Education Bioinformatics PhD candidate, College of Computing, Georgia Institute of Technology M.S. degree in Computer Science, Illinois Institute of Technology (IIT), 2005 B.E. degree in Computer Science, University of Science & Technology of China (USTC), 2003 Research Interests Data Mining, Text mining on Biomedical Data/Literature, Data Management Research Advisors Prof. Alexander Gray, Prof. Sham Navathe RESUME (wguan @ cc.gatech.edu)

SELECTED COURSES

Design & Analysis of Algorithms, Advanced Database Systems, Foundation of Machine Learning & Data Mining, Natural Language Processing & Learning, Bioinformatics, Biostatistics, Simulation of Biological Sys, Computational Statistics, Nonlinear Optimization, Multivariate Data Analysis, Financial Optimization

RESEARCH EXPERIENCE

Fast Computing Lab, College of Computing, Georgia Tech, 2007 - 2010. Advisor: Prof. Alexander Gray

• Gene prediction with conditional random field and max-margin markov network
• Energy function learning for ab initio protein folding: weight optimization using ranking through classification approaches such as rankboost, rankingSVM, ranking perceptrons
• Functional data analysis on ovarian cancer metabolic mass spectrometry data
• Combine support vector machine related feature selection methods with statistical analysis for cancer detection using ovarian cancer mass spectrometry data
• Incorporate Gene Ontology into gene selection in ovarian cancer microarray data analysis

Database Lab, College of Computing, Georgia Tech, 2005 - 2007. Advisor : Prof. Sham Navathe

• Extend PostgreSQL with information retrieval features, tested on MEDLINE database
• Query-based summarization system on MEDLINE database
• Dimension reduction techniques for biomedical text categorization

Information Retrieval Lab, Illinois Inistitute of Technology, 2004 - 2005. Advisor Prof. Ophir Frieder

• Context-Constrained role based access control model for health care domain

Artificial Intelligence Lab, Univ. of Sci. & Tech. of China, 2002 - 2003. Advisor: Prof. Qingsheng Cai:

• Hidden markov model based information extraction on webpages with attribute misplacement/missing problem

WORK EXPERIENCE

IBM T.J Watson Research Center, medical text and image analysis group, summer 2007. Manager: Dr. Anni Coden

• Developed and evaluated word disambiguation and named entity recognition components of MedTAS, an NLP system targeted for analyzing pathology reports

Yahoo data mining research group, summer 2006. Manager: Dr. Pavel Berkhin

• Conducted experiments on integrating content based filtering and collaborative filtering techniques to build up recommendation framework for Yahoo!Shopping datasets

PUBLICATIONS

- W. Guan, A. Ozakin, A. Gray, J. Borreguero, S. Pandit, J. Skolnick. Learning protein folding energy function. Research in Computational Molecular Biology (RECOMB) 2010, submitted

- W. Guan, M. Zhou, C. Hampton, A. Gray, J. McDonald, F. Fernandez. Ovarian cancer detection from metabolomic liquid chromatography/ mass spectrometry data by support vector machines. BMC bioinformatics, 10:259, 2009

- A. Coden, G. Savova, I. Sominsky, M. Tanenblatt, J. Masanz, K. Schuler, J. Cooper, W. Guan, P.C. Groen. Automatically extracting cancer disease characteristics from pathology reports into a disease knowledge representation model. Journal of Biomedical Informatics, available online 2008

- S. Navathe, U. Patil, W. Guan. Genomic and proteomic databases: foundations, current status and future applications. Journal of Computing Science and Engineering 2007, 1:1

- W. Guan, A. Gray, S. Navathe, N. Bowen, J. McDonald. Discovering ovarian cancer biomarkers using gene ontology based microarray analysis. Workshop on Data Mining for Bioinformatics, 2007

TA EXPERIENCE

• CS3510 Design and Analysis of Algorithms
• CS4400 Introduction to Database Systems
• CS6400 Database System Concepts& Design
• CS7001 Grad Studies-Computing

LINKS

• Fast Computing Lab

Last Modified: Sep. 9th, 2009