Predicting functional effects of cancer-associated somatic mutations using a deep-learning framework

Cancer is a genetic disease characterized by a progressive accumulation of genomic aberrations.  When somatic mutations arise in single cells at certain key genetic positions, cells may lose control in cell replication cycles and eventually lead to tumorigenesis.  Here, we are developing a deep-learning framework to assign a quantitative score to estimate cancer-promoting risk of each given genetic mutation.


Visualization of cancer omics data

High throughput sequencing technology have generated a large volume of omics data and greatly boost our understanding of cancer.  Here, we aim to develop a powerful and easy-to-use web-based framework, which enables users to explore, visualize, and analyze multidimensional cancer genomics data.

Copyright © 2018 All Rights Reserved.