Human- and machine-centred designs of molecules and materials for sustainability and decarbonization

Nature Reviews Materials, Год журнала: 2022, Номер 7(12), С. 991 - 1009

Опубликована: Авг. 24, 2022

Язык: Английский

---

A data-science approach to predict the heat capacity of nanoporous materials

Nature Materials, Год журнала: 2022, Номер 21(12), С. 1419 - 1425

Опубликована: Окт. 13, 2022

Язык: Английский

---

A multi-modal pre-training transformer for universal transfer learning in metal–organic frameworks

Nature Machine Intelligence, Год журнала: 2023, Номер 5(3), С. 309 - 318

Опубликована: Март 13, 2023

Язык: Английский

---

MOFormer: Self-Supervised Transformer Model for Metal–Organic Framework Property Prediction

Journal of the American Chemical Society, Год журнала: 2023, Номер 145(5), С. 2958 - 2967

Опубликована: Янв. 27, 2023

Metal-organic frameworks (MOFs) are materials with a high degree of porosity that can be used for many applications. However, the chemical space MOFs is enormous due to large variety possible combinations building blocks and topology. Discovering optimal specific applications requires an efficient accurate search over countless potential candidates. Previous high-throughput screening methods using computational simulations like DFT time-consuming. Such also require 3D atomic structures MOFs, which adds one extra step when evaluating hypothetical MOFs. In this work, we propose structure-agnostic deep learning method based on Transformer model, named as MOFormer, property predictions MOFormer takes text string representation MOF (MOFid) input, thus circumventing need obtaining structure accelerating process. By comparing other descriptors such Stoichiometric-120 revised autocorrelations, demonstrate achieve state-of-the-art prediction accuracy all benchmarks. Furthermore, introduce self-supervised framework pretrains via maximizing cross-correlation between its representations structure-based crystal graph convolutional neural network (CGCNN) >400k publicly available data. Benchmarks show pretraining improves both models various downstream tasks. revealed more data-efficient quantum-chemical than CGCNN training data limited. Overall, provides novel perspective learning.

Язык: Английский

---

Machine Learning-Assisted Low-Dimensional Electrocatalysts Design for Hydrogen Evolution Reaction

Nano-Micro Letters, Год журнала: 2023, Номер 15(1)

Опубликована: Окт. 13, 2023

Abstract Efficient electrocatalysts are crucial for hydrogen generation from electrolyzing water. Nevertheless, the conventional "trial and error" method producing advanced is not only cost-ineffective but also time-consuming labor-intensive. Fortunately, advancement of machine learning brings new opportunities discovery design. By analyzing experimental theoretical data, can effectively predict their evolution reaction (HER) performance. This review summarizes recent developments in low-dimensional electrocatalysts, including zero-dimension nanoparticles nanoclusters, one-dimensional nanotubes nanowires, two-dimensional nanosheets, as well other electrocatalysts. In particular, effects descriptors algorithms on screening investigating HER performance highlighted. Finally, future directions perspectives electrocatalysis discussed, emphasizing potential to accelerate electrocatalyst discovery, optimize performance, provide insights into electrocatalytic mechanisms. Overall, this work offers an in-depth understanding current state its research.

Язык: Английский

---

From Platform to Knowledge Graph: Evolution of Laboratory Automation

JACS Au, Год журнала: 2022, Номер 2(2), С. 292 - 309

Опубликована: Янв. 10, 2022

High-fidelity computer-aided experimentation is becoming more accessible with the development of computing power and artificial intelligence tools. The advancement experimental hardware also empowers researchers to reach a level accuracy that was not possible in past. Marching toward next generation self-driving laboratories, orchestration both resources lies at focal point autonomous discovery chemical science. To achieve such goal, algorithmically data representations standardized communication protocols are indispensable. In this perspective, we recategorize recently introduced approach based on Materials Acceleration Platforms into five functional components discuss recent case studies focus representation exchange scheme between different components. Emerging technologies for interoperable multi-agent systems discussed their applications automation. We hypothesize knowledge graph technology, orchestrating semantic web systems, will be driving force bring knowledge, evolving our way automating laboratory.

Язык: Английский

---

MOF based composites with engineering aspects and morphological developments for photocatalytic CO2 reduction and hydrogen production: A comprehensive review

Journal of environmental chemical engineering, Год журнала: 2023, Номер 11(2), С. 109408 - 109408

Опубликована: Фев. 1, 2023

Язык: Английский

---

Progress toward the computational discovery of new metal–organic framework adsorbents for energy applications

Nature Energy, Год журнала: 2024, Номер 9(2), С. 121 - 133

Опубликована: Янв. 9, 2024

Язык: Английский

---

ARC–MOF: A Diverse Database of Metal-Organic Frameworks with DFT-Derived Partial Atomic Charges and Descriptors for Machine Learning

Chemistry of Materials, Год журнала: 2023, Номер 35(3), С. 900 - 916

Опубликована: Янв. 20, 2023

Metal–organic frameworks (MOFs) are a class of crystalline materials composed metal nodes or clusters connected via semi-rigid organic linkers. Owing to their high-surface area, porosity, and tunability, MOFs have received significant attention for numerous applications such as gas separation storage. Atomistic simulations data-driven methods [e.g., machine learning (ML)] been successfully employed screen large databases develop new experimentally synthesized validated CO2 capture. To enable discovery any application, the first (and arguably most crucial) step is database curation. This work introduces ab initio REPEAT charge MOF (ARC–MOF) database. ∼280,000 which either characterized computationally generated, spanning all publicly available databases. A key feature ARC–MOF that it contains density functional theory-derived electrostatic potential fitted partial atomic charges each MOF. Additionally, pre-computed descriptors out-of-the-box ML applications. An in-depth analysis diversity with respect currently mapped design space was performed─a critical, yet commonly overlooked aspect previously reported Using this analysis, balanced subsets from various purposes identified, case study effect training set on performance. Other chemical geometric analyses presented, an charge-assignment method atomistic simulation uptake in MOFs.

Язык: Английский

---

Single‐Atom Nanozymes for Catalytic Therapy: Recent Advances and Challenges

Advanced Functional Materials, Год журнала: 2024, Номер 34(16)

Опубликована: Янв. 4, 2024

Abstract As a powerful tool, nanozyme catalysts broaden the avenues to implement bio‐inspired solutions for addressing many important concerns, covering energy, healthcare, environment, and more. Recent endeavors, characterized by atomic precision, have enabled extensive exploration of single‐atom nanozymes (SAzymes) with high catalytic activity, superior substrate selectivity, integrated multifunctionalities, thus becoming an emerging field that bridges nanotechnology biology. This review provides brief outline progress summarizes latest research advances regarding SAzymes in biomedical therapeutics, mainly including tumor therapy, wound antibacterial tissue anti‐inflammatory focus on their prototypical synthesis therapeutic mechanisms. Finally, current challenges future perspectives engineering advanced are also discussed outlooked. It is anticipated this area shall provide useful guidance therapy.

Язык: Английский

---