Yutao Kuang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yutao Kuang has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Jolene P. Reid
Department of Chemistry, University of British Columbia, Vancouver, V6T 1Z1, Canada
9 shared publications - Isaiah O. Betinol
Department of Chemistry
3 shared publications Ben Niu
University of British Columbia, Department of Chemistry, 2036 Main Mall, Vancouver, British Columbia V6T 1Z1, Canada
1 shared publication- Ben Niu
University of British, Columbia
1 shared publication Brian P. Mulley
Department of Chemistry
1 shared publication- Chatura Goonesinghe
Department of Chemistry, University of British Columbia, 2036 Main Mall, Vancouver, British Columbia V6T 1Z1, Canada
1 shared publication
Latest Publications
- 15 May 2026
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 148 (21) , 21545-21557
Data-Driven Interrogation of Reactivity in Acid-Catalyzed Carbonyl–Olefin Metathesis with Machine Learning and Large Language Models
Carbonyl–olefin metathesis (COM) has emerged as a powerful yet mechanistically complex transformation for forging carbon–carbon bonds. Although diverse Brønsted and Lewis acid catalysts enable COM reactivity, predicting which catalyst will be effective for a given substrate remains challenging. Likewise, machine learning (ML) and large language models (LLMs) are emerging tools for planning experiments in organic synthesis, but their relative strengths in mechanistically rich catalytic systems like COM remain unclear. Here we address both challenges through a practical ML framework that combines a rigorously curated, blinded data set of 147 COM reactions with tiered predictive models to guide catalyst and substrate selection. A Morgan-fingerprint baseline enables rapid structure-based screening, while quantum-derived descriptor models achieve higher accuracy (R2 ≈ 0.92) and retain performance on external substrates; feature-importance and SHAP analyses identify catalyst HOMO energy, dimerization propensity, and substrate carbonyl polarization as dominant drivers of reactivity. Reactivity-cliff analysis distinguishes smoothly interpolating catalysts, such as FeCl3 and ZnCl2, from cliff-rich ion-pair systems, identifying regions where predictions are intrinsically unreliable and targeted experiments are most informative. Variance-guided Bayesian optimization recovers most full-model performance using only ∼40% of the reaction matrix, while a parallel GPT-4o-guided, code-free acquisition protocol offers a lower-barrier alternative that outperforms random sampling and, in this setting, exceeds expert selection. Together, these results establish a mechanistically interpretable, data-efficient framework for predicting, explaining, and prioritizing COM experiments in a controlled reaction matrix, and show how uncertainty-aware ML and LLM-guided selection can augment decision-making in mechanistically related COM systems.
- 15 May 2026
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 148 (21) , 21545-21557
Data-Driven Interrogation of Reactivity in Acid-Catalyzed Carbonyl–Olefin Metathesis with Machine Learning and Large Language Models
Carbonyl–olefin metathesis (COM) has emerged as a powerful yet mechanistically complex transformation for forging carbon–carbon bonds. Although diverse Brønsted and Lewis acid catalysts enable COM reactivity, predicting which catalyst will be effective for a given substrate remains challenging. Likewise, machine learning (ML) and large language models (LLMs) are emerging tools for planning experiments in organic synthesis, but their relative strengths in mechanistically rich catalytic systems like COM remain unclear. Here we address both challenges through a practical ML framework that combines a rigorously curated, blinded data set of 147 COM reactions with tiered predictive models to guide catalyst and substrate selection. A Morgan-fingerprint baseline enables rapid structure-based screening, while quantum-derived descriptor models achieve higher accuracy (R2 ≈ 0.92) and retain performance on external substrates; feature-importance and SHAP analyses identify catalyst HOMO energy, dimerization propensity, and substrate carbonyl polarization as dominant drivers of reactivity. Reactivity-cliff analysis distinguishes smoothly interpolating catalysts, such as FeCl3 and ZnCl2, from cliff-rich ion-pair systems, identifying regions where predictions are intrinsically unreliable and targeted experiments are most informative. Variance-guided Bayesian optimization recovers most full-model performance using only ∼40% of the reaction matrix, while a parallel GPT-4o-guided, code-free acquisition protocol offers a lower-barrier alternative that outperforms random sampling and, in this setting, exceeds expert selection. Together, these results establish a mechanistically interpretable, data-efficient framework for predicting, explaining, and prioritizing COM experiments in a controlled reaction matrix, and show how uncertainty-aware ML and LLM-guided selection can augment decision-making in mechanistically related COM systems.
