1 February 2019 in Applied Surface Science
11 July 2025 in ACS Omega
The capability of predicting molecular properties plays a crucial role in drug development, and the learning of molecular representations stands as the primary step in tasks aimed at predicting molecular properties. Static three-dimensional (3D) structural information has been shown to significantly aid in molecular representation; however, molecules are in constant motion and change, implying that their properties should be closely linked with dynamic molecular conformations. Traditional four-dimensional (4D) Quantitative Structure–Property Relationship (QSPR) methods, while incorporating time as a dimension, have high computational costs and fail to fully integrate the temporal dimension, leading to ineffective integration of molecular conformation ensembles. Inspired by deep learning-based molecular dynamics (DLMD) techniques and multifidelity learning (MFL) strategies, in this work, a multichannel spatiotemporal feature adaptive fusion network framework (MCST-AFN) based on a low-fidelity molecular dynamics model is proposed. This framework integrates deep learning technology with molecular dynamics (MD) simulations, effectively enhancing molecular representation while significantly reducing computational costs. Initially, a low-fidelity molecular dynamics simulation model is trained using real molecular dynamics simulation data. Compared to existing tools such as Amber, this low-fidelity model can update atomic coordinates at a lower computational cost and output multichannel atom-level embeddings that encapsulate information across different time scales. Subsequently, an attention-based network is constructed to achieve adaptive fusion of multichannel spatiotemporal features, and a self-supervised learning task for atom masking prediction is designed to further enhance molecular representation. The MCST-AFN was tested on 13 benchmark data sets for molecular property prediction, achieving an average performance improvement of 2.10% across 12 data sets. The most significant enhancement was seen in the ESOL data set, with a performance boost of 19.70%.
30 September 2026 in ChemCatChem
Aluminum oxide is an earth‐abundant yet catalytically inert p‐block oxide, as its lack of accessible d orbitals limits oxygen‐intermediate binding in the conventional adsorbate evolution mechanism (AEM). Herein, we activate the intrinsic oxygen evolution reaction (OER) activity of Al 2 O 3 by incorporating high‐valence Cr species through a one‐step molten‐salt electrochemical strategy. Using Cr 2 AlC MAX phase as an integrated Cr, Al, and C precursor, selective Al extraction, Cr incorporation, and in situ carbon reconstruction are coupled to form Cr‐doped Al 2 O 3 nanoparticles anchored on a conductive graphene scaffold (Cr‐Al 2 O 3 @G). The integrated route mitigates nanoparticle agglomeration and weak interfacial contact typical of multi‐step syntheses. Cr‐Al 2 O 3 @G delivers an overpotential of 310 mV at 10 mA cm −2 , markedly lower than bare Al 2 O 3 and comparable to commercial IrO 2 , while offering an estimated ∼70,000‐fold lower metal cost. It also achieves a metal‐mass‐normalized activity of 112 A g −1 . Mechanistic studies involving pH‐dependent kinetics, tetramethylammonium cation inhibition, and in situ 18 O‐isotope differential electrochemical mass spectrometry (DEMS) reveal that Cr incorporation reconstructs the Al‐O electronic environment and promotes a lattice‐oxygen‐mediated (LOM) pathway. This work provides a MAX‐phase‐derived strategy for cost‐effective activation of p‐block oxides.