Odin Zhang[张昊天]
(HaotianZhang)
Dual B.S. in Physics and Pharmaceutics at ZJU
Ph.D. in Computer Science at UW Allen School
odinz [AT] uw.edu
Bio
Hello! I'm Odin. My English name closely resembles the pronunciation of my Chinese name and carries a double meaning: 昊天, akin to a deity in Chinese Taoism, and Odin, the chief god in Norse mythology. I earned a dual B.S. in Physics and Pharmaceutics from Zhejiang University in 2022, advised by Prof. Tingjun Hou, focusing on small molecule (drug) design. I then graduated one year ahead of schedule with an M.S. in Medical Science from Zhejiang University and was honored with the university’s highest distinction — the Chu Kochen Scholarship. In 2024, I began my Ph.D. studies at the University of Washington, focusing on protein design under the supervision of Prof. David Baker. In 2025, I obtained my Computer Science Master’s degree and transferred to The Chinese University of Hong Kong (CUHK) to continue my Ph.D., co-supervised by Prof. Pheng-Ann Heng, Prof. David Baker, and Prof. Gaurav Bhardwaj. My current research centers on multi-modal molecular design, where I lead the development of ODesign, the first all-to-all generative model for molecular design across multiple modalities. I'm always open to potential collaborations and am passionate about crazy ideas. My CV could be found here.
Previously, I interned at Carbon Silicon AI in Hangzhou, and worked as an AI consultant for Pledge Therapeutics in Boston. Currently, I am endeavoring to establish a startup to realize my ambitious vision for the next generation of molecular design: a system that is driven by generative AI, underpinned by physical constraints and domain knowledge, all tailored to serve the needs of expert molecular designers.
Beyond my professional pursuits, I am a contemporary hippie. I continually question the meaning of life and engage in dialogues with the ancient Greek philosophers, Buddha, Romantic poets, and hermits. I am on a perpetual quest for truth. I aim to bring a vision of eternal freedom to all beings through acts of kindness and bizarre behaviors. If you share similar thoughts, please talk to me. I am glad to meet you on the road. As Albert Camus said, "Do not walk behind me, for I may not lead; do not walk in front of me, for I may not follow; just walk beside me and be my friend."
——在众神当中只有我最易朽
News
Publications [Google Scholar]
* indicates equal contribution.Book
Graph Neural Networks in Modern AI-Aided Drug Discovery
Odin Zhang*, Haitao Lin*, Xujun Zhang*, Xiaorui Wang*, ...., Tingjun Hou.
A year and a half of work reviewing over 500 papers, this book connects the frontiers of GNNs—from uncertainty and interpretability to Graph Transformers—with the landscape of AI-driven drug discovery, defining my early scientific vision.
Chem. Rev., 2025
Molecular Design
ECloudGen: leveraging electron clouds as a latent variable to scale up structure-based molecular design
Odin Zhang*, Jieyu Jin*, Zhenxing Wu*, ..., Chang-yu Hsieh, Tingjun Hou
We introduced the Generative Chemical Space Paradox and developed ECloudGen to address it, treating electron clouds as latent variables to bridge structural and textual molecular representations.
Nat. Compt. Sci., 2025
Deep Lead Optimization: Leveraging Generative AI for Structural Modification
Odin Zhang*, Haitao Lin* ..., Peichen Pan, Tingjun Hou
J. Am. Chem. Soc., 2024, 146, 46, 31357–31370
We categorized two main types of lead optimization, goal-directed and structure-directed. Then we first idenfitied four sub-tasks of the structure-directed one.
Deep lead optimization enveloped in protein pocket and its application in designing potent and selective ligands targeting LTK protein
Shicheng Chen*, Odin Zhang*, Chenran Jiang*, Huifeng Zhao*, Xujun Zhang*, ..., Chang-yu Hsieh, Yong Huang, Tingjun Hou, Peichen Pan
Nat. Mach. Intell., 7, 448–458 (2025)
When you face some problems in drug discovery, just delete!
PPFLOW: Target-Aware Peptide Design with Torsional Flow Matching
Haitao Lin*, Odin Zhang*, Huifeng Zhao, ..., Stan.Z. Li
PPFLOW formulates peptide generation as a torsional flow matching process, allowing structure-conditioned, target-aware peptide design with accurate conformational control.
ICLR, 2024
SurfGen: Learning on Topological Surface and Geometric Structure for 3D Molecular Generation
Odin Zhang*, Tianyue Wang*, Gaoqi Weng, ..., Chang-yu Hsieh, Tingjun Hou.
Nat. Compt. Sci, 3, 849–859 (2023)
Inspired from key-and-lock model, we build a 3D molecular design model directly on topological protein surface through Geodesic-GNN and Geoatton-GNN, which satisfy the physical equivariance.
ResGen: Learning the Interaction Patterns through Multiscale Modeling and SE(3)-Framework for 3D-Pocket Molecular Generation
Odin Zhang, Jintu Zhang, Xujun Zhang, ..., Chang-yu Hsieh, Tingjun Hou.
Nat. Mach. Intell., 5, 1020–1030 (2023)
We construct a novel 3D Pocket-aware molecular generation model via multi-scale modeling, achieving SOTA performance on CrossDock dataset and our curated real-world dataset.
Structure Prediction and Virtual Screening
Protein–peptide docking with a rational and accurate diffusion generative model
Huifeng Zhao, Odin Zhang#,..., Tingjun Hou#, Yu Kang#
(corresponding author)We introduced RAPiDock, a diffusion-based generative model that learns to dock peptides into proteins with atomic-level accuracy.