- Open Access
- 15 December 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Practical Data-Driven Interrogation of Reactivity in Acid-Catalyzed Carbonyl–Olefin Metathesis with Machine Learning and Large Language Models
Carbonyl–olefin metathesis (COM) has emerged as a powerful yet mechanistically complex transformation for forging carbon–carbon bonds. Although diverse Brønsted and Lewis acid catalysts enable COM reactivity, predicting which catalyst will be effective for a given substrate remains challenging. Likewise, machine learning (ML) and large language models (LLMs) are emerging tools for planning experiments in organic synthesis, but their relative strengths in mechanistically rich catalytic systems like COM remain unclear. Here we address both challenges through a practical ML framework that combines a rigorously curated, blinded dataset of 147 COM reactions—spanning structurally diverse substrates and Brønsted, Lewis, and superelectrophilic ion-pair catalysts—with tiered predictive models to guide catalyst and substrate selection. A Morgan-fingerprint baseline captures substantial yield variation, demonstrating that structure-only representations provide rapid initial screening. Physically informed models based on quantum-derived descriptors of independent catalyst and substrate structures achieve higher accuracy (R² ≈ 0.92) and maintain performance on external substrates, while feature-importance and SHAP analyses reveal catalyst HOMO energy, dimerization propensity, and substrate carbonyl polarization as dominant determinants of reactivity. Reactivity-cliff analysis distinguishes smoothly interpolating catalysts such as FeCl₃ and ZnCl₂ from cliff-rich ion-pair systems, identifying regions where predictions are intrinsically unreliable and targeted experiments are most informative. Variance-guided Bayesian optimization recovers most full-model performance using only ~40% of the reaction matrix, while a parallel GPT-4–driven, code-free acquisition protocol surpasses expert selection and substantially outperforms random sampling. Together, these results provide a mechanistically interpretable, data-efficient blueprint for COM catalyst discovery and demonstrate how uncertainty-aware ML and LLMs can augment human intuition in complex catalytic systems.
- 15 December 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessPractical Data-Driven Interrogation of Reactivity in Acid-Catalyzed Carbonyl–Olefin Metathesis with Machine Learning and Large Language Models
Carbonyl–olefin metathesis (COM) has emerged as a powerful yet mechanistically complex transformation for forging carbon–carbon bonds. Although diverse Brønsted and Lewis acid catalysts enable COM reactivity, predicting which catalyst will be effective for a given substrate remains challenging. Likewise, machine learning (ML) and large language models (LLMs) are emerging tools for planning experiments in organic synthesis, but their relative strengths in mechanistically rich catalytic systems like COM remain unclear. Here we address both challenges through a practical ML framework that combines a rigorously curated, blinded dataset of 147 COM reactions—spanning structurally diverse substrates and Brønsted, Lewis, and superelectrophilic ion-pair catalysts—with tiered predictive models to guide catalyst and substrate selection. A Morgan-fingerprint baseline captures substantial yield variation, demonstrating that structure-only representations provide rapid initial screening. Physically informed models based on quantum-derived descriptors of independent catalyst and substrate structures achieve higher accuracy (R² ≈ 0.92) and maintain performance on external substrates, while feature-importance and SHAP analyses reveal catalyst HOMO energy, dimerization propensity, and substrate carbonyl polarization as dominant determinants of reactivity. Reactivity-cliff analysis distinguishes smoothly interpolating catalysts such as FeCl₃ and ZnCl₂ from cliff-rich ion-pair systems, identifying regions where predictions are intrinsically unreliable and targeted experiments are most informative. Variance-guided Bayesian optimization recovers most full-model performance using only ~40% of the reaction matrix, while a parallel GPT-4–driven, code-free acquisition protocol surpasses expert selection and substantially outperforms random sampling. Together, these results provide a mechanistically interpretable, data-efficient blueprint for COM catalyst discovery and demonstrate how uncertainty-aware ML and LLMs can augment human intuition in complex catalytic systems.
