Junseok Choe
A5017744069- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Chemical Synthesis and Analysis
- Computational Drug Discovery Methods
- Molecular Biology Techniques and Applications
- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- Click Chemistry and Applications
Korea University
2020-2023
Abstract Motivation Recent advances in deep learning have offered solutions to many biomedical tasks. However, there remains a challenge applying survival analysis using human cancer transcriptome data. As the number of genes, input variables model, is larger than amount available patient samples, deep-learning models are prone overfitting. To address issue, we introduce new architecture called VAECox. VAECox uses transfer and fine tuning. Results We pre-trained variational autoencoder on...
Abstract Motivation Protein–ligand binding affinity prediction is a central task in drug design and development. Cross-modal attention mechanism has recently become core component of many deep learning models due to its potential improve model explainability. Non-covalent interactions (NCIs), one the most critical domain knowledge task, should be incorporated into protein–ligand for more explainable drug–target interaction models. We propose ArkDTA, novel neural architecture guided by NCIs....
Abstract Objective Applications of machine learning in healthcare are high interest and have the potential to improve patient care. Yet, real-world accuracy these models clinical practice on different subpopulations remains unclear. To address important questions, we hosted a community challenge evaluate methods that predict outcomes. We focused prediction all-cause mortality as question. Materials Using Model-to-Data framework, 345 registered participants, coalescing into 25 independent...
Abstract Applications of machine learning in healthcare are high interest and have the potential to significantly improve patient care. Yet, real-world accuracy performance these models on different subpopulations remains unclear. To address important questions, we hosted a community challenge evaluate methods that predict outcomes. overcome privacy concerns, employed Model-to-Data approach, allowing citizen scientists researchers train private health data without direct access data. We...