Siyuan GUO

Siyuan GUO

Tongji University & City Univeristy of Hong Kong

I am Siyuan Guo, a Ph.D. candidate in Computer Science and Technology at Tongji University, Shanghai, China. My research mainly focuses on Bioinformatics, Precision Medicine, Generative Model, and Multimodal Molecular Learning. I am also interested in applying machine learning and deep learning methods to challenging problems in computational biology and data mining.

Currently, I lead the Bioinformatics Research Team at the ADMIS Lab of Tongji University under the supervision of Prof. Jihong Guan and Prof. Shuigeng Zhou. I am also a joint Ph.D. student at City University of Hong Kong and Tongji University, where I am supervised by Prof. Dapeng Wu (IEEE Fellow) at City University of Hong Kong. My recent work centers on large-scale molecular datasets, diffusion-based molecular generation, and molecular property prediction.

You can find my profiles here: Google Scholar GitHub

🔥 News

  • 2021.06 - Present: Leading the Bioinformatics Research Team at the ADMIS Lab of Tongji University.
  • 2022: Our work “Fusing Geometric and Scene Information for Cross-View Geo-Localization” was published at CIKM 2022.
  • 2024: Our work “Diffusing on two levels and optimizing for multiple properties: A novel approach to generating molecules with desirable properties” was published at IEEE/ACM transactions on computational biology and bioinformatics.
  • 2025: Our work “M^3-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery” was published at Journal of Bioinformatics and Computational Biology.
  • 2025: Our work “Effective and explainable molecular property prediction by chain-of-thought enabled large language models and multi-modal molecular information fusion” was published at Journal of Chemical Information and Modeling.
  • 2025: Our work “Game Theoretical AI for Precision Medicine” was published at Transactions on Artificial Intelligence.
  • Recent: Working on AI-driven drug design and discovery, including large-scale multimodal molecular datasets and diffusion-based molecular generation.

📝 Publications

CIKM 2022
paper

Fusing Geometric and Scene Information for Cross-View Geo-Localization

Siyuan Guo, Tianying Liu, Wengen Li*, Jihong Guan, Shuigeng Zhou

Proceedings of the 31st ACM International Conference on Information & Knowledge Management (CIKM 2022)

  • Proposed a Geometric and Scene Information Fusion (GSIF) model for more accurate cross-view geo-localization.
  • The method effectively fuses geometric information and scene information to improve image matching performance.
JBCB
paper

M3-20M: A Large-Scale Multi-Modal Molecule Dataset for AI-driven Drug Design and Discovery

Siyuan Guo, Lexuan Wang, Changjin Wang, Jinxian Wang, Han Peng, Huayang Shi, Wengen Li, Jihong Guan, Shuigeng Zhou

Journal of Bioinformatics and Computational Biology

  • Introduces M3-20M, a large-scale multimodal molecular dataset containing over 20 million molecules.
  • Integrates SMILES, 2D molecular graphs, 3D molecular structures, physicochemical properties, and text descriptions.
  • Designed to support AI-driven drug design and discovery.
IEEE TCBB
paper

Diffusing on Two Levels and Optimizing for Multiple Properties: A Novel Approach to Generating Molecules with Desirable Properties

Siyuan Guo, Jihong Guan, Shuigeng Zhou

IEEE/ACM transactions on computational biology and bioinformatics

  • Proposes a novel diffusion-based framework for generating molecules with desirable properties.
  • Performs diffusion on both molecule level and molecular fragment level.
  • Explicitly optimizes multiple molecular properties while improving molecular validity.

🎖 Honors and Awards

  • Outstanding Graduate of Tongji University (Top 1%)
  • Best Team Player (Individual Award) in the Microsoft Job Hack Contest
  • Meritorious Winner in the Interdisciplinary Contest in Modeling (ICM)
  • First Prize in the Tongji University Mathematics Modeling Competition
  • Second Prize in the National Chemistry Contest of China (Provincial Level) for High School Students

📖 Educations

  • 2021 - Present, Ph.D. candidate in Computer Science and Technology, Tongji University, Shanghai, China
    • Average Score: 91.76/100
  • 2017 - 2021, Bachelor’s Degree in Computer Science and Technology, Tongji University, Shanghai, China
    • Average Score: 87.52/100

💼 Academic Experience

  • 2021.06 - Present, Leader of the Bioinformatics Research Team, ADMIS Lab, Tongji University
    • Lead a group of Ph.D. candidates and master students to conduct research on bioinformatics, especially molecular generation.
    • Participate in the project New Methods For Predicting Drug Molecular Properties, funded by the National Natural Science Foundation of China under grant No. 62372326.
  • 2020.09 - 2022.06, Main Participant, Research on Human Behavior and Event Evolution Integrating Geographical and Spatial Data Project
    • Proposed the GSIF model for more accurate cross-view geo-localization.
    • Project funded by the National Natural Science Foundation of China under grant No. U1936205.
  • 2021.09 - 2022.06, Teaching Assistant, Database System Concepts Course
    • Helped guide student projects, instruct experiments, and tutor students.

🛠 Skills

  • Programming Languages: Python (PyTorch), PHP, C++, C
  • Platforms: Windows, Linux

  • 💻 Internships

  • 2019.12 - 2020.06, Microsoft, China.

🏃‍♀️ Hobbies:

-Fitness🏋️‍♂️ (35kg bench press, 45kg squat, 60kg deadlift)

-Table tennis🏓