 |
|---|
Research Projects
Publications available at Google Scholar
DEEPPATH
INTEGRATED PATHWAYS ENRICHMENT OF OMICS FEATURES
WE ARE DEVELOPING A GENERAL METHODS TO CAPTUR LINEAR AND NON-LINEAR ENRICHMENT OF OMICS FEATURES TO FIND IMPORTANT PATHWAYS.
Functional intergartion of omic features
Advances in high-throughput technologies such as DNA sequencing techniques and liquid chromatography-mass spectrometry enable capturing various snapshots of human biology activities in the level of big biomedical data. This provides an unprecedented depth of structural and molecular profiling of human biology. Yet, integrating and analyzing such data is an unmet need. These modern biological screens yield enormous numbers of measurements, and finding statistically significant associations among features and integrating these different omics features in metabolic functional level with ease of interpretation is essential. In this project, we will develop statistical and machine learning tools by adapting deep learning approaches to find enriched metabolic pathways.
Drift Correction in Metabolomics Data
Liquid chromatography tandem mass spectrometry (LC-MS) has emerged as the major technology used for metabolomic profiling, however raw datasets require extensive processing before they may be analyzed toward discovering biological patterns and disease associations. We develop approaches and create computational methods to increase the biological signal-noise ratio. These approaches include removing batch effects, drift correction, clustering chemical compounds, and removal of non-biological background signals.
Novel biomarkers discovery using deep learning of omics data
​