Nat. Mach. Intell., 7, 1308–1321 (2025)
KarmaDock: a deep learning paradigm for ultra-large library docking with fast speed and high accuracy
Xujun Zhang*, Odin Zhang*, ..., Chang-yu Hsieh, Tingjun Hou.
Nat. Compt. Sci.,3, 739–740 (2023).
A Deep Learning-based docking method, from binding pose to virtual screening.
Re-Dock: Towards Flexible and Realistic Molecular Docking with Diffusion Bridge
Yufei Huang*, Odin Zhang*, Lirong Wu, ..., Stan.Z. Li
We developed Re-Dock, a diffusion-bridge framework that enables flexible and realistic molecular docking starting from apo protein conformations.
ICLR, 2024
Leveraging language model for advanced multiproperty molecular optimization via prompt engineering
Wu, Zhenxing, Odin Zhang, ..., Tingjun Hou
Nat. Mach. Intell.(2024): 1-11.
We introduced the prompt engineering for molecular optimization, generalizing single-objective to multi-objectve optimization tasks
Highly accurate and efficient deep learning paradigm for full-atom protein loop modeling with KarmaLoop
Tianyue Wang*, Xujun Zhang*, Odin Zhang*, ..., Chang-yu Hsieh, Tingjun Hou.
Research7 (2024): 0408.
A SOTA method for the geometry prediction of the loop domain in proteins
SDEGen: Learning to Evolve Molecular Conformations from Thermodynamic Noise for Conformation Generation
Odin Zhang*, ShengMing Li*, Jintu Zhang, .., Yu Kang, Tingjun Hou.
Chem. Sci., 14, 1557-1568
We construct a novel conformation generation model via the stochastic differential equation-based generative model, which is a kind of diffusion process.
Infinite Physical Monkey: Do Deep Learning Methods Really Perform Better in Conformation Generation?
Odin Zhang, Jintu Zhang, Huifeng Zhao, Dejun Jiang, Yafeng Deng.
Bio Arxiv
We present our opinions on conformation generation, discussing another two papers on arxiv platform
Classical CADD and Molecular Dynamics
Quasiclassical Trajectory Simulation as a Protocol to Build Locally Accurate Machine Learning Potentials
Jintu Zhang*, Odin Zhang*, Zhixin Qin, Yu Kang, Xin Hong, Tingjun Hou.
J. Chem. Inf. Model. 2023, 63, 4, 1133–1142
We show that quasiclassical trajectory (QCT) calculations can be invoked to efficiently obtain locally accurate ML-PESs, thus accelearing molecular dynamics
Boxing
I am also a boxing enthusiast, because "faced with the overpowering savagery of a king-like force, truth, knowledge, thought, understanding, and wit all flee, banished from the battlefield."
I am a thorough hippie, and I like to describe myself with rock and roll. Research, boxing, and religion are merely metaphors of my existence. I pursue freedom, absurdity, and the impossible eternity.
Zan/Pessimistic/Romantic
Dedicate to HanShan and The Dharma Bums 我不是真的想成功， 我只是想自由地失败。
山中何太冷，自古非今年。
沓嶂恒凝雪，幽林每吐烟。
草生芒种后，叶落立秋前。
此有沉迷客，窥窥不见天。
It's cold in the mountains, and not just this year.
The jagged cliffs are always piled high with snow, and the deep canyon species of trees are always spitting mist outward.
The grass is still sprouting in June, and the leaves start falling in August when they first arrive.
And here I was, mesmerized like a drug addict who had just finished a hit.
从明天起，做一个幸福的人
喂马，劈柴，周游世界
从明天起，关心粮食和蔬菜
我有一所房子，面朝大海，春暖花开
从明天起，和每一个亲人通信
告诉他们我的幸福
那幸福的闪电告诉我的
我将告诉每一个人
给每一条河每一座山取一个温暖的名字
陌生人，我也为你祝福
愿你有一个灿烂的前程
愿你有情人终成眷属
愿你在尘世获得幸福
我只愿面朝大海，春暖花开
Face to the sea,spring blossoms
From tomorrow,be a felicific man.
Feed a horse,split firewood,
and travel around the world.
From tomorrow,only care about cereal and vegerable.
I have a house facing to the sea.
There is spring all the year around and all is blooming.
From tomorrow,communciate with every kinsfolk.
Tell them my happiness.
What the felicific lightning has told me is
what I will tell everyone.
Give every river and every mountain a fragant name.
Stranger,I also bless you.
Hope you have boundless prospects.
Hope you have your Jack or Jill.
Hope you find your happiness in the world.
I only shall face to the sea and long for spring blossoms.
A conversation at the bottom of the heart
You have fulfilled your long-standing dream, and broken through all obstacles.
Why do you still feel so painful?
At the moment I realise my dream,
I really felt great satisfaction at the bottom of my heart.
But almost in an instant,
I felt the endless nothingness.
What did the aurora bring to me?
There seems to be nothing.
I still clearly remember the palpitation in my heart when I dreamed of seeing the aurora as a child,
but when I grew up, the throbbing became lighter and lighter.
I was overwhelmed by life, and was no longer able to complete the so-called dream.
But when I buried my dream,
my heart was unwilling.
So, I' ve tried my best,
and came here with the body that I didn't know how long I could live,
I long for the aurora to bring me an eternal meaning,
so that I can fight (against) life bravely.
But that doesn't exist.
It has no meaning at all.
My life will not change, and my story will not fly to the blue sky.
In that case, what is the meaning of life?
The dream that can be moved for it will be dull after it is realized.
All our pursues will turn into nothingness in the end.
Why should we purse it?
So, I'm not going to go on.
Since life has no meaning, let me go.
Let me go to the abyss, to embrace the eternal nothingness,
to embrace the eternal death.