Software developed in my lab

GUST: Genes under Selection in Tumors
Predicts oncogenes, tumor suppressor genes and passenger genes using somatic SNVs detected in a collection of tumors. It supports contextual classifications of genes for specific tissue types and cancer types.
Know-GRRF: KnowGuided Regularized Random Forests
Incorporates prior knowledge from multiple domains to guide feature selection. It provides a general framework for all feature selection tasks. We demonstrate its power in biomarker discovery.
MAGOS: Model-based Adaptive Grouping of Subclones
Decompose subclonal structure in tumors from bulk-sequencing data. It makes accurate and reproducible subclone identifications in samples sequenced at depth as low as 30x, thus suitable to analyzing whole-genome sequencing data.
TreeMap: A Nested Machine- and Statistical-Learning Approach to Discover Causal Variant
Fine-map causal variants for eQTL and GWAS studies by considering hierarchical linkage structure among genetic variants.
TreeGuidedLasso: An R implementation of the tree-guided group lasso algorithm