Prof Xuejun Liu
	College of Computer Science & Technology Nanjing University of Aeronautics & Astronautics 29 Jiangjun Road, Jiangning District Nanjing, 211106 Phone: +86 (0)25 84896491-16212 E-mail: xuejun.liu@nuaa.edu.cn

Research Interests

• Machine learning and its applications

  Machine learning techniques aim to discover the underlying mechanisms among experimental data. For biological data, we can reveal new biological knowledge to help with cure of diseases, and for aerodynamic data, such as wind tunnel data, laws of aerodynymanic physics can be efficiently and acurrately established and thus contribute to the design of aircrafts.

• Machine learning aided numerical simulation technology

  Numerical simulation is a technology relying on computers to solve problems in nature and engineering through modeling, finite element analysis, numerical calculation and image display. Machine learning can be utilized to assist some stages of numerical simulation so as to efficiently obtain more accurate simulation results.

  
  

Teachings

• Algorithm design and analysis
• Multivariate statistical analysis
• Machining learning
  

Graduate Students

• Zhao, Shuchang (PhD)
• Wu, Haizhou (PhD)
• Liu, Zijing (PhD)
• Qu, Xiyao (PhD)
• Xuan, Yang
• Ding, Ziyuan
• Xu, Shanjie
• Li, Caiyun
• Yu, Jian (PhD)
• Xu, Ran
• Wang, Zhipeng
• Wang, Hongfei
• Yu, Boyang
  

Former Students

Publications

• Liu, Z., Liu, X.*, An, W., Qu, X. and Lyu, H., Portfolio-Based Bayesian Optimization for Airfoil Design, AIAA Journal , 2021 accepted.
  
• Wu, T., Liu, X.*, An, W., Huang, Z. and Lyu, H., A Mesh Optimization Method Using Machine Learning Technique and Variational Mesh Adaptation, Chinese Journal of Aeronautics , 2021 accepted.
  
• Wu, H., Liu, X.*, An, W. and Lyu, H., A generative deep learning framework for airfoil flow field prediction with sparse data, Chinese Journal of Aeronautics , 2021 accepted.
  
• Li, J., Liu, X.* and Zhang, D., Detecting differential transcript usage across multiple conditions for RNA-seq data based on the smoothed LDA model, Frontiers of Computer Science , 2021 15: 153319.
  
• Wu, H., Liu, X.*, An, W., Chen, S. and Lyu, H., A deep learning approach for efficiently and accurately evaluating the flow field of supercritical airfoils, Computers and Fluids , 2020 198: 104393.
  
• Yu, X. and Liu, X.*, Mapping RNA-seq reads to transcriptomes efficiently based on learning to hash method, Computers in Biology and Medicine , 2020 116: 103539.
  
• Sun, L, An, W., Liu, X.* and Lyu, H., On developing data-driven turbulence model for DG solution of RANS, Chinese Journal of Aeronautics , 2019 32:1869-1884.
  
• Liu, Z., Liu, X.* and Cai, X. A new hybrid aerodynamic optimization framework based on differential evolution and invasive weed optimization, Chinese Journal of Aeronautics, 2018 31:1437-1448.(Journal link)
  
• Zhang, L. and Liu, X.*, PBSeq: Modeling based-level bias to estimate gene and isoform expression for RNA-seq data, International Journal of Machine Learning and Cybernetics, 2017 8:1247-1258.(Journal link )
  
• Zhang, L. and Liu, X.*, A Comprehensive Review on RNA-seq Data Analysis, Transactions of Nanjing University of Aeronautics and Astronautics, 2016 33:339-361.
  
• Zhang, L. and Liu, X.*, A structured sparse regression method for estimating isoform expression level from multi-sample RNA-seq data, Genetics and Molecular Research, 2016 15:gmr7670.(Journal link )
  
• Liu, X.*, Shi, X., Chen, C. and Zhang, L., Improving RNA-Seq expression estimation by modeling isoform- and exon-specific read sequencing rate, BMC Bioinformatics, 2015 16:332.(Journal link )
  
• Liu, X.*, Zhang, L. and Chen, S., Modeling exon-specific bias distribution improves the analysis of RNA-seq data, PLoS ONE, 2015 10(10):e0140032.(Journal link)
  
• Zhang, L., Liu, X.* and Chen, S., Detecting Differential Expression from RNA-seq Data with Expression Measurement Uncertainty, Frontiers of Computer Science, 2015, 9(4).DOI: 10.1007/s11704-015-4308-6. (Journal link )
  
• Liu, X.*, Zhu, Q. and Lu, H., Modeling multi-response surfaces for airfoil design with multiple output Gaussian process regression, Journal of Aircraft, 2014 51(3):740-747.
  
• Liu, X.*, Gao, Z., Zhang, L. and Rattray, M., puma 3.0: improved uncertainty propagation methods for gene and transcript expression analysis, BMC Bioinformatics, 2013 14:39. (Journal link )
  
• Liu, X.* and Rattray, M., Including probe-level measurement error in robust mixture clustering of replicated microarray gene expression, Statistical Applications in Genetics and Molecular Biology: 2010 Vol. 9 : Iss. 1, Article 42. (Journal link )
  
• Pearson, R., Liu, X., Sanguinetti, G., Milo, M., Lawrence, N. D. and Rattray, M.*, puma: a Bioconductor package for Propagating Uncertainty in Microarray Analysis, BMC Bioinformatics, 2009 10:211. (featured article, Journal link )
  
• Liu, X., Lin, K. K., Andersen, B. and Rattray, M.*, Including probe-level uncertainty in model-based gene expression clustering, BMC Bioinformatics, 2007 8:98. (Journal link )
  
• Liu, X., Milo, M., Lawrence, N. D. and Rattray, M.*, Probe-level measurement error improves accuracy in detecting differential gene expression, Bioinformatics, 2006 22(17): 2107-2113. (Journal link )
  
• Rattray, M.*, Liu, X., Sanguinetti, G., Milo, M. and Lawrence, N. D., Propagating uncertainty in Microarray data analysis, Briefings in Bioinformatics, 2006 7(1):37-47. (Jounal link)
  
• Liu, X., Milo, M., Lawrence, N. D.* and Rattray, M.*, A tractable probabilistic model for Affymetrix probe-level analysis across multiple chips, Bioinformatics, 2005 21(18):3637-3644. (Jounal link)
  

Softwares

• NLDMseq: a software for the calculation of isoform usage from RNA-seq data given a reference transcriptome.

• PGSeq: a bioinformatics tool for estimating negative binomial distributed gene and isoform expression by modeling exon-specific bias from RNA-seq data.

• pumaclustii: an R package to propagate probe-level measurement error in a robust t-mixture clustering model for replicated gene expression data.

• mmgmos: an R package to estimate the expression levels and the confidence of measures for multiple arrays of the same type of Affymetrix GeneChips using the multi-chip modified gamma Model for Oligonucleotide Signal (multi-mgMOS) and the modified gamma Model for Oligonucleotide Signal (mgMOS).

• pplr: an R package to include probe-level measurement error into the variance estimates of gene expression levels and to detect up-regulated genes by calculating probability of positive log-ratio (PPLR).

• pumaclust: an R package to propagate probe-level measurement error in the model-based clustering of gene expression data.