CV

Miao-Jiong Tang

Integrated M.S.-Ph.D. student in chemistry, Department of Chemistry, Zhejiang University
Hangzhou, China · mj_t@zju.edu.cn · (+86)136-5663-9176 · CPC member · CET-6
GitHub · Google Scholar · ORCID · PDF CV

Summary

Integrated M.S.-Ph.D. student in chemistry at Zhejiang University, working on data-driven organic synthesis reaction modeling and computational acceleration. My research connects asymmetric catalysis, molecular/reaction data infrastructure, quantum-chemical computation, and graph representation learning; first-author papers in Angew. Chem., Int. Ed., Sci. Data, and Chem. Asian J., with contribution to the Nat. Mach. Intell. RXNGraphormer framework.

Education

Zhejiang University · Chemistry, Integrated M.S.-Ph.D.
Department of Chemistry | Research: data-driven organic synthesis reaction modeling and computational acceleration | Advisor: Prof. Xin Hong
2022.09 - 2027.06 expected | Hangzhou, China

Research focuses on a closed loop of quantum-chemical computation, data construction, model learning, and reaction applications for asymmetric catalysis, molecular properties, and reaction performance prediction.

Zhejiang University · B.S. in Chemistry
Chu Kochen Honors College, Qiushi Chemistry Program | GPA 3.77/4.0 | Advisor: Prof. Xin Hong
2018.09 - 2022.06 | Hangzhou, China

Training in chemistry, programming, scientific computing, and machine learning; early research focused on molecular descriptors, spectrum-based representations, and reaction performance prediction.

Honors, Awards, and Funding

Zhejiang University Qiushi Rising Star doctoral funding, 2026
Zhejiang University Outstanding Graduate Student; NHU Innovation Scholarship
Zhejiang University Outstanding Graduate; Outstanding Communist Youth League Member; MCM Meritorious Winner twice
Academic scholarships (Second Class once, Third Class twice); Chu Kochen Honors College Elite Student Scholarship; provincial SRTP project; National Chemistry Experiment Innovation Design Competition Third Prize

Internship Experience

Fudan Qingpu Institute of Future Technology · Research intern | 2026.07 - present

Designed topological-reaction transition-state generation algorithms and optimized Ascend-based training and inference.

Shanghai Academy of AI for Science · Matter Science Department · Algorithm intern | 2024.07 - 2025.03

Designed fictitious reaction generation algorithms for reaction embeddings, yield/selectivity prediction, and synthesis planning.

Project Experience

MolGR molecular graph reconstruction toolkit
XYZ-to-RDKit molecular graph reconstruction Python package | 2025.12 - present | Lead developer

Developed a C++/Python XYZ-to-RDKit toolkit with bond orders, 3D conformers, optional dative bonds, and stereochemistry; optimized candidate enumeration, scoring, and post-processing for millisecond-level reconstruction and improved metal/spin handling.

N,N′-dioxide asymmetric Michael addition modeling platform
First-author paper: Angew. Chem., Int. Ed. 2026 | 2024.10 - 2025.08 | First author / lead

Curated N,N′-dioxide/metal-catalyzed Michael addition reactions and built mechanism-aware GNN and similarity-weighted extrapolation workflows for catalyst selection and selectivity prediction.

MolOP molecular computation log parser and data engine
Computational chemistry data parsing and automation toolkit | 2023.10 - present | Lead developer

Developed a type-aware, unit-aware, parallelizable parser and data engine for molecular computation logs, supporting quantum-chemical data production and automated workflows.

Tianchi Scientific Intelligence Competition: molecular property prediction
Quantum-chemical energy and force prediction for organic molecules | 2023.08 - 2023.10 | Team member

Used graph neural networks to predict quantum-chemical energies and forces of organic molecules, with model and training-strategy optimization.

QM9star molecular dataset and qm9star_query platform
First-author paper: Sci. Data 2024 | 2023.03 - 2024.06 | First author / lead

Built a DFT-optimized dataset for ions, radicals, and neutral molecules, plus database queries, API services, GNN examples, and tutorials.

Spectrum-based molecular representations for reaction performance prediction
First-author paper: Chem. Asian J. 2023 | 2022.04 - 2023.02 | First author / lead

Parsed molecular NMR spectrum images with image-recognition workflows and applied spectrum-derived vectors to reaction performance prediction.

Professional Skills

Machine learning: Proficient in Python-based research data mining, scripting, and model experimentation; familiar with supervised learning, GNNs, Transformer/pre-training models, and image-processing workflows for molecular property prediction, reaction selectivity, synthesis planning, and spectrum-based representations.

Computational chemistry: Experienced with Gaussian, xTB, and related tools; able to combine Python scripts with computation software for mechanism studies, batch optimization, log parsing, and data production; understands electronic structure, transition states, atomic/bond properties, and 3D conformations for molecular representation and model interpretation.

Ascend and operator optimization: Experienced with the Huawei Ascend platform and operator optimization; able to deploy and profile workloads, locate performance bottlenecks, and improve operator implementations and data flow for Ascend hardware.

Cheminformatics: Experienced with RDKit, OpenBabel, and molecular toolkit extension; able to build molecular and reaction data infrastructure from XYZ/SMILES, computation logs, literature reactions, spectrum images, and quantum-chemical outputs.

Research engineering: Experienced in chemical databases, API services, command-line tools, and reproducible data pipelines; familiar with backend development, Linux, CI/CD, containers, and virtualization for maintainable research software and automated workflows.

Publications

Currently 3 first-author SCI papers and 8 co-authored papers. See the publications page for the complete publication list; the PDF CV lists complete ACS-style citations with representative works first.