A central thesis of the Analytics suite is that by abstracting a diverse set of bioinformatics tasks into a small set of core analytical operations, we will be able to focus on the most basic computational challenges in extracting hypotheses out of genomics data and streamline the development of core technology for biological data analysis. In addition to identifying standard (widely used) analytical functionalities for incorporation into the cloud-based KnowEnG framework, we have been working on the advanced analytic tasks described in the following sections.


Cancer drug response prediction from genomic profiles

Computational Methods for Analyzing Transcriptional Regulators of Drug Response

False discovery rate control for simultaneously significant features

Bio-Text Mining for Construction of Biomedical Information Networks

Saul: A language for declarative learning based programming

Gene Set Characterization

DATASPREAD: Unifying Databases and Spreadsheets

Discriminative Random Walks with Restart (DRaWR)

Exploiting ontology graph for predicting sparsely annotated gene function

Project Leaders

Jiawei Han

Saurabh Sinha