Wonho Zhung

Wonho Zhung

Ph.D. Student in Intelligent Chemistry Lab (ICL), advised by Prof. Woo Youn Kim in Korea Advanced Institute of Science and Technology (KAIST)

Intelligent Chemistry Lab

Biography

I am a Ph.D. student at the Intelligent Chemistry Lab at KAIST (PI: Prof. Woo Youn Kim). My goal is to devise deep learning strategies for finding hit compounds to lessen the time and cost consumed in early-stage drug discovery. I’m currently working on protein-ligand binding affinity prediction and generative modeling for structure-based ligand design. Other approaches regarding the biochemical application of deep learning are highly intrigued.

Besides research, I love playing the violin. As a violinist in the KAIST orchestra, I enjoy performing classical music in ensembles.

Interests
  • DL for chemical & biological application
  • Structure-based Drug Design (SBDD)
  • 3D Graph Neural Networks (3D GNNs)
  • Generative models
Education

  • BSc in Chemistry and Biological Science (Double Major), 2020

    Korea Advanced Institute of Science and Technology (KAIST)

Experience

 
 
 
 
 
Research Project
Intelligent Chemistry Lab (ICL)
Feb 2024 – Present Dept. of Chemistry, KAIST, Republic of Korea
Non-covalent Interaction-generative Diffusion Model for Reliable 3D Molecule Design.
(Supervised by Prof. Wooyoun Kim, Dept. of Chemistry, KAIST)
 
 
 
 
 
Research Project
Intelligent Chemistry Lab (ICL)
Sep 2023 – Present Dept. of Chemistry, KAIST, Republic of Korea
Discovering Bioisosteres with Deep Learning for a Fine Control of Multiple Molecular Properties.
(Supervised by Prof. Wooyoun Kim, Dept. of Chemistry, KAIST)
 
 
 
 
 
Research Project
Intelligent Chemistry Lab (ICL)
Sep 2022 – Mar 2024 Dept. of Chemistry, KAIST, Republic of Korea
3D Molecular Generative Framework for Interaction-guided Drug Design.
(Supervised by Prof. Wooyoun Kim, Dept. of Chemistry, KAIST)
 
 
 
 
 
Research Project
Intelligent Chemistry Lab (ICL)
Mar 2022 – Aug 2022 Dept. of Chemistry, KAIST, Republic of Korea
Spatially Constrained 3D Scaffold-based Molecular Generative Modeling Toward a Controllable Drug Design.
(Supervised by Prof. Wooyoun Kim, Dept. of Chemistry, KAIST)
 
 
 
 
 
Research Project
Intelligent Chemistry Lab (ICL)
Dec 2019 – Feb 2022 Dept. of Chemistry, KAIST, Republic of Korea
Physically Informed Graph Neural Network for Predicting Drug-target Interaction.
(Supervised by Prof. Wooyoun Kim, Dept. of Chemistry, KAIST)
 
 
 
 
 
MGH-MIT-KAIST Summer Internship Program
Wellman Center for Photomedicine
Jul 2019 – Aug 2019 Massachusetts General Hospital (MGH), Boston, USA
Designing Nano-constructs to Modulate Cellular Uptake and Enhance Photodynamic Therapy Efficacy in Pancreatic Cancer.
(Supervised by Prof. Tayyaba Hasan, Dept. of Dermatology, MGH)
 
 
 
 
 
Undergraduate Researcher
Bio-Nanomedicine Lab (BNL)
Dec 2017 – Dec 2018 Dept. of Biological Science, KAIST, Republic of Korea
Development of Biotinylated Bilirubin Nanoparticle for Potential Anti-inflammation Therapy.
(Supervised by Prof. Sangyong Jon, Dept. of Biological Science, KAIST)
 
 
 
 
 
Summer Session
University of California, Berkeley
Jul 2016 – Aug 2016 USA

Recent Publications

NCIDiff: Non-covalent Interaction-generative Diffusion Model for Improving Reliability of 3D Molecule Generation Inside Protein Pocket
Advancements in deep generative modeling have changed the paradigm of drug discovery. Among such approaches, target-aware methods that …
Wonho Zhung, Joongwon Lee, Woo Youn Kim*
PDF Cite DOI
DeepBioisostere: Discovering Bioisosteres with Deep Learning for a Fine Control of Multiple Molecular Properties
Optimizing molecules to improve their properties is a fundamental challenge in drug design. For a fine-tuning of molecular properties …
Hyeongwoo Kim, Seokhyun Moon, Wonho Zhung, Jaechang Lim, Woo Youn Kim*
PDF Cite DOI
3D Molecular Generative Framework for Interaction-guided Drug Design
Deep generative modeling has a strong potential to accelerate drug design. However, existing generative models often face challenges in …
Wonho Zhung, Hyeongwoo Kim, Woo Youn Kim*
PDF Cite DOI
Toward Generalizable Structure-based Deep Learning Models for Protein–ligand Interaction Prediction: Challenges and Strategies
Accurate and rapid prediction of protein–ligand interactions (PLIs) is the fundamental challenge of drug discovery. Deep learning …
Wonho Zhung, Seokhyun Moon, Woo Youn Kim*
PDF Cite DOI
Photoimmunotherapy Retains Its Anti-Tumor Efficacy with Increasing Stromal Content in Heterotypic Pancreatic Cancer Spheroids
Mohammad A. Saad, Wonho Zhung, Margaret Elizabeth Stanley, Sydney Formica, Stacey Grimaldo-Garcia, Girgis Obaid, Tayyaba Hasan*
PDF DOI
See all publications

Recent Posts

Tutorial: Protein-Ligand Complex MD Simulation with OpenMM
OpenMM toolkit을 이용한 protein-ligand complex MD simulation 맛보기
Last updated on Jun 17, 2022 3 min read
Tutorial: Tethered Docking with RxDock
RxDock의 scaffold-based tethered docking 기능 맛보기
Last updated on Jun 30, 2022 5 min read
NVAE: A Deep Hierarchical Variational Autoencoder
This post is based on a paper “NVAE: A Deep Hierarchical Variational Autoencoder” by Arash Vahdat and Jan Kautz at NeurIPS 2020.
Last updated on Sep 29, 2021 5 min read
Pixel Recurrent Neural Networks
This post is based on a paper “Recurrent Pixel Neural Networks” by Oord et al. at ICML 2016.
Last updated on Sep 29, 2021 4 min read
SchNet: A Continuous-filter convolutional neural network for modeling quantum interactions
This post is based on a paper “SchNet: A Continuous-filter convolutional neural network for modeling quantum interactions” by Kristof T. Schütt, Klaus-Robert Müller at NeurIPS 2017.
Last updated on Mar 29, 2022 5 min read
See all posts

Popular Topics

3D Molecular generative model 3D Representation AI602 Autoregressive Bayesian Bioisostere Deep learning Diffusion model Docking Drug discovery Drug-Target Interaction Generalizability Generalization Graph Neural Network Hodu MD Paper Summary Protein-ligand interaction SBDD Structure-based drug design

Contact