Data-Based Prediction of Redox Potentials via Introducing Chemical Features into the Transformer Architecture DOI
Zhan Si, Deguang Liu, Wan Nie

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(22), P. 8453 - 8463

Published: Nov. 8, 2024

Rapid and accurate prediction of basic physicochemical parameters molecules will greatly accelerate the target-orientated design novel reactions materials but has been long challenging. Herein, a chemical language model-based deep learning method, TransChem, developed for redox potentials organic molecules. Embedding an effective molecular characterization (combining spatial electronic features), nonlinear messaging approach (Mol-Attention), perturbation shows high accuracy in predicting potential radicals comprising over 100,000 data (R2 > 0.97, MAE <0.09 V) is generalized to smaller 2,1,3-benzothiadiazole set (<3000 points) electron affinity (660 data) with low 0.07 V 0.18 eV, respectively. In this context, self-developed set, i.e., oxidation (OP) full-space disubstituted phenol (OPP-data total set: 74,529), predicted by TransChem high-throughput, active strategy. The rapid reliable OP could hopefully screening plausible reagents highly selective cross-coupling derivatives. This study presents important attempt guide modeling knowledge, while demonstrates state-of-the-art (SOTA) predictive performance on benchmark sets its better understanding conformational relationships.

Language: Английский

Revolutionizing the structural design and determination of covalent–organic frameworks: principles, methods, and techniques DOI
Yikuan Liu, Xiaona Liu, An Su

et al.

Chemical Society Reviews, Journal Year: 2023, Volume and Issue: 53(1), P. 502 - 544

Published: Dec. 15, 2023

Covalent organic frameworks (COFs) represent an important class of crystalline porous materials with designable structures and functions. The interconnected monomers, featuring pre-designed symmetries connectivities, dictate the COFs, endowing them high thermal chemical stability, large surface area, tunable micropores. Furthermore, by utilizing pre-functionalization or post-synthetic functionalization strategies, COFs can acquire multifunctionalities, leading to their versatile applications in gas separation/storage, catalysis, optoelectronic devices. Our review provides a comprehensive account latest advancements principles, methods, techniques for structural design determination COFs. These cutting-edge approaches enable rational precise elucidation COF structures, addressing fundamental physicochemical challenges associated host-guest interactions, topological transformations, network interpenetration, defect-mediated catalysis.

Language: Английский

Citations

46
Reaction performance prediction with an extrapolative and interpretable graph model based on chemical knowledge DOI Creative Commons

Shu-Wen Li,

Li‐Cheng Xu, Cheng Zhang

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: June 15, 2023

Accurate prediction of reactivity and selectivity provides the desired guideline for synthetic development. Due to high-dimensional relationship between molecular structure function, it is challenging achieve predictive modelling transformation with required extrapolative ability chemical interpretability. To meet gap rich domain knowledge chemistry advanced graph model, herein we report a knowledge-based model that embeds digitalized steric electronic information. In addition, interaction module developed enable learning synergistic influence reaction components. this study, demonstrate achieves excellent predictions yield stereoselectivity, whose corroborated by additional scaffold-based data splittings experimental verifications new catalysts. Because embedding local environment, allows atomic level interpretation on overall performance, which serves as useful guide engineering towards target function. This offers an interpretable approach performance prediction, pointing out importance knowledge-constrained purpose.

Language: Английский

Citations

27
Exploring Chemical Reaction Space with Machine Learning Models: Representation and Feature Perspective DOI

Yuheng Ding,

Bo Qiang, Qixuan Chen

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(8), P. 2955 - 2970

Published: March 15, 2024

Chemical reactions serve as foundational building blocks for organic chemistry and drug design. In the era of large AI models, data-driven approaches have emerged to innovate design novel reactions, optimize existing ones higher yields, discover new pathways synthesizing chemical structures comprehensively. To effectively address these challenges with machine learning it is imperative derive robust informative representations or engage in feature engineering using extensive data sets reactions. This work aims provide a comprehensive review established reaction featurization approaches, offering insights into selection features wide array tasks. The advantages limitations employing SMILES, molecular fingerprints, graphs, physics-based properties are meticulously elaborated. Solutions bridge gap between different will also be critically evaluated. Additionally, we introduce frontier pretraining, holding promise an innovative yet unexplored avenue.

