MOSAEC-DB: a comprehensive database of experimental metal–organic frameworks with verified chemical accuracy suitable for molecular simulations

Chemical Science, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

MOSAEC-DB represents the largest and most diverse dataset of experimental MOFs suitable for simulation machine learning applications. Novel approaches utilizing metal oxidation states enhance its chemical accuracy relative to past MOF databases.

Language: Английский

---

Controlling Guest Diffusion by Local Dynamic Motion in Soft Porous Crystals to Separate Water Isotopologues and Similar Gases

Accounts of Chemical Research, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 29, 2024

ConspectusThe precise and effective separation of similar mixtures is one the fundamental issues essential tasks in chemical research. In field gas/vapor separation, size difference among molecular pairs/isomers light hydrocarbons aromatic compounds generally 0.3-0.5 Å, boiling-point 6-15 K. These are necessary industrial raw materials have great demands. Still, their mainly relies on energy-intensive distillation technology. On other hand, remarkably substances such as oxygen/argon isotopologues usually exhibit differences only 0-0.07 Å 1-3 Although can be realized, efficiency considerably low. Therefore, effectively separating crucial chemistry industry, but it remains a significant challenge. Porous coordination polymers (PCPs) or metal-organic frameworks (MOFs) emerging platforms for designing adsorbents mixtures. However, reported PCPs did not work well substances. The framework structures mainstream remain unchanged (rigid) significantly change (globally flexible) upon adsorption. rigid globally flexible find controlling pore aperture subangstrom precision challenging, prerequisite distinguishing Thus, novel mechanisms design principles urgently needed to realize PCPs-based adsorptive mixtures.To confront obstacles mixtures, our group started contributing this 2017. We employed locally platform, whose local motions side substituent groups potentially regulate apertures control diffusion PCPs. Specifically, we encoded dynamic flipping into diffusion-regulatory gate functionality. ligands were designed by integrating carboxylic with nonplanar fused-ring moieties, latter moieties exhibiting motion around equilibrium positions small energy increases. Such lead opening blocking PCP channels, thus termed crystals (FDCs). FDCs feature distinctive temperature-responsive adsorption behaviors due competition thermodynamics kinetics under regulation, enabling differentiation each gate-admission temperature much higher than component. Even when sizes same water isotopologue separate amplifying diffusion-rate differences. Finally, combining thermodynamic kinetic factors, achieve temperature-switched recognition CO

Language: Английский

---

From Data to Discovery: Recent Trends of Machine Learning in Metal–Organic Frameworks

JACS Au, Journal Year: 2024, Volume and Issue: 4(10), P. 3727 - 3743

Published: Sept. 12, 2024

Renowned for their high porosity and structural diversity, metal-organic frameworks (MOFs) are a promising class of materials wide range applications. In recent decades, with the development large-scale databases, MOF community has witnessed innovations brought by data-driven machine learning methods, which have enabled deeper understanding chemical nature MOFs led to novel structures. Notably, is continuously rapidly advancing as new methodologies, architectures, data representations actively being investigated, implementation in discovery vigorously pursued. Under these circumstances, it important closely monitor research trends identify technologies that introduced. this Perspective, we focus on emerging within field MOFs, challenges they face, future directions development.

Language: Английский

---

Machine learning-enhanced photocatalysis for environmental sustainability: Integration and applications

Materials Science and Engineering R Reports, Journal Year: 2024, Volume and Issue: 161, P. 100880 - 100880

Published: Nov. 14, 2024

Language: Английский

---

Metal–Organic Frameworks through the Lens of Artificial Intelligence: A Comprehensive Review

Langmuir, Journal Year: 2024, Volume and Issue: 40(42), P. 21957 - 21975

Published: Oct. 9, 2024

Metal–organic frameworks (MOFs) are a class of hybrid porous materials that have gained prominence as noteworthy material with varied applications. Currently, MOFs in extensive use, particularly the realms energy and catalysis. The synthesis these poses considerable challenges, their computational analysis is notably intricate due to complex structure versatile applications field science. Density functional theory (DFT) has helped researchers understanding reactions mechanisms, but it costly time-consuming requires bigger systems perform calculations. Machine learning (ML) techniques were adopted order overcome problems by implementing ML data sets for synthesis, structure, property predictions MOFs. These fast, efficient, accurate do not require heavy computing. In this review, we discuss models used MOF incorporation artificial intelligence (AI) predictions. advantage AI would accelerate research, synthesizing novel multiple properties oriented minimum information.

