential energy surface growing exponentially with cluster size. Although machine learning approaches have had much success in materials sciences, their applications in clusters are often hindered by the geometric

No abstract