Chao Lan
PhD. Candidate, Graduate Research Assistant
Research Description: Chao works on machine learning algorithms to study data from multiple sources. He is interested in using feature extraction methods to better construct better models for multi-view data. He is also interested in analyzing chemical toxicity prediction with multiview data (protein sequencs, chemical structures, known toxicities).

Kaige Yan
PhD. Candidate, Graduate Research Assistant
Research Description: Kaige works on multi-core machines to support large scale knowledge discovery from richly-structured data. He is studying GPU-based techniques to speed up graph similarity search at the present time. 

Hongliang Fei
PhD. Candidate, Graduate Research Assistant
Research Description: Hongliang's research focues on feature selection techniques for data sets with low sample size but high dimensionality in which the features have a structured relationship, such as a chain, a tree and a general graph. The data sets are diverse including both vectorial data such as Miroarray and semi-structured data such as graphs. The goal of his research is to build more accurate and interpretable regression or classification models. He is also interested in sparse learning, multi-task learning with structured input and output.

Brian Quanz
PhD. Candidate, NSF Graduate Research Fellowship awarded
Research Description: Brian's work focuses on developing machine learning methods for real-world cheminformatics data that is usually not collected under ideal circumstances. A key issue of focus is leveraging the large amounts of data with no ground truth information, or labels, which are expensive and time consuming to obtain, and labeled data from different data sources than the task of interest to improve predictive models constructed for specific tasks and data. For instance using available labeled interaction data for sets of chemicals and certain proteins to help predict interaction for different sets of chemicals and proteins.

back to home