研究内容/Research Topics
現在、我々が直面している人口減少・超高齢化と言う大きな課題を解決するためには、メディカルビッグデータに基づく"Evidence-based"ヘルスケアや個別化医療は必修・不可欠です。
AI技術開発分野では、統計科学、情報科学、人工知能などの理論・技術に基づき、健康・医療におけるメディカルビッグデータ解析し、がんなどの疾患の複雑なシステムを理解するためのAI・統計モデリング技術開発及び新手法を用いたバイオメディカル研究を行います。
個別化医療向けた統計モデリング・AI技術開発
近年、医療分野においては、患者個々のDNAやRNAを読み取り、得られたデータの解析から抽出された情報の活用に基づいて治療の成功率の向上を目指すゲノム個別化医療(genomic personalized medicine)の研究が急速に進んでいます。
本研究室では、個別化医療に役立てることを目指し、ゲノム情報等の膨大なパーソナルオミクスデータの解析を通じて疾患の複雑なシステムを理解し、個別化医療へのエビデンスを得るための統計モデルやAI技術開発の研究を行っています。

ネットワークバイオロジ
遺伝子の発現制御関係を表す遺伝子ネットワークは、がんなどの複雑な疾病におけるドライバー遺伝子変異の探索などの複雑な疾患のシステム的理解に向けて活用されています。
本研究室では、メディカルビッグデータに基づき遺伝子ネットワークを構築し、遺伝子制御パターンによるがんの進化なのどの疾患のメカニズムの理解、分子標的薬の感受性予測等に関するネットワークバイオロジ研究を行っています。

研究業績 / Publications
~2022
- H. Park, S. Imoto and S. Miyano.GRN-classifier: Gene regulatory network-based classifier and its applications to gastric cancer drug (5-FU) marker identification.Journal of Computational Biology, In press.
- H. Park, S. Imoto and S. Miyano.PredictiveNetwork: predictive gene network estimation with application to gastric cancer drug response-predictive network analysis. BMC Bioinformatics, 23(1):342. (2022)
- H. Park, R. Yamaguchi, S. Imoto and S. Miyano.Xprediction: Explainable EGFR-TKIs response prediction based on drug sensitivity specific gene networks.PLoS One, 17(5):e0261630. (2022)
- H. Park, R. Yamaguchi, S. Imoto and S. Miyano.Uncovering Molecular Mechanisms of Drug Resistance via Network-Constrained Common Structure Identification. Journal of Computational Biology, 29(3):257-275. (2022)
- H. Park, K. Maruhashi, R. Yamaguchi, S. Imoto and S. Miyano.Global gene network exploration based on explainable artificial intelligence approach. PLoS One, 15(11):e0241508. (2020)
- H. Park, R. Yamaguchi, S. Imoto and S. Miyano.Automatic sparse principal component analysis.Canadian Journal of Statistics, 49(3):678-697. (2020)
~2019
- H. Park and S. Konishi. Sparse kernel subspace method for classifying and representing patterns from data with complex structure. Online first in Communications in Statistics - Simulation and Computation. https://doi.org/10.1080/03610918.2019.1620271. (2019)
- H. Park, M. Yamada, S. Imoto and S. Miyano. Robust sample-specific stability selection with effective error control. Journal of Computational Biology, 26(3): 202-217. (2018)
- H. Park and S. konishi. Sparse common component analysis for multiple high-dimensional datasets via non-centered principal component analysis. Online first in Statistical Papers. https://doi.org/10.1007/s00362-018-1045-6. (2018)
- H. Park, T. Shimamura, S. Imoto and S. Miyano. Adaptive NetworkProfiler for identifying cancer characteristic-specific gene regulatory networks. Journal of Computational Biology, 25: 130-145. (2018) (High-Impact article).
- H. Park. Outlier resistant high dimensional regression modeling based on distribution-free outlier detection and tuning parameter selection. Journal of Statistical Computation and Simulation, 87, 1799-1812. (2017)
- H. Park, Y. Shiraishi, S. Imoto and S. Miyano. Adaptive penalized logistic regression for uncovering biomarker associated with anti-cancer drug sensitivity. IEEE IEEE/ACM Transactions on Computational Biology and Bioinformatics, 14: 771-782. (2017)
- H. Park and S. Konishi. Principal component selection via adaptive regularization method and Generalized information criterion. Statistical Papers, 58: 147-160. (2017)
- H. Park, A. Niida, S. Imoto and S. Miyano. Interaction based feature selection for driver gene selection via copy number driven expression levels, Journal of Computational Biology, 24, 138-152. (2017)
- H. Park and S. Konishi. (2016) Robust regularized nonlinear regression modeling via L_1-type approach. Bulletin Informatics and Cybernetics, 48, 47-61.
- H. Park and S. Konishi. (2016) Robust logistic regression modeling via the elastic net-type regularization and tuning parameter selection. Journal of Statistical Computation and Simulation, 86, 1450-1461.
- H. Park and S. Konishi. (2016) Robust solution path for high dimensional sparse regression modeling, Communications in Statistics - Simulation and Computation, 45:115-129.
- S. Ito, H. Park, Y. Shiraishi, T. Shimamura, Y. Tamada, S. Imoto, S. Miyano. (2016) Comprehensive unravelling of systems disorders of cancer by K computer (in Japanese), Experimental Medicine, 34 (5).
- H. Park, S. Imoto and S. Miyano. (2015) Recursive random lasso for identifying anti-cancer drug targets. PLOS ONE, 10(11).
- H. Park, A. Niida, S. Imoto and S. Miyano. (2015) Sparse overlapping group lasso for integrative multi-omics analysis. Journal of Computational Biology, 22(2), 73-84. (Featured article).
- H. Park and F. Sakaori. (2014) Forecasting symbolic candle chart-valued time series. Communications for Statistical Applications and Methods, 21(6), 471-486.
- H. Park, T. Shimamura, S. Imoto and S. Miyano. (2014) Robust prediction of anti-cancer drug sensitivity and susceptibility-specific biomarker. PLOS ONE, 9(10).
- H. Park, F. Sakaori and S. Konishi. (2014) Robust sparse regression modeling and tuning parameter selection via the efficient bootstrap information criteria, Journal of Statistical Computation and Simulation, 84 (7), 1596-1607.
- H. Park and F. Sakaori. (2013) Lag weighted lasso for time series model, Computational statistics, 28 (2).
- H. Park. (2012) Novel resampling methods for tuning parameter selection in robust sparse regression modeling, Bulletin Informatics and Cybernetics, 44, 49-64.
- H. Park, F. Sakaori and S. Konishi. (2012) Selection of tuning parameters in robust sparse regression modeling, Proceedings of COMPSTAT2012, pp.713-723. A Springer Company.
- H. Park and J. Lee. (2009) Effects of environmental factors on monthly cerebrovascular mortality in Seoul, Korea (in Korean). Journal of the Korean Data Analysis Society, 11, 687-698.