Integrating Machine Learning and Large Language Models to Advance Wu Exploration of Electrochemical Reactions DOI Creative Commons
Zhiling Zheng, Federico Florit, Brooke Jin

et al.

Published: Aug. 28, 2024

Electrochemical C-H oxidation reactions offer a sustainable route to functionalize hydrocarbons, yet the identification of competent substrates and their synthesis optimization remains challenging. Here, we report an integrated approach combining machine learning (ML) large language models (LLMs) streamline exploration electrochemical reactions. Utilizing batch rapid screening platform, evaluated wide range reactions, initially classifying by reactivity, while LLMs text-mined literature data augment training set. The resulting ML models, one for reactivity prediction other site selectivity, both achieved high accuracy (>90%) enabled virtual set commercially available molecules. To optimize reaction conditions interest upon screening, were prompted generate code iteratively improve yield, lowering barrier scientists access programs, this strategy efficiently identified high-yield eight drug-like substances or intermediates. Notably, benchmarked reliability 10 different LLMs, including llama, Claude, GPT-4, on generating executing codes related based natural prompts given chemists showcase tool-making tool-using capabilities potentials accelerating research across four diverse tasks. In addition, collected experimental benchmark dataset comprising 1071 yields our findings revealed that integrating outperformed using either method alone. We envision combined offers robust generalizable pathway advancing synthetic chemistry

Language: Английский

Electrochemical Commodity Polymer Up‐ and Re‐Cycling: Toward Sustainable and Circular Plastic Treatment DOI Creative Commons
Maxime Hourtoule, Sven Trienes, Lutz Ackermann

et al.

Macromolecular Rapid Communications, Journal Year: 2025, Volume and Issue: unknown

Published: April 18, 2025

Abstract The demand for commodity plastics reaches unprecedented dimensions. In contrast to the well‐developed plethora of methods polymer synthesis, sustainable strategies end‐of‐life management continue be scarce. While mechanical re‐cycling often results in downgraded materials, chemical or up‐cycling offers tremendous potential an efficient and green approach, thereby addressing precarious treatment post‐use within a circular carbon economy. Recently, electrochemistry surfaced as uniquely powerful tool via functionalization degradation obtaining either novel polymers with valorized properties high‐value recycled small molecules, respectively. discussing recent progress that domain, future perspectives electrochemical modifications until January 2025 are outlined herein.

Language: Английский

Citations

0
N–N Atropisomer Synthesis via Electrolyte- and Base-Free Electrochemical Cobalt-Catalysed C–H Annulation DOI

Jiating Cai,

Linzai Li,

Chuitian Wang

et al.

Green Chemistry, Journal Year: 2024, Volume and Issue: 26(23), P. 11524 - 11530

Published: Jan. 1, 2024

An exogenous electrolyte- and base-free electrochemical cobalt-catalysed atroposelective C–H annulation has been established to construct N–N axially chiral isoquinolinones in excellent enantioselectivities good yields.

Language: Английский

Citations

3
Integrating Machine Learning and Large Language Models to Advance Exploration of Electrochemical Reactions DOI Creative Commons
Zhiling Zheng, Federico Florit, Brooke Jin

et al.

Published: Aug. 28, 2024

Electrochemical C-H oxidation reactions offer a sustainable route to functionalize hydrocarbons, yet the identification of competent substrates and their synthesis optimization remains challenging. Here, we report an integrated approach combining machine learning (ML) large language models (LLMs) streamline exploration electrochemical reactions. Utilizing batch rapid screening platform, evaluated wide range reactions, initially classifying by reactivity, while LLMs text-mined literature data augment training set. The resulting ML models, one for reactivity prediction other site selectivity, both achieved high accuracy (>90%) enabled virtual set commercially available molecules. To optimize reaction conditions interest upon screening, were prompted generate code iteratively improve yield, lowering barrier scientists access programs, this strategy efficiently identified high-yield eight drug-like substances or intermediates. Notably, benchmarked reliability 10 different LLMs, including llama, Claude, GPT-4, on generating executing codes related based natural prompts given chemists showcase tool-making tool-using capabilities potentials accelerating research across four diverse tasks. In addition, collected experimental benchmark dataset comprising 1071 yields our findings revealed that integrating outperformed using either method alone. We envision combined offers robust generalizable pathway advancing synthetic chemistry