Language: Английский

Citations

10
HCat-GNet: a Human-Interpretable GNN Tool for Ligand Optimization in Asymmetric Catalysis DOI Creative Commons
Eduardo Alberto Aguilar Bejarano, Ender Özcan, Raja K. Rit

et al.

iScience, Journal Year: 2025, Volume and Issue: 28(3), P. 111881 - 111881

Published: Jan. 24, 2025

Language: Английский

Citations

1
Recommending reaction conditions with label ranking DOI Creative Commons
Eunjae Shim, Ambuj Tewari, Tim Cernak

et al.

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

Published: Jan. 1, 2025

Label ranking is introduced as a conceptually new means for prioritizing experiments. Their simplicity, ease of application, and the use aggregation facilitate their ability to make accurate predictions with small datasets.

Language: Английский

Citations

1
Transfer learning across different photocatalytic organic reactions DOI Creative Commons
Naoki Noto,

Ryuga Kunisada,

Tabea Rohlfs

et al.

Nature Communications, Journal Year: 2025, Volume and Issue: 16(1)

Published: April 10, 2025

Language: Английский

Citations

1
Machine learning-guided strategies for reaction conditions design and optimization DOI Creative Commons
Lung-Yi Chen, Yi‐Pei Li

Beilstein Journal of Organic Chemistry, Journal Year: 2024, Volume and Issue: 20, P. 2476 - 2492

Published: Oct. 4, 2024

This review surveys the recent advances and challenges in predicting optimizing reaction conditions using machine learning techniques. The paper emphasizes importance of acquiring processing large diverse datasets chemical reactions, use both global local models to guide design synthetic processes. Global exploit information from comprehensive databases suggest general for new while fine-tune specific parameters a given family improve yield selectivity. also identifies current limitations opportunities this field, such as data quality availability, integration high-throughput experimentation. demonstrates how combination engineering, science, ML algorithms can enhance efficiency effectiveness design, enable novel discoveries chemistry.

Language: Английский

Citations

5
Multi‐modal Homogeneous Chemical Reaction Performance Prediction with Graph and Chemical Language Information DOI Open Access
Shen Wang,

Weiren Zhao,

Yining Liu

et al.

Chinese Journal of Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 20, 2025

Comprehensive Summary Accurate prediction for chemical reaction performance offers optimal direction synthetic development. To this end, we present a novel multi‐modal model called MMHRP‐GCL to achieve the of homogeneous yield, enantioselectivity, and activation energy by fusing information from text graph modalities, requiring only 8 simple descriptors Reaction SMILES obtained without high‐cost DFT computation, capable managing reactions involving fluctuating number molecules. Experimental results on 4 datasets show that outperforms at least 7 generalized SOTA methods. Ablation study confirms critical roles complementation as well significance modality alignment atomic features in prediction. Albeit there is still room improvement interpretation relationships, has remarkable ability identify important atoms. A statistically interpretable feature importance test challenging dataset further demonstrates utility potential model. As high‐accuracy, low‐cost, interpretable, general model, provides valuable guidance design forward predictors catalytic reactions.

Language: Английский

Citations

0
Computational Tools for the Prediction of Site- and Regioselectivity of Organic Reactions DOI Creative Commons
Lukas M. Sigmund,

Michele Assante,

Magnus J. Johansson

et al.

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

Published: Jan. 1, 2025

This article reviews computational tools for the prediction of regio- and site-selectivity organic reactions. It spans from quantum chemical procedures to deep learning models showcases application presented tools.

Language: Английский

Citations

0
Research on Multidimensional Power Big Data Clustering Algorithm Based on Graph Mode DOI Creative Commons
Xue Han, Yue Zhang, Sheng Gao

et al.

Journal of Advanced Computational Intelligence and Intelligent Informatics, Journal Year: 2025, Volume and Issue: 29(2), P. 358 - 364

Published: March 19, 2025

Power system data possess many characteristics and indicators, having certain high dimensions redundant information, which can easily increase the calculation storage overhead. To reduce dimension of power data, eliminate delay time, a clustering algorithm is proposed. Firstly, an based on PCA kernel local Fisher identification used to large multidimensional samples enhance accuracy subsequent clustering. Thereafter, are processed after reduction optimize quality by introducing bloom filter structure. In graph model, completed parallel processing data. Simulation results show that correctness stability this method over 85%, time decreased, representing good application prospects.

Language: Английский

Citations

0