Language: Английский

---

MOF-KAN: Kolmogorov–Arnold Networks for Digital Discovery of Metal–Organic Frameworks

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 2452 - 2459

Published: Feb. 27, 2025

Digital discovery of functional materials, such as metal–organic frameworks (MOFs), entails accurate and data-efficient approaches to navigate complex chemical structural space. Based on an innovative deep learning approach, namely, Kolmogorov–Arnold Networks (KANs), we introduce MOF-KAN, a state-of-the-art architecture the first application KANs digital MOFs. Through meticulous fine-tuning network architecture, demonstrate that MOF-KAN outperforms standard multilayer perceptrons (MLPs) in predicting diverse properties for MOFs, including gas separation, electronic band gap, thermal expansion. Furthermore, excels low-data regimes, facilitating robust performance challenging prediction scenarios. Feature importance analysis reveals accurately captures critical features MOFs relevant targeted properties. not only serves transformative tool rational design materials but also holds broad applicability across various domains physical sciences.

Language: Английский

---

Accelerating Band Gap Prediction and High-Throughput Screening of Covalent Organic Frameworks Based on Transfer Learning

The Journal of Physical Chemistry C, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---

Hybrid Data Driven Deep Learning Framework for Material Property Prediction

Journal of Machine and Computing, Journal Year: 2025, Volume and Issue: unknown, P. 1068 - 1083

Published: April 5, 2025

The research presents a hybrid approach of regression modeling with data-driven analysis for predicting steel's mechanical properties by analyzing the effects composition on strength. study fills gap models in accurately performance based since traditional methods cannot fully capture complex relationships between alloying elements and material properties. Various have been used properties, such as Linear Regression, Random Forest Support Vector Regression (SVR), XGBoost Neural Networks, this paper, Graph Attention Transformer Network (GAT-TransNet) is proposed. Incorporating novel graph attention into transformer architecture model, GAT-TransNet handles data improves predictive accuracy. Data-driven analyses are also carried out alongside to establish how elements, carbon (C), manganese (Mn), chromium (Cr), affect strength, yield hardness, ductility. established that model outperformed other models, an R² score 0.95, lowest MAE 1.40, MSE 4.41, thus underscoring its superior capability compared existing models. insights show hardens increases wear resistance, while enhances corrosion resistance tensile This has great importance optimizing specific steel compositions industrial applications. Combining machine learning methodologies analysis, complements design promises better efficiency targeting production.

Language: Английский

---

Harmonizing Adsorption and Diffusion in Active Learning Campaigns of Gas Separations in a MOF

The Journal of Physical Chemistry C, Journal Year: 2025, Volume and Issue: unknown

Published: May 16, 2025

Language: Английский

---

Efficient Xylene Isomer Separation: Accelerated Screening with Active Learning and Molecular Simulation

Energy & Fuels, Journal Year: 2024, Volume and Issue: 38(11), P. 9381 - 9394

Published: May 13, 2024

Separating xylene isomers is vital in the petrochemical industry, yet it poses a considerable challenge due to their proximate boiling points, mandating selective adsorbents. This work utilizes active learning (AL) coupled with molecular simulations rapidly screen 324,426 hypothetical metal–organic frameworks (hMOFs) identify optimal materials for preferential para-xylene (pX) adsorption. To begin, diverse subset, representative of entire hMOF set, was curated using structural and chemical descriptors evaluated through multiple screening methodologies. comparative analysis highlighted superior efficiency AL targeted processes, requiring on an average only 500 multicomponent Grand Canonical Monte Carlo most pX-selective framework, encompassing 50.5% top 100 candidates. With equivalent evaluation budget, both machine (ML) evolutionary algorithms demonstrate inadequate performance. While former consistently fails performers, latter continuously identifies significantly inferior materials. AL, other hand, surpasses rival approaches by effectively balancing exploration exploitation, guiding toward regions associated high Furthermore, we report impact different surrogate models, acquisition functions, batch strategies convergence our model. We found that Gaussian process model expected improvement (EI) function Kriging-Believer upper bound (KBUB) strategy acquires highest MOF just 86 acquisitions. Examining candidates revealed complex correlation between pX selectivity features hMOFs. In particular, pcu topology, along pore size ranging from 5 6 Å, emerged as dominant characteristic pressure-dependent pressure maximizing uptake selectivity. computational workflow, integrating simulations, shows promise accelerating data-driven material innovation separation applications.

Language: Английский

---