Language: Английский

Citations

2
High-throughput experimentation and machine learning-promoted synthesis of α-phosphoryloxy ketones via Ru-catalyzed P(O)O-H insertion reactions of sulfoxonium ylides DOI
Lin An, Jingyuan Liu,

Yougen Xu

et al.

Science China Chemistry, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 10, 2024

Language: Английский

Citations

2
Parameterization and quantification of two key operando physio-chemical descriptors for water-assisted electro-catalytic organic oxidation DOI Creative Commons
Bailin Tian, Fangyuan Wang, Pan Ran

et al.

Nature Communications, Journal Year: 2024, Volume and Issue: 15(1)

Published: Nov. 22, 2024

Electro-selective-oxidation using water as a green oxygen source demonstrates promising potential towards efficient and sustainable chemical upgrading. However, surface micro-kinetics regarding co-adsorption reaction between organic intermediates remain unclear. Here we systematically study the electro-oxidation of aldehydes, alcohols, amines on Co/Ni-oxyhydroxides with multiple characterizations. Utilizing Fourier transformed alternating current voltammetry (FTacV) measurements, show identification quantification two key operando parameters (ΔIharmonics/IOER ΔVharmonics) that can be fundamentally linked to altered coverage ( $$\Delta {\theta }_{{{{{\rm{OH}}}}}^{*}}/{\theta }_{{{{{\rm{OH}}}}}^{*}}^{{{{\rm{OER}}}}}$$ ) changes in adsorption energy vital oxygenated $${\Delta G}_{{{{\rm{OH}}}}*}^{{{{\rm{EOOR}}}}}-{\Delta G}_{{{{\rm{OH}}}}*}^{{{{\rm{OER}}}}}$$ ), under influence adsorption/oxidation. Mechanistic analysis based these descriptors reveals distinct optimal oxyhydroxide states for each organics, elucidates critical catalyst design principles: balancing M3+δ−OH* coverages fine-tuning ΔG elementary steps, e.g., via precise modulation compositions, crystallinity, defects, electronic structures, and/or bimolecular interactions. Water-assisted electro-catalytic selective oxidation is production value-added chemicals. authors quantify physio-chemical mechanistic investigation rational design.

Language: Английский

Citations

2
Integrating Machine Learning and Large Language Models to Advance Wu Exploration of Electrochemical Reactions DOI Creative Commons
Zhiling Zheng, Federico Florit, Brooke Jin

et al.

Published: Aug. 28, 2024

Electrochemical C-H oxidation reactions offer a sustainable route to functionalize hydrocarbons, yet the identification of competent substrates and their synthesis optimization remains challenging. Here, we report an integrated approach combining machine learning (ML) large language models (LLMs) streamline exploration electrochemical reactions. Utilizing batch rapid screening platform, evaluated wide range reactions, initially classifying by reactivity, while LLMs text-mined literature data augment training set. The resulting ML models, one for reactivity prediction other site selectivity, both achieved high accuracy (>90%) enabled virtual set commercially available molecules. To optimize reaction conditions interest upon screening, were prompted generate code iteratively improve yield, lowering barrier scientists access programs, this strategy efficiently identified high-yield eight drug-like substances or intermediates. Notably, benchmarked reliability 10 different LLMs, including llama, Claude, GPT-4, on generating executing codes related based natural prompts given chemists showcase tool-making tool-using capabilities potentials accelerating research across four diverse tasks. In addition, collected experimental benchmark dataset comprising 1071 yields our findings revealed that integrating outperformed using either method alone. We envision combined offers robust generalizable pathway advancing synthetic chemistry

Language: Английский

Citations

1