- 9 May 2025
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 15 (11) , 8799-8810
Machine Learning Enables a Top-Down Approach to Mechanistic Elucidation in Asymmetric Catalysis
- 9 May 2025
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 15 (11) , 8799-8810
Machine Learning Enables a Top-Down Approach to Mechanistic Elucidation in Asymmetric Catalysis
- 22 April 2025
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 15 (9) , 7588-7600
Selective Block Copolymerization of Lactide and Methyl Methacrylate with Cationic Indium Catalysts: Exploring the Influence of Noncovalent Ligand Interactions
- 22 April 2025
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 15 (9) , 7588-7600
Selective Block Copolymerization of Lactide and Methyl Methacrylate with Cationic Indium Catalysts: Exploring the Influence of Noncovalent Ligand Interactions
- Top Cited Papers
- 18 March 2025
- Published by American Chemical Society (ACS) in Chemical Reviews
- Vol. 125 (8) , 4184-4286
Controlling Stereoselectivity with Noncovalent Interactions in Chiral Phosphoric Acid Organocatalysis
Chiral phosphoric acids (CPAs) have emerged as highly effective Brønsted acid catalysts in an expanding range of asymmetric transformations, often through novel multifunctional substrate activation modes. Versatile and broadly appealing, these catalysts benefit from modular and tunable structures, and compatibility with additives. Given the unique types of noncovalent interactions (NCIs) that can be established between CPAs and various reactants─such as hydrogen bonding, aromatic interactions, and van der Waals forces─it is unsurprising that these catalyst systems have become a promising approach for accessing diverse chiral product outcomes. This review aims to provide an in-depth exploration of the mechanisms by which CPAs impart stereoselectivity, positioning NCIs as the central feature that connects a broad spectrum of catalytic reactions. Spanning literature from 2004 to 2024, it covers nucleophilic additions, radical transformations, and atroposelective bond formations, highlighting the applicability of CPA organocatalysis. Special emphasis is placed on the structural and mechanistic features that govern CPA-substrate interactions, as well as the tools and techniques developed to enhance our understanding of their catalytic behavior. In addition to emphasizing mechanistic details and stereocontrolling elements in individual reactions, we have carefully structured this review to provide a natural progression from these specifics to a broader, class-level perspective. Overall, these findings underscore the critical role of NCIs in CPA catalysis and their significant contributions to advancing asymmetric synthesis.
- 18 March 2025
- Published by American Chemical Society (ACS) in Chemical Reviews
- Vol. 125 (8) , 4184-4286
Top Cited PapersControlling Stereoselectivity with Noncovalent Interactions in Chiral Phosphoric Acid Organocatalysis
Chiral phosphoric acids (CPAs) have emerged as highly effective Brønsted acid catalysts in an expanding range of asymmetric transformations, often through novel multifunctional substrate activation modes. Versatile and broadly appealing, these catalysts benefit from modular and tunable structures, and compatibility with additives. Given the unique types of noncovalent interactions (NCIs) that can be established between CPAs and various reactants─such as hydrogen bonding, aromatic interactions, and van der Waals forces─it is unsurprising that these catalyst systems have become a promising approach for accessing diverse chiral product outcomes. This review aims to provide an in-depth exploration of the mechanisms by which CPAs impart stereoselectivity, positioning NCIs as the central feature that connects a broad spectrum of catalytic reactions. Spanning literature from 2004 to 2024, it covers nucleophilic additions, radical transformations, and atroposelective bond formations, highlighting the applicability of CPA organocatalysis. Special emphasis is placed on the structural and mechanistic features that govern CPA-substrate interactions, as well as the tools and techniques developed to enhance our understanding of their catalytic behavior. In addition to emphasizing mechanistic details and stereocontrolling elements in individual reactions, we have carefully structured this review to provide a natural progression from these specifics to a broader, class-level perspective. Overall, these findings underscore the critical role of NCIs in CPA catalysis and their significant contributions to advancing asymmetric synthesis.
