Welcome to THU-ATOM (AI Transforming Optimal Medicine) Lab

Welcome to THU-ATOM Lab at the Institute for AI Industry Research (AIR), Tsinghua University.

Led by Professor Yanyan Lan, our lab is at the forefront of AI for science, focusing on pioneering research in biopharmaceuticals and healthcare. We tackle critical challenges in these fields by leveraging advanced data-driven and deep learning methods, offering solutions that surpass traditional approaches in speed, accuracy, and high-throughput capabilities.

Our research spans a broad spectrum of cutting-edge technologies, including representation learning, generative models, deep graph neural networks, and information retrieval applied to molecules and proteins.

Our grand vision is to accelerate drug design, reduce development costs, expand the boundaries of AI-enabled drug research and development, and make significant contributions to human health.

Join us and be part of this revolutionary journey!

Research
Protein Structure Prediction
Design advanced protein structure prediction pipelines that have better performance than the AlphaFold.
Molecular pretraining
Develop cutting-edge self-supervised learning models for performance boost of molecular property predictions, protein structure predictions and so on.
Ultra-fast virtual screening
Seek extreme speed and accuracy of virtual screening methods to achieve genome-wide drug discovery.
Generative AI drug discovery
Leverage powers of generative models like diffusion-based generative models or autoregressive language models for molecule modification, design and evaluation.
Group
Professor
Postdoc
Hongliang Li
Research Assistant
Wenyu Zhu
Research Assistant
Phd Student
Phd Student
Phd Student
Phd Student
Bicheng Lin
Phd Student
Yanwen Huang
Intern
Jiaxin Zheng
Intern
Alumni
Yuanle Mo
Gaochao Liu
Minghao Li
Minsi Ren
Jianing Li
Recent Publications
Pre-training with Fractional Denoising to Enhance Molecular Property Prediction
Yuancheng Sun,
Zhi-Ming Ma,
Qiwei Ye,
UniCorn: A Unified Contrastive Learning Approach for Multi-view Molecular Representation Learning
Rethinking Specificity in SBDD: Leveraging Delta Score and Energy-Guided Diffusion
ICML 2024/Paper
Protein-ligand binding representation learning from fine-grained interactions
Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
Multimodal Molecular Pretraining via Modality Blending
Qiying Yu,
Yudi Zhang,
Shikun Feng,
Hao Zhou,
Jingjing Liu
ICLR 2024/Paper
Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation
Yuxuan Song,
Jingjing Gong,
Minkai Xu,
Ziyao Cao,
Stefano Ermon,
Hao Zhou,
NeurIPS 2023/Paper
DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening
NeurIPS 2023/Paper/Project Page/Code
Fractional Denoising for 3D Molecular Pre-training
Full Publication List
Projects
Drug The Whole Genome
Jiaxin Tan,
Wenyu Zhu,
Yuan Xiao,
Yanwen Huang,
Yue Jin,
Yafei Yuan,
Jiekang Tian,
Weiying Ma,
Yaqin Zhang,
Chuangye Ye,
Wei Zhang,
Photos
Team building at Baiwangshan in 2024
Group photo of the team on Teachers' Day 2024
ICLR 2024
ICLR 2024
ICLR 2024
Team building with AIR+ in Wuxi 2024
Xin Hong won the team championship in the university's faculty badminton competition
Team badminton activity
Professor Lan's birthday party in 2023
Group photo of the team on Teachers' Day 2023
Group photo of the team on Teachers' Day 2022
Contact Us
Prof. Yanyan Lan
Email: lanyanyan@tsinghua.edu.cn
Address: 12 / F, block C, Qidi science and technology building, Tsinghua Science and Technology Park, Haidian District, Beijing, 100000