FFLAME: a fragment-to-framework learning approach for MOF potentials [0.03%]
FFLAME：一种用于MOF势函数的片段到框架学习方法
Xiaoqi Zhang,Yutao Li,Xin Jin et al.
Xiaoqi Zhang et al.
Metal-organic frameworks (MOFs) exhibit immense structural diversity and hold promise for applications ranging from gas storage and separation to energy storage and conversion. However, structural flexibility makes accurate and scalable pro...
Prospective active transfer learning on the formal coupling of amines and carboxylic acids to form secondary alkyl bonds [0.03%]
基于胺和羧酸形成次价键的偶联反应的主动迁移学习展望
Eunjae Shim,Ambuj Tewari,Paul M Zimmerman et al.
Eunjae Shim et al.
Tailoring a reaction condition to suit new substrates can be labor-intensive. While machine learning can aid this endeavor, conventional strategies require large datasets to make useful predictions. Active transfer learning (ATL) tackles th...
GoFlow: efficient transition state geometry prediction with flow matching and E(3)-equivariant neural networks [0.03%]
基于流匹配和E(3)等变神经网络的高效过渡态几何预测方法
Leonard Galustian,Konstantin Mark,Johannes Karwounopoulos et al.
Leonard Galustian et al.
Transition state (TS) geometries of chemical reactions are key to understanding reaction mechanisms and estimating kinetic properties. Inferring these directly from 2D reaction graphs offers chemists a powerful tool for rapid and accessible...
An automated platform for "on-demand" high-speed catalyst synthesis by flame spray pyrolysis [0.03%]
一种基于火焰喷雾热解的“按需”合成高速催化剂的自动化平台
Konstantin M Engel,Patrik O Willi,Robert N Grass et al.
Konstantin M Engel et al.
Flame-Spray Pyrolysis (FSP) is a versatile synthetic aerosol method to produce inorganic mixed-metal nanoparticles, frequently used for catalysts, battery materials, or chromophores. This work introduces a novel automated robotic platform b...
ELECTRUM: an electron configuration-based universal metal fingerprint for transition metal compounds [0.03%]
基于电子排布的过渡金属化合物通用金属指纹:ELECTRUM
Markus Orsi,Angelo Frei
Markus Orsi
Machine learning has experienced a drastic rise in interest and applications in all fields of chemistry, enabling researchers to leverage large chemical datasets to gain novel insights. The success of machine learning-driven projects in che...
Multi-level QTAIM-enriched graph neural networks for resolving properties of transition metal complexes [0.03%]
基于多级QTAIM增强图神经网络的过渡金属配合物性质解析方法研究
Winston Gee,Abigail Doyle,Santiago Vargas et al.
Winston Gee et al.
Here we evaluate the robustness and utility of quantum mechanical descriptors for machine learning with transition metal complexes. We utilize ab initio information from the quantum theory of atoms-in-molecules (QTAIM) for 60 k transition m...
Assessing zero-shot generalisation behaviour in graph-neural-network interatomic potentials [0.03%]
评估图神经网络间原子势能的零样本泛化行为
Chiheb Ben Mahmoud,Zakariya El-Machachi,Krystian A Gierczak et al.
Chiheb Ben Mahmoud et al.
With the rapidly growing availability of machine-learned interatomic potential (MLIP) models for chemistry, much current research focuses on the development of generally applicable and "foundational" MLIPs. An important question in this con...
Jan Janssen,Janine George,Julian Geiger et al.
Jan Janssen et al.
Numerous Workflow Management Systems (WfMS) have been developed in the field of computational materials science with different workflow formats, hindering interoperability and reproducibility of workflows in the field. To address this chall...
GEOM-drugs revisited: toward more chemically accurate benchmarks for 3D molecule generation [0.03%]
重访GEOM药物：面向三维分子生成的更准确化学基准测试
Filipp Nikitin,Ian Dunn,David Ryan Koes et al.
Filipp Nikitin et al.
Deep generative models have shown significant promise in generating valid 3D molecular structures, with the GEOM-drugs dataset serving as a key benchmark. However, current evaluation protocols suffer from critical flaws, including incorrect...
Quan Zhang,William W Sprague,Shivani S Kozarekar et al.
Quan Zhang et al.
Developing efficient tools for discovering novel synthesis pathways is essential to advance chemical production methods that maximize the use of resources and energy. We introduce DORAnet (Designing Optimal Reaction Avenues Network Enumerat...