- Date of birth: October, 15, 1991
- Address: AITRICS
- E-mail: seongokryu@aitrics.com
- Github: http://github.com/seongokryu
Profile
Hi, I am a Research scientist working for AITRICS. I am managing the team that develops machine learning systems accelerate drug discovery processes. Our team has strong skills on graph neural networks, Bayesian deep learning, and deep generative models, all of those are evidentaly necessary for developing AIs in drug discovery. We have been developing various prediction systems across bio-activity, toxicity, and ADME properties, which allows reliable predictions via Bayesian learning algorithms.
Affiliation
- 2020. 02 ~ : Research Scientist, AITRICS
Education
- 2014. 02 ~ 2020. 02 : Ph.D in Chemistry, KAIST
- 2009. 02 ~ 2014. 02 : B.S. in Chemistry and Physics, KAIST
Research Interest
- Graph Neural Networks
- Generative Models of Molecules
- Bayesian Deep Learning
- Applications of Deep Learning for Drug Discovery
- Data Efficient Deep Learning with Self-supervised Learning, Transfer Learning, etc..
Teaching experience
- General Chemistry Experiment I - 2014 Spring
- Chemistry Experiment I - 2016 Fall
- Physical Chemistry I - 2015 Spring, 2016 Spring, 2017 Spring and 2018 Spring
- Physical Chemistry II - 2015 Fall and 2017 Fall
- Artificial Intelligence and Chemistry - 2018 Fall
Technical
- C++
- Python
- TensorFlow and PyTorch
- Linux
Publications
- Molecular generative model based on adversarially regularized autoencoder
- Seung Hwan Hong, Jaechang Lim, Seongok Ryu, Woo Youn Kim, Journal of Chemical Information and Modeling, (2020)
- Predicting Drug-target Interaction Using a Novel Graph Neural Network with 3D Structure-embedded Graph Representation
- Jaechang Lim, Seongok Ryu, Kyubyong Park, Yojoong Choe, Jiyeon Ham, and Woo Youn Kim, Journal of Chemical Information and Modeling, (2019)
- A Bayesian graph convolutional network for reliable prediction of molecular properties with uncertainty quantification
- Seongok Ryu, Yongchan Kwon, and Woo Youn Kim, Chemical Science (2019)
- Deeply learning molecular structure-property relationships using attention- and gate- augmented neural network
- Seongok Ryu, Jaechang Lim, and Woo Youn Kim. arXiv:1805.10988 (2018)
- Molecular generative model based on conditional variational autoencoder for de novo molecular design
- Jaechang Lim, Seongok Ryu, Jin Woo Kim, and Woo Youn Kim. arXiv:1806.05805 (2018)
- Effects of the locality of a potential derived from hybrid density functionals on Kohn–Sham orbitals and excited states
- Jaewook Kim, Kwangwoo Hong, Sang-Yeon Hwang, Seongok Ryu, Sunghwan Choi, and Woo Youn Kim. Physical Chemistry Chemical Physics 19.15 (2017), 10177-10186.
- Update to ACE‐molecule: Projector augmented wave method on lagrange‐sinc basis set
- Sungwoo Kang, Seongok Ryu, Sunghwan Choi, Jaewook Kim, Kwangwoo Hong, and Woo Youn Kim. International Journal of Quantum Chemistry 116.8 (2016), 644-650.
- Supersampling method for efficient grid-based electronic structure calculations
- Seongok Ryu, Sunghwan Choi, Jaewook Kim, Kwangwoo Hong, and Woo Youn Kim. The Journal of chemical physics 144.9 (2016), 094101.