cv

Researcher of AI for physical science

Shanghai Academy of Artificial Intelligence for Science

Applying cutting-edge deep learning techniques to build structure-performance relationships for chemical reactions

• RXNGraphormer

PhD

Zhejiang University

AI for precise chemical synthesis

BEng

East China University of Science and Technology

Applied Chemistry

A unified pre-trained deep learning framework for cross-task reaction performance prediction and synthesis planning

Nature Machine Intelligence

We developed RXNGraphormer, a pre-trained model that learns bond transformation patterns from over 13 million chemical reactions, achieving state-of-the-art accuracy in reaction performance prediction and synthesis planning tasks.

Transfer Learning-Enabled Ligand Prediction for Ni-Catalyzed Atroposelective Suzuki-Miyaura Cross-Coupling Based on Mechanistic Similarity: Leveraging Pd Knowledge for Ni Discovery

Journal of the American Chemical Society

We developed a transfer learning model that can predict the ligand for Ni-catalyzed atroposelective Suzuki-Miyaura cross-coupling reactions based on the mechanism similarity of Pd-catalyzed reactions. (Co-first author, third position)

Electrocatalyzed direct arene alkenylations without directing groups for selective late-stage drug diversification

Nature Communications

We developed a electrocatalytic method for direct arene alkenylations without directing groups for selective late-stage drug diversification. (Co-author)

Reaction performance prediction with an extrapolative and interpretable graph model based on chemical knowledge

Nature Communications

We developed a graph neural network based on chemical knowledge to predict the reaction reactivity and selectivity of chemical reactions. (Co-author)

Data-driven design of new chiral carboxylic acid for construction of indoles with C-central and C-N axial chirality via cobalt catalysis

Nature Communications

We developed a machine learning method to guide the design of new chiral carboxylic acids for the construction of indoles with C-central and C-N axial chirality via cobalt catalysis. (Co-author)

Exploring Spectrum-based Molecular Descriptors for Reaction Performance Prediction

Chemistry - An Asian Journal

We proposed a novel spectrum-based molecular descriptor for reaction performance prediction. (Co-author)

Enantioselectivity prediction of pallada-electrocatalysed C-H activation using transition state knowledge in machine learning

Nature Synthesis

We developed a machine learning model that can predict the enantioselectivity of pallada-electrocatalysed C-H activation reactions based on transition state knowledge. (First author)

Bridging Chemical Knowledge and Machine Learning for Performance Prediction of Organic Synthesis

Chemistry - A European Journal

A review discussing the integration of chemical knowledge and machine learning for performance prediction of organic synthesis. (Co-author)

When machine learning meets molecular synthesis

Trends in Chemistry

A review discussing the integration of machine learning and molecular synthesis. (Co-author)

Towards Data-Driven Design of Asymmetric Hydrogenation of Olefins: Database and Hierarchical Learning

Angewandte Chemie International Edition

We built a large database of asymmetric hydrogenation reactions and developed a hierarchical learning model to predict the enantioselectivity of these reactions. (First author)

A Molecular Stereostructure Descriptor Based On Spherical Projection

Synlett

We designed a molecular descriptor based on spherical projection which could capture subtle variation of molecular steric environment. (First author)

Predicting Regioselectivity in Radical C-H Functionalization of Heterocycles through Machine Learning

Angewandte Chemie International Edition

We developed a machine learning model to predict the regioselectivity of radical C-H functionalization of heterocycles. (Co-author)