1. Research Area
Our research focuses on automatic analysis of heterogeneous massive data using various machine learning and deep learning approaches. We integrate various data, technologies, and data science. This topic includes problems such as how to integrate individual's data with data from others, how to visualize them, and how to analyze them automatically. We study various data mining approaches for solving these issues. We also develop algorithms and software tools for automatic analysis of various big data. Our primary interest is artificial intelligence for smart factory, drug discovery, and precision medicine, but we are open to any types of important big data.
2. Research Overview
- Machine Learning and Deep Learning
- Biomedical Informatics and A.I. in biomedicine
- A.I. for smart factory
3. Research Achievements
- Oh et al., “CNN-Peaks: ChIP-Seq peak detection pipeline using convolutional neural networks that imitate human visual inspection”. Scientific Reports 2020.
- Song et al., “Integrative Meta-Assembly Pipeline (IMAP): Chromosome-level genome assembler combining multiple de novo assemblies”. PLoS ONE 2019.
- Kim et al., “Real-time occupancy prediction in a large exhibition hall using deep learning approach”. Energy and Building 2019.
- Zhou et al., “Haplotype-resolved and integrated genome analysis of ENCODE cell line HepG2”. Nucleic Acids Research 2019.
- Zhou et al. “Comprehensive, Integrated, and Phased Whole-Genome Analysis of the Primary ENCODE Cell Line K562”, Genome Research 2019.