- Open Access
- 18 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Machine Learning Enables a Top-Down Approach to Mechanistic Elucidation
General reaction behavior is rarely reported in asymmetric catalysis, not simply because it is difficult to achieve, but also due to the methods used for its identification and study. Traditional approaches involve compartmentalization, where the impact of individual components is first analyzed, followed by assimilation using simple response and structure matching techniques. However, extending this method to accommodate complex conditions and diverse reactions proves challenging. Here, we present a data-driven method that relies on clusterwise linear regression to derive and predictively apply general mechanistic models of enantioinduction, with minimal human intervention. When applied to the palladium-catalyzed decarboxylative asymmetric allylic alkylation (DAAA) reaction, unexpected interactions governing enantioselectivity are revealed, supported by high-level computations and additional experiments. Our results demonstrate this workflow as a powerful new tool for automating mechanistic elucidation and effectively identifying general reaction performance.
- 18 June 2024
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessMachine Learning Enables a Top-Down Approach to Mechanistic Elucidation
General reaction behavior is rarely reported in asymmetric catalysis, not simply because it is difficult to achieve, but also due to the methods used for its identification and study. Traditional approaches involve compartmentalization, where the impact of individual components is first analyzed, followed by assimilation using simple response and structure matching techniques. However, extending this method to accommodate complex conditions and diverse reactions proves challenging. Here, we present a data-driven method that relies on clusterwise linear regression to derive and predictively apply general mechanistic models of enantioinduction, with minimal human intervention. When applied to the palladium-catalyzed decarboxylative asymmetric allylic alkylation (DAAA) reaction, unexpected interactions governing enantioselectivity are revealed, supported by high-level computations and additional experiments. Our results demonstrate this workflow as a powerful new tool for automating mechanistic elucidation and effectively identifying general reaction performance.
- 2 August 2023
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 59 (72) , 10711-10721
Mechanism to model: a physical organic chemistry approach to reaction prediction
Combining a working knowledge of reaction mechanism with statistical modelling is a powerful approach to prediction.
- 2 August 2023
- Published by Royal Society of Chemistry (RSC) in Chemical Communications
- Vol. 59 (72) , 10711-10721
Mechanism to model: a physical organic chemistry approach to reaction prediction
Combining a working knowledge of reaction mechanism with statistical modelling is a powerful approach to prediction.
- 14 January 2022
- Published by American Chemical Society (ACS) in Organic Letters
- Vol. 24 (7) , 1429-1433
Guiding Target Synthesis with Statistical Modeling Tools: A Case Study in Organocatalysis
Practitioners are generally not willing to explore modern reactions where considerable synthetic effort is required to generate materials and the results are not certain. Organocatalysis exemplifies this, in which a broad set of enantioselective reactions have been successfully developed but further applications to include additional substrates are often not performed. Herein we demonstrate how statistical models can be utilized to accurately distinguish between different catalysts and reactions to guide the selection of efficient synthetic routes to obtain a target molecule.
- 14 January 2022
- Published by American Chemical Society (ACS) in Organic Letters
- Vol. 24 (7) , 1429-1433
Guiding Target Synthesis with Statistical Modeling Tools: A Case Study in Organocatalysis
Practitioners are generally not willing to explore modern reactions where considerable synthetic effort is required to generate materials and the results are not certain. Organocatalysis exemplifies this, in which a broad set of enantioselective reactions have been successfully developed but further applications to include additional substrates are often not performed. Herein we demonstrate how statistical models can be utilized to accurately distinguish between different catalysts and reactions to guide the selection of efficient synthetic routes to obtain a target molecule.