Accurate, reliable and interpretable solubility prediction of druglike molecules with attention pooling and Bayesian learning

no code implementations • 29 Sep 2022 • Seongok Ryu, Sumin Lee

In drug discovery, aqueous solubility is an important pharmacokinetic property which affects absorption and assay availability of drug.

Bayesian Inference Decision Making +1

Hit and Lead Discovery with Explorative RL and Fragment-based Molecule Generation

no code implementations • NeurIPS 2021 • Soojung Yang, Doyeong Hwang, Seul Lee, Seongok Ryu, Sung Ju Hwang

We further show with ablation studies that our method, predictive error-PER (FREED(PE)), significantly improves the model performance.

Molecular Docking Reinforcement Learning (RL)

A benchmark study on reliable molecular supervised learning via Bayesian learning

1 code implementation • 12 Jun 2020 • Doyeong Hwang, Grace Lee, Hanseok Jo, Seyoul Yoon, Seongok Ryu

Virtual screening aims to find desirable compounds from chemical library by using computational methods.

BIG-bench Machine Learning

A comprehensive study on the prediction reliability of graph neural networks for virtual screening

no code implementations • 17 Mar 2020 • Soojung Yang, Kyung Hoon Lee, Seongok Ryu

Prediction models based on deep neural networks are increasingly gaining attention for fast and accurate virtual screening systems.

Decision Making General Classification

Molecular Generative Model Based On Adversarially Regularized Autoencoder

1 code implementation • 13 Nov 2019 • Seung Hwan Hong, Jaechang Lim, Seongok Ryu, Woo Youn Kim

All models reported so far are based on either variational autoencoder (VAE) or generative adversarial network (GAN).

Generative Adversarial Network

Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks

no code implementations • 17 Apr 2019 • Jaechang Lim, Seongok Ryu, Kyubyong Park, Yo Joong Choe, Jiyeon Ham, Woo Youn Kim

Accurate prediction of drug-target interaction (DTI) is essential for in silico drug design.

Graph Attention Pose Prediction

Uncertainty quantification of molecular property prediction with Bayesian neural networks

no code implementations • 20 Mar 2019 • Seongok Ryu, Yongchan Kwon, Woo Youn Kim

Deep neural networks have outperformed existing machine learning models in various molecular applications.

Molecular Property Prediction Property Prediction +1

Uncertainty quantification of molecular property prediction using Bayesian neural network models

no code implementations • 19 Nov 2018 • Seongok Ryu, Yongchan Kwon, Woo Youn Kim

In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions.

Molecular Property Prediction Property Prediction +1

Molecular generative model based on conditional variational autoencoder for de novo molecular design

1 code implementation • 15 Jun 2018 • Jaechang Lim, Seongok Ryu, Jin Woo Kim, Woo Youn Kim

We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design.

Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network

1 code implementation • 28 May 2018 • Seongok Ryu, Jaechang Lim, Seung Hwan Hong, Woo Youn Kim

Molecular structure-property relationships are key to molecular engineering for materials and drug discovery.

Drug Discovery