Welcome to my home page. I'm very glad that you have made it this
Associate Professor of Statistics and Graduate Chair
250 N. University Street
West Lafayette, IN 47907-2067
My research group works on statistical methods
for genomics big-data.
I'm currently recruiting graduate Research Assistants but only among
Statistics Ph.D. students.
- Department of Probability and
Statistic, Peking University
B.S. in Statistics
- Department of Probability and
Statistics, Peking University
M.S. in Statitics
Department of Statistics, University of California at
Ph.D. in Statistics
Current Research Projects
- Statistical predictive models using whole-genome genetic data
This project is funded by NIH.
- Nonlinear predictive models for pharmacogenomics
The statistical developments in this project are motivated by
pharmacogenomics research, which is to use patients' whole-genome
genetic information to predict individuals' response to a drug.
- A nonparametric variable selection method for predictive models and
- Extension of Sliced Inverse Regression for high dimensional
but low sample size data, Seminar
- An open computation challenge, DREAM8 Toxicogenetics
Our group participates in the open challenge of using genomics data to
predict toxic response of individuals to some common environmental and
- Probabilistic inferences and applications in analysis of genomics
This project is funded by NSF.
- Large scale two sample multinomial inferences and genome-wide
association studies, Reprint.
- Probabilistic Inference for Multiple Testing
- Identifying isoform expression using next generation
Next generation sequencing is a recently developed biotechnology that
produces tens or hundreds of millions of short sequence reads of
transcribed genes. Isoforms of a gene are referred to
as subtle differences in a gene sequence from inclusion or exclusion of
different exons. Identifying isoform expression from next generation
sequencing data can be formulated as an interesting statistical problem,
with the isoform abundance as the unknown model parameters.
- Group variable selection for high-dimensional data with depenent
More Research Interests
- Integrative analysis of sequences, gene expression microarray, and
ChIP-chip binding data for transcriptional regulation and network
- "Statistical methods in integrative
analysis for gene regulatory modules", Lingmin Zeng, Jing Wu, and Jun Xie,
2008, Statistical Applications in Genetics and
- Analysis of survival data with censoring
- "Adjusted Kaplan-Meier Estimator and Log-rank Test with
Inverse Probability of Treatment Weighting for Survival Data", Jun
Xie and Chaofeng Liu, 2005, Statistics in Medicine.
- Statistical approaches for identifying
protein motifs with the secondary characteristics of hydrophobicity and
- Protein Multiple Alignment Incorporating Primary
and Secondary Structure Information
- Hidden Markov
model and Bayesian method of identifying cis-regulatory modules in
- "Computation-Based Discovery of Cis-Regulatory Modules by Hidden Markov
Model", Jing Wu and Jun Xie, 2008, Journal of Computational
Jun Xie's Ph.D. Students
- Completed Ph.D. students
- Nak-Kyeong Kim, Ph.D. 2005, Assistant Professor at Old Dominion
- Chuancai Wang, Ph.D. 2004 (Co-advised with Dr. Bruce Craig), Assistant
Professor in Biostatistics at Penn State University.
- Lingmin Zeng, Ph.D. 2008, Biostatistician in a pharmaceutical company
MedImmune in Maryland.
- Riyan Cheng, Ph.D. 2009 (Co-advised with Dr. Rebecca Doerge), postdoc
in University of Chicago.
- Current Ph.D. students
- Jingyi Zhu
- Donglai Chen