Lun-Hsin Kuo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lun-Hsin Kuo has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Albert Qiang
Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California USA
1 shared publicationAline Milach Teixeira
Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California USA
1 shared publicationCamilla M. Power
Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California USA
1 shared publication- Carlynda Lee
Skaggs School of Pharmacy and Pharmaceutical Sciences, University of California San Diego, La Jolla, CA, USA
1 shared publication - Caroline S. Smith
Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California USA
1 shared publication Chloe S. Cerione
Division of Chemistry and Chemical Engineering California Institute of Technology Pasadena California USA
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 148 (39) , 42541-42551
EZSolver: Template-Free Prediction of Polar Enzymatic Mechanisms via Bidirectional Flow Matching and Search
Predicting enzymatic reaction mechanisms is critical for understanding enzyme function and for the design and discovery of new enzymes. Current computational predictors rely on deterministic, rule-based dictionaries, which perform well on in-distribution tasks but fail to generalize to out-of-distribution (OOD) chemistry. To address this limitation, we present EZSolver for the polar enzymatic mechanism prediction. Powered by a flow-matching predictor (EZFlow), a template-free, generative framework, and navigated by an evaluator-guided bidirectional beam search, EZSolver learns the chemistry of electron redistribution instead of memorizing rigid templates. Evaluated across diverse enzyme classes, EZSolver achieves a 60.0% accuracy and an 84.6% chemical plausibility rate for the full-mechanism prediction of unseen polar enzymatic reactions. While rule-based models collapse without predefined templates, EZSolver successfully extrapolates chemical knowledge to infer uncatalogued pathways, as demonstrated during rigorous OOD benchmarking. By illuminating enzymatic chemical mechanisms, EZSolver helps pave the way for the automated prediction of enzyme function and the discovery and design of novel biocatalysts for sustainable chemistry.
- 22 September 2026
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 148 (39) , 42541-42551
Open AccessEZSolver: Template-Free Prediction of Polar Enzymatic Mechanisms via Bidirectional Flow Matching and Search
Predicting enzymatic reaction mechanisms is critical for understanding enzyme function and for the design and discovery of new enzymes. Current computational predictors rely on deterministic, rule-based dictionaries, which perform well on in-distribution tasks but fail to generalize to out-of-distribution (OOD) chemistry. To address this limitation, we present EZSolver for the polar enzymatic mechanism prediction. Powered by a flow-matching predictor (EZFlow), a template-free, generative framework, and navigated by an evaluator-guided bidirectional beam search, EZSolver learns the chemistry of electron redistribution instead of memorizing rigid templates. Evaluated across diverse enzyme classes, EZSolver achieves a 60.0% accuracy and an 84.6% chemical plausibility rate for the full-mechanism prediction of unseen polar enzymatic reactions. While rule-based models collapse without predefined templates, EZSolver successfully extrapolates chemical knowledge to infer uncatalogued pathways, as demonstrated during rigorous OOD benchmarking. By illuminating enzymatic chemical mechanisms, EZSolver helps pave the way for the automated prediction of enzyme function and the discovery and design of novel biocatalysts for sustainable chemistry.
- Open Access
- 21 August 2026
- Published by Wiley in ChemBioChem
- Vol. 27 (16) , e70485
Chemical Biology 2025: Highlights From the Ch/Bi145 Course at Caltech
This review highlights key advances in chemical biology reported in 2025, curated by students in the Advanced Chemical Biology course (Ch/Bi145) at the California Institute of Technology (Caltech). The selected studies span advances in bioconjugation and bioorthogonal chemistry, visualization and sensing, interaction profiling, precision control of biological systems, emerging therapeutic modalities, and synthetic chemical biology. Together, they illustrate how innovative molecular design continues to expand our ability to interrogate and manipulate biological systems.
- 21 August 2026
- Published by Wiley in ChemBioChem
- Vol. 27 (16) , e70485
Open AccessChemical Biology 2025: Highlights From the Ch/Bi145 Course at Caltech
This review highlights key advances in chemical biology reported in 2025, curated by students in the Advanced Chemical Biology course (Ch/Bi145) at the California Institute of Technology (Caltech). The selected studies span advances in bioconjugation and bioorthogonal chemistry, visualization and sensing, interaction profiling, precision control of biological systems, emerging therapeutic modalities, and synthetic chemical biology. Together, they illustrate how innovative molecular design continues to expand our ability to interrogate and manipulate biological systems.
- Open Access
EZSolver: Template-free prediction of polar enzymatic mechanisms via bidirectional flow matching and search
Predicting enzymatic reaction mechanisms is critical for understanding enzyme function and for designing and discovering new enzymes. Current computational predictors rely on deterministic, rule-based dictionaries, which perform well on in-distribution tasks but fail to generalize to out-of-distribution (OOD) chemistry. To address this limitation, we present EZSolver, a template-free, generative framework for polar enzymatic mechanism prediction. Powered by a flow matching predictor (EZFlow) and navigated by an evaluator-guided bidirectional beam search, EZSolver learns the chemistry of electron redistribution instead of memorizing rigid templates. Evaluated across diverse enzyme classes, EZSolver achieves a 60.0% accuracy and an 84.6% chemical plausibility rate for full mechanism prediction of unseen polar enzymatic reactions. While rule-based models collapse without predefined templates, EZSolver successfully extrapolates chemical knowledge to infer uncatalogued pathways, as demonstrated during rigorous OOD benchmarking. By illuminating enzymatic chemical mechanisms, EZSolver helps pave the way for automated prediction of enzyme function and discovery and design of novel biocatalysts for sustainable chemistry. TOC Graphic:
Open AccessEZSolver: Template-free prediction of polar enzymatic mechanisms via bidirectional flow matching and search
Predicting enzymatic reaction mechanisms is critical for understanding enzyme function and for designing and discovering new enzymes. Current computational predictors rely on deterministic, rule-based dictionaries, which perform well on in-distribution tasks but fail to generalize to out-of-distribution (OOD) chemistry. To address this limitation, we present EZSolver, a template-free, generative framework for polar enzymatic mechanism prediction. Powered by a flow matching predictor (EZFlow) and navigated by an evaluator-guided bidirectional beam search, EZSolver learns the chemistry of electron redistribution instead of memorizing rigid templates. Evaluated across diverse enzyme classes, EZSolver achieves a 60.0% accuracy and an 84.6% chemical plausibility rate for full mechanism prediction of unseen polar enzymatic reactions. While rule-based models collapse without predefined templates, EZSolver successfully extrapolates chemical knowledge to infer uncatalogued pathways, as demonstrated during rigorous OOD benchmarking. By illuminating enzymatic chemical mechanisms, EZSolver helps pave the way for automated prediction of enzyme function and discovery and design of novel biocatalysts for sustainable chemistry. TOC Graphic: