Pei Wang
Research Interest
I am interested in various fields of bioinformatics, including modeling large-scale proteomics data in biomarker discovery studies, analyzing CGH array/microarray with statistical methods, and studying biology pathway networks based on multiple types of data. I am also collaborating with scientists in Fred Hutchinson on a range of epidemiology studies.
Recent Projects
Network Inference based on high dimensional data
- Controlling for False Positive Findings of Trans-Hubs in e-QTL Mapping.
-
Spare Partial Correlation Estimation (space)
JASA paper 2009 Vol. 104, No. 486, 735-746 (pdf)
Software: space (R Package)
-
Regularized multivariate regression for Identifying master predictors (remMap)

Technical Report 2009 (pdf)
Software: remMap (R Package)
-
Learning network from high dimensional binary data (LogitNet)

Technical Report 2009 (pdf)
Software: logitnet
(R Package) coming soon
CGH array data.
-
CLAC (CLuter Along Chromosome) method for calling gains/losses for array CGH data.
Biostatistics Paper 2005, 6, 1 (pdf)
-
Spatial smoothing and hot spot detection for CGH data using the Fused Lasso.
Biostatistics Paper 2007 (pdf)
Software: cghFLasso (R Package)
LC-MS based Proteomics data.
-
Normlization regarding non-random missing values in high-throughput mass spectrometry data.
PSB 2006 Proceeding paper (pdf)
-
PETAL (Peptide ElemenT ALignment) method for chromatographic alignment of LC-MS data.
Biostatistics paper 2006 (pdf)
-
SASPECT (Significant AnalysiS of PEptide CounTs) method for Significant anlaysis of comparative proteomics based on LC-MS/MS Experiments
Publication
See My profile at COS Expertise.
Related Links
CPL home page (Martin McIntosh's informatic group)